Anindya Das Antar

Anindya Das Antar
University of Michigan | U-M · Division of Computer Science and Engineering

About

23
Publications
5,697
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
242
Citations
Introduction
Behavior-based Healthcare Intervention. HCI, Applied Machine Learning, Computational Modeling, Computer Vision

Publications

Publications (23)
Article
Computational models that formalize complex human behaviors enable study and understanding of such behaviors. However, collecting behavior data required to estimate the parameters of such models is often tedious and resource intensive. Thus, estimating dataset size as part of data collection planning (also known as Sample Size Determination) is imp...
Chapter
A major goal of human activity and behavior recognition (HAR) is to recognize activities and behaviors from a series of action data for different subjects under different environmental conditions. The use of wearables, smart devices, and vision-based systems enables the collection of human action and behavior data for greater health benefits, rehab...
Article
Smartphone sensor-based activity recognition seeks broad, high-level knowledge about human behaviors from multitudes of low-level sensor readings, and makes considerable headway in healthcare domain. Our primary contribution is to study the effective pre-processing technique and the extraction of robust features for the classification of sensor dat...
Article
Full-text available
Recognition of daily human activities in various locomotion and transportation modes has numerous applications like coaching users for behavior modification and maintaining a healthy lifestyle. Besides, applications and user interfaces aware of user mobility through their smartphones can also aid in urban transportation planning, smart parking, and...
Article
Full-text available
Action recognition is a very widely explored research area in computer vision and related fields. We propose Kinematics Posture Feature (KPF) extraction from 3D joint positions based on skeleton data for improving the performance of action recognition. In this approach, we consider the skeleton 3D joints as kinematics sensors. We propose Linear Joi...
Chapter
Sensor-based Human Activity Recognition (HAR) has been explored by many research communities and industries for various applications. Conventional pattern recognition approaches based on handcrafted features contributed a lot in this research field by employing general classification approaches. This chapter represents those handcrafted features in...
Article
This book offer clear descriptions of the basic structure for the recognition and classification of human activities using different types of sensor module and smart devices in e.g. healthcare, education, monitoring the elderly, daily human behavior, and fitness monitoring. In addition, the complexities, challenges, and design issues involved in da...
Chapter
Human activity analysis and recognition tasks can be considered as classification problems in most of the cases. This chapter represents the overview of classification problems explaining their different types with examples. Binary classification, multilabel classification, multi-class classification, and hierarchical classification tasks are prese...
Chapter
Sensor-based Human Activity Recognition (HAR) has been explored by many research communities and industries for various applications. In the earlier chapters, we have presented methodologies to accomplish human activity recognition, pre-processing steps of raw data from sensors, segmentation of these data using various windowing approaches, feature...
Chapter
The field of human activity recognition (HAR) using different sensor modalities poses numerous challenges to the researchers working in this domain. Though traditional pattern recognition approaches performed well in this regard earlier, the cost of poor generalization and the cost of shallow learning due to the handcrafted features have opened a n...
Chapter
Sensory modality is a primary concern in sensor-based activity recognition research. The usage of wearable devices and utilizing embedded smartphone sensor data to recognize daily activities has become famous in this research field nowadays. This chapter deals with the challenges of choosing an appropriate sensing device and application tools for d...
Chapter
Human Activity Recognition (HAR) has explored a lot recently in the academia and industries for numerous applications. There are lots of progress in the domain of vision-based action or activity recognition due to the advent of deep learning models and due to the availability of very large datasets in the last several years. However, there are stil...
Chapter
Automatic recognition of human activities using sensor-based systems is commonly known as human activity recognition (HAR). It is required to follow a structural pipeline to recognize activity using a machine learning technique. This chapter represents the different stages of this structural pipeline in detail. Following this, the preprocessing ste...
Chapter
Human Activity Recognition (HAR) using installed sensors has made renowned progress in the field of pattern recognition and human-computer interaction. To make efficient machine learning models, researchers need publicly available benchmark datasets. In this chapter, we have bestowed a comprehensive survey on sensor-based benchmark datasets. We hav...
Chapter
The constant growth of sensor-based systems and technologies for the detection of human activities has made notable progress in the field of human-computer interaction. The continuation of Internet connectivity into daily objects and physical devices has made it possible for the researchers to use IoT sensors for healthcare, elderly people monitori...
Chapter
After building the model to recognize activities from sensor data, it is essential to investigate the effectiveness of the model. The evaluation of the performance for machine learning methods can be performed using some evaluation matrices. This chapter properly explains the evaluation matrices namely accuracy, precision, recall, F1 score, balance...
Article
Full-text available
Wearable sensor-based systems and devices have been expanded in different application domains, especially in the healthcare arena. Automatic age and gender estimation has several important applications. Gait has been demonstrated as a profound motion cue for various applications. A gait-based age and gender estimation challenge was launched in the...
Conference Paper
Full-text available
Sensor-based recognition of locomotion and transportation modes has numerous application domains including urban traffic monitoring, transportation planning, and healthcare. However, the use of a smartphone in a fixed position and orientation in previous research works limited the user behavior a lot. Besides, the performance of naive methods for p...
Conference Paper
Full-text available
The scarcity of trained therapist, economic imbalance, and an increasing amount of elderly people are the reasons for poor rehabilitation treatment and inadequate healthcare facilities in many countries. Vision-based rehabilitation treatment, monitoring daily living, and advanced health-care can improve technology that allows people with an injury...
Conference Paper
Full-text available
In this paper, we have used a smartphone sensor-based benchmark Sussex-Huawei Locomotion-Transportation (SHL) dataset for rich locomotion and transportation analytics. We have shown a comparison of different sensor-based features for the identification of a specific activity level. Besides, we have proposed a "Mod technique" method, which increases...

Network

Cited By

Projects

Projects (2)