Innovative research technologies in the neurosciences have remarkably improved the perception of brain structure and function. The use of several neurofeedback training zechniques is broadly used for the memory and cognition augmentation as well as for several learning difficulties and AHDD rehabilitation.Author’s objective is to review cognitive enhancement techniques with the use of brain imaging intervention methods as well to evaluate the effects of these methods in the educational process. The efficiency and limitations of neurofeedback training with the use of EEG brain imaging, HEG scanning, namely NIR and PIR method and fMRI scan including rt-fMRI brain scanning technique are also
discussed. Moreover, technical and clinical details of several neurofeedback treatment approaches were also taken into consideration.
Fibrillation Detection using Accelerometer and Gyroscope of a Smartphoneijtsrd
Using the smartphone as an answer for the identification of Atrial Fibrillation (AFib), which uses the built-in accelerometer and gyroscope sensors (Inertial Measurement Unit, IMU) of the smartphone for detection? Contingent upon the patients circumstance, it is conceivable to utilize the created cell phone application either routinely or at times for making an estimation of the subject with no outer sensors is required. From that point forward, the application decides if the patient experiences AFib or not. Arun Pranav K. R | Elavarasan C"Fibrillation Detection using Accelerometer and Gyroscope of a Smartphone" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-3 , April 2018, URL: http://www.ijtsrd.com/papers/ijtsrd11074.pdf http://www.ijtsrd.com/computer-science/other/11074/fibrillation-detection-using-accelerometer-and-gyroscope-of-a-smartphone/arun-pranav-k-r
Este documento resume los principales tipos de drogas, sus efectos y consecuencias. Define qué es una droga y explica conceptos como dependencia psíquica, física y síndrome de abstinencia. Detalla los tipos de drogas como alcohol, cocaína, marihuana, heroína y drogas sintéticas, así como sus efectos. Ofrece consejos para padres sobre cómo prevenir el abuso de drogas en adolescentes y detectar señales de consumo. Finalmente, describe las fases para abandonar el consumo abusivo y recursos de ayuda profes
La sociedad está dividida entre los Rojos sin poderes y los Plateados con habilidades sobrenaturales que dominan a los demás. Cuando Mare Barrow, una Roja, revela que tiene sus propios poderes, es llevada al mundo de los Plateados donde descubre que incluso ellos pueden ser vulnerables. La novela La Reina Roja de Victoria Aveyard es una historia de aventura, ciencia ficción y acción que explora el conflicto entre Rojos y Plateados a través de los personajes de Mare Barrow, Cal, Maven, Kilorn, Evangeline y Farley
La obra analiza la tragedia de Hamlet. Hamlet duda en vengar la muerte de su padre a manos de su tío Claudio, quien se casó con la madre de Hamlet. Para probar su teoría, Hamlet organiza una obra donde se recrea el asesinato, notando la culpa de Claudio. Finalmente, Claudio envenena a Laertes para que mate a Hamlet en un duelo, pero Hamlet toma la daga envenenada y hiere a Laertes, quien confiesa antes de morir. Hamlet luego mata a Claudio
El documento habla sobre los intents en Android. Explica que los intents permiten comunicar entre actividades, servicios y broadcast receivers. Describe dos tipos de intents: explícitos, que especifican la clase Java a usar, e implícitos, que dejan que el sistema determine qué componente usar. También cubre elementos como acciones, datos, categorías, extras y flags que pueden incluirse en los intents.
Google comenzó en 1996 como un motor de búsqueda universitario llamado BackRub creado por Larry Page y Sergey Brin. En 1998 fundaron Google Inc. con una inversión inicial de $100,000. Google creció rápidamente y en 1999 recaudó $25 millones de capital de riesgo, lo que les permitió expandirse a nivel mundial desde su sede central en Mountain View, California. Google ahora ofrece una amplia gama de productos y servicios populares como Gmail, Google Maps, YouTube y Android.
Munna Lal is seeking a challenging position in accounts and finance. He has over 15 years of experience working in accounting, finance, and commercial roles for infrastructure and construction companies. He holds a CA Inter qualification and MBA in finance and banking. His responsibilities have included financial accounting and reporting, budgeting, taxation, auditing, and ensuring statutory compliance. He is proficient in accounting software and packages and has strong analytical, organizational, and communication skills.
Fibrillation Detection using Accelerometer and Gyroscope of a Smartphoneijtsrd
Using the smartphone as an answer for the identification of Atrial Fibrillation (AFib), which uses the built-in accelerometer and gyroscope sensors (Inertial Measurement Unit, IMU) of the smartphone for detection? Contingent upon the patients circumstance, it is conceivable to utilize the created cell phone application either routinely or at times for making an estimation of the subject with no outer sensors is required. From that point forward, the application decides if the patient experiences AFib or not. Arun Pranav K. R | Elavarasan C"Fibrillation Detection using Accelerometer and Gyroscope of a Smartphone" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-3 , April 2018, URL: http://www.ijtsrd.com/papers/ijtsrd11074.pdf http://www.ijtsrd.com/computer-science/other/11074/fibrillation-detection-using-accelerometer-and-gyroscope-of-a-smartphone/arun-pranav-k-r
Este documento resume los principales tipos de drogas, sus efectos y consecuencias. Define qué es una droga y explica conceptos como dependencia psíquica, física y síndrome de abstinencia. Detalla los tipos de drogas como alcohol, cocaína, marihuana, heroína y drogas sintéticas, así como sus efectos. Ofrece consejos para padres sobre cómo prevenir el abuso de drogas en adolescentes y detectar señales de consumo. Finalmente, describe las fases para abandonar el consumo abusivo y recursos de ayuda profes
La sociedad está dividida entre los Rojos sin poderes y los Plateados con habilidades sobrenaturales que dominan a los demás. Cuando Mare Barrow, una Roja, revela que tiene sus propios poderes, es llevada al mundo de los Plateados donde descubre que incluso ellos pueden ser vulnerables. La novela La Reina Roja de Victoria Aveyard es una historia de aventura, ciencia ficción y acción que explora el conflicto entre Rojos y Plateados a través de los personajes de Mare Barrow, Cal, Maven, Kilorn, Evangeline y Farley
La obra analiza la tragedia de Hamlet. Hamlet duda en vengar la muerte de su padre a manos de su tío Claudio, quien se casó con la madre de Hamlet. Para probar su teoría, Hamlet organiza una obra donde se recrea el asesinato, notando la culpa de Claudio. Finalmente, Claudio envenena a Laertes para que mate a Hamlet en un duelo, pero Hamlet toma la daga envenenada y hiere a Laertes, quien confiesa antes de morir. Hamlet luego mata a Claudio
El documento habla sobre los intents en Android. Explica que los intents permiten comunicar entre actividades, servicios y broadcast receivers. Describe dos tipos de intents: explícitos, que especifican la clase Java a usar, e implícitos, que dejan que el sistema determine qué componente usar. También cubre elementos como acciones, datos, categorías, extras y flags que pueden incluirse en los intents.
Google comenzó en 1996 como un motor de búsqueda universitario llamado BackRub creado por Larry Page y Sergey Brin. En 1998 fundaron Google Inc. con una inversión inicial de $100,000. Google creció rápidamente y en 1999 recaudó $25 millones de capital de riesgo, lo que les permitió expandirse a nivel mundial desde su sede central en Mountain View, California. Google ahora ofrece una amplia gama de productos y servicios populares como Gmail, Google Maps, YouTube y Android.
Munna Lal is seeking a challenging position in accounts and finance. He has over 15 years of experience working in accounting, finance, and commercial roles for infrastructure and construction companies. He holds a CA Inter qualification and MBA in finance and banking. His responsibilities have included financial accounting and reporting, budgeting, taxation, auditing, and ensuring statutory compliance. He is proficient in accounting software and packages and has strong analytical, organizational, and communication skills.
Este documento explica las diferencias entre blogs y wikis. Los blogs son sitios web actualizados periódicamente por uno o varios autores donde se comparten artículos de manera cronológica. Los wikis permiten que cualquier persona edite y contribuya al contenido de manera colaborativa. Algunas diferencias clave son que los blogs suelen tener un solo autor mientras que los wikis fomentan la autoría colectiva.
Una computadora es un mecanismo electrónico que acepta información de entrada, la procesa y produce información de salida. El hardware se compone de elementos físicos como dispositivos de entrada, salida, memoria y el procesador, mientras que el software son programas ejecutables. Existen diferentes tipos de dispositivos de entrada, salida y memoria como teclados, monitores, discos duros y RAM.
El documento describe estrategias para desarrollar el pensamiento crítico en los estudiantes, como realizar ejercicios de reflexión sobre la información en los medios de comunicación, analizar la influencia de las subculturas, fortalecer el pensamiento crítico a través del análisis de problemas sociales, y estimular la capacidad de lectura crítica y expresión de ideas. También describe la inteligencia verbal-lingüística y técnicas didácticas como debates, presentaciones y redacción de textos para aprovechar esta habilidad.
Etnofísica = Física en los pueblos - USS - Ing. Civil - Prof. Ronald Estelaronaldestelafencyt
El documento presenta una introducción a la etnofísica y etnobotánica, disciplinas que estudian las relaciones entre las personas y las plantas/la física en la cultura popular de forma no académica. Luego describe varios ejemplos de cómo mitos, tradiciones y ferias se relacionan con conceptos físicos a través de historias, experimentos y atracciones inspiradas en la física. Finalmente, anima a disfrutar de la física que nos rodea en la vida cotidiana.
Este documento proporciona una historia detallada del surgimiento y evolución de las computadoras desde los inicios del cálculo primitivo hasta el desarrollo de las computadoras electrónicas modernas. Describe los primeros medios de cálculo como el uso de los dedos y las piedras, y luego explica las máquinas mecánicas y electromecánicas clave desarrolladas a lo largo de los siglos, incluidas las invenciones de Pascal, Babbage, Hollerith y Zuse. Finalmente, señala que las
La Unión de Naciones Suramericanas (UNASUR) es una organización internacional creada en 2008 para promover la integración regional en áreas como energía, educación, salud, ambiente e infraestructura. La Comunidad Andina de Naciones (CAN) se formó en 1969 y busca el desarrollo integral de sus países miembros a través de la integración, pero tiene desventajas como la falta de exportaciones de alto valor agregado y la pérdida potencial de soberanía. La Alianza Bolivariana para las Américas (ALBA) se creó como
The document discusses the history and current state of the 26th Amendment to the U.S. Constitution, which lowered the minimum voting age from 21 to 18. It was passed in 1971 in response to the Vietnam War, allowing millions of young Americans affected by the draft to also have a voice through voting. However, some studies have found that voter turnout has been lower among younger generations since its passage.
Stuart S. Dean is a food services director and general manager with over 25 years of experience managing food service operations in diverse environments such as residential long-term care facilities, universities, and hospitals. He has a proven track record of consistently achieving goals through streamlining operations, optimizing safety, and directing teams. Dean is seeking a new position where he can utilize his leadership skills and experience to produce quality results and meet an organization's objectives.
Kagwirira Mbiti is a professional with over 17 years of experience in sales, business development, purchasing, operations management, and contract administration. She delivers on projects through strong leadership and an ability to manage teams and meet client objectives. She has experience managing budgets, monitoring performance, developing policies and procedures, and implementing category strategies. Additionally, she has experience in business development, directing brand programs, meeting business goals through sales strategies, and operations management.
Este documento presenta una guía para principiantes sobre optimización para motores de búsqueda (SEO). Explica conceptos básicos como crear títulos y descripciones únicas para cada página, mejorar la estructura del sitio web mediante categorías descriptivas y nombres de archivo claros, y optimizar el contenido para los usuarios y los motores de búsqueda. También cubre temas como el uso efectivo de robots.txt, SEO para dispositivos móviles, y promoción y análisis del sitio web. El document
Ajaya Sankar provides his curriculum vitae. He has over 15 years of experience in civil engineering projects in Qatar, India, and Oman. His experience includes construction management roles on schools, hospitals, roads, pipelines, storage tanks, and other infrastructure projects. He lists his qualifications, roles and responsibilities on various projects, technology experience, and provides references from past employers and managers.
This document provides an overview of the speaker's senior project experience completing an externship with an integrated health care agency. It describes the agency's social work background and programs offered, including a Disruptive Behavior Clinic (DBC) for children ages 5-10. As part of the project, the speaker developed procedures for collecting and managing data across the agency's 6 clinics on outcomes of the DBC program. This included creating a database to track attendance, homework completion, and scores from assessment measures administered before and after treatment. The goal was to analyze the data to determine what factors contributed to higher success rates and help improve the DBC program.
human activity recognization using machine learning with data analysisVenkat Projects
Human activity recognition, or HAR for short, is a broad field of study concerned with identifying the specific movement or action of a person based on sensor data.
The sensor data may be remotely recorded, such as video, radar, or other wireless methods. It contains data generated from accelerometer, gyroscope and other sensors of Smart phone to train supervised predictive models using machine learning techniques like SVM , Random forest and decision tree to generate a model. Which can be used to predict the kind of movement being carried out by the person, which is divided into six categories walking, walking upstairs, walking down-stairs, sitting, standing and laying?
MLM and SVM achieved accuracy of more than 99.2% in the original data set and 98.1% using new feature selection method. Results show that the proposed feature selection approach is a promising alternative to activity recognition on smart phones.
This document presents a study that evaluates using a smartphone's acceleration sensor for recognizing 12 different daily living activities and 4 types of falls, as recorded from 66 subjects. An optimized feature selection and classification scheme is proposed. For basic activity recognition of 6 common daily activities, the approach achieved 99.9% accuracy. For a more complex task including all 12 activities and 4 falls, the approach achieved 96.8% accuracy. The study aims to provide an optimized system for activity and fall recognition based on smartphone sensor data by selecting effective features from previous studies and testing on an extended public dataset called MobiAct.
Context aware system for recongnizing daily-activitiesSakher BELOUADAH
In recent decades, human activity recognition has been the subject of an important amount of research which enabled many applications in different areas, such as time management, healthcare and anomaly detection. Most of those works were based on using multiple special sensors and few address complex activities. In order to solve those issues, we propose a context-aware system based on the combination of ontological reasoning, GPS mining using k-nearest neighbors, and statistical recognition model using cascade neural networks. We first present some complex activity recognition models and discus their limitations. A general architecture of our approach is then presented along with a detailed description of each section of the system. Finally, we will present the results obtained and discus the system?s limitation and ideas that need to be addressed in future work.
Health monitoring catalogue based on human activity classification using mac...IJECEIAES
In recent times, fitness trackers and smartphones equipped with different sensors like gyroscopes, accelerometers, global positioning system sensors and programs are used for recognizing human activities. In this paper, the results collected from these devices are used to design a system that can assist an application in monitoring a person’s health. The proposed system takes the raw sensor signals as input, preprocesses it and using machine learning techniques outputs the state of the user with minimum error. The objective of this paper is to compare the performance of different algorithms logistic regression (LR), support vector machine (SVM), k-nearest neighbor (k-NN) and random forest (RF). The algorithms are trained and tested with an original number of features as well as with transformed number of features (using linear discriminant analysis). The data with a smaller number of features is then used to visualize the high dimensional data. In this paper, each data point is mapped in the high dimensional data to two-dimensional data using t-distributed stochastic neighbor embedding technique. Overall, the first high dimensional data is visualized and compared with model’s performance with different algorithms and different number of coordinates.
Draft activity recognition from accelerometer dataRaghu Palakodety
This document describes a framework for classifying human activities like standing, walking, and running using data from an accelerometer sensor on a smartphone. It discusses collecting raw sensor data, preprocessing the data through smoothing and feature extraction, training classifiers on extracted features, and classifying new data in real-time. Random forest classification achieved 83.49% accuracy on this activity recognition task using accelerometer data from an Android application.
Estimation of Walking rate in Complex activity recognitionEditor IJCATR
This document summarizes a study that investigated using a flexible conductive polymer sensor embedded in leggings to monitor knee movement and activity recognition. The sensor was connected to a wireless sensing node to collect data. Twelve subjects performed walking, running, and stair activities while wearing the smart leggings. Test-retest reliability of the sensor output range showed good to excellent reliability. Discrimination of activities was achieved using total power and median frequency features from the sensor signal, demonstrating over 90% accuracy. The system shows potential for assessing knee function during daily activities.
Este documento explica las diferencias entre blogs y wikis. Los blogs son sitios web actualizados periódicamente por uno o varios autores donde se comparten artículos de manera cronológica. Los wikis permiten que cualquier persona edite y contribuya al contenido de manera colaborativa. Algunas diferencias clave son que los blogs suelen tener un solo autor mientras que los wikis fomentan la autoría colectiva.
Una computadora es un mecanismo electrónico que acepta información de entrada, la procesa y produce información de salida. El hardware se compone de elementos físicos como dispositivos de entrada, salida, memoria y el procesador, mientras que el software son programas ejecutables. Existen diferentes tipos de dispositivos de entrada, salida y memoria como teclados, monitores, discos duros y RAM.
El documento describe estrategias para desarrollar el pensamiento crítico en los estudiantes, como realizar ejercicios de reflexión sobre la información en los medios de comunicación, analizar la influencia de las subculturas, fortalecer el pensamiento crítico a través del análisis de problemas sociales, y estimular la capacidad de lectura crítica y expresión de ideas. También describe la inteligencia verbal-lingüística y técnicas didácticas como debates, presentaciones y redacción de textos para aprovechar esta habilidad.
Etnofísica = Física en los pueblos - USS - Ing. Civil - Prof. Ronald Estelaronaldestelafencyt
El documento presenta una introducción a la etnofísica y etnobotánica, disciplinas que estudian las relaciones entre las personas y las plantas/la física en la cultura popular de forma no académica. Luego describe varios ejemplos de cómo mitos, tradiciones y ferias se relacionan con conceptos físicos a través de historias, experimentos y atracciones inspiradas en la física. Finalmente, anima a disfrutar de la física que nos rodea en la vida cotidiana.
Este documento proporciona una historia detallada del surgimiento y evolución de las computadoras desde los inicios del cálculo primitivo hasta el desarrollo de las computadoras electrónicas modernas. Describe los primeros medios de cálculo como el uso de los dedos y las piedras, y luego explica las máquinas mecánicas y electromecánicas clave desarrolladas a lo largo de los siglos, incluidas las invenciones de Pascal, Babbage, Hollerith y Zuse. Finalmente, señala que las
La Unión de Naciones Suramericanas (UNASUR) es una organización internacional creada en 2008 para promover la integración regional en áreas como energía, educación, salud, ambiente e infraestructura. La Comunidad Andina de Naciones (CAN) se formó en 1969 y busca el desarrollo integral de sus países miembros a través de la integración, pero tiene desventajas como la falta de exportaciones de alto valor agregado y la pérdida potencial de soberanía. La Alianza Bolivariana para las Américas (ALBA) se creó como
The document discusses the history and current state of the 26th Amendment to the U.S. Constitution, which lowered the minimum voting age from 21 to 18. It was passed in 1971 in response to the Vietnam War, allowing millions of young Americans affected by the draft to also have a voice through voting. However, some studies have found that voter turnout has been lower among younger generations since its passage.
Stuart S. Dean is a food services director and general manager with over 25 years of experience managing food service operations in diverse environments such as residential long-term care facilities, universities, and hospitals. He has a proven track record of consistently achieving goals through streamlining operations, optimizing safety, and directing teams. Dean is seeking a new position where he can utilize his leadership skills and experience to produce quality results and meet an organization's objectives.
Kagwirira Mbiti is a professional with over 17 years of experience in sales, business development, purchasing, operations management, and contract administration. She delivers on projects through strong leadership and an ability to manage teams and meet client objectives. She has experience managing budgets, monitoring performance, developing policies and procedures, and implementing category strategies. Additionally, she has experience in business development, directing brand programs, meeting business goals through sales strategies, and operations management.
Este documento presenta una guía para principiantes sobre optimización para motores de búsqueda (SEO). Explica conceptos básicos como crear títulos y descripciones únicas para cada página, mejorar la estructura del sitio web mediante categorías descriptivas y nombres de archivo claros, y optimizar el contenido para los usuarios y los motores de búsqueda. También cubre temas como el uso efectivo de robots.txt, SEO para dispositivos móviles, y promoción y análisis del sitio web. El document
Ajaya Sankar provides his curriculum vitae. He has over 15 years of experience in civil engineering projects in Qatar, India, and Oman. His experience includes construction management roles on schools, hospitals, roads, pipelines, storage tanks, and other infrastructure projects. He lists his qualifications, roles and responsibilities on various projects, technology experience, and provides references from past employers and managers.
This document provides an overview of the speaker's senior project experience completing an externship with an integrated health care agency. It describes the agency's social work background and programs offered, including a Disruptive Behavior Clinic (DBC) for children ages 5-10. As part of the project, the speaker developed procedures for collecting and managing data across the agency's 6 clinics on outcomes of the DBC program. This included creating a database to track attendance, homework completion, and scores from assessment measures administered before and after treatment. The goal was to analyze the data to determine what factors contributed to higher success rates and help improve the DBC program.
human activity recognization using machine learning with data analysisVenkat Projects
Human activity recognition, or HAR for short, is a broad field of study concerned with identifying the specific movement or action of a person based on sensor data.
The sensor data may be remotely recorded, such as video, radar, or other wireless methods. It contains data generated from accelerometer, gyroscope and other sensors of Smart phone to train supervised predictive models using machine learning techniques like SVM , Random forest and decision tree to generate a model. Which can be used to predict the kind of movement being carried out by the person, which is divided into six categories walking, walking upstairs, walking down-stairs, sitting, standing and laying?
MLM and SVM achieved accuracy of more than 99.2% in the original data set and 98.1% using new feature selection method. Results show that the proposed feature selection approach is a promising alternative to activity recognition on smart phones.
This document presents a study that evaluates using a smartphone's acceleration sensor for recognizing 12 different daily living activities and 4 types of falls, as recorded from 66 subjects. An optimized feature selection and classification scheme is proposed. For basic activity recognition of 6 common daily activities, the approach achieved 99.9% accuracy. For a more complex task including all 12 activities and 4 falls, the approach achieved 96.8% accuracy. The study aims to provide an optimized system for activity and fall recognition based on smartphone sensor data by selecting effective features from previous studies and testing on an extended public dataset called MobiAct.
Context aware system for recongnizing daily-activitiesSakher BELOUADAH
In recent decades, human activity recognition has been the subject of an important amount of research which enabled many applications in different areas, such as time management, healthcare and anomaly detection. Most of those works were based on using multiple special sensors and few address complex activities. In order to solve those issues, we propose a context-aware system based on the combination of ontological reasoning, GPS mining using k-nearest neighbors, and statistical recognition model using cascade neural networks. We first present some complex activity recognition models and discus their limitations. A general architecture of our approach is then presented along with a detailed description of each section of the system. Finally, we will present the results obtained and discus the system?s limitation and ideas that need to be addressed in future work.
Health monitoring catalogue based on human activity classification using mac...IJECEIAES
In recent times, fitness trackers and smartphones equipped with different sensors like gyroscopes, accelerometers, global positioning system sensors and programs are used for recognizing human activities. In this paper, the results collected from these devices are used to design a system that can assist an application in monitoring a person’s health. The proposed system takes the raw sensor signals as input, preprocesses it and using machine learning techniques outputs the state of the user with minimum error. The objective of this paper is to compare the performance of different algorithms logistic regression (LR), support vector machine (SVM), k-nearest neighbor (k-NN) and random forest (RF). The algorithms are trained and tested with an original number of features as well as with transformed number of features (using linear discriminant analysis). The data with a smaller number of features is then used to visualize the high dimensional data. In this paper, each data point is mapped in the high dimensional data to two-dimensional data using t-distributed stochastic neighbor embedding technique. Overall, the first high dimensional data is visualized and compared with model’s performance with different algorithms and different number of coordinates.
Draft activity recognition from accelerometer dataRaghu Palakodety
This document describes a framework for classifying human activities like standing, walking, and running using data from an accelerometer sensor on a smartphone. It discusses collecting raw sensor data, preprocessing the data through smoothing and feature extraction, training classifiers on extracted features, and classifying new data in real-time. Random forest classification achieved 83.49% accuracy on this activity recognition task using accelerometer data from an Android application.
Estimation of Walking rate in Complex activity recognitionEditor IJCATR
This document summarizes a study that investigated using a flexible conductive polymer sensor embedded in leggings to monitor knee movement and activity recognition. The sensor was connected to a wireless sensing node to collect data. Twelve subjects performed walking, running, and stair activities while wearing the smart leggings. Test-retest reliability of the sensor output range showed good to excellent reliability. Discrimination of activities was achieved using total power and median frequency features from the sensor signal, demonstrating over 90% accuracy. The system shows potential for assessing knee function during daily activities.
Wearable sensor-based human activity recognition with ensemble learning: a co...IJECEIAES
The spectacular growth of wearable sensors has provided a key contribution to the field of human activity recognition. Due to its effective and versatile usage and application in various fields such as smart homes and medical areas, human activity recognition has always been an appealing research topic in artificial intelligence. From this perspective, there are a lot of existing works that make use of accelerometer and gyroscope sensor data for recognizing human activities. This paper presents a comparative study of ensemble learning methods for human activity recognition. The methods include random forest, adaptive boosting, gradient boosting, extreme gradient boosting, and light gradient boosting machine (LightGBM). Among the ensemble learning methods in comparison, light gradient boosting machine and random forest demonstrate the best performance. The experimental results revealed that light gradient boosting machine yields the highest accuracy of 94.50% on UCI-HAR dataset and 100% on single accelerometer dataset while random forest records the highest accuracy of 93.41% on motion sense dataset.
Human Activity Recognition using Smartphone's sensor Pankaj Mishra
Human activity recognition plays significant role in medical field and in security system. In this project we have design a model which recognize a person’s activity based on Smartphone.
A 3- dimensional Smartphone sensor named accelerometer and gyroscope is used to collect time series signal, from which 26 features are generated in time and frequency domain. The activities are classified using 2 different dormant learning method i.e. k-nearest neighbor algorithm, decision tree algorithm.
Human activity recognition updated 1 - Copy.pptxBhaveshKhuje
This document discusses human activity recognition using inertial sensors. It begins by introducing human activity recognition and how inertial sensors are commonly used to build HAR systems. It then discusses applications of HAR systems and how deep learning models are increasingly being used for activity recognition. The document also discusses challenges with using deep learning for activity recognition on resource-constrained devices and how edge computing is a viable solution. It provides literature on the topic and discusses existing system drawbacks. The conclusion discusses a proposed new HAR system that achieves high accuracy with low power consumption.
1) The document discusses human activity recognition (HAR) in video surveillance systems. It aims to develop techniques to automatically detect unusual activities in real-time surveillance videos.
2) It proposes three stages of research: HAR for healthcare monitoring using smartphones, a squirrel search optimization method combined with deep learning for human pose estimation, and a hybrid approach using both video and sensor data with noise removal techniques to improve HAR model robustness.
3) The hybrid approach applies filters to remove noise from video and sensor data, extracts features using CNN and sensors, fuses the features, and classifies activities with SVM, achieving up to 98.7% accuracy on a sports dataset.
Recognition of anaerobic based on machine learning using smart watch sensor dataSuhyun Cho
This document discusses a study that used machine learning to recognize three types of anaerobic exercises (pull-ups, side pulls, and concentration curls) performed with dumbbells, based on sensor data from smartwatches. The researchers collected acceleration and gyroscope sensor data from smartwatches worn by subjects performing the exercises. They extracted features from the sensor data and used a support vector machine (SVM) algorithm to classify the exercises. Their best performing model used principal component analysis to reduce the features to two dimensions and a linear kernel, achieving a mean recognition rate of 97.7% for the three exercises.
Automatic Isolated word sign language recognitionSana Fakhfakh
This paper suggests a new system to help the
deaf and the hearing-impaired community improve their
connection with the hearing world and communicate
freely. The most important thing in this system is
how to help the users be free and finally have a more
natural way of communication. For this reason, we
present a new process based on two levels: a static-level
aiming to extract the most head/hands key points and
a dynamic-level with the objective of accumulating the
key-point trajectory matrix. Also our proposed approach
takes into account the signer-independence constraint.
A SIGNUM database is applied in the classification
stage and our system performances have improved with
a 94.3% recognition rate. Furthermore, a reduction
in time processing is obtained when the removing of
redundant frame step is applied. The obtained results
prove the superiority of our system compared to the
state-of- the-art methods in terms of recognition rate and
execution time.
Recognition of activities of daily living with egocentric visionNaeem Shehzad
in this presentation you can learn Recognition of activities of daily living with egocentric vision. in this presentation I mention all the data in very convenient way , hope you can get it easy.
thank you.
Real-time human activity recognition from smart phone using linear support ve...TELKOMNIKA JOURNAL
The recognition of human activity (HAR) the use of cell devices embedded in its exten sively disbursed sensors affords guidance, instructions, and take care of citizens of smart cities. Consequently, it became essential to analyze human every day sports. To examine statistical models of human conduct, synthetic intelligence strategies such as machine studying can be used. Many studies have not studied type overall performance in real-time due to statistics series. To remedy this trouble, this paper proposes a structure primarily based on open supply technology and platforms consisting of Apache Kafka, for messages to flow over the internet, method them and provide shape for existing facts in real-time and formulates the trouble of identifying human pastime by using a smartphone tool as a type hassle using statistics collection by telephone sensors. The proposed version is skilled by some machine learning algorithms. The algorithm that has proven superior and quality results helps a linear vector machines.
Gait analysis is the study of human locomotion, in particular walking and running gait patterns. It can be used to assess biomechanical abnormalities and aid in clinical diagnosis and treatment planning. Visual analysis and video recording allow observation of gait but provide limited objective data. Simple measurements of temporal and spatial gait parameters like cycle time, stride length and speed can be made using basic equipment like a stopwatch and tape measure. More advanced systems like footswitches, instrumented walkways and motion capture provide detailed quantitative spatiotemporal and kinematic data on foot-floor contact and joint motion during gait.
Human activity recognition with self-attentionIJECEIAES
The document describes a study that used a self-attention neural network architecture for human activity recognition using smartphone sensor data. The study compared the proposed self-attention model to convolutional neural network (CNN) and long short-term memory (LSTM) baselines. The self-attention model achieved a test accuracy of 91.75% for classifying six human activities, which was comparable to the baseline models. The study investigated components of the self-attention model like dropout rate, positional encoding, and scaling factors to determine the best performing model.
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...IRJET Journal
This document presents a method for recognizing gestures using ultrasound sensors and infrared array sensors. Two ultrasound sensor pairs are used to capture hand motion in vertical and horizontal directions. An infrared Grid-Eye sensor is used to trigger the ultrasound sensors when a hand gesture is detected. The sensors capture data on the distance and movement of the hand. This data is preprocessed and extracted into features representing the average and count of upward and downward motions. An artificial neural network with two hidden layers is trained on these features to classify gestures for two letters, achieving an accuracy of 83%. The proposed method aims to provide a contactless gesture recognition system without some of the disadvantages of vision-based techniques.
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Eswar Publications
In recent years, majority of researches are focused on localization system for wireless environment. These researches rely on localization using devices to track the entities. In this paper, we use, a recently proposed Device-free Passive (DfP) that uses Probabilistic techniques to track locations in large-scale real environment without the need of carrying devices. The proposed system uses the Access Points (APs) and Monitoring Point (MPs) that works by monitoring and processing the changes in the received physical signals at one or more monitoring points to detect changes in the environment. The system uses continuous space estimator to return multiple location while the mortal is in motion. Our results show that the system can achieve very high probability of detection and tracking with very few false positives.
Macroeconomics- Movie Location
This will be used as part of your Personal Professional Portfolio once graded.
Objective:
Prepare a presentation or a paper using research, basic comparative analysis, data organization and application of economic information. You will make an informed assessment of an economic climate outside of the United States to accomplish an entertainment industry objective.
Thinking of getting a dog? Be aware that breeds like Pit Bulls, Rottweilers, and German Shepherds can be loyal and dangerous. Proper training and socialization are crucial to preventing aggressive behaviors. Ensure safety by understanding their needs and always supervising interactions. Stay safe, and enjoy your furry friends!
Assessment and Planning in Educational technology.pptxKavitha Krishnan
In an education system, it is understood that assessment is only for the students, but on the other hand, the Assessment of teachers is also an important aspect of the education system that ensures teachers are providing high-quality instruction to students. The assessment process can be used to provide feedback and support for professional development, to inform decisions about teacher retention or promotion, or to evaluate teacher effectiveness for accountability purposes.
How to Fix the Import Error in the Odoo 17Celine George
An import error occurs when a program fails to import a module or library, disrupting its execution. In languages like Python, this issue arises when the specified module cannot be found or accessed, hindering the program's functionality. Resolving import errors is crucial for maintaining smooth software operation and uninterrupted development processes.
A Strategic Approach: GenAI in EducationPeter Windle
Artificial Intelligence (AI) technologies such as Generative AI, Image Generators and Large Language Models have had a dramatic impact on teaching, learning and assessment over the past 18 months. The most immediate threat AI posed was to Academic Integrity with Higher Education Institutes (HEIs) focusing their efforts on combating the use of GenAI in assessment. Guidelines were developed for staff and students, policies put in place too. Innovative educators have forged paths in the use of Generative AI for teaching, learning and assessments leading to pockets of transformation springing up across HEIs, often with little or no top-down guidance, support or direction.
This Gasta posits a strategic approach to integrating AI into HEIs to prepare staff, students and the curriculum for an evolving world and workplace. We will highlight the advantages of working with these technologies beyond the realm of teaching, learning and assessment by considering prompt engineering skills, industry impact, curriculum changes, and the need for staff upskilling. In contrast, not engaging strategically with Generative AI poses risks, including falling behind peers, missed opportunities and failing to ensure our graduates remain employable. The rapid evolution of AI technologies necessitates a proactive and strategic approach if we are to remain relevant.
বাংলাদেশের অর্থনৈতিক সমীক্ষা ২০২৪ [Bangladesh Economic Review 2024 Bangla.pdf] কম্পিউটার , ট্যাব ও স্মার্ট ফোন ভার্সন সহ সম্পূর্ণ বাংলা ই-বুক বা pdf বই " সুচিপত্র ...বুকমার্ক মেনু 🔖 ও হাইপার লিংক মেনু 📝👆 যুক্ত ..
আমাদের সবার জন্য খুব খুব গুরুত্বপূর্ণ একটি বই ..বিসিএস, ব্যাংক, ইউনিভার্সিটি ভর্তি ও যে কোন প্রতিযোগিতা মূলক পরীক্ষার জন্য এর খুব ইম্পরট্যান্ট একটি বিষয় ...তাছাড়া বাংলাদেশের সাম্প্রতিক যে কোন ডাটা বা তথ্য এই বইতে পাবেন ...
তাই একজন নাগরিক হিসাবে এই তথ্য গুলো আপনার জানা প্রয়োজন ...।
বিসিএস ও ব্যাংক এর লিখিত পরীক্ষা ...+এছাড়া মাধ্যমিক ও উচ্চমাধ্যমিকের স্টুডেন্টদের জন্য অনেক কাজে আসবে ...
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
it describes the bony anatomy including the femoral head , acetabulum, labrum . also discusses the capsule , ligaments . muscle that act on the hip joint and the range of motion are outlined. factors affecting hip joint stability and weight transmission through the joint are summarized.
INSIGHTS IN EEG VERSUS HEG AND RT-FMRI NEURO FEEDBACK TRAINING FOR COGNITION ENHANCEMENT
1. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
DOI: 10.5121/ijaia.2016.7601 1
HUMAN ACTIVITY TRACKING BY MOBILE PHONES
THROUGH HEBBIAN LEARNING
Jafet A. Morales and David Akopian
Department of Electrical and Computer Engineering, University of Texas at San Antonio,
San Antonio, Texas, USA
ABSTRACT
A method for human activity recognition using mobile phones is introduced. Using the accelerometer and
gyroscope typically found in modern smartphones, a system that uses the proposed method is able to
recognize low level activities, including athletic exercises, with high accuracy. A Hebbian learning
preprocessing stage is used to render accelerometer and gyroscope signals independent to the orientation
of the smartphone inside the user’s pocket. After preprocessing, a selected set of features are obtained and
used for classification by a k-nearest neighbor or a multilayer perceptron. The trained algorithm achieves
an accuracy of 95.3 percent when using the multilayer perceptron and tested on unknown users who are
asked to perform the exercises after placing the mobile device in their pocket without any constraints on the
orientation. Comparison of performance with respect to other popular methods is provided.
KEYWORDS
accelerometer, gyroscope, human activity recognition, smartphone
1. INTRODUCTION
Human activity recognition (HAR) has been intensively studied over recent years [1]. From a
broad perspective, activity monitoring can be done by processing signals from sensors external to
subject’s body [2], video processing [3], and sensors mounted on the subject’s body [4] [5] [6].
Examples of specific study aspects are such as measurement of arm [7] and foot [8] motions and
trunk postural changes [9]. Recently HAR-related research gained strong attention due to
healthcare-related mobile applications. These applications are able to provide users with
information related to their daily activities and exercise routines. The current paper introduces an
activity tracking method that uses signals from sensors worn by the subject, particularly signals
coming from accelerometers and gyroscopes, which are typically mounted on modern
smartphones. The proposed algorithms, however, can possibly be used on wearable sensors that
are otherwise mounted on the user. In this section a brief survey of HAR research that makes use
of wearable accelerometers and gyroscopes is provided, including problem definition,
architecture of the sensor array, capture and preprocessing of the data, feature set and
classification, and performance evaluation.
In past research, activities that were tracked via wearable sensors ranged from low level to high
level activities, which are loosely defined in the literature. In the current paper, low level
activities refer to stationary or postural activities (i.e., remaining seated or standing), transitional
activities (i.e., sitting or standing up), or repetitive activities that are composed of more than one
short-duration cycle (i.e., performing squats as an exercise or simply walking). High level
activities are much harder to detect using only accelerometer and gyroscope instrumentration,
since they vary from individual to individual and there are other factors involved, such as time of
the day and location. The work activity, for instance, is a high level activity that depends on the
individual, day of the week, and location. The motion signals obtained from a teenager playing
2. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
2
video games at home on a Tuesday morning may actually be very similar to those of middle aged
man working at the office. Thus high level activity recognition seems to be out of the scope of
algorithms that only make use of accelerometer and gyroscope signals from smartphones. This
also applies to many other high level activities such as going-on-a-vacation. The authors believe
that positioning signals, time signals, and user provided data can be used by smartphones to
identify high level activities. But this proposition is under the assumption that high level activities
are sequences of low level activities that are somewhat similar as long as they are performed by
the same individual, at the same location, and in the same seasonal timeframe. Still, most HAR
research is at the current time focused on processing the signals coming out of available sensors
in order to achieve better low level activity recognition. Researchers usually attempt to identify at
least the most basic activities such as walking and not moving[4], [5], [6], [10], [11], [12], [13].
Some researchers push their algorithms further by making them identify a larger set of activities
that includes walking, travelling the stairs up or down, or not moving [4], [5], [12]. Sports-related
activities, such as remaining still, running, walking, and bicycling, have also been detected with
accelerometers and gyroscopes [4], [12]. Some algorithms have been designed to distinguish
amongst stationary activities such as sitting or remaining upright [4], [6], [10] [11]. In general,
the contribution to low level activity recognition done by the algorithms in discussion is usually
in the preprocessing, feature extraction, and classification stages they propose. In terms of
accuracy, 90% levels are already achieved most of the time. The problem is not in the detection
accuracy, but on the small number of activities that have been explored and on the usability of
these algorithms outside of the laboratory.
Most wearable sensor based HAR algorithms, supervised, or unsupervised, are far from
performing low level activity HAR with the level of accuracy that humans can achieve through a
visual inspection. The ideal wearable sensor HAR algorithm would be able to recognize all of the
low level activities performed by any user during an entire day. This is a task extremely easy for
human beings by visual inspection, but currently impossible for smartphones. In general, human
beings can perform a large number of activities throughout the day and this may be too much to
ask for any contemporary machine.
There is an interrelationship between the activity set and the learning methods that can be used to
identify each activity. One method that is good for detecting one set of activites (i.e., using kNN
to classify walking, running, and other exercise activities) may not necessarily be the best choice
for detecting another activity set (i.e., fall detection).Another issue with some studies is that
outside of a lab setting, users position the smartphone with different orientations and on different
on-body locations. Studies that have addressed this problem include [11] [14] [15] [16].
The placement architecture of the sensor array varies in reported research. Sensor arrays differ in
the type of sensors, number of sensors, and location of sensors. In most cases, a single three-axial
accelerometer is attached to the body, although in some cases more than one accelerometer have
been used [4]. Up to 5 bi-axial accelerometers attached at locations in ankle, wrist, hip, arm, and
thigh in [4] but it was determined that there was not much improvement in accuracy to using only
hip and wrist or thigh and wrist locations. The waist location has already been studied in [4], [6],
[11] and the pelvic region was studied in [5].
The way the data is captured is different for every researcher. The sampling rate is usually
between 20 Hz [10], [13] and 50 Hz [5], [11]. Most researchers do not specify why they use a
particular sample rate. The size of the window to be processed ranges from one second [6], [11],
[12] up to ten seconds [10]. Windows that overlap at 50% were used in [4], [5] but no explanation
is given about the benefit of using overlapping windows and whether this benefit depends on the
period of the activity that is being monitored and the size of the window. Overlapping windows
of 50% may be better for online recognition in the sense that they can provide the user with a
classification result in intervals of time that are half the size of those of non-overlapping window
3. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
3
systems. But they can also increase computational expense by mobile phones and increase the
load on the battery as the calculations are performed online by the device.
Motion signals are usually preprocessed before performing classification. For example, spikes in
the three axes of inertial sensors can be removed by using an FIR filter of fifth order with a cut-
off close to .5 radians/sec or a similar filter, as done in [13]. A median filter can also be used, as
done in [6]. Gravity can then be subtracted by additional preprocessing [6], [11]. Gravity was
eliminated in [6] with a .25Hz cutoff elliptic low pass IIR filter of third-order. In [11] the signal is
normalized by subtracting mean and dividing by standard deviation.
Several features have been used for activity recognition with wearable motion sensors. Frequency
domain features are in some cases obtained by finding the location of peaks [6], or taking discrete
fourier transform (DFT) coefficient values or DFT bin values [10], [12]. However, most popular
features are obtained from the time domain. These include mean acceleration [4], [5], [10], [11],
power [4], [5], [12], standard deviation [5], [10], [11], periods [10], [12], [13], and signal
magnitude areas [6]. All of these features can be calculated individually for each channel or for
the magnitude of the 3-dimensional acceleration vector. But features that relate different
channels, such as interchannel correlation have also been used [4], [5]. For classification, decision
trees are popular [4], [5], [6], [10], [13], along with kNN [4], [5], [11], SVMs [5], [8], neural
networks [10], dynamic time warping (DWT) [12], and plurality voting [5].
Currently, researchers obtain accuracies usually between 90 and 95% [6], [10], [11], [12] for
HAR using wearable motion sensors. Accuracy greater than 99% has been reported in [13] for
distinguishing between the states of walking and remaining idle. There are two popular ways of
testing the accuracy of human activity recognition algorithms based on wearable sensor signals.
When doing the personalized validation, the algorithm is trained and tested on each individual
separately by using all frames of the individual in question but one. The algorithm is then tested
on the remaining frame of that individual [4], [5], [12]. When performing the leave-one-subject-
out type of validation the method in question is first trained on all subjects but one. The method is
then tested on the remaining subject. Accuracy is typically higher in the personalized validation
but the leave-one-user-out type of validation is also important because it is an indicator of
potential for deployment to the masses. In some cases all frames from all users and all activities
are mixed together into a pool and the system is tested by performing a folded cross-validation on
a percentage of frames that are randomly chosen from the pool [5], [10], [12]. Most of the
methods in question can classify the commonly practiced cyclic activities of jogging, walking,
bicycling, going up or going down the stairs. For this type of activities, simple features such as
the location and height of a peak in the frequency domain, the angle with respect to gravity, or a
measurable period are not enough information to classify the activities. In such cases testing by
cross-validation is possible because a data can also be used for training.
Not all algorithms of interest can be tested using cross-validation. In some cases, accuracy is
calculated as the portion of frames in the dataset which are correctly classified [6], [10]. This is
the case of algorithms that make decisions based on a small set of equations that are
parameterized by just a few features, rather than by using classifiers trained on previous
examples. The benefit of this type of algorithms is that they do not need to be trained and
therefore are not overfitted to the dataset of the researcher. Also, these algorithms are not
complex and processing intensive. However, they can only be used to distinguish simple
activities, such as certain stationary positions, transitional activities, and being active or inactive.
For example, setting a threshold for the angle between a horizontal axis (alternatively, an axis in
the direction of gravity) and an axis that goes through the device from top to bottom can be used
to distinguish between sitting and standing up. The method proposed in [6] can be used to
identify the activities of falling, sitting, standing, being active while standing up, being active
while lying, and lying on back, front, left, or right side of the body. The algorithm uses a decision
4. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
4
thee that makes decisions based on thresholding of signal magnitude area, acceleration peaks, and
an angle with respect to gravity. Validation based on the percentage of frames that are classified
correctly without performing data partitioning for training and testing also applies to the
algorithm proposed in [13]. In this case, the algorithm can discriminate between resting and
walking by calculating an Average Magnitude Difference Function (AMDF) at a given delay and
finding the location of peaks. In general, the performance of wearable inertial sensor-based HAR
algorithms is usually shown in accuracy percentages and confusion tables.
There are some similarities between attachable motion sensor and smartphone based methods for
HAR. First of all, the type of signals are typically accelerometer and gyroscope signals.
Parameters for signal capture, such as the frame size and the rate of sampling can also be
expected to be similar. Calculated features and methods of classification may also be similar
between smartphone based methods and attachable motion sensor methods, even though sensor
may be worn differently. Using a mobile phone typically means that the sensors will be attached
to the arm or to the waist or inside a pocket. Already explored pockets include front pant pockets
[10], [11], [12], shirt pockets [11], and jacket pockets [13]. When the inertial sensors or the
smartphone device are attached to a body part, the orientation of the signals in the training and
testing stages will be the same. In this case, high accuracy results can be expected. This situation
is mostly seen in users who do not want the device jumping around through the empty space in
their pockets while they exercise and at the same time do not want to hold it in their hands.
Outside of these particular scenarios, the user can be expected to have the device in his hand(s),
pockets, purse, or laying on a table or other flat surface. The algorithm proposed in this paper is
tested in front pant pockets, but the authors expect decent performance on fixed scenarios as well,
due to pocket signals being more unpredictable than fixed device signals. Pocket signals require
more processing than fixed device signals in order to account for many additional factors. First,
the device can be oriented on different ways as it is placed by the user on his/her pocket. Pocket
signals are also different because the device bounces around in the free space of the pocket.
Finally, the pocket deforms and moves on the surface of the body depending on the location of
the pocket, clothing, and shape of the body. None of these effects are present in fixed orientation
signals, where effects on variability are only due to the angle at which the device is attached
around the limb, how far it is attached from the joint, and the size of the individual.
Section 2 of this paper proposes a window-based as well as an adaptive method for obtaining
orientation-invariant accelerometer and gyroscope signals. The features used by a proposed HAR
algorithm that uses orientation-invariant signals and the method used to generate this list of
features are described in Section 3. The classification stage of the HAR algorithm is described in
Section 4 in a brief manner. Section 5 of the paper focuses on testing and performance of the
HAR algorithm. Finally, Section 6 presents conclusions on the overall performance of the
algorithm.
2. ORIENTATION-INVARIANT ACCELEROMETER AND GYROSCOPE SIGNALS
Currently most methods for HAR are based on wearable inertial sensors calculate features
directly from the acceleration in the X, Y, and Z directions of the device’s coordinate system.
This means that, for those methods to give maximum accuracy, the device must be oriented the
same way during the training and testing phases. In scenarios outside of the laboratory, however,
the orientation of a smartphone with respect to the user’s frame is less predictable. One way to
eliminate the effect of random orientations is to process the signal in such a way that a particular
activity always generates the same processed signal, but still different signals are obtained for
different activities. This can be done by transforming the signal to a different coordinate system.
This coordinate system may or may not be the same for all activities. A separate coordinate
system can be used for each activity, as long as the resulting acceleration signatures are not the
same. Principal component analysis (PCA) was used for preprocessing the motion signals in
5. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
5
[11], [14], [15], [16]. Performance is to be evaluated differently from smartphone based methods
to attachable accelerometer based methods. If the algorithm is to work regardless of the
orientation of the accelerometers, performance must be evaluated by testing on several
orientations. In such case, it can be evaluated by training on a single orientation and testing on
several orientations as done in [11], or simply by training and testing on randomly chosen
orientations, as done in [16].
A PCA was used in [11] to classify activities recorded with a mobile phone with a set of different
orientations. Gravity was first eliminated by subtracting mean. This results in a signal that
contains only linear acceleration, that is, the acceleration due to motion. The acceleration along
the direction of the subtracted gravity signal is then used as an orientation-invariant component.
An additional orientation-invariant component is then obtained by finding the principal
component of acceleration on the plane orthogonal to the gravity vector. The third orientation-
invariant signal is then found by taking the acceleration orthogonal to the other two components.
A different approach to orientation-invariance was taken in [14], [15], where the PCA transform
of acceleration was calculated in three-dimensions, and not only on the two dimensions
orthogonal to gravity. Only the principal component of acceleration was used to extract features
from in [14][15]. Three PCA components of accelerometer and three PCA components of
gyroscope where used in [16] to distinguish human activities by using a smartphone.
One of the disadvantages of using the method described above to obtain orientation-invariant
signals is that the transform operation must be performed in an entire window in the vicinity of
the sample of interest, so that transformation of the signal is typically performed in chunks that
may or may not overlap, in order to reduce computational complexity. This introduces a
minimum delay due to the spacing between the last sample of one window and the next one.
Also, because the PCA transform is very signal dependent there may be “blind spots” in which
part of the window corresponds to one activity and another part of the window corresponds to a
different activity. In such cases, even though the PCA transform has provided a fully recoverable
orientation-invariant signal, the transformed signal does not correspond to any of the stored
activities, making it impossible to target the activity at the sample of interest.
Using the generalized Hebbian algorithm, orientation-invariant components for a motion sample
can be calculated as soon as the 3-dimensional motion sample is received, without having to
perform a PCA on an entire window of data around the sample of interest. This eliminates the
lower boundary on the delay due to spacing between windows and delegates it to the feature
extraction algorithm. Additionally, blind spots can be detected as changes in the transform
operator. Once a blind spot has been spotted, the results of classification can be ignored in order
to avoid delivering faulty results, or a different classification algorithm may be used to target the
blind spot.
2.1. ORIENTATION-INVARIANT WINDOWS BY PRINCIPAL COMPONENT ANALYSIS
One way of obtaining a set of orientation-invariant motion signals is by applying principal
component analysis (PCA) to the original accelerometer and gyroscope signals. The resulting six
motion signal components can then be used for human activity recognition, as done in [16] and
explained only for the sake of completeness in this paper. When using PCA transform signals, the
orientation of the PCA coordinates with respect to the smartphone and the user willdepend on
how variance in the 3-dimensional motion signals is distributed with respect to the smartphone
and how the smartphone is positioned with respect to the user, making the coordinate system
extremely case dependent. It is unlikely that two different activities of interest from a small set of
activities will generate similar motion signatures. In this section, application of PCA to wearable
inertial sensor 3-dimensional signals is described in detail. For a more in-depth discussion of
PCA analysis on signals of even higher dimensionality the reader is referred to [17].
6. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
6
A sample of an acceleration frame is represented by
1
2
3
j
j j
j
a
a
a
=
a (1)
where j
ia is the jth acceleration sample in the ith coordinate. A window of acceleration samples
can then be aggregated into a matrix
1 2
1 1 1
1 2
2 2 2
1 2
3 3 3
n
n
n
a a a
a a a
a a a
=
A
L
L
L
(2)
where each row contains the samples for acceleration along one axis while each column is an
acceleration vector sample. The PCA transform is applied on a centralized matrix that is
calculated by subtracting the average acceleration vector from each column
1 2
1 1 1
1 2
2 2 2
1 2
3 3 3
n
n
n
a a a
a a a
a a a
=
A
L
L
L
(3)
An orthonormal transform can be used to decorrelate the dimensions of A through the linear
transformation
A
B = P A (4)
where A
P is the transform operator for the window A . This transform is found by performing a
diagonalization of the covariance matrix of A .The covariance matrix of A is calculated as
1 T
n
=A
Ω AA (5)
While A
Ω is not a diagonal matrix, the covariance matrix of B, denoted as B
Ω , should be a
diagonal matrix, meaning that the components of B are decorrelated. Since A
Ω is symmetric, it
is diagonalized with
T
=A
Ω ΦΛΦ (6)
Fig. 1. Coordinate System for the Smartphone used in this Project
7. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
7
where Λ is a diagonal matrix with eigenvalues for A , andΦ is the orthonormal eigenvector
matrix of A
Ω . The PCA transform is then
T
=A
P Φ (7)
Once the signal has been preprocessed for orientation invariance, HAR can be done by using the
pattern recognition techniques described before, so long as the motion detecting device (i.e.,
smartphone) is placed in the same location during training and testing.Similar preprocessing can
also used to obtain orientation-invariant angular velocity signals. Three-axis gyroscopes output
three signals. Each signal is the angular speed in rad/sec about an orthogonal axis. A typical
coordinate system for smartphone motion signals is portrayed in Figure 1. In smartphones, the
axes for accelerometers and gyroscopes are oriented the same way.
Angular frequency can be represented with a vector
w=w u (8)
where
2 2 2
1
x
y
x y z
z
w
w
w w w
w
=
+ +
u (9)
is a unit vector pointing in the direction of the axis of rotation and
2 2 2
x y zw w w w= + + (10)
where iw is the angular frequency or speed about the i axis, and w is the angular speed around the
axis of rotation of the angular velocity vector.Angular velocity vectors can also be made
orientation-invariant by a linear transformation. In this case, the three signals obtained from the
three-axial gyroscope are PCA transformed.
Many activities have distinguishing patterns in more than one of the six components that can be
obtained through the transformations above. This can easily be understood by picturing a user
jogging at a constant speed with the smartphone in his front right pocket. In this activity, the
mobile phone moves back and forth in the direction the user is running, but also up and down as
each foot jumps and falls back on the floor. The smartphone does not move along a single axis, so
that more than one axis is needed to represent it. Therefore, using only the principal component
from the PCA coordinate system may not be enough to discriminate between different activities
in some cases. Similarly, angular velocity signals coming from gyroscopes are not necessarily
well represented using only the principal component. When a user is jogging with a mobile phone
in one of his/her front pant or short pockets, clothes can force the device to orbit around the user’s
leg, always facing the outside of the leg. This means the device will rotate about an axis that goes
through it and that is parallel to the leg of the user. At the same time, due to the typical way
humans move their legs when they run, the device will also orbit around a line going through the
user’s waist, perpendicular to gravity and the direction of running. Therefore, the principal
component may not represent the rotations of the smartphone well enough to allow for accurate
classification when there are several activities to be classified. Example PCA-transformed signals
for the jogging activity are shown in Figure 2. In some activities, patterns can also be detected
visually in the third component of the PCA transformation.
8. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
8
2.2. ORIENTATION-INVARIANT SAMPLES BY GENERALIZED HEBBIAN ALGORITHM
The generalized Hebbian algorithm is an unsupervised learning method based on Hebb’s learning
rule about the way synaptic strengths in the brain are adjusted. According to Hebb’s learning rule,
strengths of the synapses in the brain are adjusted through changes that are proportional to the
pre-synaptic input and the output in the post-synaptic neuron, which means that the rate of
adjustment is proportional to the correlation between the input and the output signals. This idea is
used in the generalized Hebbian algorithm in order to decorrelate the components in a multi-
dimensional signal.
The simplified neuron model is given by
1
n
T
i i
i
y w x
=
= = ∑w x (11)
where w is a synaptic weight. Hebbs learning rule for neurons can be written as follows
i iw x yα∆ = 1i = ,...,n (12)
where iw∆ is the change in the weight for ix . The weight update for every iteration can be written
as
( 1) ( )i i iw n w n x yα+ = + (13)
Normalizing to ensure that the length of the weight vector is one so that the vector does not grow
infinitely large,
( )
1
1/
1
t
t i i
i rrn
t
m m
m
w x y
w
w x y
α
α
+
=
+
=
+
∑
(14)
where 2r = for Euclidean distance. Using a Taylor expansion, the expression for (t 1)iw + can be
simplified
9. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
9
Fig. 2. Principal components (left column) and generalized Hebbian components (right column) of motion
signals for jogging activity; first component of acceleration (a); second component of acceleration (b); third
component of acceleration (c); principal component of gyroscope signal (d); second component of
gyroscope signal (e); third component of gyroscope signal (f).
t 1
1 1
' 0
( ')
( ' 0)
'
t t i
i i
w
w w
α
α
α α
α
+
+ +
=
∂
≈ = +
∂
2
2
1
1
2
' 0
( ' )
( ' ) ( ' )
( ' )
( ' 0)
( ' )
t
j j jn
jt t
i j j i t
j
j j
jt
i t
j j
j
yx w yx
yx w ayx wi yx
w yx
w
w yx
α
α
α
α
α α
α
=
+
=
+
+ − +
+
= = +
+
∑
∑
∑
∑
(15)
Substituting 2
( ) 1t
j
j
w =∑ in the expression above,
1
( ) ( )t t t t
i i i i j j
j
w w yx w yx wα α+
≈ + − ∑ (16)
10. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
10
Fig. 3. Convergence of the Hebbian algorithm to the jogging activity principal components can be verified
by observing the difference between the true 3-dimensional acceleration 2 2 2
x y za a a+ + and the
acceleration obtained by inverting the transformation on the orientation-invariant signals
The update for the weight can then be rewritten as
( ) ( )i i i j j
j
w yx w y x wα α∆ = − ∑ (17)
This result is Oja’s rule and is typically written in vector form as
2
( )y yα∆ = −w x w (18)
Oja’s rule is related to the principal components. Substituting T
y = x w ,
( )T T T
α∆ = −w xx w w xx ww (19)
Upon convergence, w is approximately constant and 0∆ ≈w so that the above equation can be
rewritten as
T T T
≈xx w w xx ww (20)
For the average T
xx , the above equation can be written as
[ ] [ ]T T T
E E≈xx w w xx ww
T
x xΩ ≈ Ωw w ww (21)
which is the eigenvector, eigenvalue equation for xΩ , which is the covariance matrix for x. In
general, the eigenvectors with the largest eigenvalues point in the direction of highest variance.
For a network with a single output neuron, only one eigenvector is defined by w. This
eigenvector w points in the direction of the principal component. Therefore, for a single output
neuron that learns via Oja’s rule (18), it can be said that upon convergence, T
w is the PCA
11. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
11
Table 1. Table of Features Obtained from Hebbian Signals that were Selected by CFS.
transform operator and T
w x is the principal component [18]. Multiple component extraction
methods are explored in [19].
In this paper, the proposed method for HAR makes use of orientation-invariant signals obtained
through the generalized Hebbian algorithm. Figure 2 shows the motion signals generated by a
user as he is jogging. Figure 3 shows the difference between the total acceleration signal
2 2 2
x y za a a+ + and the signal recovered by inverting the transformation. Such curve, and the
similarity between Hebbian components and PCA components can be used to verify convergence
of the Hebbian algorithm
3. FEATURE EXTRACTION AND CLASSIFICATION
The feature set used by the system was created by selecting from a pool of features from [5][10]
and [16]. In order to improve accuracy and reduce computational expenses, a feature selection
was performed. Selection was done with a correlation-based feature selection (CFS) method
proposed in [20], in conjunction with a backwards greedy search. The backwards greedy search
starts by using all features and removes one at each iteration step. At each iteration, the feature to
be eliminated from the selection is the one for which a figure of merit is maximized when the
features is not included in the subset. The purpose of the CFS feature selection algorithm is to
find a subset of features that are lowly correlated with each other, but highly correlated with the
class label.
Features are eliminated at each iteration until no more eliminations can be done without
diminishing performance. A figure of merit from [21] is used,
( 1)
cf
s
ff
kr
M
k k k r
=
+ +
(22)
where ffr is the average Pearson correlation between each possible pair of features and cfr is the
average Pearson correlation between each feature and the class.The features in use are not
necessarily continuous. In cases where all the features in use are continuous, Pearson’s
correlation can be used to obtain a figure of merit in (22).
12. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
12
However, in order to include categorical features and classes, which are also categorical, all
continuous features are discretized using a discretization algorithm in [22]. Symmetrical
uncertainty is then calculated between each pair of features and used instead of Pearson’s
correlation in (11). Such quantity has a value in the range [0,1]. Symmetrical uncertainty is
calculated as
2
( ) ( )
G
U
H Y H X
= −
+
(23)
where H is information entropy and ( ) ( | )G H Y H Y X= − is the mutual information or expected
information gain for a given feature pair (X,Y). Information gain is the decrement in the entropy
of X when the value of feature Y is known, or viceversa. As opposed to information gain,
symmetrical uncertainty is a normalized quantity that is not biased by the number of categories in
a feature.
The feature selection can be performed by adding or eliminating features one at a time or by
testing several subsets by feeding each into the classifier and checking accuracy of results. But
such method is computationally expensive. In such case, the resulting feature subset would also
depend on the classifier. Using a performance metric, such as the one in (11) to calculate for each
subset without actually having to feed it into the classifier is less computationally expensive.
In general, the resulting feature subset will not be optimal but it will be a local minimum that
produces a smaller set of features and results in better accuracy, found with a reasonable amount
of computational expense. The original pool of features was made of features chosen from those
described in Section I and additional features proposed by the authors. The final set of features
obtained after performing feature selection in the proposed algorithm are shown in Table 1. All
the features obtained during the training stage were converted to z-scores.
The authors have chosen to use kNN because there are many implementations readily available.
In this case the authors have used the WEKA implementation [23]. A disadvantage of instance-
based algorithms is that they are computationally expensive. However, one benefit of instance-
based algorithms is their ability to adapt to new data. New instances can be added to the training
data simply by calculating features vectors and storing them, as opposed to other algorithms that
may require the entire classification model to be calculated again, such as decision trees. Old
instances can be eliminated easily as well for adaptation. Algorithms with such ability may prove
advantageous when deploying to the masses, given that each user has his or her own way of
performing an activity (i.e., different users may have a different gait). A multilayer perceptron
was also chosen in our implementation because of the ability of neural networks to approximate
any continuous function within an input interval to any desired level of accuracy. The
approximation that results for discontinuous functions can still be useful. A neural network with a
single hidden layer can approximate any function by adding more neurons to the hidden layer in
order to increase accuracy. Neural networks are popular for solving pattern recognitions problems
and there are also many implementations readily available. In this case the authors have chosen to
use the WEKA implementation. SVM was not chosen for this study because it is computationally
expensive. Decision trees were not chosen either to avoid overfitting due to the high number of
features in use.
13. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
13
Table 2. Simulation Accuracies for 236 Activity Samples (%)
Euclidean distance was used with kNN. The highest accuracy was obtained using only one
neighbor. For the multilayer perceptron, nodes with a sigmoid activation function were used. A
momentum of .2 and a learning rate of .3 were used for training by backpropagation. The learning
rate controls the size of the adjustments to the weights in the neural network as it is being trained
by backpropagation. The momentum is a number in the range [0,1] that controls the rate of
change in the adjustments. If the momentum is set to zero, the adjustments depend only on the
learning rate, the error in the output of the neuron, and the value of the input, but not on the size
of previous adjustments. If the momentum is set to one, the size of the adjustments will be
constant. The network was trained by backpropagation for 500 epochs. A single epoch is one pass
through all patterns in the training set.
4. TESTING
The proposed algorithm extracts the features in Table 1 from orientation-invariant signals
obtained through the generalized Hebbian algorithmand classifies them either with a kNN
classifier or a multilayer perceptron. The results for the multilayer perceptron are more accurate
than those obtained when using kNN. Nevertheless, kNN results are also described here for
completeness and because kNN is easier to implement than the multilayer perceptron. The
algorithm was tested on exercise activities from university students. The athletic exercises in the
database include resting, walking, jogging, squatting, and doing jumping jacks. Each user was
asked to place the smartphone in the front right pocket. The users were not asked to place the
smartphone with any particular orientation inside the pocket. Each exercise frame lasts for a total
of 5 seconds. A total of 236 frames were captured.
The data was captured with a smartphone that houses an InvenSense MPU-6050 three-axial
accelerometer and three-axial gyro sensor. The device also includes a Digital Motion Processor
(DMP) which can be used to process the signals. The DMP can also be used to process signals
coming from an external sensor, such as a magnetometer that can be interfaced through I2C. The
MPU-6050 transfers the data to the host also via I2C. It outputs signals with a resolution of 16-bit
and can be set to span four different ranges. The MPU-6050 has a printout of 4x4x.9mm. The
smartphone used for this research does not take advantage of all the capabilities of the MPU-
6050, but there are boards in the market that do
14. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
14
Table 3. Confusion table for the Unknown Subject Test Applied to the Proposed Method.
Two different tests were performed: unknown-subject and single-subject. The unknown-subject
test was done by training the system with all subjects except the unknown subject and then testing
it on the frames from the subject on which the system was not trained. The overall accuracy of the
unknown-subject was calculated by averaging accuracy across all subjects. The single-subject
test, which evaluates performance when the algorithm is trained and tested in the same subject,
was done by taking the samples from one subject and doing a 5-fold stratified cross-validation.
The overall accuracy of the single-subject test was found by averaging accuracy across all folds
and across all subjects.
A performance comparison was done with the methods in [5] and [10]. Both methods were
simulated using the Weka toolkit in the classification stage. The algorithm in [5] has its own
feature set and classifies instances with C4.5 and kNN. The method proposed in [10] also uses the
Weka toolkit. This method was simulated by extracting the features in [10] from the acceleration
window without applying orientation-invariant preprocessing, and then classifying with the
multilayer perceptron and the C4.5 [24] classifiers in the Weka toolkit, using the settings that
were also used for the proposed algorithm. No feature standardization procedure is mentioned in
[10]. The results are shown in Table 2.
The proposed method outperforms the other two popular methods, which can easily be replicated
in a lab setting and used as benchmarks. For the unknown-subject test, the proposed method
performs much better than the other two methods, especially when using the multilayer
perceptron. Performance improvement is expected given that different users position the
smartphone in different orientations inside their pockets. A single user, however, may or may not
be inclined to place the device in one particular orientation.
The high accuracy obtained with the proposed algorithm may also be due to feature
standardization. For the unknown subject test the proposed algorithm obtained much higher
results than the methods in [5] and [10]. For single subject activity recognition both classifiers
yield accuracy higher than 95%. The authors propose using orientation-invariant preprocessing,
the standardized features in Table 1, and a multilayer perceptron for classification. Yet,
classification with kNN was also tested because it may be easier to implement for some of the
readers. The confusion table for the test with unknown subjects with the proposed HAR algorithm
is shown in Table 3.
5. CONCLUSION
The proposed method for human activity recognition using wearable motion sensors properly
accounts for random orientations of the sensors. The method is particularly useful in the case of a
smartphone inside a user’s front pant pocket. The preprocessing stage of the proposed method
renders the motion signals orientation-invariant. A small standardized feature set calculated from
motion signals is then fed into a multilayer perceptron. The method introduced in this paper
15. International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 7, No. 6, November 2016
15
outperforms other modern methods when classifying several low level activities from unknown
subjects, including exercises typically performed by athletes.
REFERENCES
[1] D. Guan, T. Ma, W. Yuan, Y.K. Lee, and A.M. Jehad Sarkar, “Review of Sensor-based Activity
Recognition Systems,” IETE Technical Review, Vol. 28 Issue 5, p418, Sep/Oct (2011).
[2] S.M. Mahmoud, A. Lotfi, and C. Langensiepen , "Behavioural Pattern Identification in a Smart Home
Using Binary Similarity and Dissimilarity Measures," Proceedings of the 2011 Seventh International
Conference on Intelligent Environments – IE’11, pp.55-60, 25-28 July (2011).
[3] S.K. Tasoulis, C.N. Doukas, I. Maglogiannis, V.P. Plagianakos, "Statistical data mining of streaming
motion data for fall detection in assistive environments," 2011 Annual International Conference of the
IEEEEngineering in Medicine and Biology Society, EMBC, pp.3720,3723, Aug. 30-Sept. 3 (2011).
[4] L. Bao and S. S. Intille, "Activity recognition from user-annotated acceleration data," in Proceedings
of PERVASIVE 2004, vol. LNCS 3001, A. Ferscha and F. Mattern, Eds. Berlin Heidelberg: Springer-
Verlag, pp. 1-17, (2004).
[5] N. Ravi, N. Dandekar, P. Mysore, and M.L. Littman, 2005. Activity recognition from accelerometer
data. Proceedings of the 17th conference on Innovative applications of artificial intelligence, Bruce
Porter (Ed.), Vol. 3. (2005).
[6] D.M. Karantonis, M.R. Narayanan, M. Mathie, N.H. Lovell, and B.G. Celler, "Implementation of a
real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring," IEEE
Transactions on Information Technology in Biomedicine, vol.10, no.1, pp.156,167, January (2006)
[7] G.X. Lee, K.S. Low, and T. Taher, “Unrestrained measurement of arm motion based on wearable
wireless sensor network,” IEEE Transactions on Instrumentation and Measurement, Vol. 59, No.5,
pp. 1309-1317, (2010).
[8] X. Yun, J. Calusdian, E. R. Bachmann, and R.B. McGhee, “Estimation of human foot motion during
normal walking using inertial and magnetic sensor measurement,” IEEE Transactions on
Instrumentation and Measurement, Vol. 61, No.7, pp. 2059-2072, (2012).
[9] W.-Y. Wong and M.-S. Wong, “Measurement of postural change in trunk movements using three
sensor modules,” IEEE Transactions on Instrumentation and Measurement, Vol. 58, No.8, pp. 2737-
2742, (2009).
[10] J.R. Kwapisz, G.M. Weiss, and S.A. Moore, 2011. Activity recognition using cell phone
accelerometers. ACM SIGKDD Explorations Newsletter, Volume 12 Issue 2, Pages 74-82, December
(2010).
[11] A. Henpraserttae, S. Thiemjarus, and S. Marukatat, "Accurate Activity Recognition Using a Mobile
Phone Regardless of Device Orientation and Location," International Conference on Body Sensor
Networks (BSN), pp.41-46, 23-25 May (2011).
[12] V.Q. Viet, H.M. Thang, and D.J. Choi, "Balancing Precision and Battery Drain in Activity
Recognition on Mobile Phone," International Conference on Parallel and Distributed Systems
(ICPADS), pp.712-713, 17-19 Dec. (2012).
[13] M. Hynes, H. Wang and and L. Kilmartin, "Off-the-shelf mobile handset environments for deploying
accelerometer based gait and activity analysis algorithms," Annual International Conference of the
IEEE Engineering in Medicine and Biology Society, pp.5187,5190, 3-6 Sept. (2009).
[14] T. Mashita, D. Komaki, M. Iwata, K. Shimatani, H. Miyamoto, T. Hara, K. Kiyokawa, H. Takemura,
and S. Nishio, "A content search system for mobile devices based on user context recognition,"
Proceedings of IEEE Virtual Reality, Pages 1-4 (2012).
[15] T. Mashita, K. Shimatani, M. Iwata, H. Miyamoto, D. Komaki, T. Hara, K. Kiyokawa, H. Takemura,
and S. Nishio, "Human activity recognition for a content search system considering situations of
smartphone users," Proceedings of IEEE Virtual Reality, Pages 1,2, 4-8 March (2012).
[16] J.A. Morales, D. Akopian, S. Agaian, "Human activity recognition by smartphones regardless of
device orientation", Proceedings of SPIE Conference on Mobile Devices and Multimedia: Enabling
Technologies, Altorithms, and Applications, Reiner Creutzburg and David Akopian, Editors, 18
February (2014).
[17] L. Zhang, W. Dong, D. Zhang, and G. Shi, "Two-stage image denoising by principal component
analysis with local pixel grouping," Pattern Recognition, Volume 43, Issue 4, Pages 1531-1549, April
(2010).