project presentation halfway

1. MIDWAY PROJECT PRESENTATION
PROJECT: HUMAN ACTIVITY RECOGNITION USING
SMARTPHONES
NATIONAL INSTITUTE OF SCIENCE AND EDUCATIONAL
RESEARCH
PAPER-CS660
MACHINE LEARNING
PRESENTED BY PINKI PRADHAN
Click to add text

2. RELATED PAPERS:
• Related papers that I am going to elaborate here are given below:
• Paper 1: Wearable Sensor-Based Human Activity Recognition Using Hybrid Deep Learning Techniques
• Paper 2: A lightweight deep learning model for human activity recognition on edge devices
• INTRODUCTION OF PAPER1:
• Human behavior recognition (HAR) is the detection, interpretation, and recognition of human behaviors,
which can use smart heath care to actively assist users according to their needs.
• Human behavior recognition has wide application prospects, such as monitoring in smart homes, sports,
game controls, health care, elderly patients care, bad habits detection, and identification.
• It plays a significant role in depth study and can make our daily life become smarter, safer, and more
convenient.
• This work proposes a deep learning based scheme that can recognize both specific activities and the
transitions between two different activities of short duration and low frequency for health care applications.

3. DATASET:
• These people used the international standard Data Set, Smart phone Based Recognition of Human
Activities and Postural Transitions Data Set to conduct an experiment, which is abbreviated as HAPT
dataset.
• PROPOSED METHOD:
• They input the composite image into a three-layer CNN network that can automatically extract the motion
features from the activity image and abstract the features, then map them into the feature map. Then the
feature vector is inputted into the LSTM model, establish a relationship between time and action
sequence, and finally introduce the full connection layer to achieve the fusion of multiple features

4. • Why Sensors?
• Human behaviour data can be acquired from computer vision . But the vision based approaches have many
limitations in practice.
• But in case of sensors, these wearable sensors are small in size, high in sensitivity, strong in anti interference
ability and most importantly they are integrated with our mobile phones and these sensors can accurately
estimate the current acceleration and angular velocities of motion sensors in real time.
• Why CNN?
• The traditional pattern of behavior recognition research using decision tree, support vector machine (SVM), and
other machine learning algorithms can obtain much satisfactory results, in premise of some controlled
experimental environments and a small number of labeled data. However, the accuracy of these methods
depends on the effectiveness and comprehensiveness of manual feature extraction.
• CNN follows a hierarchical model which works on building a network , like a funnel and finally gives out a fully
connected layer where all the networks are connected to each other and output is processed.
• The main advantages of CNN compared to other neural network is that it automatically detects the important
features without any human supervision.

5. • Why LSTM?
• LSTM is used here to establish recognition models to capture time relations in input sequences and could
achieve more accurate recognition.
• This work proposes a deep learning based scheme that can recognize both specific activities and the
transitions between two different activities of short duration and low frequency for health care applications.
The experimental results show that the proposed approach can help improve the recognition rate up to
95.87% and the recognition rate for transitions higher than 80%, which are better than those of most existing
similar models over the open HAPT dataset.

6. • PAPER 2:
• Here the architecture for proposed Lightweight model is developed using Shallow Recurrent Neural Network
(RNN) combined with Long Short Term Memory (LSTM) deep learning algorithm.
• They have used a dataset called WISDM(Wireless sensor data mining) dataset collected from accelerometer and
having 1,098,207 rows and 6 columns.
• PROPOSED METHOD:
• The proposed model is developed
using RNN combined with LSTM.
• It has a shallow structure with just
two hidden layers and 30 neurons
making it feasible to be deployed
on edge computing devices like

7. • In previous paper they are using CNN-LSTM but here RNN-LSTM is used . RNNs are capable of
capturing temporal information from sequential data. It consists of input, hidden, and output
layer. Hidden layer consist of multiple nodes.
• RNN networks suffer from the problem of exploding and vanishing gradient. This hinders the
ability of network to model wide-range temporal dependencies between input readings and
human activities for long context windows.
• RNNs based on LSTM can eliminate this limitation, and can model long activity windows by
replacing traditional RNN nodes with LSTM memory cells . So here RNN is used for Activity
recognition and LSTM is used to recognize different types of transition of activations.

8. • Here i have used 8 libraries in my project such as pandas, numpy, tensorflow, scipy, matplotlib, sklearn,
seaborn, pickle.
• I have used WISDM dataset, same dataset that was used in paper2. These dataset consists of 1,098,206 records
and 6 columns.

9. DATA EXPLORATION:

10. • GRAPH FOR SITTING:

11. GRAPH FOR JOGGING: