International Journal of Automation, Artificial Intelligence and Machine Learning

Application of Big Data Analytics to Determine Traffic Congestion

Uneb Gazder — 2024-09-18

This study focused on the application of big data analytics to estimate roadway congestion. The implementation of big data allows a convenient approach of data collection without any field or observer biasness. It also relieves the restriction of a limited sample. Highway Capacity Manual 2000 suggested considering travel speed as the most appropriate parameter for describing traffic congestion. Therefore, this research employs a speed performance index with the concept of big data analytics to describe traffic congestion of road. This research estimates speed performance index for different sections of road. The data was gathered for three main roads of Karachi i.e. Rashid Minhas Road, Shahra e Faisal Road and Main Korangi Road. The major achievement of this study project is to propose a novel approach to calculate the speed of a vehicle without field measurements. The data is collected through Smartphone with the aid of an application available online namely My Track. The data that was utilized for this project mainly comprises of GPS Exchange Format (GPX) routes that are converted into Extensible Markup Language (XML) to run the developed script. The script was able to determine the status of congestion on a variety of highways with the help of speed performance index. The same script can be used by administrators and other transportation service providers for estimating the congestion on a real-time basis. The methods and procedures from this study would aid in the transportation planning process, especially for route selection of individuals as well as services.

Empowering Women in Mathematics: Pioneering a Rigorous and Inclusive STEM Paradigm for Vikasit Bharat 2047

Santoshi Shukla — 2024-11-07

As India marches towards its centenary of independence in 2047, the nation’s progress is closely tied to its advancements in science, technology, engineering, and mathematics (STEM). However, the journey towards an equitable STEM landscape, where women are equal stakeholders, remains a critical challenge. The underrepresentation of women in mathematics, a foundational discipline within STEM, poses significant hurdles to achieving national and global goals of scientific innovation and technological leadership. This paper explores the critical role of empowering women in mathematics, both as a standalone discipline and as an essential pillar of the broader STEM ecosystem, and its potential to shape a new paradigm for India’s future.

The history of mathematics is rich with contributions from women, yet their stories have often been marginalized. From Hypatia of Alexandria to India’s own Shakuntala Devi and contemporary mathematicians like Neena Gupta, women have consistently broken barriers to leave an indelible mark on mathematical thought. Despite these successes, systemic challenges such as gender bias, societal expectations, and lack of mentorship continue to hinder women’s full participation in the field. This paper examines these barriers in the Indian context and explores how they can be dismantled through targeted interventions at the educational, institutional, and policy levels.

India’s recent strides in promoting girls’ education and STEM participation through initiatives like "Beti Bachao, Beti Padhao" and STEM education programs have created a favorable environment. However, the representation of women in higher-level mathematics education, research, and academic leadership roles remains disproportionately low. The paper highlights the importance of nurturing young girls’ interest in mathematics from school to university, and the role that academic institutions must play in creating inclusive environments where women can thrive. Practical strategies for encouraging this interest include the establishment of women-led mathematics clubs, mentorship programs, and scholarship initiatives aimed at fostering early engagement with mathematics.

As we look towards 2047, the integration of women into the fabric of mathematical research and STEM professions is essential for national growth. Mathematics is increasingly at the core of cutting-edge STEM fields like artificial intelligence (AI), machine learning, and quantum computing. Women’s participation in these fields can have far-reaching effects, not only in advancing technology but also in addressing societal challenges like healthcare optimization, environmental modeling, and resource management. By fostering a culture that supports women’s contributions to mathematics, India can enhance its global standing in STEM innovation and leadership.

This paper also presents a case study of the author’s research on mathematical modeling, showcasing how interdisciplinary approaches rooted in mathematical principles can drive societal progress. The author’s work exemplifies the potential of mathematics to not only solve complex technical problems but also to influence cultural and historical understanding, as seen in projects like Vedic Geometry and the mathematical underpinnings of ancient temple architecture.

In conclusion, empowering women in mathematics is not just an issue of gender equity but a national imperative. As India envisions a new Bharat by 2047, women mathematicians and STEM professionals must be at the forefront of this transformation. By breaking down barriers and creating pathways for women to excel in mathematics, India can build a more innovative, inclusive, and prosperous future. This paper calls for a collective effort from educational institutions, policymakers, and industries to invest in women’s STEM education and career development, ensuring that their contributions shape the future of a technologically advanced and equitable India.

Successful PLC Based Solar Powered Automated Irrigation System Prototyping for Water-Strained Agricultural Nations Like Pakistan

Faazla Iqbal — 2024-11-07

Water scarcity poses a critical challenge to agricultural sustainability in nations like Pakistan, despite abundant solar energy potential offering a sustainable solution for year-round productivity enhancement. This research focuses on designing and prototyping a PLC-based solar-powered automated irrigation system tailored for water-strained agricultural nations.

The primary goal of this research is to design, prototype, and evaluate a PLC-based solar-powered automated irrigation system. The study utilizes PLC technology (Siemens SIMATIC S7-1200) for automation, incorporating capacitive moisture sensors for closed-loop control based on soil moisture and environmental data for data-driven decision making and precision agriculture. HMI is employed for real-time monitoring and control interface. Results from prototype development show promising outcomes in optimizing water use efficiency and reducing reliance on unreliable electricity sources. This paper underscores the potential of such technologies in fostering sustainable AgriTech development and addressing the pressing water challenges faced by agricultural sectors in developing countries. Prototype development and testing have shown significant improvements in water efficiency compared to traditional irrigation methods. Automated control based on real-time sensor feedback has demonstrated precise water management, enhancing crop yield potential without increasing water consumption.

Application Optimizing AI Performance on Edge Devices: A Comprehensive Approach using Model Compression, Federated Learning, and Distributed Inference

Venkata Mohit Tamanampudi — 2024-12-02

One major problem arises when AI models are run on edge devices because these have limited processing power, battery, and time constraints. This article explores methods to improve the performance of AI models in such settings so that they operate optimally and simultaneously and provide fast and accurate results. Some methods include model compression techniques such as pruning and quantizing, which make the model small sized to make the required computations with low energy utilization and knowledge distillation. Moreover, a special concern is checking the possibility of using federated learning as one of the ways of training AI models on devices spread across a distributed network while maintaining users’ privacy and avoiding the need to transfer the data to the central server. Another approach, distributed inference, in which the computations are suitably divided between different devices, is also investigated to enhance system performance and reduce latency. The use of these techniques is described in terms of the limited capabilities inherent to devices like smartphones, IoT sensors, and autonomous systems. In this work, efforts have been made to improve the inference and model deployment in edge AI systems, which is instrumental in enhancing the end user experience and smart energy usage by bringing sophisticated scale out edge-computing solutions closer to reality through application optimized edge AI models and frameworks.

Case Study: The Next Generation of Network Management - AI, Automation, and Security in a Connected World

Vaishali Nagpure — 2024-12-09

Modern data center networks face unprecedented challenges in ensuring robust security due to the evolving complexity of cyber threats and the increasing sophistication of attack vectors. This study proposes comprehensive, multi-layered security architecture tailored for data center environments, integrating advanced technologies such as Next-Generation Firewalls (NGFWs), Zero Trust Architecture (ZTA), AI-driven anomaly detection, SQL-based policy management, and Neo4j knowledge graphs. The architecture leverages NGFWs for deep packet inspection and application-layer filtering, fortifying the network perimeter while enabling advanced threat detection. ZTA principles enforce least-privilege access, requiring continuous authentication and contextual validation for all users and devices. A relational database underpins security policy management, ensuring granular control and consistent enforcement across the network. Neo4j knowledge graphs offer a dynamic, graph-based visualization of the network topology, enabling real-time analysis of relationships and communication paths to uncover potential vulnerabilities, attack vectors, and insider threats. The core of the system’s intelligence lies in the integration of machine learning models, particularly Long Short-Term Memory (LSTM) networks, for anomaly detection and predictive analytics. By analyzing real-time network traffic data, the AI models autonomously detect unusual patterns indicative of security incidents, enabling proactive threat mitigation. The synergy between these components ensures a scalable and resilient security framework capable of addressing modern security challenges. This architecture is designed to automate key aspects of threat detection, incident response, and policy enforcement, significantly reducing operational overhead while improving response times. The result is a flexible and adaptive security solution that enhances visibility, control, and protection of critical data center resources. By combining these cutting-edge technologies, this proposed framework demonstrates its capability to provide a robust defense mechanism for data center networks, ensuring operational continuity and compliance with stringent security requirements. This paper highlights the system's technical components, demonstrates its functionality through a detailed use case, and underscores its effectiveness in securing complex, high-value network environments against evolving cyber threats.

Building Foundation Models in Biology

Sumanth Pareekshit Venkatesh Murthy — 2024-12-11

Over the last three years, Foundation models such as Dall-E and ChatGPT have taken the world by storm and have ushered in the "AI Boom". The next challenge is to build such models in Biology. This article examines the way text-based foundation models were built and the ways in which the approach has to be tweaked to build Foundation models in Biology. More specifically, it looks at the three components of the scaling laws - Data, Architecture and Compute and how they can be adapted to build foundation models in Biology.
These Foundation models can then be used for a variety of downstream tasks such as Identification and if possible, prevention of conditions, treatment planning and nutrition planning.

Leveraging Machine Learning, Cloud Computing, and Artificial Intelligence for Fraud Detection and Prevention in Insurance: A Scalable Approach to Data-Driven Insights

Sreenivasarao Amirineni — 2024-12-16

This paper aims to establish an understanding of how developments in technology have affected insurance fraud detection and control. This paper discusses the applicability of combining ML, cloud environment and AI to build flexible and effective fraud discovery systems. The existing strategies for fraud detection and prevention may have a weakness with the amount, variety and real-time nature of data. This paper proposes a detailed framework to improve the effectiveness of fraud detection with the help of ML algorithms for accurate prediction models, AI for decision automation support, and cloud computing for future expansion. It will be clear from the above results that enhanced detection accuracy, operations efficiency and compliance to set legal standards have been attained. This research work’s objective is to present recommendations for insurers interested in preventing fraud while keeping the antidote affordable and easily soluble in large volumes.

Optimizing Travel Insurance Purchase Detection using Predictive Models

Benjamin Borketey — 2024-12-26

What traveler features should be considered when designing airline travel insurance policies, and can predictive modeling enhance the accuracy of purchase predictions? Motivated by the increased need to safeguard investments due to frequent flight interruptions and cancellations during the COVID-19 pandemic and its travel restrictions, we investigate the uptake of flight travel insurance using predictive models. This study applies various machine learning techniques to a dataset consisting of 1,987 travelers, examining whether they purchased travel insurance (a binary classification problem). Performance metrics such as misclassification rate, precision, recall, F-score, and the area under the receiver operating characteristic curve (AUC) are used to assess model effectiveness. The models were optimized using cross-validation on the training data. Among the models tested, eXtreme Gradient Boosting Machine (XGBoost) achieved the highest accuracy rate of 86%, along with the best AUC, precision, recall, and specificity, indicating a 98% accuracy in predicting who will purchase travel insurance. Other robust models, such as ensemble methods and neural networks, also demonstrated strong performance, with similar AUC and precision scores. Features such as annual income, age, travel history, and education history were found to be the most significant predictors, while chronic disease history had little impact. Parsimonious predictive models, using only the most important variables, yielded better performance. Our findings highlight the critical role of predictive accuracy in helping insurers mitigate the financial risk due to travel interruptions.