Activity Recognition by Using LoRaWAN Sensor

Hossain, Tahera; Ahad, Md. Atiqur Rahman; Tazin, Tahia; Inoue, Sozo

doi:10.1145/3267305.3267652

Cited by 32 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hossain et al created a network using LoraWAN technology. Sensor nodes transmit the accelerometer data to LoraWAN gateway [14]. Balli et al created WSN consists of smartwatches and smartphone.…”

Section: Introductionmentioning

confidence: 99%

Design of a Wearable Wireless Multi-Sensor Monitoring System and Application for Activity Recognition Using Deep Learning

Ascioglu

Şenol

2020

IEEE Access

View full text Add to dashboard Cite

Human activity monitoring and recognition systems assist experts in evaluating various health problems including obesity, cardiac diseases and, sports injury detection. However, these systems have two challenging points; monitoring activities for outdoor applications and extracting relevant features using hand-crafted techniques from multi-dimensional and large datasets. To address these challenges, we have focused on new dataset generation for activity recognition, a novel design of a sensor-based wireless activity monitoring system, and its application to deep learning neural networks. The designed monitoring system consists of one master and four slave devices, and can collect and record acceleration and gyroscope information. The slave devices were attached on arm, chest, thigh, and shank areas of the human body. Activity data were collected and recorded from sixty healthy people for thirteen activity types including drink from cup and cleaning table. These activities were divided into three activity categories as basic, complex, and all, which is the combination of basic and complex activities. Obtained datasets were fed into deep learning neural networks namely convolutional neural network (CNN), long-short term memory (LSTM) neural networks, and convolutional LSTM (ConvLSTM) neural networks. The performance of each neural network for each category type was separately examined. The results show that ConvLSTM outperforms CNN and LSTM as far as activity recognition is concerned.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of a Wearable Wireless Multi-Sensor Monitoring System and Application for Activity Recognition Using Deep Learning

Ascioglu

Şenol

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Other than the two main machine learning-based tasks in this paper (profiling and prediction), machine learning has been applied in LoraWAN networks for several applications. For example, in [25], the authors used Q-Learning for resource allocation; in [26] a deep learning-based approach has been used to exploit time difference of arrival for correct mobile station positioning; in [27] an ARIMA model has been used to predict future trends starting from air pollution sensors; in [28], the authors exploit LoRaWAN sensors and supervised learning for activity recognition; in [29,30], machine learning has been used for localization purposes and, finally, in [31] a mixture of unsupervised, supervised and decision model techniques has been used for load balancing in LoRaWAN networks.…”

Section: Related Workmentioning

confidence: 99%

Predicting LoRaWAN Behavior: How Machine Learning Can Help

et al. 2020

View full text Add to dashboard Cite

Large scale deployments of Internet of Things (IoT) networks are becoming reality. From a technology perspective, a lot of information related to device parameters, channel states, network and application data are stored in databases and can be used for an extensive analysis to improve the functionality of IoT systems in terms of network performance and user services. LoRaWAN (Long Range Wide Area Network) is one of the emerging IoT technologies, with a simple protocol based on LoRa modulation. In this work, we discuss how machine learning approaches can be used to improve network performance (and if and how they can help). To this aim, we describe a methodology to process LoRaWAN packets and apply a machine learning pipeline to: (i) perform device profiling, and (ii) predict the inter-arrival of IoT packets. This latter analysis is very related to the channel and network usage and can be leveraged in the future for system performance enhancements. Our analysis mainly focuses on the use of k-means, Long Short-Term Memory Neural Networks and Decision Trees. We test these approaches on a real large-scale LoRaWAN network where the overall captured traffic is stored in a proprietary database. Our study shows how profiling techniques enable a machine learning prediction algorithm even when training is not possible because of high error rates perceived by some devices. In this challenging case, the prediction of the inter-arrival time of packets has an error of about 3.5% for 77% of real sequence cases.

show abstract

“…The systems of 5G need to implement context awareness, based on the network, devices, applications, as well as the environment users located in, using contextual information that can be perceived to provide users with personalized services. Hossain et al [4] explored LoRa Wide Area Network sensor for human activity recognition and proposed an activity recognition framework by exploiting the sensor and its accelerometer data. Shin et al [5] proposed a pedestrian dead reckoning system (PDR) based on mobile phone location awareness algorithm, and used the acceleration sensors in the mobile phone to estimate the users' step size and the number of steps.…”

Section: Related Workmentioning

confidence: 99%

“…At the same time, by using OpenStreetMap, we can get the road network information of the area where the phone holder is located. The spatial position of the phone holder at time t can be defined as (4).…”

Section: ) Data Format and Pre-processingmentioning

confidence: 99%

Context Awareness-Based Accident Prevention During Mobile Phone Use

Sun

Guo³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In recent years, with the continuous development of technologies, people's dependence on smartphones is growing increasingly. Excessive dependence has been causing a considerable number of people to face potential accidents and injuries on account of the use of mobile phones. Based on the above considerations, this paper defines the dangerous context in mathematical forms, using the data collected by sensors in phones and context-aware technology to study the accident prevention methods in the process of using mobile phones. The research involves three parts. Human behavior awareness subproblem refers to the type of behavior currently being taken by the mobile phone holder, which is different from the traditional human behavior recognition problem. The spatial position awareness subproblem refers to the perception of whether the phone holder is in a dangerous area prone to accidental injury. The interactive awareness subproblem refers to how the mobile phone holder interacts with the mobile phone to determine whether the mobile phone holder is in the process of using the mobile phone. The study of accident prevention methods during the use of mobile phones will be based on the output of the above subproblems. After designing and implementing the solutions toward the three subproblems, algorithms are integrated, and the application is designed. INDEX TERMS Dangerous context, context awareness, mobile phone use, accident prevention.

show abstract

Activity Recognition by Using LoRaWAN Sensor

Cited by 32 publications

References 5 publications

Design of a Wearable Wireless Multi-Sensor Monitoring System and Application for Activity Recognition Using Deep Learning

Design of a Wearable Wireless Multi-Sensor Monitoring System and Application for Activity Recognition Using Deep Learning

Predicting LoRaWAN Behavior: How Machine Learning Can Help

Context Awareness-Based Accident Prevention During Mobile Phone Use

Contact Info

Product

Resources

About