International Transactions in Artificial Intelligence

Anomaly detection using Machine Learning for temperature/ humidity/ leak detection IoT

Harsh Yadav — 2024-04-03

Anomaly detection plays a pivotal role in ensuring the integrity, reliability, and security of IoT devices, particularly in critical applications such as temperature, humidity, and leak detection systems. This research paper investigates the application of machine learning techniques for anomaly detection in IoT devices deployed for monitoring environmental conditions. We explore the challenges associated with traditional threshold-based methods and propose a data-driven approach leveraging machine learning algorithms for more accurate and adaptive anomaly detection. The study involves collecting real-world sensor data from temperature, humidity, and leak detection IoT devices and developing supervised and unsupervised machine learning models to identify abnormal patterns and anomalies. Various algorithms such as Isolation Forest, One-Class SVM, and Autoencoders are evaluated for their effectiveness in detecting anomalies in sensor data streams. Experimental results demonstrate the superiority of machine learning-based approaches over traditional methods, with improved accuracy, sensitivity, and robustness in detecting anomalous events. The findings of this research contribute to advancing anomaly detection techniques in IoT devices and have significant implications for enhancing the reliability and efficiency of environmental monitoring systems in diverse domains, including smart buildings, industrial facilities, and agriculture.

IoT Security: Issues, Challenges, and Solutions

Prof. Dravid Sood — 2024-06-07

The rapid proliferation of IoT devices has introduced significant security challenges. This paper reviews the major security issues in IoT ecosystems, including authentication, data privacy, and vulnerability management. It discusses current solutions and proposes strategies to enhance IoT security, emphasizing the need for robust encryption, secure communication protocols, and effective access control mechanisms. The study also explores emerging technologies such as blockchain and AI for IoT security enhancement.

Energy-Efficient Routing Protocols for IoT Networks

Prof. Kounj Harris — 2024-06-06

Energy efficiency is critical for prolonging the operational lifespan of IoT devices, especially those deployed in large-scale networks. This paper reviews state-of-the-art routing protocols designed specifically for IoT environments to optimize energy consumption. It evaluates protocols based on their ability to minimize communication overhead, reduce packet loss, and prolong battery life. The study discusses the performance metrics used to assess these protocols and proposes directions for future research in energy-efficient routing for IoT networks.

IoT in Healthcare: Opportunities and Challenges

Prof. Pankaj Singh — 2024-06-07

IoT applications in healthcare promise transformative benefits, from remote patient monitoring to personalized medicine. This paper examines the opportunities and challenges of integrating IoT into healthcare systems. It highlights successful implementations of IoT devices for monitoring chronic conditions and real-time health data analytics. The study also addresses concerns related to data privacy, regulatory compliance, and interoperability standards in IoT-driven healthcare solutions.

Investigate Methods for Visualizing the Decision-Making Processes of a Complex AI System, Making Them More Understandable and Trustworthy in financial data analysis

Mohanarajesh Kommineni — 2024-01-31

Artificial intelligence (AI) has been incorporated into financial data analysis at a rapid pace, resulting in the creation of extremely complex models that can process large volumes of data and make important choices like credit scoring, fraud detection, and stock price projections. But these models' complexity—particularly deep learning and ensemble methods—often leads to a lack of transparency, which makes it challenging for stakeholders to comprehend the decision-making process. This opacity has the potential to erode public confidence in AI systems, especially in the financial industry where choices can have big financial repercussions.

With an emphasis on financial data analysis, this study explores different approaches to visualizing the decision-making processes of complicated artificial intelligence systems. We investigate various methods of interpretability such as heatmaps, decision trees, SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and feature importance metrics. These techniques give financial professionals a greater understanding of and confidence in AI-driven judgments by providing means to improve the transparency and comprehensibility of AI systems. The trade-offs between interpretability and model accuracy, the difficulties with bias and fairness in financial AI, and the significance of maintaining security and privacy in visualization techniques are also covered in the study. Finally, we suggest a paradigm for strengthening the trustworthiness of AI in finance, balancing the requirement for accurate forecasts with openness and ethical considerations.