This document discusses challenges in using wireless sensor networks for environmental monitoring applications. It notes that sensor nodes have limited energy, which poses challenges for applications that need to run for months or years. The document describes the hardware capabilities of wireless sensor nodes and their energy consumption during different operating modes. It also provides an overview of using machine learning models to model sensor measurements over time and across sensors, with the goal of reducing energy usage through adaptive model selection.
The document discusses using terahertz radiation to characterize electronic components. It describes the experimental setup for terahertz imaging in both transmission and reflection modes. Key applications discussed include using terahertz techniques to determine the refractive index and absorption coefficient of materials, which can be used to distinguish authentic integrated circuits from counterfeits. The document also shows how terahertz imaging can identify features like different layers within objects and blacktopped integrated circuits that are difficult to detect using other methods like x-rays.
IRJET- Review on Image Processing based Fire Detetion using Raspberry PiIRJET Journal
The document describes a proposed image processing system using a Raspberry Pi to detect fires. The system would use a camera to capture images and the Raspberry Pi would process the images to detect fire signatures using heat patterns and colors. If a fire is detected, the system would sound an alarm. The proposed system aims to provide early fire detection without the need for additional sensors. It reviews existing fire detection methods and outlines the modules of the proposed system, including image capture, color-based segmentation, fire pattern recognition, and an emergency alarm trigger.
Cost-Efficient Sensor Deployment in Indoor Space with ObstaclesUbi NAIST
The document proposes algorithms for cost-efficient sensor deployment in indoor spaces with obstacles. It formulates the problem of minimizing deployment cost while achieving full coverage and connectivity. A heuristic algorithm is presented that calculates the "per-cost volume" of potential sensor locations and iteratively places sensors to maximize this value. The algorithm is extended to address mobile obstacle coverage by dividing the monitoring area into spherical wedges and ensuring at least one sensor is placed in each wedge. An evaluation demonstrates the approach reduces costs by 45% compared to alternative methods and experiments validate achieving mobile 3-coverage.
This study presents a new method for non-destructive testing (NDT) using infrared thermography combined with microwave excitation. The method is applied to detect defects in two types of samples - a concrete slab reinforced with carbon fiber reinforced polymer (CFRP) and a wooden plate with a metallic insert. A microwave excitation system using a magnetron and horn antenna is developed to heat the samples in a protective room. Thermograms show higher temperature rises in defect areas, indicating the potential of microwave excitation for detecting deeper defects compared to surface excitation methods. Initial results demonstrate the feasibility of using microwave excitation with infrared thermography for NDT applications in civil engineering structures.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Jual Sokkia SET62 Total Station, yang digunakan sebagai alat ukur sudut dan jarak yang dilengkapi dengan Electric Distance Meter (EDM) yang terintegrasi dalam satu unit alat. Perangkat ini juga telah dilengkapi dengan processor sehingga mampu menghitung jarak datar, koordinat, dan beda tinggi secara langsung tanpa perlu bantuan kalkulator lagi.
A Study on Privacy Level in Publishing Data of Smart Tap NetworkHa Phuong
This document describes a study on quantifying privacy levels in publishing smart tap network data. It outlines the background, related works, methodology, results and conclusions. The methodology proposes using entropy, specifically approximate entropy and sample entropy, to quantify the amount of human activity information contained in power consumption data. This "privacy level" is defined as the entropy rate of a data set relative to white noise. The study applies this methodology to analyze smart tap data from the IREF building over 5 weeks, setting parameters like time lag, pattern length m, and threshold r for calculating entropy. The results show entropy rates can help determine safe privacy levels for publishing power consumption data.
This is a straightforward image classification study to create and compare classifiers (KNN, Neural Networks and Adaboost) that decide the correct orientation of a given image i.e. 0°,90°,180° or 270°
The document discusses using terahertz radiation to characterize electronic components. It describes the experimental setup for terahertz imaging in both transmission and reflection modes. Key applications discussed include using terahertz techniques to determine the refractive index and absorption coefficient of materials, which can be used to distinguish authentic integrated circuits from counterfeits. The document also shows how terahertz imaging can identify features like different layers within objects and blacktopped integrated circuits that are difficult to detect using other methods like x-rays.
IRJET- Review on Image Processing based Fire Detetion using Raspberry PiIRJET Journal
The document describes a proposed image processing system using a Raspberry Pi to detect fires. The system would use a camera to capture images and the Raspberry Pi would process the images to detect fire signatures using heat patterns and colors. If a fire is detected, the system would sound an alarm. The proposed system aims to provide early fire detection without the need for additional sensors. It reviews existing fire detection methods and outlines the modules of the proposed system, including image capture, color-based segmentation, fire pattern recognition, and an emergency alarm trigger.
Cost-Efficient Sensor Deployment in Indoor Space with ObstaclesUbi NAIST
The document proposes algorithms for cost-efficient sensor deployment in indoor spaces with obstacles. It formulates the problem of minimizing deployment cost while achieving full coverage and connectivity. A heuristic algorithm is presented that calculates the "per-cost volume" of potential sensor locations and iteratively places sensors to maximize this value. The algorithm is extended to address mobile obstacle coverage by dividing the monitoring area into spherical wedges and ensuring at least one sensor is placed in each wedge. An evaluation demonstrates the approach reduces costs by 45% compared to alternative methods and experiments validate achieving mobile 3-coverage.
This study presents a new method for non-destructive testing (NDT) using infrared thermography combined with microwave excitation. The method is applied to detect defects in two types of samples - a concrete slab reinforced with carbon fiber reinforced polymer (CFRP) and a wooden plate with a metallic insert. A microwave excitation system using a magnetron and horn antenna is developed to heat the samples in a protective room. Thermograms show higher temperature rises in defect areas, indicating the potential of microwave excitation for detecting deeper defects compared to surface excitation methods. Initial results demonstrate the feasibility of using microwave excitation with infrared thermography for NDT applications in civil engineering structures.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Jual Sokkia SET62 Total Station, yang digunakan sebagai alat ukur sudut dan jarak yang dilengkapi dengan Electric Distance Meter (EDM) yang terintegrasi dalam satu unit alat. Perangkat ini juga telah dilengkapi dengan processor sehingga mampu menghitung jarak datar, koordinat, dan beda tinggi secara langsung tanpa perlu bantuan kalkulator lagi.
A Study on Privacy Level in Publishing Data of Smart Tap NetworkHa Phuong
This document describes a study on quantifying privacy levels in publishing smart tap network data. It outlines the background, related works, methodology, results and conclusions. The methodology proposes using entropy, specifically approximate entropy and sample entropy, to quantify the amount of human activity information contained in power consumption data. This "privacy level" is defined as the entropy rate of a data set relative to white noise. The study applies this methodology to analyze smart tap data from the IREF building over 5 weeks, setting parameters like time lag, pattern length m, and threshold r for calculating entropy. The results show entropy rates can help determine safe privacy levels for publishing power consumption data.
This is a straightforward image classification study to create and compare classifiers (KNN, Neural Networks and Adaboost) that decide the correct orientation of a given image i.e. 0°,90°,180° or 270°
The Palm OTDR X-60 is an optical time domain reflectometer with a dynamic range of 32/30 dB at wavelengths of 1310/1550 nm. It can measure distances from 0.3 to 180 km with an event blind zone of 2 m and attenuation blind zone of 9 m. The device has a sampling resolution of 0.125 to 8 m, stores traces on an SD card, and operates for over 8 hours on a lithium battery.
The GaugeKeeper is an optical water level measurement system that uses a camera and image processing to remotely measure and record water levels, along with images. It provides redundant water level data transmission from remote sites in real-time with alarm alerts. Historical data, including measurements and images, can be downloaded for visual verification. The system requires no expensive trips to remote measurement sites and has TCP/IP connectivity for remote access to data.
This thesis describes the design and implementation of a star tracker for CubeSats. The author designed hardware modules for real-time star detection and centroid calculation using an FPGA. An image sensor and lens were selected, and a baffle was designed. Noise correction algorithms were developed. Testing showed the star tracker could detect stars up to magnitude 4.0 with sub-pixel centroiding accuracy of 0.0536 degrees. Future work includes integrating modules into an FPGA, implementing star identification and attitude algorithms, and testing the complete system.
First results from the full-scale prototype for the Fluorescence detector Arr...Toshihiro FUJII
The Fluorescence detector Array of Single-pixel Telescopes (FAST) is a design concept for the next generation of ultrahigh-energy cosmic ray (UHECR) observatories, addressing the requirements for a large-area, low-cost detector suitable for measuring the properties of the highest energy cosmic rays. In the FAST design, a large field of view is covered by a few pixels at the focal plane of a mirror or Fresnel lens. Motivated by the successful detection of UHECRs using a prototype comprised of a single 200 mm photomultiplier-tube and a 1 m2 Fresnel lens system [Astropart.Phys. 74 (2016) 64-72], we have developed a new full-scale prototype consisting of four 200 mm photomultiplier-tubes at the focus of a segmented mirror of 1.6 m in diameter. In October 2016 we installed the full-scale prototype at the Telescope Array site in central Utah, USA, and began steady data taking. We report on first results of the full-scale FAST prototype, including measurements of artificial light sources, distant ultraviolet lasers, and UHECRs.
35th International Cosmic Ray Conference — ICRC2017 18th July, 2017
Bexco, Busan, Korea
This document evaluates the accuracy of land cover classification from image time series data from the Venμs, Sentinel-2, and Formosat-2 sensors. It finds that with few images, spectral resolution is most important, but with many images temporal resolution matters more due to cloud cover issues. A simulation framework was developed that models the sensors' spectral responses using input time series data from Formosat-2. Results show that Venμs and Sentinel-2 perform equivalently with around 15 images, while Formosat-2 requires at least 20 due to its lower temporal resolution. Overall, the study analyzed the tradeoff between temporal and spectral resolution for land cover mapping from satellite image time series.
This document is the thesis titled "Application of non-intrusive experimental techniques to roughness-induced transition in hypersonic flows" by Francesco Avallone submitted to the University of Naples Federico II in partial fulfillment of the requirements for the Doctor of Philosophy degree. The thesis investigates roughness-induced transition in hypersonic flows through experimental studies using non-intrusive techniques such as infrared thermography and particle image velocimetry in the Hypersonic Test Facility Delft wind tunnel. The thesis is composed of introductory chapters on hypersonic flows, the wind tunnel facility, and measurement techniques followed by results chapters analyzing the effects of roughness geometry, the separated flow region upstream, and wake region downstream on
Fast and High-Precision 3D Tracking and Position Measurement with MEMS Microm...Ping Hsu
We demonstrate real-time fast-motion tracking of an object in a 3D volume, while obtaining its precise XYZ co-ordinates.
Two separate scanning MEMS micromirror sub-systems track the object in a 20 kHz closed-loop. A demonstration system capable
of tracking full-speed human hand motion provides position information at up to 5m distance with 16-bit precision, or <=20μm
precision on the X and Y axes (up/down, left/right,) and precision on the depth (Z-axis) from 10μm to 1.5mm, depending on distance.
TH1.L10.5: VALIDATION OF TIE-POINT CONCEPTS BY THE DEM ADJUSTMENT APPROACH OF...grssieee
The document discusses validation of tie-point concepts for DEM calibration using TanDEM-X data. It describes extracting calibration points from overlap areas between acquisitions and from ICESat data to serve as ground control points. It compares using single points versus area-based approaches for tie-points and examines the impact of varying numbers of ICESat points and tie-points on calibration accuracy. Analysis of ICESat parameters aimed to identify the most accurate ground control points.
1) MEMSat is a ThinSat CubeSat project developed by Kyle Ikuma to study the performance of two different IMU sensors in low-Earth orbit.
2) The project required turning Ikuma's bedroom into a makeshift lab to house the necessary equipment over the summer as the sole researcher.
3) The MEMSat payload circuit design included the two IMUs, a Teensy microcontroller, sensors to measure light, acceleration, angular velocity and magnetic field stored in a custom 35-byte data packet for downlinking to Earth. The design was tested and assembled on a professionally manufactured PCB after challenges with an initial prototype.
The document outlines the vision and guidelines for teaching social skills and addressing relationships and sexuality to students in Training Level 1 (TL1) at the Sint-Janshof school. It discusses components like communication, self-reliance, and meaningful free time. It provides guidance on maintaining appropriate physical distance, addressing teachers, expressing affection, gym class, toilet use, puberty, relationships, independence, sex education, procreation, masturbation, homosexuality, and out-of-school activities. Examples are given of addressing social interaction issues and promoting positive behavior through individualized reinforcement systems.
This document summarizes the history of psychological disorders and their treatment. It discusses early beliefs that abnormal behavior was caused by demons or humoral imbalances. It then describes the introduction of more humane care in asylums in the 16th century and early psychological explanations proposed by Mesmer involving magnetic fluids. The development of diagnostic systems like the DSM is outlined as well as the role of psychopharmacology and specific disorders like depression, bipolar disorder, anxiety disorders, and ADHD. Causes proposed for different disorders include physiological, cognitive, and psychoanalytic explanations.
The document provides an overview of various psychotherapy approaches and techniques. It discusses psychoanalytic therapy, person-centered therapy, gestalt therapy, behavior therapies including applied behavior analysis and cognitive-behavioral therapy. It also briefly describes questionable therapies like primal therapy and subliminal tapes. Key figures mentioned include Freud, Rogers, Perls, Ellis, and Beck. The document compares percentages of time spent on different activities between counselors and psychotherapists.
Social Skills Training In Students With Autismrmaxwell1
The document discusses social skills training for students with autism. It outlines a 6 step process for developing social skills programs: 1) assess students' skills, 2) decide which skills to target, 3) set specific and measurable goals, 4) choose intervention methods and materials, 5) track student progress, and 6) facilitate generalization of skills. Example goals, curricula, data tracking methods and techniques for generalization are provided. The overall goal is for students to independently function socially as adults.
This document provides an overview of Sister Callista Roy and her adaptation model of nursing. It discusses her background and career, the development and components of her theory, and applications of the model to nursing practice, research, and education. The adaptation model views the person as an adaptive system who is constantly interacting with a changing environment. Nursing aims to promote the person's adaptation through four modes: physiological, self-concept, role function, and interdependence. The theory has been widely implemented in nursing curriculum and has generated testable hypotheses for research.
Sister Callista Roy's Adaptation Model views the client as an adaptive system that must constantly interact with and adapt to changes in the environment. The goal of nursing according to Roy's model is to help clients adapt in four key areas: physiological needs, self-concept, role function, and interdependence. Roy's model provides a framework for nursing practice by outlining the nursing process of assessing stimuli, diagnosing responses, setting goals, intervening, and evaluating outcomes to help clients effectively adapt.
This document discusses principles of counseling techniques. It defines counseling as a process between two individuals where a counselor assists a client. It outlines three main types of counseling - directive, non-directive, and eclectic. Directive counseling involves the counselor directing the client, non-directive focuses on a client-centered approach, and eclectic combines elements of both. The document also discusses qualities of effective counselors, the counseling process, and factors for counseling success.
This document outlines various counseling techniques and qualities of an effective counselor. It discusses that counseling is an intimate guidance practice that is as old as human societies. It then describes different counseling methods like prescriptive, non-directive, and directive techniques. The document also lists qualities of counselors like interpersonal skills, personal adjustment, and leadership abilities. Finally, it discusses recent developments in counseling like using experiences and imagination to treat fears.
1. The document provides an overview of digital modulation for mobile communication systems. It discusses key concepts like sampling, bandwidth, modulation theory, and digital modulation schemes.
2. The document covers sampling theory including the sampling theorem and concepts like energy, power, power spectral density, and pulse shaping filters. It explains how sampling works by modeling the sampling function as a train of Dirac impulse functions.
3. Key learning outcomes are listed and cover understanding principles of sampling and digital modulation, as well as modulation schemes like BPSK and QPSK. Concepts of bit error probability, eye diagrams, and spectrum analyzers are also introduced.
The document describes the implementation of a wideband spectrum sensing algorithm using a software-defined radio. It discusses using an energy detection based approach to sense the local frequency spectrum and determine which portions are unused. The algorithm is first tested via simulations in MATLAB using known signal parameters. It is then tested using real data collected from a Universal Software Radio Peripheral (USRP) to analyze the actual wireless spectrum.
Smart dust consists of tiny autonomous sensing devices called motes that are less than 1.5mm3 in volume and 5mg in mass. Motes can collect sensor data and transmit it wirelessly over distances of 15-50m to a base station using radio frequency, passive optical reflectors, or active laser transmitters. They incorporate sensors, microprocessors, memory, transmitters and receivers, and thick film batteries or solar cells to operate independently for long periods with very low power usage. Potential applications include environmental monitoring, infrastructure inspection, health monitoring, and more.
This document describes a landslide monitoring project that uses wireless sensor nodes to monitor factors like slope angle, water depth, and temperature that could indicate an impending landslide. Sensors are connected to Arduino nodes that transmit the data via XBee radios. The network switches between a tree and star topology depending on whether a light or heavy landslide is detected. The project aims to warn people and authorities about landslides so protective measures can be taken.
The Palm OTDR X-60 is an optical time domain reflectometer with a dynamic range of 32/30 dB at wavelengths of 1310/1550 nm. It can measure distances from 0.3 to 180 km with an event blind zone of 2 m and attenuation blind zone of 9 m. The device has a sampling resolution of 0.125 to 8 m, stores traces on an SD card, and operates for over 8 hours on a lithium battery.
The GaugeKeeper is an optical water level measurement system that uses a camera and image processing to remotely measure and record water levels, along with images. It provides redundant water level data transmission from remote sites in real-time with alarm alerts. Historical data, including measurements and images, can be downloaded for visual verification. The system requires no expensive trips to remote measurement sites and has TCP/IP connectivity for remote access to data.
This thesis describes the design and implementation of a star tracker for CubeSats. The author designed hardware modules for real-time star detection and centroid calculation using an FPGA. An image sensor and lens were selected, and a baffle was designed. Noise correction algorithms were developed. Testing showed the star tracker could detect stars up to magnitude 4.0 with sub-pixel centroiding accuracy of 0.0536 degrees. Future work includes integrating modules into an FPGA, implementing star identification and attitude algorithms, and testing the complete system.
First results from the full-scale prototype for the Fluorescence detector Arr...Toshihiro FUJII
The Fluorescence detector Array of Single-pixel Telescopes (FAST) is a design concept for the next generation of ultrahigh-energy cosmic ray (UHECR) observatories, addressing the requirements for a large-area, low-cost detector suitable for measuring the properties of the highest energy cosmic rays. In the FAST design, a large field of view is covered by a few pixels at the focal plane of a mirror or Fresnel lens. Motivated by the successful detection of UHECRs using a prototype comprised of a single 200 mm photomultiplier-tube and a 1 m2 Fresnel lens system [Astropart.Phys. 74 (2016) 64-72], we have developed a new full-scale prototype consisting of four 200 mm photomultiplier-tubes at the focus of a segmented mirror of 1.6 m in diameter. In October 2016 we installed the full-scale prototype at the Telescope Array site in central Utah, USA, and began steady data taking. We report on first results of the full-scale FAST prototype, including measurements of artificial light sources, distant ultraviolet lasers, and UHECRs.
35th International Cosmic Ray Conference — ICRC2017 18th July, 2017
Bexco, Busan, Korea
This document evaluates the accuracy of land cover classification from image time series data from the Venμs, Sentinel-2, and Formosat-2 sensors. It finds that with few images, spectral resolution is most important, but with many images temporal resolution matters more due to cloud cover issues. A simulation framework was developed that models the sensors' spectral responses using input time series data from Formosat-2. Results show that Venμs and Sentinel-2 perform equivalently with around 15 images, while Formosat-2 requires at least 20 due to its lower temporal resolution. Overall, the study analyzed the tradeoff between temporal and spectral resolution for land cover mapping from satellite image time series.
This document is the thesis titled "Application of non-intrusive experimental techniques to roughness-induced transition in hypersonic flows" by Francesco Avallone submitted to the University of Naples Federico II in partial fulfillment of the requirements for the Doctor of Philosophy degree. The thesis investigates roughness-induced transition in hypersonic flows through experimental studies using non-intrusive techniques such as infrared thermography and particle image velocimetry in the Hypersonic Test Facility Delft wind tunnel. The thesis is composed of introductory chapters on hypersonic flows, the wind tunnel facility, and measurement techniques followed by results chapters analyzing the effects of roughness geometry, the separated flow region upstream, and wake region downstream on
Fast and High-Precision 3D Tracking and Position Measurement with MEMS Microm...Ping Hsu
We demonstrate real-time fast-motion tracking of an object in a 3D volume, while obtaining its precise XYZ co-ordinates.
Two separate scanning MEMS micromirror sub-systems track the object in a 20 kHz closed-loop. A demonstration system capable
of tracking full-speed human hand motion provides position information at up to 5m distance with 16-bit precision, or <=20μm
precision on the X and Y axes (up/down, left/right,) and precision on the depth (Z-axis) from 10μm to 1.5mm, depending on distance.
TH1.L10.5: VALIDATION OF TIE-POINT CONCEPTS BY THE DEM ADJUSTMENT APPROACH OF...grssieee
The document discusses validation of tie-point concepts for DEM calibration using TanDEM-X data. It describes extracting calibration points from overlap areas between acquisitions and from ICESat data to serve as ground control points. It compares using single points versus area-based approaches for tie-points and examines the impact of varying numbers of ICESat points and tie-points on calibration accuracy. Analysis of ICESat parameters aimed to identify the most accurate ground control points.
1) MEMSat is a ThinSat CubeSat project developed by Kyle Ikuma to study the performance of two different IMU sensors in low-Earth orbit.
2) The project required turning Ikuma's bedroom into a makeshift lab to house the necessary equipment over the summer as the sole researcher.
3) The MEMSat payload circuit design included the two IMUs, a Teensy microcontroller, sensors to measure light, acceleration, angular velocity and magnetic field stored in a custom 35-byte data packet for downlinking to Earth. The design was tested and assembled on a professionally manufactured PCB after challenges with an initial prototype.
The document outlines the vision and guidelines for teaching social skills and addressing relationships and sexuality to students in Training Level 1 (TL1) at the Sint-Janshof school. It discusses components like communication, self-reliance, and meaningful free time. It provides guidance on maintaining appropriate physical distance, addressing teachers, expressing affection, gym class, toilet use, puberty, relationships, independence, sex education, procreation, masturbation, homosexuality, and out-of-school activities. Examples are given of addressing social interaction issues and promoting positive behavior through individualized reinforcement systems.
This document summarizes the history of psychological disorders and their treatment. It discusses early beliefs that abnormal behavior was caused by demons or humoral imbalances. It then describes the introduction of more humane care in asylums in the 16th century and early psychological explanations proposed by Mesmer involving magnetic fluids. The development of diagnostic systems like the DSM is outlined as well as the role of psychopharmacology and specific disorders like depression, bipolar disorder, anxiety disorders, and ADHD. Causes proposed for different disorders include physiological, cognitive, and psychoanalytic explanations.
The document provides an overview of various psychotherapy approaches and techniques. It discusses psychoanalytic therapy, person-centered therapy, gestalt therapy, behavior therapies including applied behavior analysis and cognitive-behavioral therapy. It also briefly describes questionable therapies like primal therapy and subliminal tapes. Key figures mentioned include Freud, Rogers, Perls, Ellis, and Beck. The document compares percentages of time spent on different activities between counselors and psychotherapists.
Social Skills Training In Students With Autismrmaxwell1
The document discusses social skills training for students with autism. It outlines a 6 step process for developing social skills programs: 1) assess students' skills, 2) decide which skills to target, 3) set specific and measurable goals, 4) choose intervention methods and materials, 5) track student progress, and 6) facilitate generalization of skills. Example goals, curricula, data tracking methods and techniques for generalization are provided. The overall goal is for students to independently function socially as adults.
This document provides an overview of Sister Callista Roy and her adaptation model of nursing. It discusses her background and career, the development and components of her theory, and applications of the model to nursing practice, research, and education. The adaptation model views the person as an adaptive system who is constantly interacting with a changing environment. Nursing aims to promote the person's adaptation through four modes: physiological, self-concept, role function, and interdependence. The theory has been widely implemented in nursing curriculum and has generated testable hypotheses for research.
Sister Callista Roy's Adaptation Model views the client as an adaptive system that must constantly interact with and adapt to changes in the environment. The goal of nursing according to Roy's model is to help clients adapt in four key areas: physiological needs, self-concept, role function, and interdependence. Roy's model provides a framework for nursing practice by outlining the nursing process of assessing stimuli, diagnosing responses, setting goals, intervening, and evaluating outcomes to help clients effectively adapt.
This document discusses principles of counseling techniques. It defines counseling as a process between two individuals where a counselor assists a client. It outlines three main types of counseling - directive, non-directive, and eclectic. Directive counseling involves the counselor directing the client, non-directive focuses on a client-centered approach, and eclectic combines elements of both. The document also discusses qualities of effective counselors, the counseling process, and factors for counseling success.
This document outlines various counseling techniques and qualities of an effective counselor. It discusses that counseling is an intimate guidance practice that is as old as human societies. It then describes different counseling methods like prescriptive, non-directive, and directive techniques. The document also lists qualities of counselors like interpersonal skills, personal adjustment, and leadership abilities. Finally, it discusses recent developments in counseling like using experiences and imagination to treat fears.
1. The document provides an overview of digital modulation for mobile communication systems. It discusses key concepts like sampling, bandwidth, modulation theory, and digital modulation schemes.
2. The document covers sampling theory including the sampling theorem and concepts like energy, power, power spectral density, and pulse shaping filters. It explains how sampling works by modeling the sampling function as a train of Dirac impulse functions.
3. Key learning outcomes are listed and cover understanding principles of sampling and digital modulation, as well as modulation schemes like BPSK and QPSK. Concepts of bit error probability, eye diagrams, and spectrum analyzers are also introduced.
The document describes the implementation of a wideband spectrum sensing algorithm using a software-defined radio. It discusses using an energy detection based approach to sense the local frequency spectrum and determine which portions are unused. The algorithm is first tested via simulations in MATLAB using known signal parameters. It is then tested using real data collected from a Universal Software Radio Peripheral (USRP) to analyze the actual wireless spectrum.
Smart dust consists of tiny autonomous sensing devices called motes that are less than 1.5mm3 in volume and 5mg in mass. Motes can collect sensor data and transmit it wirelessly over distances of 15-50m to a base station using radio frequency, passive optical reflectors, or active laser transmitters. They incorporate sensors, microprocessors, memory, transmitters and receivers, and thick film batteries or solar cells to operate independently for long periods with very low power usage. Potential applications include environmental monitoring, infrastructure inspection, health monitoring, and more.
This document describes a landslide monitoring project that uses wireless sensor nodes to monitor factors like slope angle, water depth, and temperature that could indicate an impending landslide. Sensors are connected to Arduino nodes that transmit the data via XBee radios. The network switches between a tree and star topology depending on whether a light or heavy landslide is detected. The project aims to warn people and authorities about landslides so protective measures can be taken.
This document summarizes a research paper on detecting intruders in a wireless sensor network using low-power passive infrared (PIR) sensors. It presents an algorithm that uses the Haar transform and support vector machines to distinguish intruder signatures from clutter signatures in the sensor data. The algorithm was tested through simulations and field experiments, achieving detection rates over 90% while minimizing false alarms. However, limitations were observed when testing in high-clutter summer conditions. An analytical model of intruder signatures suggests that velocity and direction information cannot be extracted from a single sensor but may require a network of spatially distributed sensors.
Design and implementation of advanced security system based on one time passwIAEME Publication
This document describes the design and implementation of an advanced security system based on one-time passwords for highly secure areas. The system uses multiple sensors including PIR, IR, vibration, and magnetic sensors to detect intrusions. When a sensor is triggered, the system requests a one-time password that is sent to authorized users' mobile phones. The system is aimed at providing security for places like defense establishments, nuclear plants, and other secure facilities by only allowing access to those who can provide the correct one-time password.
A continuous time adc and digital signal processing system for smart dust and...eSAT Journals
This document discusses a continuous-time (CT) analog-to-digital converter (ADC) and digital signal processing system suitable for applications like smart dust and wireless sensor networks. The key benefits of the CT system are lower noise, no need for a clock generator or anti-aliasing filter.
The paper proposes a clockless, event-driven CTADC based on delta modulation. An unbuffered, area-efficient segmented resistor string digital-to-analog converter is used. This architecture achieves an 87.5% reduction in resistors, switches and flip-flops for an 8-bit converter compared to prior designs.
The CTADC uses a level-crossing sampling technique where samples are generated when
A continuous time adc and digital signal processing system for smart dust and...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
A continuous time adc and digital signal processing system for smart dust and...eSAT Journals
This document discusses a continuous-time (CT) analog-to-digital converter (ADC) and digital signal processing system suitable for smart dust and wireless sensor applications. The system uses a clockless event-driven ADC based on CT delta modulation. The ADC output is digital data continuous in time known as "data tokens". The system achieves lower power consumption and area than conventional clocked systems by operating without a clock generator or anti-aliasing filter. The 8-bit ADC system achieves a signal-to-noise ratio of 55.73 dB and effective number of bits of over 9 within an input band of 220 kHz, demonstrating its suitability for smart dust applications.
This document provides an overview of hardware platforms for Internet of Things (IoT) systems. It discusses sensors and actuators, describing different types of sensors and their characteristics. It then examines node architecture, using the XM1000 mote as a case study to illustrate the typical components of a node, including sensors, microcontroller, communication unit, and power supply. Finally, it analyzes communication architecture, focusing on the IEEE 802.15.4 standard for low-power wireless personal area networks, covering its physical layer, medium access control layer operation, and networking solutions built upon it like ZigBee and 6LoWPAN.
Energy-Efficient Target Coverage in Wireless Sensor Networks Based on Modifie...ijasuc
One of the major issues in Target-coverage problem of wireless sensor network is to increase the network
lifetime. This can be solved by selecting minimum working nodes that will cover all the targets. This
paper proposes a completely new method, in which minimum working node is selected by modified Ant
colony Algorithm. Experimental results show that the lever of algorithmic complication is depressed and
the searching time is reduced, and the proposed algorithm outperforms the other algorithm in terms.
Energy-Efficient Target Coverage in Wireless Sensor Networks Based on Modifie...ijasuc
One of the major issues in Target-coverage problem of wireless sensor network is to increase the network
lifetime. This can be solved by selecting minimum working nodes that will cover all the targets. This
paper proposes a completely new method, in which minimum working node is selected by modified Ant
colony Algorithm. Experimental results show that the lever of algorithmic complication is depressed and
the searching time is reduced, and the proposed algorithm outperforms the other algorithm in terms.
Energy-Efficient Target Coverage in Wireless Sensor Networks Based on Modifie...ijasuc
One of the major issues in Target-coverage problem of wireless sensor network is to increase the network
lifetime. This can be solved by selecting minimum working nodes that will cover all the targets. This
paper proposes a completely new method, in which minimum working node is selected by modified Ant
colony Algorithm. Experimental results show that the lever of algorithmic complication is depressed and
the searching time is reduced, and the proposed algorithm outperforms the other algorithm in terms.
Weather monitoring plays a very important role in human life hence study of weather system is necessary.
Currently there are two types of the weather monitoring stations available i.e. wired and wireless. Wireless
system has some advantages over the wired one hence popular now a days. The parameters are include in
weather monitoring usually temperature, humidity atmospheric pressure, light intensity, rainfall etc. There are
many techniques existed using different processor such as PIC, AVR, ARM etc. Analog to digital channel are
used to fetch the analog output of the sensors. The wireless techniques used in the weather monitoring having
GSM, FM channel, Zigbee, RF etc Protocols.
Transducers are devices that convert one form of energy to another. Silicon can be used in smart sensors and transducers due to its piezoresistance and ability to detect various signals including light, force, temperature, and chemicals. Smart sensors integrate transduction elements with electronics, which provides advantages like smaller size, self-calibration, computation, communication, and multi-sensing capabilities.
Distributed Beamforming in Sensor NetworksDaniel Tai
The document discusses two papers on distributed beamforming techniques in sensor networks. The first technique computes beamforming vectors iteratively using feedback from the receiver to maximize SNR. The second technique uses an adaptive least squares algorithm by the cluster head to minimize error between the received and reference signals. Key differences are that the first method is fully distributed while the second has a cluster head, and the first uses feedback while the second uses a reference signal. Simulation results show convergence over time for the first method and the impact of factors like node density for the second.
This document describes a radar jamming circuit designed to jam an X-band radar. The circuit uses an ATmega16 microcontroller, Basic Stamp microcontroller, two X-band motion detector modules, and an LCD display. One motion detector acts as the radar and the other acts as a jammer, generating a 10.5 GHz frequency using the Doppler effect. Testing showed that when the jammer was active, it successfully denied the radar detection by reducing the number of detected pulses compared to when no jamming occurred. The results demonstrate that an active jamming technique can effectively deny the use of the radar spectrum within a certain distance between the radar and jammer.
Design and Simulation Microstrip patch Antenna using CST Microwave StudioAymen Al-obaidi
The document describes the design and simulation of a microstrip patch antenna in CST Microwave Studio. It begins with an introduction to microstrip patch antennas and their applications. Then, it outlines the theoretical design of a rectangular patch antenna for 2.4 GHz WiFi using transmission line equations. Finally, it details the simulation process in CST Microwave Studio, including adding the patch, feedline, substrate and ground plane, assigning materials and frequencies, setting up the port and monitors, and solving to obtain results like the bandwidth and radiation pattern.
1) The document discusses methods for improving the sensitivity of electronic support measure (ESM) receivers through post-integration processing using autocorrelation and cross-correlation.
2) Autocorrelation processing takes advantage of the periodic nature of radar signals to improve detection of high repetition frequency signals. It provides a sensitivity gain that depends on the integration window and pulse repetition interval.
3) Three estimators are examined for extracting radar parameters: a straightforward method, interpolation method, and maximum likelihood method, with the maximum likelihood method providing the best accuracy.
Similar to Adaptive model selection in Wireless Sensor Networks (20)
A statistical criterion for reducing indeterminacy in linear causal modelingGianluca Bontempi
This document proposes a new statistical criterion called C to help distinguish between causal patterns in completely connected triplets when inferring causal relationships from observational data. The criterion is based on differences in values of the term S, which is derived from the covariance matrix, between different causal hypotheses. This criterion informs an algorithm called RC that incorporates both relevance and causal measures to iteratively select variables. Experiments on linear and nonlinear networks show RC has higher accuracy than other algorithms at inferring network structure. The criterion C and RC algorithm help address challenges of causal inference from complex data where dependencies are frequent.
Combining Lazy Learning, Racing and Subsampling for Effective Feature SelectionGianluca Bontempi
This document discusses approaches to feature selection for machine learning models, specifically comparing global versus local modeling techniques. It proposes combining lazy learning, racing, and subsampling for effective feature selection. Lazy learning uses local linear models for prediction rather than global nonlinear models, improving computational efficiency when many predictions are needed. Racing and subsampling allow efficient evaluation of feature subsets during wrapper-based feature selection by discarding poor-performing subsets early based on statistical tests of performance on subsets of the data. Experimental results are said to validate this combined approach for feature selection.
A model-based relevance estimation approach for feature selection in microarr...Gianluca Bontempi
This document presents a model-based approach for estimating feature relevance for feature selection in microarray datasets. It aims to provide an unbiased relevance estimation between filter and wrapper methods. The approach combines a low-bias k-nearest neighbor cross-validation error estimator with either a direct probability model estimator or a mutual information filter estimator to reduce variance. Experimental results on 20 public microarray datasets compare the proposed combined estimators to a support vector machine wrapper approach.
Machine Learning Strategies for Time Series PredictionGianluca Bontempi
This document introduces machine learning strategies for time series prediction. It begins with an introduction to the speaker and his background and research interests. It then provides an outline of the topics to be covered, including notions of time series, machine learning approaches for prediction, local learning methods, forecasting techniques, and applications and future directions. The document discusses what the audience should know coming into the course and what they will learn.
This document discusses using feature selection techniques to address the curse of dimensionality in microarray data analysis. It presents the problem of having many more features than samples in bioinformatics tasks like cancer classification and network inference. It describes filter, wrapper and embedded feature selection approaches and proposes a blocking strategy that uses multiple learning algorithms to evaluate feature subsets in order to improve selection robustness when samples are limited. Finally, it lists several microarray gene expression datasets that are commonly used to evaluate feature selection methods.
A Monte Carlo strategy for structure multiple-step-head time series predictionGianluca Bontempi
The document proposes a Monte Carlo approach called SMC (Structured Monte Carlo) for multiple-step-ahead time series forecasting that takes into account the structural dependencies between predictions. It generates samples using a direct forecasting approach and weights them based on how well they satisfy dependencies identified by an iterated approach. Experiments on three benchmark datasets show the SMC approach achieves more accurate forecasts as measured by SMAPE than iterated, direct, or other comparison methods for most prediction horizons tested.
THM1: Formalizing a problem as a prediction problem is often the most important contribution of a data scientist.
THM2: A predictor is an estimator, i.e. an algorithm which takes data and returns a prediction. Reality is stochastic, so data and predictions are stochastic.
THM3: Learning is challenging since data must be used both to create prediction models and to assess them. Bias and variance must be balanced to achieve good generalization.
FP7 evaluation & selection: the point of view of an evaluatorGianluca Bontempi
The document discusses the process of evaluating proposals for EU funding as an EU evaluator. It begins by introducing the author's expertise and background evaluating FP6 and FP7 proposals. It then outlines the evaluation process, which involves individual evaluation of assigned proposals followed by consensus building and panel evaluation. Key aspects covered include managing conflicts of interest, maintaining confidentiality, and adhering to a code of conduct. The evaluation criteria for integrated projects focus on relevance to program objectives, potential impact, scientific and technological excellence, quality of consortium, and quality of management.
Local modeling in regression and time series predictionGianluca Bontempi
The document discusses global modeling versus local modeling approaches for regression and time series prediction problems. Global modeling fits a single analytical function to all input data, while local modeling performs separate fits to subsets of nearby data points. The document outlines the local modeling approach using lazy learning, which stores all training data and performs local fits when making predictions for new query points. It then applies lazy learning techniques to problems in regression, time series prediction, and feature selection.
This document discusses feature selection methods for causal inference in bioinformatics. It describes how relevance and causality differ, with relevant features not always being causal. Information theory concepts like mutual information, conditional mutual information, and interaction information are introduced to quantify dependence and independence between variables. The min-Interaction Max-Relevance (mIMR) filter method is proposed to select features based on both relevance to the target and minimal interaction, approximating causal relationships. Experimental results on breast cancer gene expression datasets show mIMR outperforms conventional ranking in predictive performance, identifying a potential causal signature for survival.
Computational Intelligence for Time Series PredictionGianluca Bontempi
This document provides an overview of computational intelligence methods for time series prediction. It begins with introductions to time series analysis and machine learning approaches for prediction. Specific models discussed include autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA) processes. Parameter estimation techniques for AR models are also covered. The document outlines applications in areas like forecasting, wireless sensors, and biomedicine and concludes with perspectives on future directions.
The Ipsos - AI - Monitor 2024 Report.pdfSocial Samosa
According to Ipsos AI Monitor's 2024 report, 65% Indians said that products and services using AI have profoundly changed their daily life in the past 3-5 years.
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...Social Samosa
The Modern Marketing Reckoner (MMR) is a comprehensive resource packed with POVs from 60+ industry leaders on how AI is transforming the 4 key pillars of marketing – product, place, price and promotions.
End-to-end pipeline agility - Berlin Buzzwords 2024Lars Albertsson
We describe how we achieve high change agility in data engineering by eliminating the fear of breaking downstream data pipelines through end-to-end pipeline testing, and by using schema metaprogramming to safely eliminate boilerplate involved in changes that affect whole pipelines.
A quick poll on agility in changing pipelines from end to end indicated a huge span in capabilities. For the question "How long time does it take for all downstream pipelines to be adapted to an upstream change," the median response was 6 months, but some respondents could do it in less than a day. When quantitative data engineering differences between the best and worst are measured, the span is often 100x-1000x, sometimes even more.
A long time ago, we suffered at Spotify from fear of changing pipelines due to not knowing what the impact might be downstream. We made plans for a technical solution to test pipelines end-to-end to mitigate that fear, but the effort failed for cultural reasons. We eventually solved this challenge, but in a different context. In this presentation we will describe how we test full pipelines effectively by manipulating workflow orchestration, which enables us to make changes in pipelines without fear of breaking downstream.
Making schema changes that affect many jobs also involves a lot of toil and boilerplate. Using schema-on-read mitigates some of it, but has drawbacks since it makes it more difficult to detect errors early. We will describe how we have rejected this tradeoff by applying schema metaprogramming, eliminating boilerplate but keeping the protection of static typing, thereby further improving agility to quickly modify data pipelines without fear.
ViewShift: Hassle-free Dynamic Policy Enforcement for Every Data LakeWalaa Eldin Moustafa
Dynamic policy enforcement is becoming an increasingly important topic in today’s world where data privacy and compliance is a top priority for companies, individuals, and regulators alike. In these slides, we discuss how LinkedIn implements a powerful dynamic policy enforcement engine, called ViewShift, and integrates it within its data lake. We show the query engine architecture and how catalog implementations can automatically route table resolutions to compliance-enforcing SQL views. Such views have a set of very interesting properties: (1) They are auto-generated from declarative data annotations. (2) They respect user-level consent and preferences (3) They are context-aware, encoding a different set of transformations for different use cases (4) They are portable; while the SQL logic is only implemented in one SQL dialect, it is accessible in all engines.
#SQL #Views #Privacy #Compliance #DataLake
The Building Blocks of QuestDB, a Time Series Databasejavier ramirez
Talk Delivered at Valencia Codes Meetup 2024-06.
Traditionally, databases have treated timestamps just as another data type. However, when performing real-time analytics, timestamps should be first class citizens and we need rich time semantics to get the most out of our data. We also need to deal with ever growing datasets while keeping performant, which is as fun as it sounds.
It is no wonder time-series databases are now more popular than ever before. Join me in this session to learn about the internal architecture and building blocks of QuestDB, an open source time-series database designed for speed. We will also review a history of some of the changes we have gone over the past two years to deal with late and unordered data, non-blocking writes, read-replicas, or faster batch ingestion.
Global Situational Awareness of A.I. and where its headedvikram sood
You can see the future first in San Francisco.
Over the past year, the talk of the town has shifted from $10 billion compute clusters to $100 billion clusters to trillion-dollar clusters. Every six months another zero is added to the boardroom plans. Behind the scenes, there’s a fierce scramble to secure every power contract still available for the rest of the decade, every voltage transformer that can possibly be procured. American big business is gearing up to pour trillions of dollars into a long-unseen mobilization of American industrial might. By the end of the decade, American electricity production will have grown tens of percent; from the shale fields of Pennsylvania to the solar farms of Nevada, hundreds of millions of GPUs will hum.
The AGI race has begun. We are building machines that can think and reason. By 2025/26, these machines will outpace college graduates. By the end of the decade, they will be smarter than you or I; we will have superintelligence, in the true sense of the word. Along the way, national security forces not seen in half a century will be un-leashed, and before long, The Project will be on. If we’re lucky, we’ll be in an all-out race with the CCP; if we’re unlucky, an all-out war.
Everyone is now talking about AI, but few have the faintest glimmer of what is about to hit them. Nvidia analysts still think 2024 might be close to the peak. Mainstream pundits are stuck on the wilful blindness of “it’s just predicting the next word”. They see only hype and business-as-usual; at most they entertain another internet-scale technological change.
Before long, the world will wake up. But right now, there are perhaps a few hundred people, most of them in San Francisco and the AI labs, that have situational awareness. Through whatever peculiar forces of fate, I have found myself amongst them. A few years ago, these people were derided as crazy—but they trusted the trendlines, which allowed them to correctly predict the AI advances of the past few years. Whether these people are also right about the next few years remains to be seen. But these are very smart people—the smartest people I have ever met—and they are the ones building this technology. Perhaps they will be an odd footnote in history, or perhaps they will go down in history like Szilard and Oppenheimer and Teller. If they are seeing the future even close to correctly, we are in for a wild ride.
Let me tell you what we see.
Open Source Contributions to Postgres: The Basics POSETTE 2024ElizabethGarrettChri
Postgres is the most advanced open-source database in the world and it's supported by a community, not a single company. So how does this work? How does code actually get into Postgres? I recently had a patch submitted and committed and I want to share what I learned in that process. I’ll give you an overview of Postgres versions and how the underlying project codebase functions. I’ll also show you the process for submitting a patch and getting that tested and committed.
Adaptive model selection in Wireless Sensor Networks
1. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Yann-A¨el Le Borgne, Gianluca Bontempi
Machine Learning Group
Department of Computer Science
Universit´e Libre de Bruxelles
May 15th, 2009
2. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Wireless sensors: latest trend of Moore’s law (1965)
“The number of transistors that can be
placed inexpensively on an integrated circuit
doubles every two years.”
1950 1990 2000 2010
Computing devices get
Smaller
Cheaper
→ Enable new kinds of interactions with our world
3. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Wireless sensors
Sensor nodes can collect, process and communicate data
[Warneke et al., 2001; Akyildiz et al., 2002]
TMote Sky
Deputy dust
Sensors: Light, temperature, humidity,
pressure, acceleration, sound, . . .
Radio: ∼ 10s kbps, ∼ 10s meters
Microprocessor: A few MHz
Memory: ∼ 10s KB
4. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Environmental monitoring and periodic data collection
Base
station
Wireless node
Internet
Sensor network
Base station
separate calibration procedures to test the system prior to
placing it in the field, and then spent a day in the forest
with ropes, harnesses, and a notebook.
We decided on the following envelope for our deployment:
Time: One month during the early summer, sampling all
sensors once every 5 minutes. The early summer con-
tains the most dynamic microclimatic variation. We
decided that sampling every 5 minutes would be suffi-
cient to capture that variation.
Vertical Distance: 15m from ground level to 70m from
ground level, with roughly a 2-meter spacing between
nodes. This spatial density ensured that we could cap-
ture gradients in enough detail to interpolate accu-
rately. The envelope began at 15m because most of
the foliage was in the upper region of the tree.
Angular Location: The west side of the tree. The west
side had a thicker canopy and provided the most buffer-
ing against direct environmental effects.
Radial Distance: 0.1-1.0m from the trunk. The nodes
were placed very close to the trunk to ensure that we
were capturing the microclimatic trends that affected
the tree directly, and not the broader climate.
Figure 1 shows the final placement of each mote in the
tree. We also placed several nodes outside of our angular
and radial envelope in order to monitor the microclimate in
the immediate vicinity of other biological sensing equipment
that had previously been installed.
Figure 1: The placement of nodes within the tree
4.1 Hardware and Network Architecture
The sensor node platform was a Mica2Dot, a repackaged
Mica2 mote produced by Crossbow, with a 1 inch diameter
form factor. The mote used an Atmel ATmega128 micro-
controller running at 4 MHz, a 433 MHz radio from Chip-
con operating at 40Kbps, and 512KB of flash memory. The
mote was connected to digital sensors using I2C and SPI
serial protocols and to analog sensors using the on-board
ADC.
The choice of measured parameters was driven by the bio-
logical requirements. We measured traditional climate vari-
ables – temperature, humidity, and light levels. Tempera-
ture and relative humidity feed directly into transpiration
models for redwood forests. Photosynthetically active radi-
ation (PAR, wavelength from 350 to 700 nm) provides infor-
mation about energy available for photosynthesis and tells
us about drivers for the carbon balance in the forest. We
measure both incident (direct) and reflected (ambient) levels
of PAR. Incident measurements provide insight into the en-
ergy available for photosynthesis, while the ratio of reflected
to incident PAR allows for eventual validation of satellite
remote sensing measurements of land surface reflectance.
The Sensirion SHT11 digital sensor provided temperature
(± 0.5◦
C) and humidity (± 3.5%) measurements. The in-
cident and reflected PAR measurements were collected by
two Hamamatsu S1087 photodiodes interfaced to the 10-bit
ADC on Mica2Dot.
The platform also included a TAOS TSL2550 sensor to
measure total solar radiation (300nm - 1000nm), and an
Intersema MS5534A to measure barometric pressure, but
we chose not to use them in our deployment. During cali-
bration, we found that the TSR sensor was overly sensitive,
and would not produce useful information in direct sunlight.
Because TSR and PAR would have told roughly the same
story, and because PAR was more useful from the biology
viewpoint, we decided not to gather data on total solar ra-
diation. As for the pressure sensor, barometric pressure is
simply too diffuse a phenomenon to show appreciable differ-
ences over the height of a single redwood tree. A standard
pressure gradient would exist as a direct function of height,
but any pressure changes due to weather would affect the
entire tree equally. Barometric pressure sensing should be
useful in future large-scale climate studies.
The package for such a deployment needs to protect the
electronics from the weather while safely exposing the sen-
sors. Our chosen sensing modalities place specific require-
ments on the package. Standardized temperature and hu-
midity sensing should be performed in a shaded area with
adequate airflow, implying that the enclosure must provide
such a space while absorbing little radiated heat. The out-
put of the sensors that measure direct radiation is dependent
on the sensor orientation, so the enclosure must expose these
sensors and level their sensing plane. The sensors measuring
ambient levels of PAR must be shaded but need a relatively
wide field of view.
The package designed for this deployment is shown in Fig-
ure 2. The mote, the battery, and two sensor boards fit in-
side the sealed cylindrical enclosure. The enclosure is milled
from white HDPE, and reflects most of the radiated heat.
The endcaps of the cylinder form two sensing surfaces – one
captures direct radiation, the other captures all other mea-
surements. The white “skirt” provides extra shade, protec-
53
One-to-one applications Many-to-one applications
Data is sent by nodes periodically to a base station.
Applications: Medical, interactive arts, ecology, industry,
disaster prevention.
5. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Challenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
Operation mode Telos node
Standby 5.1 µA
MCU Active 1.8 mA
MCU + Radio RX 21.8 mA
MCU + Radio TX (0dBm) 19.5 mA
The radio is the most energy consuming module.
95% of energy consumption in typical data collection tasks [Madden, 2003].
If run continuoulsy with the radio, the lifetime is about 5 days.
6. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Challenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
Operation mode Telos node
Standby 5.1 µA
MCU Active 1.8 mA
MCU + Radio RX 21.8 mA
MCU + Radio TX (0dBm) 19.5 mA
The radio is the most energy consuming module.
95% of energy consumption in typical data collection tasks [Madden, 2003].
If run continuoulsy with the radio, the lifetime is about 5 days.
7. Preliminaries Adaptive Model Selection Adaptive Model Selection
Supervised learning
Goal:
Using examples, find relationships in data by means of
prediction models hθ (parametric functions).
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
0 20 40 60 80 100 120
020406080100120
x
y
Time
Measurement
t
si[t]
Model
si[t] = θt
Training
examples
8. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Modeling data with parametric functions
Let S = {1, 2, . . . , S} be the set of S sensor nodes.
Let t ∈ N denote time instants, or epochs.
Let si [t] be the measurement of sensor i ∈ S at epoch t.
A model is a parametric function
hθ : Rn
→ R
x → ˆsi [t] = hθ(x)
hθ : Model with parameter θ ∈ Rp
x ∈ Rn: Input.
ˆsi [t] ∈ R: approximation to si [t]
Temporal models, e.g., ˆsi [t] = θ1si [t − 1] + θ2si [t − 2]
x = (si [t − 1], si [t − 2]): past measurements of sensor i are
used to model si [t].
Spatial models, e.g., ˆsi [t] = θ1sj [t] + θ2sk [t]
x = (sj [t], sk [t]), j, k ∈ S: measurements of sensors j and k are
used to model measurements of sensor i.
9. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Modeling data with parametric functions
Let S = {1, 2, . . . , S} be the set of S sensor nodes.
Let t ∈ N denote time instants, or epochs.
Let si [t] be the measurement of sensor i ∈ S at epoch t.
A model is a parametric function
hθ : Rn
→ R
x → ˆsi [t] = hθ(x)
hθ : Model with parameter θ ∈ Rp
x ∈ Rn: Input.
ˆsi [t] ∈ R: approximation to si [t]
Temporal models, e.g., ˆsi [t] = θ1si [t − 1] + θ2si [t − 2]
x = (si [t − 1], si [t − 2]): past measurements of sensor i are
used to model si [t].
Spatial models, e.g., ˆsi [t] = θ1sj [t] + θ2sk [t]
x = (sj [t], sk [t]), j, k ∈ S: measurements of sensors j and k are
used to model measurements of sensor i.
10. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Modeling data with parametric functions
Let S = {1, 2, . . . , S} be the set of S sensor nodes.
Let t ∈ N denote time instants, or epochs.
Let si [t] be the measurement of sensor i ∈ S at epoch t.
A model is a parametric function
hθ : Rn
→ R
x → ˆsi [t] = hθ(x)
hθ : Model with parameter θ ∈ Rp
x ∈ Rn: Input.
ˆsi [t] ∈ R: approximation to si [t]
Temporal models, e.g., ˆsi [t] = θ1si [t − 1] + θ2si [t − 2]
x = (si [t − 1], si [t − 2]): past measurements of sensor i are
used to model si [t].
Spatial models, e.g., ˆsi [t] = θ1sj [t] + θ2sk [t]
x = (sj [t], sk [t]), j, k ∈ S: measurements of sensors j and k are
used to model measurements of sensor i.
11. Preliminaries Adaptive Model Selection Adaptive Model Selection
Learning
Learning procedure
The model parameters are obtained by a learning procedure,
based on a training set of N examples. A loss function L(y, ˆy)
is used to minimize the model error.
Target function
Prediction model
Training set
output ˆy
output yinput x
error L(y, ˆy)
Learning procedure
Loss function: Quadratic, Zero/One, . . .
Learning procedure: Linear/nonlinear regression, K nearest
neighbors, SVM, . . .
12. Preliminaries Adaptive Model Selection Adaptive Model Selection
Learning
Learning procedure
The model parameters are obtained by a learning procedure,
based on a training set of N examples. A loss function L(y, ˆy)
is used to minimize the model error.
Target function
Prediction model
Training set
output ˆy
output yinput x
error L(y, ˆy)
Learning procedure
Loss function: Quadratic, Zero/One, . . .
Learning procedure: Linear/nonlinear regression, K nearest
neighbors, SVM, . . .
14. Preliminaries Adaptive Model Selection Adaptive Model Selection
State of the art: Temporal replicated models
Overview
Base
station
Wireless node
Model Copy of modelhθ hθ
Models are used to predict sensors’ measurements over time.
A user defined threshold determines when a sensor node
updates the model.
Constant model [Olston et al., 2001]
ˆsi [t] = si [t − 1]
Most simple: no parameter to compute
15. Preliminaries Adaptive Model Selection Adaptive Model Selection
Temporal replicated models
Overview
Temperature measurements, Solbosch greenhouse.
160 170 180 190 200 210 220
30323436384042
Accuracy: 2°C
Constant model
Time instants
Temperature(°C)
q q q q q
Sensor node
Base station
5 updates instead of 58
→ more than 90% of communication savings.
16. Preliminaries Adaptive Model Selection Adaptive Model Selection
Temporal replicated models
From simple to complex model
Constant model
ˆsi [t] = si [t − 1]
Most simple
No parameter to compute
Not complex
Autoregressive model AR(p)
ˆsi [t] = θ1si [t−1]+. . .+θpsi [t−p]
Regression
θ = (XT X)−1XT Y
using N past observations
Least Mean Square
Provides a way to compute
θ recursively with µ as the
step size
0 5 10 15 20
202530354045
Accuracy: 2°C
Constant model
Time (Hour)
Temperature(°C)
q qq qqq qq q q qq q q q q q q q q q
0 5 10 15 20
202530354045
Accuracy: 2°C
AR(2)
Time (Hour)
Temperature(°C)
q qq q q qqq q qq q q q q q q
17. Preliminaries Adaptive Model Selection Adaptive Model Selection
Temporal replicated models
From simple to complex model
Constant model
ˆsi [t] = si [t − 1]
Most simple
No parameter to compute
Not complex
Autoregressive model AR(p)
ˆsi [t] = θ1si [t−1]+. . .+θpsi [t−p]
Regression
θ = (XT X)−1XT Y
using N past observations
Least Mean Square
Provides a way to compute
θ recursively with µ as the
step size
0 5 10 15 20
202530354045
Accuracy: 2°C
Constant model
Time (Hour)
Temperature(°C)
q qq qqq qq q q qq q q q q q q q q q
0 5 10 15 20
202530354045
Accuracy: 2°C
AR(2)
Time (Hour)
Temperature(°C)
q qq q q qqq q qq q q q q q q
18. Preliminaries Adaptive Model Selection Adaptive Model Selection
State of the art: Temporal replicated models
Pros and cons
Pros:
Guarantee the observer with accuracy.
Simple or complex models can be used (from constant model
[Olston, 2001] to autoregressive models [Santini et al., Tulone
et al., 2006]).
Cons:
In most cases, no a priori information is available on the
measurements. Which model to choose a priori?
The metric (update rate) does not consider the number of
parameters of the models.
19. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Motivation
Tradeoff: More complex models better predict measurements,
but have a higher number of parameters.
Model complexity
Metric
Communication costs
Model error
AR(p) : ˆsi[t] =
p
j=1
θjsi[t − j]
20. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Collection of models
With Adaptive Model Selection (AMS), a collection of K
models {hk}, 1 ≤ k ≤ K, of increasing complexity are run by
the node. Wk: metric estimating the communication savings.
h1 h2 h3 h4
Model complexity
(W1) (W2) (W3) (W4)
21. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Metric to assess communication savings
Metric suggested: the weighted update rate
Wk[t] = CkUk[t]
Update rate Uk [t]: percentage of updates for model k at
epoch t ([Olston, 2001, Jain et al., 2004, Santini et al., Tulone
et al., 2006]).
Model cost Ck : takes into account the number of parameters
of the k-th model.
Ck = P
P−D+1
P: Size of the packet.
D: Size of the data load.
→ P − D is the packet overhead
SYNC Packet Address Message Group Data . . . Data CRC SYNC
BYTE Type Type ID Length BYTE
1 2 3 5 6 7 . . . Size D P-2 P
22. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Model selection
When an update is required, the model hk with
k = argminkWk[t] is sent to the base station.
Assuming stationarity in the data, the confidence in each
estimated Wk[t] increases with t.
Running poorly performing models is detrimental to energy
consumption.
Racing [Maron, 1997]: Model selection technique based on
the Hoeffding bound, which allows to discard poorly
performing models.
23. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Model selection
When an update is required, the model hk with
k = argminkWk[t] is sent to the base station.
Assuming stationarity in the data, the confidence in each
estimated Wk[t] increases with t.
Running poorly performing models is detrimental to energy
consumption.
Racing [Maron, 1997]: Model selection technique based on
the Hoeffding bound, which allows to discard poorly
performing models.
24. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Hoeffding bound
Let x be a random variable with range R. Let µ be its mean.
Let µ[t] be an estimate of µ using t samples of x.
Given a confidence 1 − δ, the Hoeffding bound states that
P(|µ − µ[t]| < ∆) > 1 − δ
with ∆ = R ln 1/δ
2t [Hoeffding, 1963].
In AMS, the random variable considered is the model
performance Wk. Wk[t] is the estimate of Wk after t epochs.
We have Wk[t] = CkU[t]. The range of Wk[t] is R = 100Ck
as U[t] ≤ 100.
25. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Hoeffding bound
Let x be a random variable with range R. Let µ be its mean.
Let µ[t] be an estimate of µ using t samples of x.
Given a confidence 1 − δ, the Hoeffding bound states that
P(|µ − µ[t]| < ∆) > 1 − δ
with ∆ = R ln 1/δ
2t [Hoeffding, 1963].
In AMS, the random variable considered is the model
performance Wk. Wk[t] is the estimate of Wk after t epochs.
We have Wk[t] = CkU[t]. The range of Wk[t] is R = 100Ck
as U[t] ≤ 100.
26. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Best model: Wk[t] for which k = arg minkWk[t]. Upper
bound is Wk[t] + 100Ck
ln 1/δ
2t .
If a model hk has
Wk [t] − 100Ck
ln 1/δ
2t
> Wk[t] + 100Ck
ln 1/δ
2t
then it can be discarded.
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
Upper bound
for error
Estimated error
for
h3
h4
The test used is Wk [t] − Wk[t] > 100(Ck + Ck ) ln 1/δ
2t
Using racing, models h1 and h6 are discarded.
27. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
Upper bound
for error
Estimated error
for
h3
h4
The test used is Wk [t] − Wk[t] > 100(Ck + Ck ) ln 1/δ
2t
Using racing, models h1 and h6 are discarded.
28. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Experimental evaluation
14 time series, various types of measured physical quantities.
Data set Sensed quantity Sampling period Duration Number of samples
S Heater temperature 3 seconds 6h15 3000
I Light light 5 minutes 8 days 1584
M Hum humidity 10 minutes 30 days 4320
M Temp temperature 10 minutes 30 days 4320
NDBC WD wind direction 1 hour 1 year 7564
NDBC WSPD wind speed 1 hour 1 year 7564
NDBC DPD dominant wave period 1 hour 1 year 7562
NDBC AVP average wave period 1 hour 1 year 8639
NDBC BAR air pressure 1 hour 1 year 8639
NDBC ATMP air temperature 1 hour 1 year 8639
NDBC WTMP water temperature 1 hour 1 year 8734
NDBC DEWP dewpoint temperature 1 hour 1 year 8734
NDBC GST gust speed 1 hour 1 year 8710
NDBC WVHT wave height 1 hour 1 year 8723
Error threshold is set to 0.01r where r is the range of the
measurements.
AMS is run with k = 6 models: the constant model (CM) and
autoregressive models AR(p) with p ranging from 1 to 5.
29. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Experimental evaluation
Assuming a packet overhead of 24 bytes, the model cost is set
to CCM = 1 for the CM, and to CAR(p) = 24+2p
24+1 for an AR(p).
CM AR1 AR2 AR3 AR4 AR5 AMS
S Heater 74 78 68 70 76 81 AR2
I Light 38 42 44 48 51 53 CM
M Hum 53 55 55 60 62 66 CM
M Temp 48 50 50 54 56 60 CM
NDBC DPD 65 89 89 95 102 109 CM
NDBC AWP 72 75 81 88 93 99 CM
NDBC BAR 51 52 44 47 49 50 AR2
NDBC ATMP 39 41 40 43 46 49 CM
NDBC WTMP 27 28 23 25 27 28 AR2
NDBC DEWP 57 54 58 62 67 71 AR1
NDBC WSPD 74 87 92 99 106 113 CM
NDBC WD 85 84 91 98 104 111 AR1
NDBC GST 80 84 90 96 103 110 CM
NDBC WVHT 58 58 63 67 71 76 CM
Bold numbers report significantly better update rates
(Hoeffding bound, δ = 0.05).
For all time series, the AMS selects the best model.
30. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Experimental evaluation
Number of models remaining over time:
0 200 400 600 800 1000
02468101214
timeChange[1, ]
rep(1,7)
6 4 3 2 1
6 1
6 5 4 3 1
6 5 3 1
6 2 1
6 3 2 1
6 5 4 3 2 1
6 5 4 1
6 5 1
6 4 3 2 1
6 1
6 3 2 1
6 3 2 1
6 4 3 2 1
Time instants
S Heater
I Light
M Hum
M Temp
NDBC DPD
NDBC AWP
NDBC BAR
NDBC ATMP
NDBC WTMP
NDBC DEWP
NDBC WSPD
NDBC WD
NDBC GST
NDBC WVHT
The speed of convergence of the racing algorithm depends on
the time series, and is in most cases reasonably fast.
31. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Conclusions
In summary, Adaptive Model Selection
Takes into account the cost of sending model parameters,
Allows sensor nodes to determine autonomously the model
which best fits their measurements,
Provides a statistically sound selection mechanism to discard
poorly performing models,
Gave in experimental results about 45% of communication
savings on average,
Was implemented in TinyOS, the reference operating system.
32. Preliminaries Adaptive Model Selection Adaptive Model Selection
Additional contributions
Several deployments at the ULB.
Data sets (and code) available at www.ulb.ac.be/di/labo.
Microclimate monitoring - Solbosch greenhouses.
18 sensors in three greenhouses. Several experiments.
Data collected: Temperature, humidity and light.
Sampling interval: 5 minutes.
Experimental setups monitoring - Unit of Social Ecology.
18 sensors in three experimental labs, running for 5 days.
Data collected: Temperature, humidity and light.
Sampling interval: 5 minutes.
PIMAN project (R´egion Bruxelles Capitale - 2007/2008):
Goal: localize an operator in an industrial environment.
Techniques: Triangulation, multidimensional scaling, Kalman filters.
Several deployments (up to 48 sensors).
34. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Data centric networking
A sensor network can be seen as a distributed database.
SQL can be used as the language to interact with the network:
SELECT temperature FROM sensors
WHERE location=[0,0, 15, 35]
DURATION=00:00:00,10:00:00
EPOCH DURATION 30s
1
5
7
6
3
2 4
Base
station
1
5
7
6
3
2 4
Base
station
1
5
7
6
3
2 4
Base
station
The query is broadcasted from the base station to the
network. Sensors involved in the query establish a routing
structure towards the base station.
35. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Challenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
ess Sensor Networks
allenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
Operation mode Telos node
Standby 5.1 µA
MCU Active 1.8 mA
MCU + Radio RX 21.8 mA
MCU + Radio TX (0dBm) 19.5 mA
he radio is the most energy consuming module.
% of energy consumption in typical data collection tasks [Madden, 2003].
un continuoulsy with the radio, the lifetime is about 5 days.
x10
The radio is the most energy consuming module.
95% of energy consumption in typical data collection tasks [Madden, 2003].
If run continuoulsy with the radio, the lifetime is about 5 days.
36. Preliminaries Adaptive Model Selection Adaptive Model Selection
Wireless Sensor Networks
Challenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
ess Sensor Networks
allenges in environmental monitoring:
Long-running applications (months or years),
Limited energy on sensor nodes.
Operation mode Telos node
Standby 5.1 µA
MCU Active 1.8 mA
MCU + Radio RX 21.8 mA
MCU + Radio TX (0dBm) 19.5 mA
he radio is the most energy consuming module.
% of energy consumption in typical data collection tasks [Madden, 2003].
un continuoulsy with the radio, the lifetime is about 5 days.
x10
The radio is the most energy consuming module.
95% of energy consumption in typical data collection tasks [Madden, 2003].
If run continuoulsy with the radio, the lifetime is about 5 days.
37. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Overview
Goal: Uncover structure and relationships in a set of
observations, by means of models (mathematical functions).
!
!
!
!
! !
!
!
!
!
!
!
! !
!
! !
!
!
!
!
!
0 1 2 3 4 5 6 7
01234567
x[1:22]
y2[1:22]
!
!
!
!
! !
!
!
!
!
!
!
! !
!
! !
!
!
!
!
!
0 1 2 3 4 5 6 7
01234567
x[1:22]
y2[1:22]
Variable 1 ( )x Variable 1 ( )x
Variable2()y
Variable2()y
Learning
Procedure
Observations
y = h(x)Model
A learning procedure is used to find the model.
38. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Learning methodology
Unknown relationship
Observations
Learning procedure
Model
Input Output
Output
x y
ˆy
L(y, ˆy)Error
Input x can have several dimensions (Image classification)
Different models exist (linear models, neural networks,
decision trees, ...) with specific learning procedures.
39. Preliminaries Adaptive Model Selection Adaptive Model Selection
Machine learning
Modeling sensor data
Temporal model:
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
0 20 40 60 80 100 120
020406080100120
x
y
Time
Measurement
t
si[t]
Model
si[t] = θt
Training
examples
Input: Time.
Output: The measurement si [t] of a sensor i at time t.
Model: si [t] = θt.
The model approximates the set of measurements with just one
parameter θ.
40. Preliminaries Adaptive Model Selection Adaptive Model Selection
Learning with wireless sensor data
Thesis statement
Machine learning techniques can be used to reduce
communication by approximating sensor data with models.
→ Instead of sending all the measurements, only the parameters of
the models are transmitted.
Effective approach as sensor data are
temporally and spatially related (correlations)
Noisy: exact measurements rarely needed.
41. Preliminaries Adaptive Model Selection Adaptive Model Selection
Contribution I:
Adaptive Model Selection (AMS)
Temporal modeling
42. Preliminaries Adaptive Model Selection Adaptive Model Selection
Replicated models
Overview
Recall: In environmental monitoring, a sensor sends its
measurements periodically.
Measurements s[t] are sent at every time t.
Base
station
Wireless node
s[t]
s[t]
t
s[t]
t
Replicated models:
Models h are sent instead of the measurements.
Base
station
Wireless node
s[t]
t t
h
ˆs[t]
43. Preliminaries Adaptive Model Selection Adaptive Model Selection
Replicated models
Overview
Models computed by the sensor node
→ The node can compare the model prediction with the true
measurements:
A new model is sent if |s[t] − ˆs[t]| >
is user-defined, and application dependent.
Simple learning procedure must be used. Most simple model:
Constant model [Olston et al., 2001]
ˆsi [t] = si [t − 1]
Simply: The next measurement is the same as the previous
one
no parameter to compute
44. Preliminaries Adaptive Model Selection Adaptive Model Selection
Replicated models
Constant model
Temperature measurements, Solbosch greenhouse. = 2◦C.
160 170 180 190 200 210 220
30323436384042
Accuracy: 2°C
Constant model
Time instants
Temperature(°C)
q q q q q
Sensor node
Base station
5 updates instead of 58
→ more than 90% of communication savings.
45. Preliminaries Adaptive Model Selection Adaptive Model Selection
Replicated models
Autoregressive models
More complex models can be used: autoregressive models AR(p)
[Santini et al., Tulone et al., 2006].
ˆs[t] = θ1s[t − 1] + . . . + θps[t − p]
0 5 10 15 20
202530354045
Accuracy: 2°C
AR(2)
Time (Hour)
Temperature(°C)
● ●● ● ● ●●● ● ●● ● ● ● ● ● ●
Time (hours)
Temperature(°C)
An AR(2) reduces the number
of updates by 6 percents
in comparison to
the constant model.
46. Preliminaries Adaptive Model Selection Adaptive Model Selection
Replicated models
Pros and cons
Pros:
Guarantee the observer with accuracy.
Simple or complex models can be used.
Cons:
In most cases, no a priori information is available on the
measurements. Which model to choose a priori?
The metric (update rate) does not consider the number of
parameters of the models.
47. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Motivation
Tradeoff: More complex models better predict measurements,
but have a higher number of parameters.
Model complexity
Metric
Communication costs
Model error
AR(p) : ˆsi[t] =
p
j=1
θjsi[t − j]
48. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Collection of models
A collection of K models {hk}, 1 ≤ k ≤ K, of increasing
complexity are run by the node.
Base
station
Wireless node
s[t]
t t
{h1, h2,
. . . , hK}
ˆs[t]
h2
Wk: new metric estimating the communication costs.
When an update is needed, the model with the lowest Wk is
sent.
49. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Metric to assess communication savings
Wk: the weighted update rate
Wk[t] = CkUk[t]
Update rate Uk [t]: percentage of updates for model k at
epoch t ([Olston, 2001, Jain et al., 2004, Santini et al., Tulone
et al., 2006]).
Model cost Ck : takes into account the number of parameters
of the k-th model.
Ck = P
P−D+1
P: Size of the packet.
D: Size of the data load.
→ P − D is the packet overhead
SYNC Packet Address Message Group Data . . . Data CRC SYNC
BYTE Type Type ID Length BYTE
1 2 3 5 6 7 . . . Size D P-2 P
50. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Model selection
Model performances Wk[t] are estimated over time.
When data collection starts, no idea which model is best.
Running poorly performing models is detrimental to energy
consumption.
Racing [Maron, 1997]: Model selection technique based on
the Hoeffding bound, which allows to select the best
performing model.
51. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Model selection
Model performances Wk[t] are estimated over time.
When data collection starts, no idea which model is best.
Running poorly performing models is detrimental to energy
consumption.
Racing [Maron, 1997]: Model selection technique based on
the Hoeffding bound, which allows to select the best
performing model.
52. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
W1[t]
Upper bound
forWk[t]
Lower bound
for W1[t]
W1[t]
W2[t]
W3[t]
W4[t]
W5[t]
W6[t]
At first, all models are in competition.
53. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
W1[t]
Upper bound
for
Wk[t]
W1[t]
W2[t] W3[t]
W4[t]
W5[t]
W6[t]
As time passes, model h1 statistically outperforms h6.
54. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
Upper bound
for
Wk[t]
W1[t]
W2[t]
W3[t]
W4[t]
W5[t]
W3[t]
h3 then statistically outperforms h5.
55. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Racing
Model type
Weightedupdaterate
h1 h2 h3 h4 h5 h6
Upper bound
for
Wk[t]
W1[t]
W2[t]
W3[t]
W4[t]
W3[t]
h3 finally is selected as the best one.
56. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Experimental evaluation
14 time series, various types of measured physical quantities.
Data set Sensed quantity Sampling period Duration Number of samples
S Heater temperature 3 seconds 6h15 3000
I Light light 5 minutes 8 days 1584
M Hum humidity 10 minutes 30 days 4320
M Temp temperature 10 minutes 30 days 4320
NDBC WD wind direction 1 hour 1 year 7564
NDBC WSPD wind speed 1 hour 1 year 7564
NDBC DPD dominant wave period 1 hour 1 year 7562
NDBC AVP average wave period 1 hour 1 year 8639
NDBC BAR air pressure 1 hour 1 year 8639
NDBC ATMP air temperature 1 hour 1 year 8639
NDBC WTMP water temperature 1 hour 1 year 8734
NDBC DEWP dewpoint temperature 1 hour 1 year 8734
NDBC GST gust speed 1 hour 1 year 8710
NDBC WVHT wave height 1 hour 1 year 8723
Error threshold is set to 0.01r where r is the range of the
measurements.
AMS is run with k = 6 models: the constant model (CM) and
autoregressive models AR(p) with p ranging from 1 to 5.
57. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Experimental evaluation
CM AR1 AR2 AR3 AR4 AR5 AMS
S Heater 74 78 68 70 76 81 AR2
I Light 38 42 44 48 51 53 CM
M Hum 53 55 55 60 62 66 CM
M Temp 48 50 50 54 56 60 CM
NDBC DPD 65 89 89 95 102 109 CM
NDBC AWP 72 75 81 88 93 99 CM
NDBC BAR 51 52 44 47 49 50 AR2
NDBC ATMP 39 41 40 43 46 49 CM
NDBC WTMP 27 28 23 25 27 28 AR2
NDBC DEWP 57 54 58 62 67 71 AR1
NDBC WSPD 74 87 92 99 106 113 CM
NDBC WD 85 84 91 98 104 111 AR1
NDBC GST 80 84 90 96 103 110 CM
NDBC WVHT 58 58 63 67 71 76 CM
Bold numbers report significantly better update rates
(Hoeffding bound, δ = 0.05).
For all time series, the AMS selects the best model.
58. Preliminaries Adaptive Model Selection Adaptive Model Selection
Adaptive Model Selection
Conclusions
In summary, Adaptive Model Selection
Takes into account the cost of sending model parameters,
Allows sensor nodes to determine autonomously the model
which best fits their measurements,
Provides a statistically sound selection mechanism to discard
poorly performing models,
Gave in experimental results about 45% of communication
savings on average,
Energy for computation is not a problem (negligible),
Was implemented in TinyOS, the reference operating system.