The intelligent urban nexus: AI-driven decision making in smart city development R. Manivannan, M. Rajakumaran, A. Dennis Ananth, S. Markkandeyan, R. Venkatesan, et al. Blockchain Based Solutions for Accessibility in Smart Cities, 2024 Artificial intelligence (AI) in smart urban solutions offers benefits like efficient energy/water management, and reduced pollution, noise, and traffic. Challenges include data reliability, third-party dependence, and skill shortages. AI operates via data-driven processes and intelligent algorithms, enabling machines to learn, adapt, and perform human-like tasks. This chapter explores AI's role, applications, and challenges in smart cities, focusing on gathering and disseminating intelligence. It provides insights into AI's significance in shaping smart cities for enhanced social awareness and connectivity. This chapter aims to explore the role of AI, its applications, and the challenges inherent in the concepts and technologies associated with AI in smart cities. Specifically, it focuses on AI's contribution to gathering and disseminating intelligence in smart urban environments. Through this analysis, the paper seeks to provide insights into AI's significance in shaping smart cities for enhanced social awareness and connectivity.
Artificial intelligence in records structures research: A systematic literature review and research agenda P. Immaculate Rexi Jenifer, M. Rajakumaran, A. Dennis Ananth, S. Markkandeyan, R. G. Gokila Machine Learning and Generative AI in Smart Healthcare, 2024 AI has received expanded interest from the data systems (IS) studies network in recent years. There is, however, a developing difficulty that studies on AI should enjoy a loss of cumulative building of information, which has overshadowed IS research formerly. This look at addresses this subject, by way of engaging in a scientific literature overview of AI studies in IS between 2005 and 2020. The seek approach ended in 1877 research, of which 98 had been diagnosed as primary research and a synthesise of key issues which might be pertinent to this take a look at is presented. In doing so, this has a look at makes important contributions, namely (i) an identification of the modern mentioned enterprise price and contributions of AI, (ii) research and sensible implications on the use of AI and (iii) opportunities for destiny AI studies inside the shape of the AI research.
Blockchain-enabled smart health monitoring system in WBAN V. Sathya, A. Dennis Ananth, M. Rajakumaran, S. Markkandeyan, R. Venkatesan Applying Internet of Things and Blockchain in Smart Cities Industry and Healthcare Perspectives, 2024 The rising need for continuous health monitoring due to unhealthy lifestyles has spurred interest in Wireless Body Area Networks (WBANs). WBANs employ biosensors worn on the body to assess various health indicators, transmitting data wirelessly to doctors for analysis while ensuring patient confidentiality. However, the limited power of biosensors necessitates energy-efficient data transmission for prolonged functionality. Moreover, ensuring data security is paramount. Blockchain technology, known for its secure and decentralized nature, offers a solution. By integrating blockchain with WBANs, or “healthchain,” data confidentiality and integrity can be preserved while facilitating efficient routing protocols. This fusion promises to revolutionize healthcare by securely storing patient data and facilitating its utilization by medical professionals.
An Intelligent stacking Ensemble-Based Machine Learning Model for Heart abnormality J. Vijayakumar, H. Senthil Kumar, P Kalyanasundaram, S. Markkandeyan, N Sengottaiyan Proceedings of the 2022 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2022, 2022 The genesis of cardiovascular disease is still a global issue that has not been addressed, and the high suffering, impairment, and death rates that are associated with cardiovascular illnesses are the disease's primary features. Therefore, there is a need for artificial intelligence (AI) tools that are both effective and quick in the earlier detection of potential results in individuals who have cardiovascular disease. The Internet of Things (IoT) is growing more pervasive, and this is helping to improve the possibilities of AI technologies. Sensors connected to the internet of things are used to gather data, which is then retrieved and forecasted using technology to predict. Common machine learning technologies that are currently in use are not very good in handling data disparities and have a rather poor level of model accuracy rate. The findings of this article propose a classification algorithm aggregation approach that relies on stackable prototype merging to address this problem. These authors take into account the information will be analyzed and training methodologies used by various algorithms. In order to prevent fitting problem, we utilize a basic linear classifier known as Logistic Regression (LR) as that of the macro classifier. We verified the methodology by utilizing a fused Heart Dataset that was compiled from numerous machine learning libraries at the University of California, Irvine, as well as another Heart Attack Dataset that was made publically accessible, and we compared it to 10 single classifier models. According to the findings of the experiments, the stacking classifier that was developed is superior to other classifiers in terms of both its accuracy and its application.
Fall Detection and Activity Recognition using Hybrid Convolution Neural Network and Extreme Gradient Boosting classifier H. Senthil Kumar, P Kalyanasundaram, S. Markkandeyan, N Sengottaiyan, J. Vijayakumar Proceedings of the 2022 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2022, 2022 The branch of study that focuses on ambient assisted living systems has shown a significant amount of interest in the problem of activity and fall detection. These types of systems make use of a variety of sensing technologies to track human movements and attempt to determine the activity being carried out for the goal of health monitoring as well as other applications. In this regard, in addition to activity identification, fall detection is a very essential role. Falls are a leading cause of injuries and even fatalities, hence it is imperative that falls be detected as soon as possible. This study provides a fall detection and activity identification system that not only takes into account the many activities involved in day-to-day life but also takes into account the detection of falls while taking into consideration the intensity and the direction in which the fall occurred. The data from the Inertial Measurement Unit that is included in the SisFall database is first split into non-overlapping segments that last for three seconds each. Following the appropriate augmentation of the data, exacting the feature with the help of a Convolutional Neural Network, followed by an eXtreme Gradient Boosting (XGB) final step for categorization into the different output groups. The results of the studies demonstrate that the gradient-boosted CNN works far better than previous similar approaches, with an unweighted average recall of 88 percent being achieved.
Effort reduction in social network privacy International Journal of Applied Engineering Research, 2015
Performance analysis of features and algorithms applied in web page classification – Survey International Journal of Applied Engineering Research, 2014
