Authors - Linda Sara Mathew, Anna Irene Ditto, Anna Keerthana V, Cristal James Tomy Abstract - With proper and real-time crop mapping and yield prediction, agricultural planning, food security, and climate-resilient decisions are necessitated. The conventional field surveys are slow, expensive and inconsistent whereas the increased supply of multispectral, hyperspectral and SAR satellite imagery has made automated crop surveillance possible. Nevertheless, operational methods continue to suffer significant setbacks, such as low accuracy in the presence of a cloud cover, lack of empirical models of the complex time-dependence of temporal growth, difficulties in treating mixed pixels in the smallholder landscape, and the lack of a single framework that incorporates optical, SAR, and phenology data. Even though recent researchers have investigated deep spatio temporal models to map rice, SAR–optical fusion, mixed-pixel decomposition, temporal attention networks, multi-GPU UNet architectures, and phenology-based yield estimation, none of them have an all-encompassing, scalable framework. The study suggests a Multimodal Deep Spatio-Temporal Framework that involves multispectral alongside SAR images and phenological data, which can be used to automatically map crops and predict yields. With CNN-LSTM encoders, attention-based TCNs, adaptive mixed-pixel processing, multimodal fusion, and multi-GPU segmentation, the framework should help provide a powerful, scalable agricultural intelligence system that can be used to monitor the region and country in real-time.
Authors - Emerson Joey Caro Abstract - Detecting brain tumors or Brain Tumor Detection(BTD) from MRI scans is an essential step in the assessing of the presence and characteristics of any tumors and formulating an appropriate clinical management plan. The manual interpretation of MRI images by radiolo gists is not time-efficient as well as susceptible to mistakes, which drives the need for automated, accurate and reliable computational methods. In this study we will compare the most advanced Deep Learning (DL) ar chitectures, including traditional CNNs (VGG19, ResNet50, DenseNet), modernized CNNs inspired by transformer design (ConvNext) and Effi cientNet, to tell apart between tumor and non-tumor categories in brain MRI scans. Each model is trained and evaluated on a standardized dataset relying on measurable data such as accuracy, precision, recall, F1-score, F1 score, and confusion matrix. Our results demonstrate that modern CNN architectures such as ConvNext and EfficientNet outper form traditional CNNs, which capture both local texture, spatial patterns and the global spatial context, leading to improved context, resulting in enhanced classification performance. This benchmark is informative in evaluating the best models used in deep learning and adopt them to identify brain tumors, and in turn may be used in optimizing the use of diagnostic decision-making to improve and reducing the burden on the diagnosis.
Authors - Vasavi Ravuri, Indupriya Vempati, Sai Anuradha Kappaganthula, Pavani Muppalla, Navya Taduri Abstract - In the shadow of overlooked safety violations, different factories have lost thousands, in terms of capital as well as lives. Which is especially harrowing as these were caused due to easily preventable work accidents or easily noticeable defective machinery. Our paper dives into how artificial intelligence based methodologies, particularly, would help in mitigating these risks based on past and present research. We also recommend a potential prototype system according to the findings from the literature we reviewed, for Real-Time worker safety check and automated industrial machine quality inspection system. We have reviewed four major topics pertaining to our system: [1] Personal Protective Equipment (PPE) compliance detection through CCTV monitoring as opposed to manual monitoring, [2] industrial machine quality inspection for automatic defect identification [3] evaluation of previously used object detection models and their performance for industry applications, and [4] system level considerations for practical deployment of the said systems on a large scale. We have compared methods, deployment strategies and results from existing studies to identify key criteria like scalable architectures as well as low latency processing. We are highlighting challenges such as insufficient annotated data for rare machinery defects, good accuracy in harsh industrial conditions that might hinder detection of safety violations, and ethical issues with worker monitoring as well in this paper.
Authors - Siddalingappagouda Biradar, Vinod B Durdi, Suganthi Neelagiri, Devaraju Ramakrishna, Preeti Khanwalkar, Shashi Raj K Abstract - Phishing attacks continue to evolve in scale and sophistication, working on weaknesses across infrastructure, content, and user behavior. Earlier studies demonstrated that hybrid feature representations combining URL, HTML, and infrastructure features significantly outperform single-source approaches, with tree-based and deep learning models achieving detection accuracies exceeding 95%. However, these studies also revealed limitations related to global feature selection, cluster-agnostic learning, and evaluation protocols that may lead to optimistic performance estimates. In this paper, propose a multi-cluster phishing detection framework that organizes features into three complementary clusters: Cluster 0 (C0) for infrastructure and transport-layer characteristics, Cluster 1 (C1) for URL and HTML content features, and Cluster 2 (C2) for behavioral and campaign-level patterns. To address the limitations of traditional feature selection methods, we introduce HC²FS (Heuristic-Constrained Class-Conditional Feature Selection), a cluster-aware and class-conditional approach that preserves low-variance yet highly discriminative phishing indicators. The proposed system is evaluated on large-scale datasets comprising over 600 combined features, using a strict 80% training and 20% testing split enforced prior to feature selection and model training.
Authors - Koutaro HACHIYA, Ioannis PATIAS Abstract - Inference latency remains a critical bottleneck in deploying large language models, for real-time and resource-constrained environments. Prior work has proposed latency formulations that express latency as a function of key parameters. However, they often assume a linear dependence on sequence length, which fails to generalize to tasks involving significantly longer sequences, such as document-level language modeling, long-context retrieval, or time-series forecasting, where latency scales nonlinearly and unpredictably. This paper addresses the limitations of existing latency formulations by proposing three complementary enhancements to improve generalization across varying sequence lengths. First, we introduce a nonlinear term for sequence length, capturing the superlinear growth in latency observed in transformer-based architectures due to quadratic attention mechanisms and memory overhead. Second, we propose a sequence-length-dependent scaling factor for the sequence length parameter itself, allowing the model to adaptively adjust its sensitivity based on empirical latency profiles across different tasks and hardware configurations. Third, we incorporate an empirical correction term enabling calibration of the latency model to account for hardware-specific and implementation-level nuances. By explicitly modeling the nonlinear and context-sensitive behavior of sequence length, our approach offers a more faithful representation of latency dynamics. This work lays the foundation for more adaptive and hardware-aware latency estimation frameworks, with implications for model deployment, scheduling, and cost optimization in production systems. We conclude by discussing future directions for integrating dynamic profiling and reinforcement learning to further refine latency predictions in evolving runtime environments.
Authors - Joao Paulo Sousa, Tiago Lopes, Tatiana Ferreira, Tatiana Batista, Pedro Malheiro, Joao Vitorino, Barbara Barroso, Carlos Costa Abstract - Medical hyperspectral imaging (MHSI) represents a burgeoning paradigm in diagnostic visualization, capable of capturing contiguous spectral signatures across hundreds of narrow wavelengths to delineate pathological structures invisible to the human eye. Despite its diagnostic richness, the advancement of deep learning models in the MHSI domain is severely constrained by two primary challenges: the extreme scarcity of high-quality, pixel-level annotated datasets and the overwhelming data redundancy inherent in high-dimensional hypercubes. Traditional self-supervised methods, particularly masked image modeling, often fail to prioritize discriminative tissue signatures, while domain-agnostic transfer learning from natural images proves inappropriate due to structural and feature-level incongruities. This paper introduces a novel high-quality research methodology: Reinforced Spatio-Spectral In-Context Learning (RSS-ICL). This framework integrates an asynchronous advantage actor-critic (A3C) reinforcement learning agent with visual in-context learning (ICL). The proposed model employs the RL agent to dynamically learn adaptive masking strategies that prioritize high-entropy, "hardto- reconstruct" spatio-spectral voxels, thereby forcing the backbone architecture to capture intricate biochemical signatures during pre-training. By reformulating segmentation as a supportquery inpainting task, RSS-ICL facilitates universal medical segmentation, allowing the model to adapt to novel clinical tasks and unseen tissue types in a zero-shot or one-shot manner. Theoretical arguments suggest that this synergistic approach effectively bridges the gap between low-level signal recovery and high-level semantic understanding in hyperspectral analysis. Through rigorous methodological development and empirical support from existing selfsupervised benchmarks, this paper outlines a path for accelerating the deployment of interpretable, annotation-efficient clinical AI.
Authors - Sushmita Sarkar, Sumit Kumar Debnath Abstract - Multi-angle image synthesis is highly important when it comes to the generation of 3D scenes. But the current methods are either ex pensive in terms of computational costs or lack photorealism in their outputs. We propose a novel sketch and text based multiview image generation approach that solves the above-mentioned problems by mak ing use of multimodal diffusion models efficiently. Our pipeline utilises DreamShaper v8 for converting the input sketch and text into a pho torealistic 2D image and then passes this 2D image into a fine-tuned Zero123plus model for the final generation of consistent multiview im ages, showing a 43.69% improvement in the overall perceptual quality compared to baseline sketch-to-multiview models. Moreover, our pipeline shows flexibility in scalability by generating anywhere from 6 to 64 consis tent multiview images according to the requirements of the downstream tasks. We demonstrate the success of our pipeline through extensive ex periments conducted using voxel-based grid approaches and Neural Ra diance Fields (NeRF). Our pipeline greatly reduces computational costs, all while maintaining photorealism in the outputs, confirming the poten tial of sketch and text based multimodal conditioning as an intuitive and efficient paradigm for controlled 3D content generation.
Authors - Carl Kugblenu, Petri Vuorimaa Abstract - Compressed-domain audio steganography poses a critical foren sic challenge in modern VoIP systems, particularly within low-bitrate codecs. Traditional deep learning models often lack interpretability and struggle with low embedding rates. This paper introduces AUSPEX, a lightweight forensic framework ( 170k parameters) optimized for uni versal compressed audio steganalysis. A novel three-channel tensoriza tion strategy is proposed; incorporating raw bits, temporal derivatives, and bit stability to amplify subtle embedding perturbations. A non trainable high-pass residual stream further enhances sensitivity to first and second-order temporal noise. To ensure forensic transparency, a dual level explainability framework integrates intrinsic spatial attention with post-hoc Integrated Gradients, providing bit-level evidence attribution. Experiments demonstrate detection across CNV and PMS algorithms at low embedding rates. AUSPEX advances the field by unifying ef f icient, edge-deployable detection with rigorous human-centric forensic interpretability.
Authors - Nitika Gawande, Pradnya Bapat, Sanyukta Sasane, Trupti Bankar, Rakhi Dongaonkar, Rashmi Apte, Mangesh Bedekar Abstract - The abstract of the study emphasizes the thorough discussion of cussword usage in Hollywood films over a period of thirty five years, from 1990 to 2025, particularly in genres such as Action, Comedies, and Romances. On the basis of a carefully selected dataset of cusswords from Kaggle along with a considerable subtitle file dataset (.srt), the results have been obtained to determine whether profanity has been used over the years with an appropriate level of intensity in the respective genres of films.
Authors - Kostiantyn Hrishchenko, Oleksii Pysarchuk Abstract - Flexible Job Shop Scheduling Problems (FJSP) involve large discrete decision spaces and strict feasibility constraints, making them challenging for deep reinforcement learning methods. In this work, we study how state represen tation and feature extraction architecture influence the performance of action masked Proximal Policy Optimization (PPO) in flexible scheduling. The scheduling task is formulated as a sequential assignment of operations to machines with a fixed discrete action space, where infeasible actions are removed using a feasibility mask. The environment state is represented using three heter ogeneous feature blocks describing resource availability, operation readiness, and time-related attributes of assignment alternatives. We compare a baseline single-branch encoder with a multi-branch feature extraction architecture that processes these blocks separately before aggregation. Experiments were conducted on the Brandimarte MK benchmark suite (MK01 MK10). Under identical training conditions, the multi-branch representation achieved lower makespan on 9 out of 10 instances, with relative improvements ranging from 2.4% to 27.8% compared to the single-branch baseline. The largest reductions were observed on MK06 (−27.8%) and MK10 (−25.2%), while per formance remained comparable on MK08. Training results indicate improved stability and more consistent convergence for structured representations. These results demonstrate that structured state design and feature extraction ar chitecture are critical factors in action-masked reinforcement learning for flexible job shop scheduling.
Authors - Abhishek Chaudhari, Mahalakshmi Bodireddy, Aditya Bhor, Onkar Dadas, Prajakta Shinkar, Chinmay Chougule Abstract - The growing mental health challenges around the globe need access to scalable, available, and safety conscious digital interventions. The paper describes a mental health support platform, based on AI, which combines conversational intelligence, multi-therapeutic persona modeling, structured mood analytics, proactive crisis identification, multi-lingual interaction, and voice-based access in a secure full stack design. The system, which runs on the Google Gemini AI, provides context-sensitive therapeutic dialogue and performs four-dimensional mood analysis of anxiety, stress, depression, and wellbeing, allowing longitudinal assessment by providing interactive dashboards and automated reporting. A safety-first crisis override system offers validated emergency capacity in the high-risk situations. The platform also includes multilingual voice feedback to facilitate inclusion of the visually impaired users and non-English speaking communities in providing inclusive digital mental health care. The proposed system is capable of changing the prevalent perception that AI and its applications may never be responsible and scalable because it integrates therapeutic diversity, structured analytics, accessibility features, and proactive safety controls into a single framework.
Authors - Anvar Saidmakhmudovich Usmanov, Mikhail Borisovich Khamidulin, Shakhlo Rustamovna Abdullaeva, Fazilat Dzhamoliddinovna Akhmedova, Shoh-Jakhon Khamdаmov Abstract - This paper presents a data-driven forecasting and anomaly detection dashboard for live births in Surigao del Norte, utilizing the Family Health Service Information System (FHSIS) data from 2021 and onwards. The research methodology is based on the CRISP-DM framework, with business under-standing for the needs of maternal services planning in the provinces and municipalities, data preparation for municipalities by quarters, time aware modeling, evaluation, and deployment through the API and visualization layer. The research employs several machine learning techniques for forecasting, such as ARIMA/SARIMA, Exponential Smoothing (ETS and Holt-Winters), and the Prophet method, along with a naïve method. The performance of the models is evaluated through the symmetric Mean Absolute Percentage Error (sMAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Scaled Error (MASE). A strict evaluation criterion for the deployment of the model is also implemented, such as the availability of sufficient data points in the past for the model to be deployed (i.e., 12 data points in the past), the accuracy of the model (sMAPE < 20%), and the performance of the model in comparison with the naïve method (MASE < 1). A low confidence filter is also implemented for the series with intermittent data to prevent incorrect results. The results show high reliability of the forecasting model for the entire province and better interpretability for strategic planning. However, the results also show that some of the municipalities with low population volumes and intermittent data points pose a challenge in the operation of the model.
Authors - Michele Della Ventura Abstract - Feature representations that are both high-dimensional and reduce redundancy often prove to be significant constraints on the performance of object detection. In this study, we present the first hybrid metaheuristic feature selection framework that combines the enhanced grey wolf optimizer (EGWO) and firefly algorithm (FA) with a deep learning-based detection pipeline. The proposed EGWO-EFA method for identifying useful and compact feature subsets has been shown to reduce dimensionality by over 99.99% on the Pascal VOC and Brain Tumor M2PBP datasets. The experiments conducted demonstrate that, compared to classical feature selection, this method has an improved F1-score and precision, by an average of 2%. In addition, the overall pipeline execution time is considerably shorter. These results show that hybrid metaheuristic optimization is an effective approach to scalable and efficient object detection for high-dimensional feature representations.
Authors - Roshna Dhakal, Khanista Namee Abstract - Modern railway system increasingly rely on digital technologies such as Communication-Based Train Control (CBTC), European Train Control System (ETCS) and Supervisory Control and Data Acquisition (SCADA) systems, raising significant cyber-security challenges. We have seen 220% increase in attacks over five years from opportunistic ransomware to sophisticated targeted threats. This paper provides an overview of railway cybersecurity and surveys the coverage area considering ICT architectures, cyber threat models, and AI-based defense approaches. 75% of cases employed Distributed Denial of Service (DDoS) tactics while ransomware had affected 54% of the OT environments. We describe a comparative taxonomy of Artificial Intelligence and Ma-chine Learning approaches including the methods based on supervised learning, unsupervised learning, and advanced deep learning practices with detection accuracy as high as 97.46%. However, there exist several challenges: few available public data sets, lack of validation in real-world scenarios, demands for explain ability from that AI system and worries about adversarial robustness. We discuss eight potential research gaps, and future directions focusing on federated learning, digital twin development, multimodal AI fusion and safety-security co-engineering frameworks.
Authors - Bhonsle Rashmi Ravindra, Shankar Chaudhary, Shivoham Singh, Hemant Kothari, Raj Kothari Abstract - Urban metro rail systems are the key to urban sustainable mobility; however, in spite of the developed technologies, projects regularly experience delays and contractual disputes. These perceived challenges are highly attributed by prior scholarship to matters of the execution phase and restricted illumination is given on the institutional circumstances that form system performance in ICT intensive infrastructure. This paper examines procurement strategy as a govern ance tool that affects the results of digital system integration and sustainability in Indian metro rail projects. Based on statutory performance audit reports and com parative case studies, the analysis indicates that fragmented procurement arrange ments fragment the integration functions to several contracts, leading to coordi nation failure, delayed commissioning, and high claims. Instead, the more coor dinated procurement models with consolidated interdependent systems and de fined integration roles have a better coordination structure and predictable deliv ery. The results indicate that the problem of metro project integration is more of an institutional than a technological problem. This research study adds to the body of knowledge on infrastructure governance by noting the design of procure ment to be one of the determinatives in the realization of effective and sustainable urban transit outcomes.
Authors - Irmawan Rahyadi Abstract -This research investigates the digital footprint of mental health infor mation as it circulates on YouTube. Using a qualitative content analysis ap proach, the study examines 100 selected videos in conjunction with social media analytics to identify recurring patterns in the dissemination of mental health dis course. The findings reveal a mix of misleading or incomplete claims, educa tional resources, personal narratives, and recovery-oriented content, illustrating how mental health discussions shape and amplify user perspectives at both broad (macro) and specific (micro) levels within the evolving field of e-health. To in terpret these dynamics, the analysis applies Gibson’s theory of transactional af fordances, which illuminates key themes of risk, relevance, lived experience, credibility, and social support. By situating these themes within the broader con text of video-sharing platforms, the study underscores the importance of YouTube as a platform for mental health communication. It underscores its role in broader public conversations about health in the digital age. The future re search should investigate mental health discourse from other social media users.
Authors - Ahir Jaimi, Niyati Patel, Nirav Bhatt Abstract - This research studied the economic impact and perceptions of air pollution, particularly PM2.5, in Chiang Mai Province, Thailand, using the Multiple Indicators Multiple Causes model (MIMIC model) and Mixed Data Sampling Regression (MIDAS model). The MIMIC model analyzed data from questionnaires administered to 5 0 7 respondents and examined factors influencing public perception of hotspots and PM2.5. The MIDAS model analyzed the impact of monthly PM2.5 levels and monthly hotspot counts on quarterly Gross Provincial Product (GPP), using data from 2019 to 2023.The MIMIC model analysis revealed that perception of burning or activities causing hotspots was the most influential factor in determining public perception of the impact of PM2.5. The effectiveness of government efforts to address the pollution problem had a negative correlation, while demographic and socioeconomic characteristics showed no statistically significant impact. This indicates that public perception is more influenced by received information or education than by personal characteristics. The MIDAS model highlighted the economic impact of hotspots and air pollution. The analysis results indicate that When hotspots or burning occur, these activities have a statistically significant positive impact on the province's GPP. A 1% increase in hotspots is correlated with an approximately 0 .14% increase in quarterly GPP, suggesting that economic activity or agricultural burning may lead to increased economic activity and consequently a short-term increase in GPP. Conversely, a decrease in PM2.5 concentration in the previous month resulted in an approximately 0.47% decrease in quarterly GPP, demonstrating that the economic costs of air pollution occur with a delayed effect rather than simultaneously. Therefore, this research highlights the importance of the correlation between short-term economic benefits and polluting activities, as well as the delayed economic losses resulting from poor and toxic air quality. This research emphasizes the importance of air quality management, risk communication and support, and economic and environmental policies to address the long-term economic and social impacts of PM2.5 pollution.
Authors - Aditya Nova Putra, Budi Riyanto, Alda Chairani, Sandy Dwiputra Yubianto Abstract - This study examines the determinants of continuance intention in YouTube live streaming consumption among Indonesian Generation Z, focusing on social interaction, entertainment, passing time, and enjoyment. Drawing upon Uses and Gratifications Theory and Computer-Mediated Communication, this research situates live streaming as an interactive digital environment where audiences actively negotiate social and emotional experiences. A quantitative explanatory survey was conducted among 108 Generation Z subscribers of the Windah Basudara YouTube channel, and the data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings reveal that social interaction and passing time significantly influence continuance intention, whereas entertainment and enjoyment do not demonstrate significant effects. These results suggest that sustained engagement in live streaming environments is driven more by interactive and habitual gratifications than by purely hedonic motivations. By highlighting the contextual dynamics of Indonesian gaming live streaming, this study extends the application of Uses and Gratifications Theory in synchronous digital media settings and offers practical implications for content creators seeking to strengthen audience retention strategies.
Authors - Steveen Eduardo Pinzon Morales, Yandry Jose Olarte Sancan, Marely del Rosario Cruz Felipe, Maricela Pinargote-Ortega Abstract - The recent decade has witnessed a more increase on the impact of applying and implementing green computing which mainly focuses in protecting the overall nature of the environment. Within the scope of this comprehensive assessment of the relevant literature, the most recent advancements in energyefficient software design, sustainable hardware design, and improved algorithms are examined and compiled. A wide range of enterprises use cloud computing for its adaptability, reliability, speed, and cost-effectiveness. The proliferation of cloud computing is affecting a shift in the manner in which we network. The application of these new technologies are mainly focused on the overall protection of the environmental aspects, they are more targeting in reducing the emission of dangerous type of gases and substances, use renewable mode of energy and thereby focusing in protecting the world for the future generations. The article is mainly involved in understanding the overall nature of implementing the green computing in realizing the overall development aspect.
Authors - Ain Geuel E. Escober, Rosicar E. Escober, Demelyn E. Monzon Abstract - This study presents the development of StewardFM, an information management system designed to evaluate the effectiveness of the Deflate compression algorithm in optimizing storage for associations and small organizations with limited cloud VPS resources. By integrating membership, event, collection, and budget management into one platform, StewardFM reduces storage overhead while maintaining essential functionality, offering a cost-efficient and scalable solution for resource-constrained organizational environments.
Authors - Sarthak, Utkarsh Kumar Singh, Ankur Yadav, Aarushi Sharma, Samarth Saxena, Vaishnavi Kumari Singh, Anisha Kumari Abstract - Cervical cancer prediction using machine learning is often limited by class imbalance, dataset variability, and insufficient control of false positive rates. While many existing models report high accuracy, they frequently fail to maintain a clinically appropriate balance between sensitivity and specificity, particularly across datasets with different sizes and feature structures [1]. Models trained on large clinical risk-factor datasets may not generalize well to smaller behavioral datasets, and recall-oriented optimization can significantly increase false positives. This study proposes a false positive–optimized ensemble framework combining behavioral and clinical risk factors and analyzes its performance across two heterogeneous datasets. Threshold tuning and ensemble techniques, including soft voting and stacking, are employed to increase minority-class detection while retaining specificity. Results indicate that independent classifiers show dataset-dependent instability, with trade-offs between recall and false positive control. However, ensemble methods provide more consistent accuracy, precision, recall, and F1-score across datasets. The findings demonstrate that threshold optimization combined with ensemble learning improves cross-dataset robustness and supports more clinically reliable cervical cancer prediction.
Authors - Sowmini Devi Veeramachaneni, Yaswanth Gavini, Arun K Pujari Abstract - Combining Particle Swarm Optimization (PSO) with gradientbased local search enhances efficiency in solving complex optimization problems. Existing hybrids often use fixed switching rules, causing premature convergence orwastedcomputation.We present an adaptive PSO–gradient descent method where stagnation detection triggers local refinement only when needed. Adam is employed for local search without extra parameters. Tests on seven benchmark functions show the approach achieves strong or competitive results on challenging cases while ensuring robust convergence on simpler ones.
Authors - Amna Ali, Rida Hijab Basit Abstract - With the advent of agentic Artificial Intelligence, systems have demonstrated significant ability to understand data and respond to changing business environments without human assistance. Agentic AI is largely being used in supply chain management (SCM) systems for automating the supply chain tasks - demand forecasting and planning, logistics and transportation optimization, supplier management and risk reduction, and warehouse management. Use of agentic AI in SCM represents a drastic shift from traditional rule-based systems to automated goal-driven systems that operate without human intervention. Such systems are supported by Natural Language Processing and deep learning models which have made the supply chain processes much easier, efficient and less prone to error. The organizations that have incorporated agentic AI in their business processes have reported operational efficiency and cost effectiveness. However, such advancements in technology have raised concerns related to privacy ethics and data security. In this paper, we have conducted the systematic review of the existing research on the usage of Agentic AI in Supply Chain Management. The paper discusses characteristics of agents in SCM, different types of architectures and analyses the limitations and challenges related to the usage of AI agents in supply chain management.
Authors - Bikram Bikash Das, Chukhu Chunka, Pantha Kanti Nath, Nippu Kumar Abstract - Credit card transaction analysis is challenged by severe class imbalance with evolving spending behavior and large-scale financial data. Many existing fraud detection approaches rely on supervised learning and assume stable fraud labels, limiting robustness under changing fraud prevalence. This study presents a large-scale, multi-year credit card trans action dataset stored in partitioned Parquet format and conducts a systematic comparison of classical machine learning, supervised deep learning, and unsupervised deep learning models for customer spend ing behavior analysis. An exploratory behavioral analysis characterizes spending heterogeneity, temporal regularities, and channel and category variations. Supervised sequence models based on LSTM and CNN ar chitectures are evaluated alongside unsupervised sequence autoencoders and hybrid detection pipelines across fraud rates ranging from 2-12%. To ensure fair evaluation under extreme imbalance, models are assessed using ranking-based metrics under fixed alert budgets, including pre cision–recall area under the curve and recall-at-K. A hybrid of Autoen coder and LSTM architectures achieves the highest performance for large systems. An integrated XAI module is introduced to derive important features providing interpretable insights.
Authors - Dao Khanh Duy, Nguyen Hoang Hieu, Karn Nasritha, Khanista Namee Abstract - This research examines the effectiveness of four state-of-the art transformer-based models (LaBSE, mBERT, XLM-RoBERTa, and mT5) for cross-lingual sentiment analysis of railway passenger feedback. We focus on transferring knowledge from high-resource languages (En glish, French, Vietnamese, and Korean) to Thai, a low-resource language in this domain. To address data imbalance and scarcity, the study inves tigates transfer learning strategies ranging from zero-shot to "ultra-shot" (using only 60 labeled samples) and high-shot paradigms. Experimental results demonstrate that while generative models like mT5 perform well in zero-shot settings, the LaBSE model achieves a superior accuracy of 94.65% under high-shot fine-tuning. Notably, our proposed ultra-shot strategy enables LaBSE to reach 90.42% accuracy with minimal data, effectively bridging the performance gap without extensive annotation. These findings suggest a strategic approach for AI systems in railway op erations: rather than investing in large-scale datasets or computationally heavy models, operators can implement the ultra-shot strategy by fine tuning robust sentence-embedding models like LaBSE with a small set of gold-standard data to achieve optimal performance and cost-efficiency.
Authors - Nazar Melnyk, Oleksandr Korochkin Abstract - Reliable prediction of rare critical events is a key enabler for modern risk management, civil protection, and decision support sys tems, yet it remains challenging due to extreme class imbalance and strict requirements on false alarm rates. We present an ensemble learn ing framework that combines a deep feed-forward neural network with a Random Forest classifier, complemented by temporal feature engineering and precision-oriented optimization. The approach addresses three ob jectives: extracting informative temporal and regional patterns from raw event logs, learning calibrated probabilistic scores under severe imbalance using focal loss, and tuning per-region decision thresholds to achieve high precision while preserving acceptable recall. As a case study we apply the framework to air alert prediction over 25 administrative regions across 38 months, totalling 774,125 hourly observations. The system attains 96.13% accuracy, 75.1% precision, and 77.9% recall, demonstrating that high-precision early warning is feasible in strongly imbalanced settings. The framework is applicable to a wide range of safety-critical rare event prediction tasks.
Authors - Lavinia Chiara Tagliabue, Silvia Meschini, Viviana Vaccaro, Hira Ovais, Silvana Dalmazzone, Gianluca Torta, Ferruccio Damiani, Stefano Rinaldi Abstract - Named Entity Recognition (NER) is an essential task for sequence labelling and information extraction that plays a fundamental role in subsequent Natural Language Processing (NLP) applications, such as information retrieval, question answering, knowledge graph development, and machine translation. Although significant advancements have been made in NER for high resource languages, achieving effective entity recognition in Indian languages continues to be an unresolved research challenge because of linguistic diversity, complex morphology, typological differences, flexible word order, script differences, and prevalent codemixing. The scarce presence of annotated datasets and the lack of standardized evaluation metrics further limit supervised and transfer learning methods in these low resource environments. This document introduces a multilingual NER framework rooted in Sentence embeddings derived from Large Language Models (LLMs) and inference guided by prompts. The suggested method employs contextual; language independent embeddings obtained from pretrained multilingual LLMs to encode semantic representations of Indian and foreign languages within a common embedding space. Rather than using traditional token level classification, entity recognition and classification are achieved via structured prompting, allowing for zero-shot and few-shot generalization without the need for task specific finetuning. The system guarantees that entity identification and retrieval take place in the same language as the input text, maintaining linguistic accuracy and reducing error propagation caused by translation. To tackle domain variability and informal writing, constraints/guardrails for prompts and simple rule-based normalization are utilized to manage orthographic differences, script inconsistencies, and codemixed phrases often found in user generated content and social media. Experimental assessment across various Indian languages shows reliable enhancements in precision, recall, and F1score compared to traditional neural and transformer-based benchmarks, especially in low resource conditions. The findings suggest that embeddings powered by LLMs along with prompt-based reasoning provide a scalable and data efficient option for multilingual NER. This project advances the development of resilient, inclusive, and language adaptive systems for extracting information in linguistically varied settings.
Authors - Murat Aydın Abstract - Combining Particle Swarm Optimization (PSO) with gradientbased local search enhances efficiency in solving complex optimization problems. Existing hybrids often use fixed switching rules, causing premature convergence orwastedcomputation.We present an adaptive PSO–gradient descent method where stagnation detection triggers local refinement only when needed. Adam is employed for local search without extra parameters. Tests on seven benchmark functions show the approach achieves strong or competitive results on challenging cases while ensuring robust convergence on simpler ones.
Authors - Hiep. L. Thi Abstract - Flexible Job Shop Scheduling Problems (FJSP) involve large discrete decision spaces and strict feasibility constraints, making them challenging for deep reinforcement learning methods. In this work, we study how state represen tation and feature extraction architecture influence the performance of action masked Proximal Policy Optimization (PPO) in flexible scheduling. The scheduling task is formulated as a sequential assignment of operations to machines with a fixed discrete action space, where infeasible actions are removed using a feasibility mask. The environment state is represented using three heter ogeneous feature blocks describing resource availability, operation readiness, and time-related attributes of assignment alternatives. We compare a baseline single-branch encoder with a multi-branch feature extraction architecture that processes these blocks separately before aggregation. Experiments were conducted on the Brandimarte MK benchmark suite (MK01 MK10). Under identical training conditions, the multi-branch representation achieved lower makespan on 9 out of 10 instances, with relative improvements ranging from 2.4% to 27.8% compared to the single-branch baseline. The largest reductions were observed on MK06 (−27.8%) and MK10 (−25.2%), while per formance remained comparable on MK08. Training results indicate improved stability and more consistent convergence for structured representations. These results demonstrate that structured state design and feature extraction ar chitecture are critical factors in action-masked reinforcement learning for flexible job shop scheduling.
Authors - Karn Na Sritha, Khang Tran Chi Nguyen, Dao Khanh Duy, Khanista Namee Abstract - Multimodal affective computing system (MACS) aims to improve the affect prediction performance by fusing the complementary cues in visual and audio channels. While late fusion approaches are modular and can be flexibly deployed, they often rely on static modality weights which pre-assumes fixed reliability among modalities. In practical situation, visual stream can be corrupted by occlusion, variation of illumination and motion artifact while audio stream could be interfered by noise and reverberation or channel mismatch. Moreover, domain shifts between different datasets further contribute to the problem of in consistent calibration across modalities, which results in inaccurate fused predic tion. In this paper, a reliability-aware late fusion model is proposed to enhance ro bustness for multimodal emotion recognition. Based on the independently trained branches of FER and SER, we conduct an analytical process for theoretical var iance-covariance stability analysis of linear late fusion with respect to a modality imbalance condition. We further investigate entropy-driven reliability estima tion and calibration-aware weighting schemes. Experiment results from original test report are incorporated into the theoretical framework, it makes evidence that one modality’s dominance is more related to entropy stable and calibration char acteristics than raw unimodal accuracy. Our results also indicate that reliability aware weighting increases robustness under simulated degradation and missing modalities, without the need for retraining unimodal models.
