A. Jose Anand
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
A. Jose Anand has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Jothiperumal Nandha Gopal
Velammal Institute of Technology, India
3 shared publications - G. Arun Sampaul Thomas
Anurag University, India
2 shared publications - Lekshmi S. Raveendran
Sathyabhama Institute of Science and Technology (Deemed to be University)
2 shared publications - Pankaj Bhambri
Guru Nanak Dev Engineering College, Ludhiana, India
2 shared publications R. Geetha
SRM Institute of Science and Technology
2 shared publications- S. Muthukaruppasamy
Velammal Institute of Technology, India
2 shared publications
Latest Publications
- 3 November 2026
- Published by IGI Global Scientific Publishing
- p. 203-236
Integrating Emotion, Social Intelligence, and Culture in Robotic Companions
The chapter discusses how emotional, social and cultural intelligence can be integrated into the design of robotic companions and their importance in promoting authentic, empathetic and adaptive human-machine relationships. It explores theoretical assumptions, technology methods, and examples of the application of emotional recognition, social adaptability, and cultural sensitivity. The most notable challenges mentioned in the discussion include ethical dilemmas, trust, and cross-cultural differences, as well as determine the way forward as influenced by affective computing, cultural AI, and large language models. Finally, the chapter encourages an integrated system that incorporates human compassion and machine predictability to increase emotional resonance, inclusivity, and universal acceptance in human socialization with AI.
- 3 November 2026
- Published by IGI Global Scientific Publishing
- p. 203-236
Integrating Emotion, Social Intelligence, and Culture in Robotic Companions
The chapter discusses how emotional, social and cultural intelligence can be integrated into the design of robotic companions and their importance in promoting authentic, empathetic and adaptive human-machine relationships. It explores theoretical assumptions, technology methods, and examples of the application of emotional recognition, social adaptability, and cultural sensitivity. The most notable challenges mentioned in the discussion include ethical dilemmas, trust, and cross-cultural differences, as well as determine the way forward as influenced by affective computing, cultural AI, and large language models. Finally, the chapter encourages an integrated system that incorporates human compassion and machine predictability to increase emotional resonance, inclusivity, and universal acceptance in human socialization with AI.
- 6 October 2026
- Published by Springer Nature
- p. 555-565
Early Fault Detection in Rotating Machinery Using CNN-Based Audio Spectrograms for Sustainable Industrial Systems
- 6 October 2026
- Published by Springer Nature
- p. 555-565
Early Fault Detection in Rotating Machinery Using CNN-Based Audio Spectrograms for Sustainable Industrial Systems
- 2 September 2026
- Published by Springer Nature
- p. 526-539
Blockchain-Based Security for Privacy System to Stop Hacks in Massive Databases for Intelligent Healthcare
- 2 September 2026
- Published by Springer Nature
- p. 526-539
Blockchain-Based Security for Privacy System to Stop Hacks in Massive Databases for Intelligent Healthcare
- 18 January 2026
- Published by Springer Nature
- p. 336-350
Predictive Analytics for Monkeypox: Utilizing Machine Learning to Forecast Outbreaks and Resource Allocation
- 18 January 2026
- Published by Springer Nature
- p. 336-350
Predictive Analytics for Monkeypox: Utilizing Machine Learning to Forecast Outbreaks and Resource Allocation
- Open Access
- 31 December 2025
- Published by Journal of Environmental Nanotechnology in Journal of Environmental Nanotechnology
- Vol. 14  (4) , 9-26
Predicting and Improving the Mechanical Strength of a Modified Natural Fiber/TiO2 Polymer Nanocomposite Using Artificial Intelligence
Artificial Intelligence (AI) including methods such as artificial neural networks (ANN) and machine learning has been employed to address numerous technical challenges. This study employed titanium dioxide (TiO2) and natural fibers derived from Paederia foetida (PF) to fabricate a high-performance hybrid nanocomposite reinforced for structural functions. A chemical mixture of KMnO4 in acetone was utilized to modify the fibers, enhancing the internal properties and improving bonding with the PF/polymer matrix. To enhance the tensile strength (TS) and flexural strength (FS) of the synthesized PF/TiO2 hybrid nanocomposite (PFMNC), an ANN model featuring hyper-parameter enhancement within a linear neural network of 3-5-1 was employed, incorporating 5 neurons in the internal layer, with the application of Box-Behnken Design (BBD). Scanning electron microscopic images indicate that KMnO4 alteration influenced the mechanical strength of the composite. The mechanical assessment findings indicate that variables influenced the tensile strength (TS) and flexural strength (FS) of PFMNC, as demonstrated by the analysis of variance R² = 0.9525 and R² = 0.9526, respectively. The anticipated outcomes closely resembled the experimental results. The model forecasted an ideal TS of 47.5613 MPa and FS of 38.12 MPa. To validate the empirical experimental research, TS and FS analyses were conducted at the projected optimal settings. The TS data indicated an average strength of 40.67 MPa, while the FS exhibited an average value of 52.98 MPa. This work has shown that the ANN-BBD modeling technique effectively attains suitable mechanical property values rapidly, reduce production costs, and conserves resources.
- 31 December 2025
- Published by Journal of Environmental Nanotechnology in Journal of Environmental Nanotechnology
- Vol. 14  (4) , 9-26
Open AccessPredicting and Improving the Mechanical Strength of a Modified Natural Fiber/TiO2 Polymer Nanocomposite Using Artificial Intelligence
Artificial Intelligence (AI) including methods such as artificial neural networks (ANN) and machine learning has been employed to address numerous technical challenges. This study employed titanium dioxide (TiO2) and natural fibers derived from Paederia foetida (PF) to fabricate a high-performance hybrid nanocomposite reinforced for structural functions. A chemical mixture of KMnO4 in acetone was utilized to modify the fibers, enhancing the internal properties and improving bonding with the PF/polymer matrix. To enhance the tensile strength (TS) and flexural strength (FS) of the synthesized PF/TiO2 hybrid nanocomposite (PFMNC), an ANN model featuring hyper-parameter enhancement within a linear neural network of 3-5-1 was employed, incorporating 5 neurons in the internal layer, with the application of Box-Behnken Design (BBD). Scanning electron microscopic images indicate that KMnO4 alteration influenced the mechanical strength of the composite. The mechanical assessment findings indicate that variables influenced the tensile strength (TS) and flexural strength (FS) of PFMNC, as demonstrated by the analysis of variance R² = 0.9525 and R² = 0.9526, respectively. The anticipated outcomes closely resembled the experimental results. The model forecasted an ideal TS of 47.5613 MPa and FS of 38.12 MPa. To validate the empirical experimental research, TS and FS analyses were conducted at the projected optimal settings. The TS data indicated an average strength of 40.67 MPa, while the FS exhibited an average value of 52.98 MPa. This work has shown that the ANN-BBD modeling technique effectively attains suitable mechanical property values rapidly, reduce production costs, and conserves resources.
- Open Access
- 15 December 2025
- Published by UK Zhende Publishing Limited Company in Lex localis - Journal of Local Self-Government
- p. 663-675
COGNITIVE COMPLEXITY REDUCTION IN DECENTRALIZED APPLICATIONS BASED ON BLOCKCHAIN TECHNOLOGY: THE PSYCHOLOGICAL ASPECTS OF USER INSTRUCTION, UNDERSTANDING, AND SELF-EFFICACY
Blockchain-based decentralized applications (dApps) face low user adoption owing to high cognitive complexity and psychological barriers, making it difficult for first-time users to understand and operate. This challenge is important because user comprehension, confidence, and perceived ease of use directly influence behavioral acceptance of decentralized systems. Although previous studies have noted usability gaps in blockchain interfaces, few studies have examined whether structured user instructions can reduce cognitive load. This study used a comparative experimental design with 200 participants with no prior dApp experience. User interaction with a centralized application was first assessed, followed by a task-based evaluation of the three dApps. Subsequently, the participants received guided education and practical training. The results show a clear improvement in user readiness: initially, 95% required assistance when using dApps, but post-training, 74% reported higher confidence and comfort levels increased from 20% to 80%. Descriptive statistics and comparative analyses were performed to assess these changes. Overall, the study demonstrates that targeted user education and structured guidance effectively reduce cognitive complexity and enhance acceptance of blockchain-based applications.
- 15 December 2025
- Published by UK Zhende Publishing Limited Company in Lex localis - Journal of Local Self-Government
- p. 663-675
Open AccessCOGNITIVE COMPLEXITY REDUCTION IN DECENTRALIZED APPLICATIONS BASED ON BLOCKCHAIN TECHNOLOGY: THE PSYCHOLOGICAL ASPECTS OF USER INSTRUCTION, UNDERSTANDING, AND SELF-EFFICACY
Blockchain-based decentralized applications (dApps) face low user adoption owing to high cognitive complexity and psychological barriers, making it difficult for first-time users to understand and operate. This challenge is important because user comprehension, confidence, and perceived ease of use directly influence behavioral acceptance of decentralized systems. Although previous studies have noted usability gaps in blockchain interfaces, few studies have examined whether structured user instructions can reduce cognitive load. This study used a comparative experimental design with 200 participants with no prior dApp experience. User interaction with a centralized application was first assessed, followed by a task-based evaluation of the three dApps. Subsequently, the participants received guided education and practical training. The results show a clear improvement in user readiness: initially, 95% required assistance when using dApps, but post-training, 74% reported higher confidence and comfort levels increased from 20% to 80%. Descriptive statistics and comparative analyses were performed to assess these changes. Overall, the study demonstrates that targeted user education and structured guidance effectively reduce cognitive complexity and enhance acceptance of blockchain-based applications.
- 9 August 2025
- Published by Springer Nature in International Journal of Information Technology
- p. 1-9
Optimizing diesel generators in industrial settings with IoT and machine learning
- 9 August 2025
- Published by Springer Nature in International Journal of Information Technology
- p. 1-9
Optimizing diesel generators in industrial settings with IoT and machine learning
- 18 April 2025
- Published by Taylor & Francis
- p. 177-192
Ethical Considerations and Privacy in AI-Powered Security
The financial sector has undergone a substantial change brought about by artificial intelligence (AI) as a tool to a number of its operations. AI-driven finance has introduced numerous advantages, such as increased efficiency, improved risk management, and tailored customer experiences. However, the widespread use of AI in finance has also brought up critical issues about data security, privacy, and moral worries. Data confidentiality is a core component of finance powered by AI. As establishments of finance gather and handle enormous volumes of delicate customer data, it is necessary to safeguard individuals’ privacy rights and ensure that their personal data is handled carefully. Neglecting data privacy can result in identity theft, data breaches, and other major consequences that may result in a decline in consumer confidence. Thus, it is essential to put into practice strong data privacy measures to maintain the integrity and reputation of financial institutions. In addition to data privacy, data security is also a key consideration in AI-driven finance. Since financial systems are interconnected and cyber threats are becoming more sophisticated, it is imperative to protect sensitive financial data from theft, manipulation, and unauthorized access. A data security breach may result in significant monetary losses, penalties from the government, and reputational harm. Therefore, robust data security measures are essential to safeguard both financial institutions and their customers. Balancing ethical, security, and privacy concerns related to data in AI-driven finance is essential for the sustainable growth and trustworthiness of the financial industry. Achieving this balance requires a holistic approach that includes technological innovation, organizational policies, and active stakeholder involvement. By focusing on data privacy, security, and ethics, financial institutions can promote responsible AI use, build customer confidence, and aid in the creation of a reliable and moral AI-powered financial environment.
- 18 April 2025
- Published by Taylor & Francis
- p. 177-192
Ethical Considerations and Privacy in AI-Powered Security
The financial sector has undergone a substantial change brought about by artificial intelligence (AI) as a tool to a number of its operations. AI-driven finance has introduced numerous advantages, such as increased efficiency, improved risk management, and tailored customer experiences. However, the widespread use of AI in finance has also brought up critical issues about data security, privacy, and moral worries. Data confidentiality is a core component of finance powered by AI. As establishments of finance gather and handle enormous volumes of delicate customer data, it is necessary to safeguard individuals’ privacy rights and ensure that their personal data is handled carefully. Neglecting data privacy can result in identity theft, data breaches, and other major consequences that may result in a decline in consumer confidence. Thus, it is essential to put into practice strong data privacy measures to maintain the integrity and reputation of financial institutions. In addition to data privacy, data security is also a key consideration in AI-driven finance. Since financial systems are interconnected and cyber threats are becoming more sophisticated, it is imperative to protect sensitive financial data from theft, manipulation, and unauthorized access. A data security breach may result in significant monetary losses, penalties from the government, and reputational harm. Therefore, robust data security measures are essential to safeguard both financial institutions and their customers. Balancing ethical, security, and privacy concerns related to data in AI-driven finance is essential for the sustainable growth and trustworthiness of the financial industry. Achieving this balance requires a holistic approach that includes technological innovation, organizational policies, and active stakeholder involvement. By focusing on data privacy, security, and ethics, financial institutions can promote responsible AI use, build customer confidence, and aid in the creation of a reliable and moral AI-powered financial environment.
- 18 April 2025
- Published by Taylor & Francis
- p. 79-94
Signature-Based Security in Wireless Communication
Modern industrial types of equipment are linked to the internet which enables process monitoring and control anywhere around the world. Most of the process equipment are not built with security mechanisms. When the industrial instruments are associated to the internet for progression monitoring and governing, the plant-sensitive information can also be accessed and modified by the intruders. This leads to the creation of random variation in the industrial process variables and this will result in the failure of plant equipment. The security procedure is vital to guard the searching procedure data and safeguard the highly valuable industrial devices with respect to the real-time scenarios. The projected work is the development and execution of a hybrid cryptography process using an embedded application that permits the protection process of sensitive parameters on the internet system. The projected heterogeneous cryptography procedure performs symmetric data encryption at the transmitter section with a key of 128-bit size in the approach called cipher block chaining (CBC), which delivers supplementary intricacy to the translated data. The decryption is carried out on the receiving side to convert the cipher text back to the original plain text. It also generates hash values using Message Digest 5 (MD5) algorithm which ensures data integrity during the entire transmission process. It achieves process information, confidentiality, and sensitive process data are unaltered during transmission over the internet. The planned security procedures enable alerts that assure the sanctuary for specialist care of industrial progressions concluded the internet for wireless data communication.
- 18 April 2025
- Published by Taylor & Francis
- p. 79-94
Signature-Based Security in Wireless Communication
Modern industrial types of equipment are linked to the internet which enables process monitoring and control anywhere around the world. Most of the process equipment are not built with security mechanisms. When the industrial instruments are associated to the internet for progression monitoring and governing, the plant-sensitive information can also be accessed and modified by the intruders. This leads to the creation of random variation in the industrial process variables and this will result in the failure of plant equipment. The security procedure is vital to guard the searching procedure data and safeguard the highly valuable industrial devices with respect to the real-time scenarios. The projected work is the development and execution of a hybrid cryptography process using an embedded application that permits the protection process of sensitive parameters on the internet system. The projected heterogeneous cryptography procedure performs symmetric data encryption at the transmitter section with a key of 128-bit size in the approach called cipher block chaining (CBC), which delivers supplementary intricacy to the translated data. The decryption is carried out on the receiving side to convert the cipher text back to the original plain text. It also generates hash values using Message Digest 5 (MD5) algorithm which ensures data integrity during the entire transmission process. It achieves process information, confidentiality, and sensitive process data are unaltered during transmission over the internet. The planned security procedures enable alerts that assure the sanctuary for specialist care of industrial progressions concluded the internet for wireless data communication.
- 18 April 2025
- Published by Taylor & Francis
- p. 193-207
Artificial Intelligence in Financial Fraud Detection
The critical role of artificial intelligence (AI) in transforming financial services fraud detection and anticipation is examined in this chapter. The complexity of financial delinquencies is affecting traditional techniques of recognition to become inadequate, therefore profession for the amalgamation of innovative technology. AI develops as a disruptive force that reinforces the defenses against fraudulent activities by utilizing anomaly detection, predictive analytics, and machine learning algorithms. It explores the many AI models, such as supervised and unsupervised learning, deep learning (DL), and natural language processing (NLP), that are used in fraud prevention. The detailed investigation shows how AI is excellent at detecting abnormalities in large, dynamic datasets and how well it can recognize complex patterns suggestive of fraudulent activity. The ethical issues raised by AI-driven fraud prevention highlight the significance of responsible and open methods in order to diminish prejudice and assurance equity in the processes of making decisions. Future plans call for the incorporation of explainable AI (XAI), federated learning, and ongoing threat adaption. Integration of AI and big data analytics (BDA) is revolutionized in financial fraud recognition, permitting the identification of abnormal transactions and inconsistency in real time. AI enhances pattern recognition, improves accuracy, and allows continuous monitoring and by adopting the continuous learning it detects evolving fraud tactics. Emerging techniques such as DL, NLP, and behavioral analytics have significantly advanced fraud detection capabilities. Implementing AI in fraud detection due its specialties, poses challenges such as data privacy concerns, false positives and false negatives, and integration with existing systems. Ensuring compliance with regulations and maintaining customer trust are critical issues. AI essential applications in fraud detection include cross-industry collaboration for better data sharing and model development, regulatory compliance through continuous monitoring, personalized fraud prevention measures, and advancements in XAI to enhance trust and transparency. AI and BDA have significant tools for combating financial fraud by improving detection accuracy and response times. Addressing the challenges related to privacy, accuracy, and system integration is crucial to fully harnessing AI's potential in safeguarding financial systems. As AI technology evolves, its role in fraud prevention will expand, providing more security tools to protect against financial fraud. By using AI technologies, organizations may improve their capacity to fend against fraudulent activities, foster stakeholder trust, and uphold moral standards in dynamic regulatory frameworks. AI is heavily regulated in fields like cybersecurity, healthcare, and finance. This chapter also covers the cooperative efforts of regulators, internet companies, and financial institutions to build a strong ecosystem that can keep up with the ever-evolving schemes of fraud.
- 18 April 2025
- Published by Taylor & Francis
- p. 193-207
Artificial Intelligence in Financial Fraud Detection
The critical role of artificial intelligence (AI) in transforming financial services fraud detection and anticipation is examined in this chapter. The complexity of financial delinquencies is affecting traditional techniques of recognition to become inadequate, therefore profession for the amalgamation of innovative technology. AI develops as a disruptive force that reinforces the defenses against fraudulent activities by utilizing anomaly detection, predictive analytics, and machine learning algorithms. It explores the many AI models, such as supervised and unsupervised learning, deep learning (DL), and natural language processing (NLP), that are used in fraud prevention. The detailed investigation shows how AI is excellent at detecting abnormalities in large, dynamic datasets and how well it can recognize complex patterns suggestive of fraudulent activity. The ethical issues raised by AI-driven fraud prevention highlight the significance of responsible and open methods in order to diminish prejudice and assurance equity in the processes of making decisions. Future plans call for the incorporation of explainable AI (XAI), federated learning, and ongoing threat adaption. Integration of AI and big data analytics (BDA) is revolutionized in financial fraud recognition, permitting the identification of abnormal transactions and inconsistency in real time. AI enhances pattern recognition, improves accuracy, and allows continuous monitoring and by adopting the continuous learning it detects evolving fraud tactics. Emerging techniques such as DL, NLP, and behavioral analytics have significantly advanced fraud detection capabilities. Implementing AI in fraud detection due its specialties, poses challenges such as data privacy concerns, false positives and false negatives, and integration with existing systems. Ensuring compliance with regulations and maintaining customer trust are critical issues. AI essential applications in fraud detection include cross-industry collaboration for better data sharing and model development, regulatory compliance through continuous monitoring, personalized fraud prevention measures, and advancements in XAI to enhance trust and transparency. AI and BDA have significant tools for combating financial fraud by improving detection accuracy and response times. Addressing the challenges related to privacy, accuracy, and system integration is crucial to fully harnessing AI's potential in safeguarding financial systems. As AI technology evolves, its role in fraud prevention will expand, providing more security tools to protect against financial fraud. By using AI technologies, organizations may improve their capacity to fend against fraudulent activities, foster stakeholder trust, and uphold moral standards in dynamic regulatory frameworks. AI is heavily regulated in fields like cybersecurity, healthcare, and finance. This chapter also covers the cooperative efforts of regulators, internet companies, and financial institutions to build a strong ecosystem that can keep up with the ever-evolving schemes of fraud.