Volume 13 | Issue 4 |

 Abstract

Skin cancer is one of the most common types of cancer worldwide, and early detection is crucial for effective treatment. Traditional diagnostic methods rely on clinical expertise, which can be subjective and time-consuming. In recent years, machine learning (ML) techniques have gained significant attention for their potential in automating skin lesion detection and classification, improving diagnostic accuracy, and reducing human dependency. This survey provides a comprehensive review of various ML-based approaches for skin lesion analysis, including feature extraction techniques, classification algorithms, and evaluation metrics. It explores different datasets used for training ML models and highlights challenges such as data imbalance, variability in lesion appearance, and interpretability of models. Additionally, recent advancements in deep learning, particularly convolutional neural networks (CNNs), are discussed, along with their impact on improving classification performance. The survey also examines the role of ensemble learning and hybrid models in enhancing diagnostic accuracy. Finally, potential future research directions are outlined to address existing limitations and further advance ML applications in dermatology.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Skin cancer, Early detection, Machine learning (ML), Skin lesion detection, Skin lesion classification, Diagnostic accuracy, Feature extraction.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study explores public perception and awareness of green taxes as a motivator for developing a sustainable circular economy in Bangalore. Green taxes are considered to act as a discourager for pollution and motivator for environmental-friendly behavior, thus playing a very important role in transforming consumer and production patterns. The study was based on the responses of 101 participants by using a structured questionnaire. It collected demographics, knowledge of green taxes, attitudes, and perceptions in regard to their efficiency towards sustainability. It showed levels of awareness and support ranging from respondent to respondent concerning green taxes. They were more skeptical of their long-run economic impact but recognized they reduced pollution. It used chi-square tests and ANOVA to test how the effect of green tax awareness may be associated with consumers' behavior, decision to buy, and perception of the long-term environment. There is a gap in public knowledge and effectiveness in reaching existing channels, which suggest ways to which policymakers may benefit in driving the sustainability consumption through circular economies, with regard to using green taxes as drivers of consumption in the pursuit of environmental concerns.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Circular Economy, Environmental Benefits, Green Taxes, Public Perception, Sustainable Practices

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The implementation of a Massive MIMO-based 6G communication system with Full Duplex (FD) and Half Duplex (HD) aims to enhance spectral efficiency and network capacity while addressing self-interference challenges. The project is executed in two phases: first, implementing FD with and without Self-Interference Cancellation (SIC) and Reconfigurable Intelligent Surfaces (RIS); second, comparing FD with HD in terms of spectral efficiency, interference management, and overall system performance. SIC techniques, including digital and analog cancellation, are employed to mitigate self-interference in FD systems, enabling simultaneous transmission and reception on the same frequency band. Key performance metrics such as Signal-to-Noise Ratio (SNR), Bit Error Rate (BER), Mean Square Error (MSE), and data rates are analyzed using MATLAB to compare FD with SIC and RIS against traditional HD systems. The results demonstrate that FD, when integrated with SIC and RIS, significantly improves spectral efficiency and data throughput while reducing latency, making it a promising technology for next-generation 6G networks.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

6G Communication, Full Duplex (FD), Half Duplex, Self-Interference Cancellation (SIC), Reconfigurable Intelligent Surfaces (RIS), Massive MIMO, Signal-to-Noise Ratio (SNR), Bit Error Rate (BER), Mean Square Error (MSE), Throughput Optimization, Terahertz (THz) Communication, mm Wave Technology, Spectral Efficiency, Zero Forcing (ZF) Method, MATLAB Simulation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The IoT-based intelligent parking system is designed to enhance parking management by automating real-time space monitoring, vehicle authentication, and billing processes. The system integrates IoT components such as ESP8266, RFID technology, and line sensors to ensure efficient and accurate tracking of parking slot occupancy. RFID authentication enables secure vehicle entry and exit, preventing unauthorized access while ensuring a seamless user experience. Real-time data transmission to a cloud server allows users to check parking availability remotely, reducing congestion and improving space utilization. The automated billing system accurately calculates parking fees based on entry and exit times, eliminating manual errors and enhancing transparency. Wireless communication ensures seamless integration with digital payment systems, further improving convenience. The system is designed to be energy-efficient and scalable, making it suitable for deployment in urban environments and smart city infrastructure. By leveraging IoT and cloud computing, the proposed system offers a cost-effective and reliable solution to modern parking challenges, optimizing space management while improving security and operational efficiency. The implementation of this system promises to alleviate parking-related issues in urban settings, providing an innovative approach to managing parking resources effectively

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IOT, Intelligent Parking System, RFID Authentication, Automated Billing, ESP8266 Micro Controller, Real-Time Monitoring.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Waterborne diseases remain a significant global health concern, particularly in developing regions where access to clean drinking water is limited. This study explores machine learning techniques for predicting waterborne diseases using physicochemical water quality parameters. The research employs various models, including Decision Trees, Random Forest, and Neural Networks, to enhance prediction accuracy. Data pre-processing, feature engineering, and model evaluation are performed to ensure robust results. The findings suggest that machine learning can significantly improve early detection and prevention strategies for waterborne diseases.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Waterborne Diseases, Machine Learning, Water Quality Prediction, Environmental Health, Public Health Surveillance, Random Forest, SVM, Predictive Analytics, Real-time Monitoring, Disease Risk Assessment

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Chronic diseases such as diabetes, cardiovascular conditions, and respiratory illnesses represent some of the most persistent and resource-intensive challenges in modern healthcare. With the increasing global burden of these conditions, the healthcare industry is turning to digital technologies for sustainable solutions. This paper explores the integration of wearable technology and artificial intelligence (AI) as a transformative approach to managing chronic diseases. Wearables, equipped with sensors and connectivity features, continuously collect real-time physiological data such as heart rate, glucose levels, and physical activity. When combined with AI-driven analytics, this data becomes a powerful tool for early detection, personalized treatment, and continuous monitoring. The paper examines the core technologies underpinning wearable-AI synergy, reviews current applications across chronic disease domains, and evaluates ethical, regulatory, and operational considerations. Additionally, it outlines challenges such as data fragmentation, user adherence, and algorithmic transparency. Future innovations like federated learning, smart fabrics, and explainable AI hold immense promise in improving the scalability and reliability of these systems. Through a comprehensive analysis, this study underscores how wearable and AI integration can revolutionize chronic disease care, shifting healthcare from reactive treatment to proactive, data-driven intervention.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI, Chronic Diseases, Healthcare

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

An autoimmune response against two hemidesmosomal proteins in the dermal-epidermal junction, BP180 and BP230, is the characteristic of bullous pemphigoid (BP), a blistering dermatosis. BP180 is an extracellular domain-bearing transmembrane glycoprotein, while BP230 is intracellularly bound and associated with the hemidesmosomal plaque. Most BP patients possess autoantibodies that bind to the noncollagenous 16A domain (NC16A) of BP180, an immunodominant region of BP180 that is extracellularly located adjacent to the protein's transmembrane domain. Autoreactive T and B cell responses to BP180 in BP patients have been reported. In mice, a bullous skin disease with a very close analog of human blood pressure is induced by passive antibody transfer to the mouse BP180 ectodomain. In this model of animals, the formation of lesions relies on mast cell degranulation, complement activation, and neutrophil and eosinophil recruitment. Dermal-epidermal separation occurs in cryosections of human skin when autoantibodies against BP180 are co-incubated with leukocytes. Granulocytes secrete proteinases that cause loss of cell-matrix adhesion. The development of new treatment strategies for BP may be facilitated by our increasing knowledge of its pathophysiology.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Autoimmunity . Bullous pemphigoid . BP180 . BP230 . Hemidesmosome

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Artificial intelligence (AI) is revolutionizing drug discovery, accelerating the identification of novel therapeutics and redefining pharmaceutical research. As we approach 2025, AI-driven innovations particularly generative AI and advanced data analytics are not only expediting drug development but also enabling precision medicine and reducing costs. This transformation is fueled by deep learning models capable of designing entirely new molecular structures, predictive analytics that optimize clinical trials, and federated learning that enhances collaborative drug discovery while maintaining data privacy.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Drug discovery, pharmaceuticals, Machine learning, innovations, Quantum computing, analytics, biomarker, Regulatory, Ethical

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Hybrid neural-fuzzy systems are used for gender estimation of dental panoramic radiographs, coupling methods such as convolutional neural net- works (CNNs), fuzzy logic, and contrast-limited adaptive histogram equaliza- tion. Stratified cross-validation is performed for analysis after pre-processing on a dataset comprising 947 images. The most successful approach of SVM augmented using expanded fuzzy rules comes with accuracy rating of 94.93% and finds a better success than traditional models. Results highlight the mer- its of hybrid strategies in maintaining accuracy and interpretability in dental diagnostics and forensic purposes.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

eural networks, fuzzy logic, dental radiography, gender classification.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Echoes of the Past: Trauma, Memory, and the Spectral in Gabriel García Márquez and Isabel Allende’s Magical Realist Works

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Collective memory , magical realism, predictive trauma

  License

Creative Commons Attribution 4.0 and The Open Definition