School of Computer Engineering (August 2021)
1. Mukherjee, P., Barik, L. B., Pradhan, C., Patra, S. S. and Barik, R. K. (2021), hQChain: Leveraging Towards Blockchain and Queueing Model for Secure Smart Connected Health, International Journal of E-Health and Medical Communications, Vol. 12, No. 6, pp. 1–20, DOI: 10.4018/IJEHMC.20211101.oa3.
Smart healthcare can be exemplified as utilizing propitious electronic technology safeguarded with blockchain for superior diagnosis of the disorders, improvised and cost-effective treatment of the patients, and enhanced quality of life. Since blockchain in smart healthcare architecture hosts a substantial amount of patient data, queueing models play a pivotal role to efficiently process the data. This paper highlights the concepts of blockchain, then delves into the smart healthcare architecture and then deals with the several queueing models that already exist. It proposes the model i.e. hQChain which is inculcating M1,b/Mb/1 queueing model into blockchain-based smart healthcare architecture.
2. Ray, N.K., Puthal, D. and Ghai, D. (2021), Federated Learning, IEEE Consumer Electronics Magazine, DOI: 10.1109/MCE.2021.3094778.
Now we are in an era of technology transformation in our everyday life, where data plays a key role in decision making and bringing the action into reality. These data are collected from many distributed sources. Federated learning (FL) is the term coined by Google. It facilitated the distributed learning process and shared the results to the outcomes to the central entity instead of conducting the complete learning process at the centre. In the traditional machine learning approach, data are brought to the model, whereas FL brings ML techniques to the data used at end devices.
3. Das, S., Bose, S., Nayak, G. K., Satapathy, S. C. and Saxena, S. (2021), Brain Tumor Segmentation and Overall Survival Period Prediction in Glioblastoma Multiforme Using Radiomic Features, Concurrency ComputatPractExper., e6501. DOI: https://doi.org/10.1002/cpe.6501 (IF:1.536).
Glioblastoma multiforme (GBM) is a fast-growing glioma that is commonly spreading into nearby brain tissue. Prediction of patient overall survival (OS) time helps the radiologist for better systematic treatment planning and clinical decision making. In this study, the OS classification was performed using ML algorithms by taking radiomic features. The experiment was performed on the well-known data set BraTs 2017 and achieves a classification AUC value of 63% for 3-class and 2-class groups using the different classifiers. Finally, the method achieves the AUC score of 0.66 using Fusedfeature+SVM+GA (3-class) and 0.70 using Fused feature+SVM+PSO ((2-class) which outperforms the state-of-the-art.
4. Das, S., Swain, M. K., Nayak, G. K., Saxena, S. and Satapathy, S. C. (2021), Effect of Learning Parameters on the Performance of U-Net Model in Segmentation of Brain Tumor, Multimedia Tools and Applications (IF: 2.757).
Glioma is one type of fast-growing brain tumor in which the shape, size and location of the tumor vary from patient to patient. The U-Net model is the most popular and extensively used deep learning model for biomedical image segmentation. This study shows the effect of different learning parameters on the performance of the deep UNet model for brain tumor segmentation. The authors have compared the performance by tuning the different learning parameters and measured the accuracy in terms of AUC and F1score. The experiment was performed on two well-known data sets, BraTs 2017 and BraTs 2018.
1. Chandak, A.V. and Ray, N. K. (2021), FTLB: An Algorithm for Fault Tolerant Load Balancing in Fog Computing, IoTApplications, Security Threats, and Counter measures, Nayak, P., Ray, N. and Ravichandran, P. (Eds.), CRC Press, Boca Raton, pp. 65–85.
Today, there is the worldwide adoption of smart services, and smart services are being implemented through Internet of Things (IoT) devices. The number of IoT devices is continuously generating data. This generated data has been passed to the cloud computing layer for processing, but it is very tedious to forward this generated data to the cloud layer for processing due to limited bandwidth and communication latency. Various algorithms, such as random, round robin, weighted round robin, least connection and weighted least connection, can be used for load balancing.
2. Nanda, S. K., Suresh, A., Soman, Q., Tripathy, D. P. and Ray, N. (2021), Development of Intelligent Internet of Things (IoT)-based System for Smart Agriculture, In IoT Applications, Security Threats, and Countermeasures, Nayak, P., Ray, N. and Ravichandran, P. (Eds.), CRC Press, Boca Raton, pp. 143–162.
The Internet of Things (IoT) is now helping all the mankind in many areas like health care, agriculture, smart home, smart city, education, entertainment industries, manufacture, mining, construction, defence, and so on. With advanced AI algorithm and advanced sensor management tools, IoT-based embedded system is now helping all in everyday activities. Modern IoT system now integrates with cloud server and storage system and with high-speed Internet protocol, IoT system enables remote monitoring and very robust management of appliances and systems. Quick development in sensor management, equipment and computing devices helps IoT-based public transportation system to enrich in public safety,
3. Pradhan, A.K., Rout, J.K. and Ray, N.K. (2021), Exploring and Presenting Security Measures in Big Data Paradigm, Privacy and Security Issues in Big Data: An Analytical View on Business Intelligence, Das, P.K., Tripathy, H. K., Md.Yusof, S.A. (Eds.), Springer, pp. 51–68. https://doi.org/10.1007/978-981-16-1007-3_4.
Big Data is a field that provides different ways to analyze and to extract information and hidden patterns. It also helps to deal with the data sets which are complex. In many cases, data offers greater statistical power while the data with higher complexity leads to a higher false discovery rate. At the current time due to the key concepts like volume, variety, and velocity which are associated with Big Data, privacy and security are the biggest challenges in this field. we have discussed different types of issues and solutions related to security and privacy in Big Data.
The book explores modern sensor technologies while also discussing security issues, which is the dominant factor for many types of IoT applications. It also covers recent (IoT) applications such as the Markovian Arrival Process, fog computing, real-time solar energy monitoring, healthcare, and agriculture. Fundamental concepts of gathering, processing, and analyzing different Artificial Intelligence (AI) models in IoT applications are covered along with recent detection mechanisms for different types of attacks for effective network communication. On par with the standards laid out by international organizations in related fields, book focuses on both core concepts of IoT along with major application areas.
1. Radhey Shyam Meena, Dr. Nisheeth Joshi, Dr. I. Sharath Chandra, Dr. Ravi Kumar, Mr. Abhaya Kumar Sahoo, Dr. Chittaranjan Pradhan, Yazusha Sharma, Tarun Jaiswal, Prof. Biju Balakrishnan, Dr. Md. KhajaMohiddin, Dr. Anirban Das, Dr. S. Balamurugan, Dr. Pavithra G, Dr. T. C. Manjunath, Patent Name: Sensor Based Artificial Nervous System To Assist Paralyzed People (Indian patent), Patent No: 202111029975.
The Sensor-Based Artificial Nervous System to assist Paralyzed People (SANS) helps the paralyzed people to make use of the SANS by wearing the artificial bypass synapse (ABS) to join two disconnected biological neurons of the human body parts automatically. The user needs to wear the ABS in between the two disconnected biological neurons. The pre-synaptic cells have been used to transfer the brain signals from the brain to ABS, and the postsynaptic cell is transferring the signals from ABS to muscle. The photodiode, transistor, and artificial neuron circuit are the internal part of the ABS which connects the disconnected neurons.