scholarly journals HUMAN ACTIVITY RECOGNITION BASED ON SMARTPHONE SENSOR DATA USING CNN

2020 ◽  
Vol XLIV-4/W3-2020 ◽  
pp. 263-265
Author(s):  
K. İsmail ◽  
K. Özacar
Keyword(s):  
Human Activity ◽  
Low Cost ◽  
Daily Activities ◽  
Sensor Data ◽  
Android Application ◽  
Old People ◽  
Model Accuracy ◽  
Sensing Technology ◽  
Smartphone Technology ◽  
Smartphone Sensor

Abstract. Human activity recognitions have been widely used nowadays by end users thanks to extensive usage of smartphones. Smartphones, by self-containing low-cost sensing technology, can track our daily activities for serving healthcare, sport, interactive AR/VR games and so on. However, smartphone technology is evolving and the techniques of using the data that smartphones go through are also improving. In this study, we used built-in sensing technologies (accelerometer and gyroscope) available in nearly every smartphone to detect the most common 5 daily activities of human by taking the data of these sensors and extract the features for a Convolutional Neural Network (CNN) model. We prepare a dataset and use TensorFlow to train the collected data from the sensors then filtered it to be processed. We also discuss the differences in CNN model accuracy with different optimizers. To demonstrate the model, we developed an android application that successfully predict an activity. We believe that after improving this application, it can be used for especially lonely old people to immediately warn authorities in case of any daily incidents.

scholarly journals Wi-CAS: A Contactless Method for Continuous Indoor Human Activity Sensing Using Wi-Fi Devices

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8404
Author(s):  
Zhanjun Hao ◽  
Daiyang Zhang ◽  
Xiaochao Dang ◽  
Gaoyuan Liu ◽  
Yanhong Bai
Keyword(s):  
Human Activity ◽  
Low Cost ◽  
Recognition Rate ◽  
Ensemble Classification ◽  
Contactless Method ◽  
Robust Solution ◽  
Sensing Technology ◽  
New Ideas ◽  
Cas A ◽  
Activity Sensing

With the new coronavirus raging around the world, home isolation has become an effective way to interrupt the spread of the virus. Effective monitoring of people in home isolation has also become a pressing issue. However, the large number of isolated people and the privatized isolated spaces pose challenges for traditional sensing techniques. Ubiquitous Wi-Fi offers new ideas for sensing people indoors. Advantages such as low cost, wide deployment, and high privacy make indoor human activity sensing technology based on Wi-Fi signals increasingly used. Therefore, this paper proposes a contactless indoor person continuous activity sensing method based on Wi-Fi signal Wi-CAS. The method allows for the sensing of continuous movements of home isolated persons. Wi-CAS designs an ensemble classification method based on Hierarchical Clustering (HEC) for the classification of different actions, which effectively improves the action classification accuracy while reducing the processing time. We have conducted extensive experimental evaluations in real home environments. By recording the activities of different people throughout the day, Wi-CAS is very sensitive to unusual activities of people and also has a combined activity recognition rate of 94.3%. The experimental results show that our proposed method provides a low-cost and highly robust solution for supervising the activities of home isolates.

scholarly journals Using Low-cost Smartphone Sensor Data for Locating Crash Risk Spots in a Road Network

2016 ◽  
Vol 14 ◽  
pp. 2015-2024 ◽  
Author(s):  
Claus Aichinger ◽  
Philippe Nitsche ◽  
Rainer Stütz ◽  
Marko Harnisch
Keyword(s):  
Road Network ◽  
Low Cost ◽  
Sensor Data ◽  
Crash Risk ◽  
Smartphone Sensor

scholarly journals Bluetooth Based Smart Automation System Using Android

2021 ◽  
Author(s):  
Swati M Patil ◽  
Poonam V Gaikwad
Keyword(s):  
Data Exchange ◽  
Low Cost ◽  
Automation System ◽  
Home Automation ◽  
Android Application ◽  
Operational Cost ◽  
Wireless Technology ◽  
Old People ◽  
And Control ◽  
Day By Day

The word automation is automatic control of operating devices with minimal or reduced human efforts. Influence of wireless technology is growing day by day. In today’s world, wireless technology doing significant role in the automation. It means automation makes technology free from human interruption. Home automation is one of the technology emerging these days. To make it more effective and efficient, cost is reduced by low cost communication technology like Bluetooth, Wi-Fi. Bluetooth is wireless technology to use in home automation. It is no operational cost technique, common in use and working in range up to 100 meters [2]. Bluetooth which is mainly used for data exchange, add new features to smartphones. With help of android application we are able to connect and control household appliances and provide security to handicapped, old people.

scholarly journals SENSOR BASED ALGORITHMS FOR DEAD RECKONING: A COMPARISON OF TWO APPROACHES FOR SMARTPHONES

2014 ◽  
pp. 50-60
Author(s):  
Daniel Caspari ◽  
Mircea Strutu ◽  
Lucas Riedhammer ◽  
Uwe Grossmann
Keyword(s):  
Patient Monitoring ◽  
Indoor Localization ◽  
Real Life ◽  
Dead Reckoning ◽  
Sensor Data ◽  
Localization System ◽  
Starting Point ◽  
Smartphone Technology ◽  
User Friendly ◽  
Smartphone Sensor

The implementation of a reliable indoor localization system can be the starting point for a variety of much desired applications. Either for efficient patient monitoring inside a hospital or as an automatic guide inside a museum, a working localization solution can be useful. Smartphone technology represents a powerful and user friendly tool in order to achieve adequate indoor positioning. This paper explores the potential of using smartphone sensor data (accelerometer and compass) in order to track the location of the person holding the device using dead reckoning algorithms. Two different approaches are under scrutiny in order to assess their performance in different real life inspired scenarios.

scholarly journals LSTM Networks Using Smartphone Data for Sensor-Based Human Activity Recognition in Smart Homes

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1636
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Recognition Performance ◽  
Human Activity Recognition ◽  
Optimization Techniques ◽  
Bayesian Optimization ◽  
Sensor Data ◽  
Lstm Network ◽  
The Impact ◽  
Smartphone Sensor

Human Activity Recognition (HAR) employing inertial motion data has gained considerable momentum in recent years, both in research and industrial applications. From the abstract perspective, this has been driven by an acceleration in the building of intelligent and smart environments and systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc. Such environments and systems necessitate and subsume activity recognition, aimed at recognizing the actions, characteristics, and goals of one or more individuals from a temporal series of observations streamed from one or more sensors. Due to the reliance of conventional Machine Learning (ML) techniques on handcrafted features in the extraction process, current research suggests that deep-learning approaches are more applicable to automated feature extraction from raw sensor data. In this work, the generic HAR framework for smartphone sensor data is proposed, based on Long Short-Term Memory (LSTM) networks for time-series domains. Four baseline LSTM networks are comparatively studied to analyze the impact of using different kinds of smartphone sensor data. In addition, a hybrid LSTM network called 4-layer CNN-LSTM is proposed to improve recognition performance. The HAR method is evaluated on a public smartphone-based dataset of UCI-HAR through various combinations of sample generation processes (OW and NOW) and validation protocols (10-fold and LOSO cross validation). Moreover, Bayesian optimization techniques are used in this study since they are advantageous for tuning the hyperparameters of each LSTM network. The experimental results indicate that the proposed 4-layer CNN-LSTM network performs well in activity recognition, enhancing the average accuracy by up to 2.24% compared to prior state-of-the-art approaches.

scholarly journals Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1715
Author(s):  
Michele Alessandrini ◽  
Giorgio Biagetti ◽  
Paolo Crippa ◽  
Laura Falaschetti ◽  
Claudio Turchetti
Keyword(s):  
Neural Network ◽  
Embedded System ◽  
Activity Recognition ◽  
Human Activity ◽  
Recurrent Neural Network ◽  
Low Cost ◽  
Low Complexity ◽  
Human Activity Recognition ◽  
Motion Artifacts ◽  
Accelerometer Data

Photoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging.

scholarly journals Similarity Embedding Networks for Robust Human Activity Recognition

2021 ◽  
Vol 15 (6) ◽  
pp. 1-17
Author(s):  
Chenglin Li ◽  
Carrie Lu Tong ◽  
Di Niu ◽  
Bei Jiang ◽  
Xiao Zuo ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Short Term Memory ◽  
Real Space ◽  
Human Activity Recognition ◽  
Sensor Data ◽  
Activity Data ◽  
Extensive Evaluation ◽  
Sensor Signals ◽  
Public Datasets

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of high-quality labeled activity data, which are hard to obtain. In this article, we design a similarity embedding neural network that maps input sensor signals onto real vectors through carefully designed convolutional and Long Short-Term Memory (LSTM) layers. The embedding network is trained with a pairwise similarity loss, encouraging the clustering of samples from the same class in the embedded real space, and can be effectively trained on a small dataset and even on a noisy dataset with mislabeled samples. Based on the learned embeddings, we further propose both nonparametric and parametric approaches for activity recognition. Extensive evaluation based on two public datasets has shown that the proposed similarity embedding network significantly outperforms state-of-the-art deep models on HAR classification tasks, is robust to mislabeled samples in the training set, and can also be used to effectively denoise a noisy dataset.

Sign in / Sign up

Export Citation Format

Share Document