AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices

Rashid, Nafiul; Demirel, Berken Utku; Faruque, Mohammad Abdullah Al

doi:10.1109/jiot.2022.3140465

Cited by 74 publications

(27 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Agarwal et al [ 22 ] suggested a lightweight profound learning approach to constructing a HAR with fewer computational resources and less delay, allowing the proposed model to be easily employed in real-world applications. Rashid et al [ 23 ] extended the CNN program [ 22 ] and offered a low-power adaptive CNN that is energy-efficient and memorable. Zhao et al [ 24 ] developed a bi-directional residual LSTM architecture with the benefit of combining forward and backwards-looking states and a good- and bad-looking direction in time.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring

et al. 2022

View full text Add to dashboard Cite

Biomedical images contain a huge number of sensor measurements that can provide disease characteristics. Computer-assisted analysis of such parameters aids in the early detection of disease, and as a result aids medical professionals in quickly selecting appropriate medications. Human Activity Recognition, abbreviated as ‘HAR’, is the prediction of common human measurements, which consist of movements such as walking, running, drinking, cooking, etc. It is extremely advantageous for services in the sphere of medical care, such as fitness trackers, senior care, and archiving patient information for future use. The two types of data that can be fed to the HAR system as input are, first, video sequences or images of human activities, and second, time-series data of physical movements during different activities recorded through sensors such as accelerometers, gyroscopes, etc., that are present in smart gadgets. In this paper, we have decided to work with time-series kind of data as the input. Here, we propose an ensemble of four deep learning-based classification models, namely, ‘CNN-net’, ‘CNNLSTM-net’, ‘ConvLSTM-net’, and ‘StackedLSTM-net’, which is termed as ‘Ensem-HAR’. Each of the classification models used in the ensemble is based on a typical 1D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network; however, they differ in terms of their architectural variations. Prediction through the proposed Ensem-HAR is carried out by stacking predictions from each of the four mentioned classification models, then training a Blender or Meta-learner on the stacked prediction, which provides the final prediction on test data. Our proposed model was evaluated over three benchmark datasets, WISDM, PAMAP2, and UCI-HAR; the proposed Ensem-HAR model for biomedical measurement achieved 98.70%, 97.45%, and 95.05% accuracy, respectively, on the mentioned datasets. The results from the experiments reveal that the suggested model performs better than the other multiple generated measurements to which it was compared.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Members of the cost accounting department, members of other accounting departments, members of the operations department, members of the services department, members of the Information Technology Department, and others as needed comprise a qualified human cadre capable of performing the calculation process (Human resources) (Ostanov and Ostanov, 2022;Rashid et al, 2022). The consistency and clarity of the link between the systems and the accounting needs, so that all team members are usually familiar with the ideas of services, calculating their costs, and the accounting process requirements.…”

Section: Current and Future Trends Related To Activity-based Costing ...mentioning

confidence: 99%

A Bibliometric Review on Activity-based Costing in Services: Exploring Current and Future Trends

Mohammad¹,

Salleh²

2022

IJARBSS

View full text Add to dashboard Cite

The aim of this study is to identify the major present and future issues identified in the literature on Activity-Based Costing (ABC) implementation as searched by the Web of Science database, with a focus on papers published between (1991) and ( 2001). ( 2022). Furthermore, the purpose of this literature review is to emphasize the most important ideas while also laying the groundwork for future research on Activity-Based Costing (ABC) that employs bibliometric analysis. The analysis identifies some of the most common terms. But also the most significant writers that referenced this topic in their research findings, the journals that are most cited in the articles evaluated, and the nations with the highest efficacy. The VOSviewer tool was used to analyse data for keywords and geographical location based on Activity-Based Costing (ABC). It acquired (1725) Web of Science papers classified. Smart libraries, which enable large-scale networking and sharing, will be the future development paradigm for new libraries. It is people-oriented and has the potential to enhance management and service by explaining the significance and benefits of using Activity-Based Costing (ABC) in services.

show abstract

“…Nonvolatile NAND flash memories are the basic building blocks of the data storage components found in a range of systems, including IoT and edge-computing platforms, wearable electronics, smartphones, self-driving cars, and the drones to solid-state drives (SSDs) used in personal computers and cloud computing infrastructures [1]. Energy efficiency is a key requirement for the data storage components used in emerging edge computing devices, as most of them are constrained by limited power sources [2][3][4]. The designers of modern flash storage systems, such as SSDs, focus exclusively on the longterm data integrity rather than on the energy efficiency.…”

Section: Introductionmentioning

confidence: 99%

EXPRESS: Exploiting Energy–Accuracy Tradeoffs in 3D NAND Flash Memory for Energy-Efficient Storage

2022

View full text Add to dashboard Cite

The density and cost-effectiveness of flash memory chips continue to increase, driven by: (a) The continuous physical scaling of memory cells in a single layer; (b) The vertical stacking of multiple layers; and (c) Logical scaling through storing multiple bits of information in a single memory cell. The physical properties of flash memories impose disproportionate latency and energy expenditures to ensure the high integrity of the data during flash memory writes. This paper experimentally explores this disproportionality on state-of-the-art commercial 3D NAND flash memories and introduces EXPRESS—a technique for increasing the energy efficiency of flash memory writes by exploiting the premature termination of the flash write operations. An experimental evaluation shows that EXPRESS reduces energy expenditures by 20–50%, relative to the traditional flash writes, at the cost of a minimal loss in the data integrity (<1%). In addition, we evaluate the effects of the page-to-page variability, program–erase cycling, and data retention on the implementation of EXPRESS, and we propose enhancements to counter these effects.

show abstract

AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices

Cited by 74 publications

References 34 publications

Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring

Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring

A Bibliometric Review on Activity-based Costing in Services: Exploring Current and Future Trends

EXPRESS: Exploiting Energy–Accuracy Tradeoffs in 3D NAND Flash Memory for Energy-Efficient Storage

Contact Info

Product

Resources

About