Empowering Cybersecurity: A Deep Dive into AI-Driven Security Intelligence Modelling
Smart Incubator for Empowering Poultry Farmers by Maximizing Egg Hatching Success
Early Disease Detection of Black Gram Plant Leaf using Cloud Computing Based YOLO V8 Model
Data Retrieval in Cancer Documents using Various Weighting Schemes
Securing Healthcare Data in Smart Cities: A Machine Learning Approach
The Farming Assistance Web Service aims to revolutionize the agricultural sector by providing a comprehensive online platform to help farmers optimize their crop cultivation and overall farming practices. This web service leverages technology to offer a range of tools, information, and services accessible through web browsers or mobile devices. This innovative platform makes it possible for suppliers, retailers, and farmers to communicate effectively. Farmers can also contact the right merchants, and the farmers are notified through SMS when dealers submit an advertisement or an offer. This system uses Firebase to allow for push notifications to be sent to users across platforms (iOS, Android, and web) to engage and re-engage with the app's audience and also to utilize their farmer login to register their complaints with the proper dealers or authorities, and the authorities will regularly access that page using their login ids and passwords. Additionally, it offers seamless integration of data, including access to agricultural information, crop suggestions, pest control guidance, and weather forecasts.
Digital solutions have emerged as powerful tools for addressing the challenges associated with garbage and waste management. This study proposes the implementation of a smart garbage monitoring system to support the Malawi Cleaning Council in their efforts to efficiently manage waste in Malawi. The system utilizes sensor technology integrated into garbage bins to monitor fill levels and transmit data to a central platform. This data is then analyzed to optimize waste collection routes and schedules, ensuring timely and cost-effective waste pickups. The smart garbage monitoring system also enables the Malawi Cleaning Council to proactively address overflowing bins and illegal dumping by receiving real-time alerts and location information. By leveraging digital technology, the system enhances the council's ability to allocate resources effectively, reduce operational costs, and improve overall waste management efficiency. The findings of this study highlight the potential of digital solutions for transforming garbage waste management and contributing to a cleaner and healthier environment in Malawi.
Cluster tendency assessment in big data poses a challenge, particularly for non-compact separated (non-CS) datasets with irregular boundaries. This paper introduces a novel Spectral-Based Visual Technique (SVT) to address this limitation. Determining the similarity features for the data objects is a crucial computation in data clustering. Distance measures such as Euclidean and cosine are widely employed in clustering applications. By pre-determining cluster tendency, the quality of clusters is obtained using the algorithms of Visual Assessment of Cluster Tendency (VAT) and cosine-based VAT (cVAT). Both VAT and cVAT utilize Euclidean and cosine distance measures to identify the similarity features of objects. For extensive data cluster tendency assessment, an extended concept of VAT, Clustering using Improved Visual Assessment of Tendency (ClusiVAT), is employed to derive clusters with scalable amounts of time and memory loads. However, it operates efficiently for Compactly Separated (CS) datasets. The research gap lies in the need to deliver the quality of big data partitions (or clusters) for non-compact separated (non-CS) datasets. Thus, this paper proposes a spectral-based visual cluster tendency technique to address the challenge of significant data clustering for non-CS datasets. Experimental analysis employs benchmarked datasets to illustrate the performance of the proposed work compared to other techniques.
Databases are critical for storing structured data, but deriving insights remains challenging. This paper investigates integrating classification, clustering, association rules, and anomaly detection within database architectures to enable intelligent analytics. A unified architecture is proposed along with an asynchronous incremental learning technique to efficiently handle dynamic data. Comprehensive experiments on diverse real-world datasets demonstrate 10–25% improvements in metrics like query latency, accuracy, and costs compared to conventional integration approaches. Emerging applications in multimedia, spatiotemporal, and IoT mining are discussed. The holistic convergence of multiple techniques is highlighted as the key innovation in progressing towards next-generation intelligent databases powered by analytics.
This paper presents machine learning-based credit card approval prediction and gives an overview of the machine learning models and algorithms that are used to authorize credit cards for users. In order to improve credit card acceptance predictions and increase accuracy and adaptability in financial risk assessment, this study uses XGBoost in machine learning. The study emphasizes the importance of XGBoost in addressing challenges such as handling missing data, avoiding overfitting, and efficiently managing large datasets. Comparisons between the decision tree classifier and XGBoost reveal the latter's advantages, including interpretability, ability to handle complex relationships, and efficiency in processing large datasets. Results from experiments using the XGBoost algorithm demonstrate an accuracy of 90.06%, affirming its efficacy in credit card approval prediction.
