Journal of Innovations in Data Science and Big Data Management

Enhancing Email Spam Filtering through Context-aware Machine Learning Techniques

Khadija Abdullahi Nashe — 2025-10-14

Unsolicited email, commonly referred to as spam, remains a major security and privacy concern in digital communication. It often carries threats such as phishing attempts, malicious attachments, and unauthorized data collection. Researchers have used advanced Deep Learning (DL) techniques and traditional Machine Learning (ML) algorithms to address this problem. Naïve Bayes, logistic regression, random forest, Support Vector Machines (SVM), and Convolutional Neural Networks (CNN) are among the models that are compared in this study. Their effectiveness is measured using standard metrics accuracy, precision, recall, and F1-score. Findings reveal that while CNN achieves strong predictive performance, simpler models like Naïve Bayes remain valuable for real-time, resource-efficient spam filtering systems.

Regression-based Approach for Concrete Compression Strength Estimation

Priyanka Pawar — 2025-10-24

Concrete strength is a critical parameter in civil engineering because it governs the load-bearing capacity, durability, and long-term performance of buildings, bridges, and other infrastructure. Conventional determination of compressive strength relies on destructive laboratory testing of cured specimens, which is time-consuming, labor-intensive, and costly, and can only be performed after the concrete has hardened. In this project, we develop a machine–learning based concrete strength prediction system that uses mix design parameters such as cement content, water, aggregates, fly ash, superplasticizer, and curing age to estimate compressive strength rapidly and non-destructively. Using Python with libraries like pandas, NumPy, scikit-learn, matplotlib, and seaborn in the Google Colab environment, the dataset from the UCI Machine Learning Repository is preprocessed, explored, and modeled with several regression algorithms (linear regression, decision tree, random forest) to identify the most accurate predictor. By leveraging statistical insights and automated model selection, the system provides reliable strength estimates in seconds, reducing the need for repeated laboratory testing, cutting project costs, accelerating decision-making in construction planning, and contributing to safer, more efficient, and sustainable engineering practices.

An Efficient Assessment of Sustainability for Open Source Technology

P L Pradhan — 2025-12-16

This research assessment focuses on improving and accelerating data processing tools for analyzing current information and knowledge management related to sustainability and various other reliable subsystems. Our goal is to develop scientific tools that enhance productivity and support decision-making while complying with recent sustainability standards, all while minimizing costs and effort. We can process and analyze unstructured information using inexpensive, open-source technologies to convert it into valuable training data. Our ultimate objective is to utilize open-source code, particularly Python, to optimize the use of human resources, machines, materials, markets, methods, and finances. This will lead to the creation of an intelligent system that communicates, interfaces, associates, interacts, and aggregates data to improve the responsiveness of sustainability systems. Advancements in artificial intelligence and machine learning make these systems consistently reliable for sustainability initiatives. Recently, there has been a global surge in the use of open-source software that enhances performance and decision-making, while also reducing costs and time. Ultimately, sustainability contributes to improving quality, managing costs, enhancing decision-making, and optimizing risk. Innovation is directly proportional to sustainability, or vice versa.

The Role of Artificial Intelligence in Modern Healthcare and Biomedical Innovation

Ritesh Upadhyay — 2025-12-16

Medical science is going through a big change, thanks to the fast growth of artificial intelligence (AI). What was once just an idea is now a key tool in healthcare, changing how medical research is done, how treatments are given, and how patients are cared for. In this review, we look at how AI is affecting different areas of medicine, including drug development, surgery, biotechnology, and treatment options. AI’s impact on healthcare is wide and deep. It makes the process of finding new drugs more efficient and cost-effective, which could help bring life-saving medicines to patients faster. In surgery, AI tools are becoming more common, helping doctors perform better and improve patient results. In biotechnology, AI is helping understand complex genes, leading to personalized medicine and better drug production. Also, AI helps create new treatments that let doctors tailor care to each patient’s needs. In this review, we’ll look at how AI has evolved in medicine, what it is being used for today, and where it might go in the future. However, there are challenges to using AI in healthcare, like ethical issues, rules that need to be followed, and protecting patient information. Overall, combining AI with medicine is changing healthcare for the better, offering new ways to treat diseases, find illnesses early, and improve patient care. This review gives an overview of how cutting-edge technology and the goal of better health can work together.

Energy-efficient Artificial Intelligence through Neuromorphic Architectures

Mutchakarla Teja Sri — 2025-12-17

The push for energy-efficient adaptable processing keeps growing as AI gets integrated into everything from cloud systems to smart devices and autonomous technologies. Neuromorphic computing mimics how brains operate, using spiking neural networks in custom hardware that acts like communicating neurons. This approach allows machines to process data in parallel while responding quickly and using minimal power instead of draining it heavily. The biggest perks include significantly lower energy consumption—potentially 10 to 1,000 times less than standard chips, maybe even 100k times less if matching human brain efficiency levels. This enables gadgets to handle AI locally without relying on cloud backups, ideal for IoT devices, wearables, robots, and self-driving vehicles that require real-time responses. Continuous learning is another advantage. Systems adapt dynamically using live data streams instead of requiring pauses for retraining cycles. Timing precision matters too—these setups excel at spotting patterns in voice signals, sensor data, or detecting unusual financial activities. Creating artificial brains that behave like biological ones remains challenging, though. Programming tools are still underdeveloped, scaling to billions of neurons is not fully achievable yet, and training methods need specialised adjustments compared to conventional AI approaches.