Journal of Fuzzy Sets and Fuzzy Logic Design (e-ISSN: 3049-0227)

An Engineering Approach to Smart Notification Filtering Using Neuro-Fuzzy System

Pratik Mane — 2026-05-30

In today’s digital world, smartphone users are constantly exposed to a large number of notifications from various applications such as messaging, social media, and emails. While some notifications are important, many are irrelevant and create unnecessary distractions, reducing productivity and increasing cognitive load. This paper proposes a smart notification filtering system that aims to intelligently manage these interruptions by understanding user behavior and context. The system uses a neural network to learn patterns from past user interactions, such as how often a user responds to certain types of notifications, at what time they are most active, and which applications they prioritize. By analyzing these behavioral patterns, the system can estimate the likelihood of a user engaging with a notification, making the filtering process personalized and adaptive over time. To enhance decision-making under uncertainty, the learned patterns are integrated with a fuzzy logic system that mimics human reasoning. Instead of relying on fixed thresholds, the fuzzy system interprets inputs like user availability, notification importance, and urgency in a flexible manner using linguistic rules (e.g., “high importance” or “low attention”). Based on this combined neuro-fuzzy approach, the system assigns a priority level to each incoming notification and decides whether it should be shown immediately, delayed, or suppressed. This hybrid model not only reduces unnecessary interruptions but also ensures that critical notifications are delivered at the right time. Experimental observations indicate that the proposed system improves notification relevance and user experience, making it a practical and efficient solution for modern smartphone usage. The proposed system emphasizes real-time adaptability and scalability, making it suitable for practical deployment in modern smartphone environments. By continuously learning from user interactions, the model dynamically updates its filtering strategy to reflect changing user preferences and usage patterns. The integration of contextual awareness with intelligent decision-making ensures that notifications are not only relevant but also delivered at appropriate times. This approach enhances user satisfaction, reduces cognitive overload, and supports more efficient human-device interaction, making the system a promising solution for next-generation smart notification management.

A Fuzzy Logic-based Approach for Improving the Accuracy and Stability of Machine Learning Models in Educational Data Analysis

Divya Dubey — 2026-08-10

The increasing adoption of machine learning techniques in educational analytics has created opportunities to predict student performance and support data-driven decision-making. Nevertheless, conventional machine learning models often struggle to manage uncertain, incomplete, and imprecise information that commonly exists in educational datasets. Fuzzy Logic provides an efficient solution by representing uncertain information through linguistic variables and rule-based reasoning, thereby improving model interpretability and robustness. This research proposes a Fuzzy Logic-based framework for enhancing the accuracy and stability of machine learning models used for educational data analysis. Student information related to daily screen time and academic performance was collected and preprocessed before being evaluated using a Mamdani Fuzzy Inference System. Input variables were transformed into fuzzy membership functions representing linguistic categories such as Low, Medium, and High. A knowledge-based rule set was then applied to infer academic performance, and the resulting fuzzy output was converted into a crisp prediction using the centroid defuzzification method. Experimental analysis indicates that the proposed fuzzy model effectively captures the nonlinear relationship between screen time and academic achievement while handling uncertainty more efficiently than conventional statistical techniques. The rule-based reasoning process also enhances model transparency, making the prediction process easier to interpret by educators and researchers. The findings demonstrate that integrating fuzzy logic with machine learning improves predictive reliability, supports informed educational decision-making, and provides a flexible framework for analysing complex real-world datasets.

Fuzzy Multi-objective Optimization of Hybrid Renewable Energy Systems Using Genetic Algorithms

Pintu Das — 2026-08-10

Combining solar panels, wind turbines, battery storage systems, and backup diesel generators into Hybrid Renewable Energy Systems (HRES) provides a reliable way to generate clean and sustainable electricity. However, designing the perfect HRES setup is a complicated process. Engineers must continuously manage conflicting objectives such as reducing initial and ongoing costs, ensuring a stable power supply, and lowering carbon emissions. Traditional mathematical methods often struggle to effectively address these competing priorities. To tackle this challenge, the study integrates a Fuzzy Multi-Objective Optimization (FMO) approach with Genetic Algorithms (GA) to determine the best HRES design. Using fuzzy logic introduces greater flexibility into the decision-making process. By defining membership functions for each objective, the system can better handle conflicting priorities in a way that is more natural than strict, conventional rules. Their model considers both financial aspects—such as capital and operating costs—and system reliability, which is measured using the Loss of Power Supply Probability (LPSP) index. Carbon emissions are treated as a key environmental factor. They explored different weighting scenarios to understand how emphasizing cost savings, grid stability, or environmental goals changes the final system configuration. The results show that adjusting these weightings significantly impacts the design of the energy system. For example, prioritizing cost leads to more use of diesel generators, reducing initial costs but increasing environmental impact; on the other hand, focusing on low emissions results in a stronger emphasis on solar and wind technologies. This research highlights how fuzzy-based multi-objective tools are effective in finding well-balanced, realistic configurations that make micro grids both dependable and environmentally friendly. These findings offer a useful guide for engineers working on the next generation of sustainable power systems. This research introduces a combined Fuzzy-Genetic Algorithm (Fuzzy-GA) approach to enhance component sizing for off-grid Hybrid Renewable Energy Systems (HRES). Utilizing fuzzy logic to address conflicting goals—cost, reliability, and emissions—enables an adaptive, human-focused design, creating a means to harmonize economic, technical, and environmental objectives.

Enhancing Virtual Assistants Through Context-aware Multimodal Emotion Recognition using Visual, Textual, and Speech Intelligence

Harshitha G. S — 2026-08-13

The growing adoption of virtual assistants has transformed the way users interact with digital systems. However, most existing assistants primarily rely on textual commands and often overlook the emotional state of the user, resulting in interactions that may feel impersonal or contextually inadequate. Human emotions are naturally expressed through multiple channels, including facial expressions, spoken language, and textual communication. Motivated by this observation, this work proposes the Adaptive Context-Aware Multimodal Emotion-Aware Virtual Assistant (ACME-VA), a framework designed to recognize and interpret emotions from facial, textual, and speech inputs simultaneously. The proposed system employs a Swin Transformer-based model for facial emotion recognition, DeBERTa-v3 for textual emotion analysis, and Wav2Vec2 for speech emotion recognition. To improve the reliability of emotion prediction, a context-aware reasoning module is incorporated to analyze modality confidence, maintain emotional history, and identify temporal changes in user emotions. The emotional representations obtained from different modalities are combined using a cross-modal attention mechanism to generate a comprehensive understanding of the user’s emotional state. Based on the final prediction, the assistant generates responses that are both contextually relevant and emotionally adaptive.

Multi-criteria Fuzzy Decision Support for Smart Water Conservation and Monitoring

Nisha Rathore — 2026-08-17

Water scarcity, deteriorating water quality, and inefficient resource utilization have become major global concerns due to rapid urbanization, industrial expansion, climate variability, and increasing population growth. Conventional water monitoring systems generally rely on fixed threshold values and deterministic decision-making approaches, which often fail to address uncertainty and ambiguity associated with environmental data. This study proposes a Multi-Criteria Fuzzy Decision Support System (MCFDSS) for intelligent water conservation and monitoring by integrating Internet of Things (IoT) sensing technologies with fuzzy logic-based decision-making. The proposed framework continuously acquires real-time information from distributed water quality and quantity sensors, including pH, turbidity, Total Dissolved Solids (TDS), water level, flow rate, and temperature. A fuzzy inference mechanism evaluates multiple conflicting criteria simultaneously to determine water quality status, conservation priority, and resource utilization recommendations under uncertain conditions. The framework further supports intelligent decision-making for reservoir management, irrigation scheduling, leakage detection, and sustainable water distribution. The proposed methodology improves decision reliability by accommodating linguistic variables and expert knowledge while reducing dependence on rigid threshold-based rules. Comparative analysis indicates enhanced decision accuracy, improved water utilization efficiency, and greater adaptability to dynamic environmental conditions. The proposed fuzzy decision support framework offers a scalable, cost-effective, and sustainable solution suitable for smart cities, agricultural irrigation systems, industrial water management, and remote rural regions where reliable water resource management is essential for long-term environmental sustainability.