Papers by Dr. Nagender Kumar Suryadevara
A hybrid SOM and HMM classifier in a Fog Computing gateway for Ambient Assisted Living Environment
2022 IEEE International Conference on Smart Internet of Things (SmartIoT)
Ambient Assisted Living Environment Towards Internet of Things Using Multifarious Sensors Integrated with XBee Platform
Smart Sensors, Measurement and Instrumentation, 2014
In this study, we reported the design and development of an integratedplatform for monitoring and... more In this study, we reported the design and development of an integratedplatform for monitoring and controlling of household appliances using internetworking technologies associated with factors of ZigBee wireless sensor network. The intelligent internetworking architectural mastery plus the reliable measurements associated with household sensors variables are comprehended. The developed system is a combination of distributed smart sensing systems and a data system for aggregation and exploration of fused data. Benefits associated with the developed system are in effective realization of household appliances monitoring variables through Internet of Things. The robustness of the system in executing multiple tasks for long durations provides the longitudinal assessment behavior of the inhabitant. The prototype has been tested in the actual home environment and the results are viewed through real-time graphical data analysis representation.
Internet of Things and Sensor Network for COVID-19, 2020
Load forecasting/prediction is a challenging task in the energy markets that require adequate att... more Load forecasting/prediction is a challenging task in the energy markets that require adequate attention in generating stable and reliable load demand to deal with energy management and planning strategies. Accurate load prediction is critical for electrical power systems operations, but nonlinear loads involve high volatility. Forecasting these kinds of complex load characteristics requires highly accurate forecasting devices. It is generally accomplished by constructing models on relative details, including weather and previous data on load demand. This study proposes six decomposition-based evolutionary neural networks for city-scale and building energy forecasting. These evolutionary neural networks have also been trained using historical load data, and weather records are already considered to have a significant effect on energy usage (for example, wind speed, precipitation, dry-dew point temperature, relative humidity, clouds fraction and mean sea level perception). The network structure of the model is built and based on error estimation, trend map, and appropriate method of measuring evolutionary neural networks efficiency. The model's hidden layers and neurons network structure is selected based on recent smart models to enhance its accuracy. Several measures were used to improve performance, such as seasonal smoothing changes, coarse-graining of the humidity ratio, load-oriented day-type classification monitoring, outlier removal, and complex climate information. Results show that used models have a very high fitting accuracy and low error rate for short, medium, and long-term forecasting/planning tasks. These models have the potential to reduce overfitting issues, thereby improving load forecasting efficiency. Further, proposed models may also use for forecasting solar and wind demand. The efficiency of the model compared to the existing two models. Forecast results show superiority and efficiency in short, medium and long-term energy forecasting and offer the ability to manage unbalanced utility loads. INDEX TERMS Evolutionary neural networks, energy forecasting, energy security, selective combination prediction, energy planning models. ACRONYMS AND NOMENCLATURE AI Artificial intelligence ANNs Artificial neural networks CFNN Cascade-forward neural networks C-SL City-scale level CV Coefficient of variation GDMALB-NN Gradient descent with momentum and adaptive learning rate backpropagation neural networks GLRM The generalized linear regression model LANN Linear artificial neural networks LMANN Levenberg-Marquardt algorithm neural networks L-RNN Layer-recurrent neural networks MAPE Mean absolute percentage error ML Machine learning M slp Mean sea level perception PB-CBNN Powell Beale-conjugate gradient backpropagation neural networks RBNN Resilient backpropagation neural networks RGSVM Regression support vector machine RLO The coefficient of correlation lower limit RUP The coefficient of correlation upper limit R Coefficient of correlation SL System load WSHP Water source heat pump NOMENCLATURE F Arbitrary error-function d Bias vectors CLD f Clouds fraction q u Correlation matrix of input vectors w ko Corresponding weight t Data samples M Data samples of CV T dp Dew point temperature (• F)
Proceedings of ICETIT 2019 Emerging Trends in Information Technology
2019 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON), 2019
Internet of Things and Sensor Network for COVID-19
SpringerBriefs in Applied Sciences and Technology, 2021
Beginning Machine Learning in the Browser
Edge computing for visitor identification using eigenfaces in an assisted living environment
Assistive Technology for the Elderly, 2020
Abstract This work proposes an edge computing-based visitor identification system for elderly or ... more Abstract This work proposes an edge computing-based visitor identification system for elderly or dementia residents to recognize the visitors to their smart home quickly. The proposed system uses audio and lighting stimulation to trigger an associative recall in the subjects for recognizing familiar persons. Frontal face haar cascade classifier is used in extracting the facial portion of the captured visitor image. Classification of the visitor is done by eigenfaces approach using the extracted facial image. Playing relevant audio file on the smart speakers located in the house triggers associative recall in the elderly or dementia persons based on the principles of music therapy. Also, relevant lighting effects by hue lights in the house assist the subjects in recognizing the visitors quickly. The system realizes the benefits of music and lighting therapy in everyday living by identifying the familiar people and exploits the advantages of edge/fog computing.
Privacy Preservation with Machine Learning
IoT Security Paradigms and Applications, 2020
COVID-19: Challenges and Advisory
Internet of Things and Sensor Network for COVID-19, 2020
According to the World Health Organization (WHO), a pandemic is “the worldwide spread of a new di... more According to the World Health Organization (WHO), a pandemic is “the worldwide spread of a new disease.” Another descriptive definition of a pandemic says: “an epidemic occurring worldwide, or over a vast area, crossing international boundaries and usually affecting a large number of people.” The WHO, on March 11, 2020, has announced the outbreak of novel coronavirus disease (nCoV or COVID-19 or SARS-CoV-2) as a pandemic. Since then, COVID-19 has come as a shock to society and health systems. It has surpassed provincial, radical, conceptual, spiritual, social, and pedagogical boundaries. In the present pandemic situation, all countries are fighting their battle with COVID-19 and looking for a practical and cost-effective solution to face the problems. This chapter highlights the COVID-19 pandemic challenges faced by individuals and healthcare systems and how society is trying to utilize the benefits of the latest technologies, such as the sensor network and the Internet of things.
Future Possibilities for Running AI Methods in a Browser
Beginning Machine Learning in the Browser, 2021
Energy and latency reductions at the fog gateway using a machine learning classifier
Sustainable Computing: Informatics and Systems, 2021
Internet of Things and Sensor Network for COVID-19, 2020
The sensor network and Internet of things (IoT) framework has been at the top of the research age... more The sensor network and Internet of things (IoT) framework has been at the top of the research agenda for more than a decade now. Many researchers have been working on building models, developing robust theories, and designing societal applications for the betterment of the general population. The COVID-19 emergency has not given us ample time to think of optimal solutions for various necessities; instead, researchers throughout the world reacted to the challenge and started working on the solutions. Never in our history of innovations, there has been such a pressing and immediate requirement for the researchers to come up with solutions and discover answers. Ease of use, reliability and robustness, accuracy, acceptability by the users and officials, an enhanced lifetime of the devices, and affordability in terms of cost are some of the major challenges that need to be addressed to ensure success. This chapter presents recent innovations in sensor technology, wireless communication, ...
Sensors, 2021
Wearable smart devices are widely used to determine various physico-mechanical parameters at chos... more Wearable smart devices are widely used to determine various physico-mechanical parameters at chosen intervals. The proliferation of such devices has been driven by the acceptance of enhanced technology in society [...]
Future Possible Applications
IoT is a creative innovation that guarantees that every single-tainted individual because of this... more IoT is a creative innovation that guarantees that every single-tainted individual because of this COVID-19 infection is monitored effectively during the isolate. During isolation, it is useful for a real observing framework. All high-hazard patients are followed effectively utilizing the IoT system.
This work proposes a fog computing-based face mask detection system for controlling the entry of ... more This work proposes a fog computing-based face mask detection system for controlling the entry of a person into a facility. The proposed system uses fog nodes to process the video streams captured at various entrances into a facility. Haar-cascade-classifiers are used to detect face portions in the video frames. Each fog node deploys two MobileNet models, where the first model deals with the dichotomy between mask and no mask case. The second model deals with the dichotomy between proper mask wear and improper mask wear case and is applied only if the first model detects mask in the facial image. This two-level classification allows the entry of people into a facility, only if they wear the mask properly. The proposed system offers performance benefits such as improved response time and bandwidth consumption, as the processing of video stream is done locally at each fog gateway without relying on the Internet.
Human Pose Classification
Fog computing framework for Big Data processing using cluster management in a resource-constraint environment
Handbook of Big Data Analytics. Volume 1: Methodologies, 2021
This article presents the implementation details related to the distributed storage and processin... more This article presents the implementation details related to the distributed storage and processing of big datasets in fog computing cluster environment. The implementation details of fog computing framework using Apache Spark for big data applications in a resource-constrained environment are given. The results related to Big Data processing, modeling, and prediction in a resource-constraint fog computing framework are presented by considering the evaluation of case studies using the e-commerce customer dataset and bank loan credit risk datasets.
A Smart Home Assistive Living Framework Using Fog Computing for Audio and Lighting Stimulation
Learning and Analytics in Intelligent Systems, 2019
This work proposes an innovative Ambient Assisted Living framework for mature adults suffering fr... more This work proposes an innovative Ambient Assisted Living framework for mature adults suffering from dementia. A novel Fog computing based ubiquitous recognition model is used to stimulate subjects and immediately trigger an associative recall in recognizing familiar persons and everyday objects. When a known person is sensed in the house, then a relevant audio file is played on smart speakers located in the house, so as to trigger associative recall based on the principles of music therapy. Also, the lighting effects are used to assist the subjects in identifying domestic objects accurately. Person and object recognition is achieved by using the Haar Cascade Classifier. The system was successful in the identification of 82% of the familiar people or objects so that the benefits of music therapy and lighting are realized for everyday living.
COVID-19, Sensors, and Internet of Medical Things (IoMT)
Internet of Things and Sensor Network for COVID-19, 2020
Industry 4.0 is preparing to confront the difficulties arising due to the COVID-19 pandemic. Thes... more Industry 4.0 is preparing to confront the difficulties arising due to the COVID-19 pandemic. These advances can provide automated and computer-assisted services for our day-to-day lives during this emergency. Different advantages of Industry 4.0 that can be conceived for alleviating impacts of COVID-19 pandemic are (i) manufacturing of prudent things identified with this infection,(ii) providing clinical assistance on time, utilizing the graceful chain, (iii) automating the clinical assistance and treatment to the infected patient to lessen the burden of specialists, (iv) learning from the experience and generate better machine learning models, (v) providing a few developments with the assistance of advance assembling and computerized innovations, and (vi) developing better hazard appraisal and worldwide general wellbeing crisis of this infection. This chapter provides details about the sensing systems used for healthcare in the view of COVID-19 crises.
Uploads
Papers by Dr. Nagender Kumar Suryadevara