Volume 14 | Issue 4 |

 Abstract

As a revolutionary technology, Artificial Intelligence (AI) has become a change in fashion communication in the digital-first market that is changing brand-consumers, brand-horses and brand-media strategies of brands. A future analytics based on the recommended system, virtual tri-on, generative design and AI allows to create an individual, immersion and skilled brand-conjumer interaction. Such applications go beyond operational effectiveness and change creativity and communication process, algorithm design, virtual affects and AR/VR experiences with stories and branding with experiences. The review is based on the findings of the scholarly literature, quality conference papers, and business case studies to explore the technological, communicative, and ethical aspects of AI in fashion communication. The thematic analysis is based on the following major areas; personalized and consumer engagement; generative and predictive applications in branding; immersive communication using AR/VR; social media dynamics and virtual influencers; and transparency and sustainability in supply chain communication. The practice examples of brands such as Nike, Gucci, H&M, Zara, Stitch Fix, etc. are case situations that demonstrate opportunities and limitations. Though AI increases personalisation, efficiency and consumer experience, it also raises the most prominent questions, such as data privacy, algorithmic bias, authenticity, labour replacement and environmental cost. The article identifies such tensions and suggests mitigation measures with the focus on responsible and ethical innovation. Lastly, it mentions future directions of research, such as explainable AI, multimodal generative systems, integration into the metaverse, and human-AI co-creation, making AI a technological resource and strategic partner in fashion communication of the future generation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Fashion Communication, Generative AI, Personalization, Virtual Influencers, Immersive Technologies, Sustainability

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Due to the tourism industry's digital transformation, there is a growing need for intelligent and tailored travel planning solutions that can combine vast amounts of destination data into well-thought-out itineraries. This paper describes an AI-driven travel itinerary planner that uses Large Language Models (LLMs) via a Flask-based web application that is connected with Groq's LLaMA-3-70B model and LangChain orchestration. By offering a single platform where users may enter preferences including location, duration, interests, budget, group type, and mode of transportation and receive well-structured itineraries, the suggested system tackles the problem of fragmented travel planning. These plans contain projected cost breakdowns, food recommendations, daily activity schedules, and hidden site's. In addition to multimodal's support for inspiration-based picture input's, the system design includes session-based trip management, which allows users to save, update, and remove itineraries. With an average reaction time of 10-15 seconds, the efficacy of the system in providing contextually relevant and personalized trip plans can be gauged from the process of experimental evaluation. The results of the experiment indicate that with a reduction in cognitive workload and a high level of personalization and info coverage, the efficacy of such systems that utilize the power of LLMs can improve the process of vacation planning significantly. The study is a development in AI-based technology for tourism.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Large Language Models, Multimodal AI, Groq, Lang Chain, Flask

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

ABSTRACT Education is played vital role in the overall development of a human. Nobody can deny this fact. Due to this, study is based on the effect of government policies on parents & teachers and the students. The continues change in format from different agencies in school curriculums is changing the basic structure of school education. Other problem is faced by the school management who has to be continuously in touch with the changing format. This not only is responsible of loss of man-power & resources but it is very difficult to change the data frequently & train the staff both administrative as well as teaching to go along with the new trend. Indian education system has been accepted & appreciated globally specially in Science, Math, commerce & Technology. We should try to keep up this reputation. The Government should focus only on these forms, which are essential, globally in demand & do constructive work in the already existing policies. On the recommendation of this commission the first national educational policy came in India in the year, 1968. The second national educational policy came in the year 1986 which was further revised in the year 1992. Now the Indian govt. has come up with a third new education policy (NEP, 2020) to strengthen the Indian education system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Indian education system, fundamental rights , Central Education Boards

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the last twenty years, Assam's political landscape has experienced significant transition, influenced by changing election dynamics, identity-driven movements, governance goals and the evolution of party systems. This era has saw the deterioration of established political hegemony, the emergence of novel political entities and the integration of regional ambitions inside national contexts. Critical factors like immigration, citizenship, ethnic identity, development, insurgency and peace agreements have profoundly impacted political discourse and electoral behavior. The execution of policies concerning the National Register of Citizens (NRC), the Citizenship Amendment Act (CAA) and diverse autonomy arrangements for ethnic groups has further transformed the political environment. Moreover, shifting alliances, the rise of coalition politics and the growing influence of national parties have transformed the power dynamics inside the state. Socio-economic development programs, infrastructural growth and welfare-focused government have significantly influenced public expectations and political narratives. This article analyzes the principal trends, catalysts and ramifications of these political transformations, emphasizing the shift in Assam's politics from conflict-driven mobilization to development-oriented governance, while still contending with issues of identity, representation and federal relations. The study seeks to offer an in-depth analysis of the changing dynamics of democracy and state politics in Assam within the larger framework of Indian politics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Assam Politics, Electoral Dynamics, Identity Politics, Immigration, National Register of Citizens (NRC), Citizenship Amendment Act (CAA), Regional Parties.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Environmental pollution and health risks caused by synthetic dyes have created a strong need for safer and more sustainable alternatives, especially in textile and other industrial sectors. Natural pigments obtained from microorganisms have recently gained attention as potential substitutes for synthetic dyes because they are biodegradable, less toxic, and can be produced under controlled conditions using fermentation techniques. Many microorganisms such as bacteria, fungi, and actinomycetes are capable of producing a variety of pigments including carotenoids, prodigiosin, violacein, and melanin, which have applications in textile dyeing as well as in food, cosmetic, and pharmaceutical industries. Compared to plant-based dyes, microbial pigments offer several benefits such as continuous production throughout the year, easier control of production parameters, and reduced dependency on natural resources. This review mainly discusses the production of microbial pigments through fermentation processes, methods used for pigment extraction and characterization, and their potential application in textile dyeing. Analytical techniques such as UV-Visible spectroscopy, FTIR, and Scanning Electron Microscopy (SEM) are also discussed for pigment analysis and for studying the surface morphology of dyed fabrics. Even though microbial pigments offer many environmental and industrial advantages, some challenges such as low production yield, scale-up difficulties, and production cost still exist. However, ongoing research in fermentation technology and biotechnology is expected to overcome these limitations, making microbial pigments a promising alternative to synthetic dyes for sustainable industrial applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords: Microbial pigments, fermentation, natural dyes, textile dyeing, SEM analysis, eco-friendly dyes, microbial colorants

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Air pollution has become a significant public health concern, especially for individuals suffering from respiratory diseases such as asthma and bronchitis. Existing air quality monitoring systems mainly provide real-time data and lack predictive capabilities for assessing future health risks. This paper presents a climate-aware respiratory risk forecasting system that utilizes environmental parameters including Air Quality Index (AQI), PM2.5, PM10, temperature, and humidity to predict respiratory risk levels using machine learning techniques such as Random Forest and XGBoost. The system classifies risk levels and provides timely alerts along with health recommendations to support preventive measures. The proposed approach improves decision-making by enabling early prediction of respiratory risks and enhancing public health awareness.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Air Quality Index (AQI), Respiratory Risk Prediction, Machine Learning, Environmental Data, Random Forest, XGBoost.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Remote work and distributed learning have driven growing demand for collaborative coding tools, especially in pair programming and technical interviews. Most existing solutions force developers to juggle separate applications for video calls, code editing, and execution -- a fragmented setup that breaks focus and slows work. This paper presents CodeLive, a browser-based platform where all three happen in one place. It uses the Monaco Editor for code editing, Socket.IO to keep code in sync across users, and WebRTC for direct peer-to-peer video and audio. A built-in chat and a JavaScript sandbox round out the feature set. By removing the need to switch between tools, CodeLive makes remote collaboration faster and less disruptive for developers, students, and interviewers alike.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Collaborative Coding, WebRTC, Pair Programming, Real-time Synchronization, Online IDE, Monaco Editor, Socket.IO, Web Application.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Recognizing emotions from human speech plays a crucial role in enhancing human-computer interaction and enabling more natural communication systems. This study focuses on the implementation of an explainable and hybrid deep learning-based speech emotion recognition and response generation system, emphasizing the proposed framework combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) architecture. A selectively compiled dataset was constructed using widely recognized emotional speech datasets, including RAVDESS, EMO-DB, and TESS, followed by the classification of speech samples into multiple emotional categories. The proposed hybrid model utilizes CNN to extract spectral features from Mel spectrograms and BiLSTM to capture temporal emotional variations using MFCC features, further enhanced by the integration of an attention mechanism to highlight emotionally significant segments of speech. The model was trained and optimized using standardized preprocessing techniques and tuning strategies to ensure robustness and reduce bias in performance evaluation. From the experimental analysis, the proposed framework demonstrates improved accuracy compared to individual models while effectively capturing emotional context. Furthermore, to enhance system usability, an emotion-aware response generation module based on the DialoGPT-small language model has been incorporated, enabling the system to produce contextually relevant and empathetic responses. Additionally, a lightweight and user-friendly interface has been developed to allow real-time speech input and visualization of results, thereby facilitating practical deployment in applications such as virtual assistants, customer support systems, and emotion-driven human-computer interaction platforms.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Speech Emotion Recognition, Deep Learning, CNN, BiLSTM, Attention, Emotion-Aware Response, DialoGPT, Human-Computer Interaction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Coastal paddy farming is highly susceptible to environmental challenges like strong winds and excessive soil moisture, which often cause crop lodging, reduced yields, and economic losses for farmers. This study proposes an innovative, sustainable system to monitor environmental conditions and predict risks using a simple artificial intelligence approach. The system uses an ESP32 microcontroller integrated with an anemometer for wind speed measurement and a soil moisture sensor for real-time soil monitoring. Data is processed and displayed on a field-mounted unit, providing farmers with immediate, easy access. Beyond real-time monitoring, the system features a Python-based predictive model. Trained on historical wind speed and soil moisture data, it identifies patterns and forecasts high-risk events such as wind speeds above 10 m/s combined with soil moisture exceeding 40% that heighten lodging risk. This proactive capability enables timely preventive actions. A protective wind screen around the paddy field further reduces wind impact, boosting crop stability. Low-cost, readily available components make the system affordable and deployable in rural areas. Overall, this practical, scalable solution enhances crop protection, optimizes field conditions, and minimizes losses. Future work includes IoT remote monitoring, automated alerts, and advanced machine learning for greater accuracy.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart agriculture, ESP32, Soil moisture sensor, Anemometer, Predictive analysis, Crop lodging, Real time monitoring.

  License

Creative Commons Attribution 4.0 and The Open Definition