Volume 13 | Issue 2 |

 Abstract

Abstract- As cyberattacks grow in complexity, they pose increasing threats to organizations reliant on networked infrastructures. Conventional risk assessment methodologies often fail to adapt to the evolving nature of these threats. This paper introduces a novel cyber risk assessment model that adopts a proactive, dynamic, and time-aware approach to evaluating security risks. The proposed model leverages the Exploit Prediction Scoring System (EPSS) to estimate the short-term likelihood of exploitation over a 30-day period. To improve accuracy, Bayesian networks are employed to capture both system vulnerabilities and asset interdependencies within the network. This information is integrated into an absorbing Markov chain along with the identified attack paths, which are explored using Depth-First Search (DFS). The model generates exploitation probability distributions over the predefined time window, which, when combined with asset impact, facilitates dynamic, proactive, and time-sensitive risk assessments. Additionally, it provides valuable insights into attack progression by estimating the time required for an adversary to compromise critical assets. To demonstrate the practical applicability of the model, a case study is presented, showcasing its effectiveness in assessing cyber risks within a SCADA environment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cyber Risk Assessment, Markov Chains, Bayesian Networks, EPSS, Attack Path Analysis, Time-to-Compromise.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The increasing sophistication of cyber-attacks and the inherent class imbalance in cybersecurity datasets present significant challenges to the development of accurate and reliable intrusion detection systems (IDSs). Most benchmark intrusion detection datasets, including CIC-IDS2017, CIC-IDS2018, NSL-KDD, UNSW-NB15, and Bot-IoT, contain disproportionately distributed attack categories, causing machine learning and deep learning models to exhibit biased learning toward majority classes while performing poorly on minority attacks. Traditional data balancing techniques, such as Random Oversampling and Synthetic Minority Over-sampling Technique (SMOTE), often fail to preserve the complex statistical characteristics and nonlinear relationships of network traffic, thereby limiting their effectiveness in realistic cybersecurity environments. This study evaluates the effectiveness of Generative Adversarial Network (GAN)-based synthetic data generation for balancing imbalanced cybersecurity datasets and enhancing intrusion detection performance across multiple benchmark datasets. The proposed evaluation framework incorporates data preprocessing, GAN-based synthetic attack generation, dataset balancing, feature engineering, and comprehensive performance assessment using conventional machine learning and deep learning classifiers. The generated synthetic samples are analyzed for their ability to preserve the distribution of minority attack classes while improving classifier learning and generalization. Furthermore, the performance of GAN-based augmentation is comparatively evaluated against traditional imbalance handling techniques to assess its impact on attack detection accuracy, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), and ROC-AUC. The study also investigates the robustness of GAN-generated data across diverse intrusion detection datasets containing heterogeneous attack categories and network traffic characteristics. The findings are expected to demonstrate that GAN-based synthetic data generation effectively mitigates class imbalance, enhances minority attack detection, reduces false-negative rates, and improves the overall reliability of intelligent intrusion detection systems. The proposed evaluation provides valuable insights into the applicability of adversarial learning for developing robust, scalable, and data-efficient cybersecurity solutions suitable for modern enterprise, cloud, and Internet of Things (IoT) environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Generative Adversarial Networks (GANs); Cybersecurity Datasets; Class Imbalance; Synthetic Data Generation; Intrusion Detection Systems (IDS); Network Attack Classification.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The agricultural supply chains (Agri-SCs) are under increasing pressure of food-safety requirements, climate changes, post harvest losses and lack of trust and coordination between farmers, aggregators, processors and retailers. Compared to current project infrastructure and practices, blockchain technology (BCT) provides tamper-proof, decentralized processes for storing data and executing so-called smart contracts, and computational intelligence (CI) -- metaheuristic optimization, machine learning, deep learning, reinforcement learning and federated learning -- provides predictive and prescriptive insights from noisy distributed agricultural data. A systematic literature review (SLR) is presented of the research at BCT-CI intersection in Agri-SC management, including journal articles, conference papers and previous SLRs published primarily from 2019 until 2026. The literature is categorized into three threads: 1) blockchain-centric solutions for traceability and trust; 2) CI-centric solutions for forecasting and multi-objective optimization; and 3) co-developed blockchain-centric integrated CI solutions such as blockchain-anchored federated learning, AI-enhanced smart contracts, and blockchain-integrated hybrid metaheuristic-deep learning optimizers. A comparative taxonomy of platforms and algorithms is suggested, and common challenges are presented, such as scalability, interoperability, data quality, cost, and regulatory ambiguity, while future developments and directions are proposed to address these issues, including everything from privacy-preserving federated optimization to quantum-resilient ledgers and generative-AI-mediated multi-agent coordination.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Blockchain; Computational Intelligence; Agricultural Supply Chain; Multi-Objective Optimization; Federated Learning; Metaheuristics; Traceability; Systematic Literature Review

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a bibliometric analysis of the research literature underpinning a proposed AI-driven, deep-learning-based multimodal emotion-recognition framework for stress and depression detection. Rather than drawing on a full commercial citation database such as Scopus or Web of Science, this study performs a structured bibliometric profiling of the curated corpus of sixty-six (66) publications compiled through targeted literature search for the associated PhD research synopsis, spanning the period 1998-2022. The analysis characterizes the corpus along five dimensions: (i) temporal distribution and growth trend of publications; (ii) distribution by publication type (journal, conference, workshop, dataset repository); (iii) leading publication venues; (iv) distribution by modality and topical focus (facial, speech, text, EEG, physiological, multimodal fusion, benchmark dataset, and survey literature); and (v) keyword frequency derived from publication titles, used as a proxy for thematic emphasis. The results show a pronounced growth in publication volume between 2017 and 2019, accounting for 42.4% of the reviewed corpus, coinciding with the broader adoption of deep-learning architectures in affective computing. Facial-expression research and general multimodal-fusion research jointly account for 48.5% of the corpus, while EEG-inclusive multimodal studies, entropy-based fusion approaches, and metaheuristic-optimization-guided fusion strategies

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

bibliometric analysis; multimodal emotion recognition; deep learning; fusion strategies; stress detection; depression detection; EEG; affective computing; research trend analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Electroencephalography (EEG) has emerged as a powerful modality for emotion recognition, offering a direct window into the neural correlates of affective states that is difficult to consciously mask, unlike facial expressions or speech. In recent years, deep learning has largely replaced traditional handcrafted-feature-and-classifier pipelines as the dominant approach in this field, owing to its ability to automatically learn discriminative spatial, spectral, and temporal representations from raw or minimally processed EEG signals. This paper reviews the evolution of deep learning methods applied to EEG-based emotion recognition . Multi-modal and multi-scale models improve recognition by learning different representations from multiple input sources. EEG-based emotion recognition, in particular, provides detailed insights into brain responses, allowing for noninvasive and continuous emotional state monitoring. Hybrid models that combine spatial, channel-wise, and graph-based attention can assist solve signal variability and noise issues. Modern emotion detection systems seek for accuracy, scalability, and explainability to fulfill the needs of real-world applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Emotion, EEG, CNN, Transformer, Multimodal

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study examined the mediating role of employee engagement amid hybrid work culture and job satisfaction among employees in the software industry. A quantitative research design was adopted, and data were collected from 280 respondents with closed ended structured questionnaire. The data analysis implemented multiple regression and mediation analysis with SPSS and SPSS PROCESS Macro (Model 4). The results indicated that hybrid work culture had significant positive impact on job satisfaction. Employee engagement had significant effect on job satisfaction. The mediation analysis revealed that employee engagement partially mediated the relationship between hybrid work culture and job satisfaction. The findings depicted importance of flexible work practices and employee engagement in improving workplace outcomes.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Hybrid work culture, employee engagement, job satisfaction, mediation analysis, employee outcomes

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the present financial environment, individuals are increasingly seeking systematic and disciplined investment options to achieve long-term financial stability and wealth creation. The Systematic Investment Plan (SIP) has emerged as one of the most popular investment strategies among retail investors, particularly in mutual funds. SIP allows investors to invest a fixed amount regularly, thereby promoting financial discipline and reducing the risk associated with market volatility through the principle of rupee cost averaging. The present study examines the role of SIP in personal financial growth and evaluates its effectiveness as an alternative investment strategy for wealth creation. The study focuses on how SIP contributes to financial planning, long-term savings, and risk management among individual investors. It also analyses the awareness, investment behaviour, and perceptions of investors towards SIP as a systematic approach to achieving financial goals. The research is based on both primary and secondary data, where primary data are collected through a structured questionnaire from individual investors, and secondary data are obtained from journals, reports, and financial publications. The findings of the study indicate that SIP plays a significant role in encouraging disciplined investment habits and enhancing long-term financial growth. It also highlights that SIP is considered a reliable and flexible investment option compared to traditional savings methods. The study concludes that SIP is an effective strategy for individuals seeking sustainable financial growth and improved investment planning.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Systematic Investment Plan (SIP), Personal Financial Growth, Mutual Funds, Investment Strategy, Wealth Creation, Financial Planning.

  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

Agriculture has historically constituted the foundation of human subsistence systems, shaping settlement pattern, social organization and belief structures. Among indigenous communities agriculture practices are often embedded within ritual and religious frameworks that seek to regulate human nature relationships. Choekor is one such indigenous agricultural ritual observed among the Monpa community of Tawang district Arunachal Pradesh. The festival is celebrated after the sowing of crops and is aimed at ensuring protection of agricultural fields, prosperity of the village and overall wellbeing of the community. Etymologically, the term Choekor is derived from, choe (sacred Buddhist scriptures) and kor (circumambulation), signifying the ceremonial circulation of sacred texts around villages and farm lands. This paper documents the ritual process, symbolic dimensions and agricultural significance of Choekor based on ethnographic fieldwork and secondary sources. The study argues that Choekor represents an indigenous knowledge system that integrates Buddhist religious ideology, agricultural practice, ecological perception and community participation. In the context of rapid socio-economic transformations and declining traditional practices, the paper emphasizes the importance of Choekor as an element of intangible cultural heritage and a repository of traditional ecological knowledge among the Monpas.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Choekor, Monpa Tribe, Agricultural knowledge, Indigenous ritual, Cultural heritage.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

River bank erosion and accretion are fundamental fluvial processes that control channel migration, floodplain development, and landscape evolution in large alluvial rivers. The River Ganga in the Prayagraj city exhibits pronounced lateral instability due to its meandering to braided planform, variable discharge, sediment load, and increasing anthropogenic interventions. This study examines the spatio-temporal dynamics of bank erosion, accretion, and stable banks along the River Ganga between 2002 and 2022 using multi-temporal satellite imagery and GIS-based overlay analysis. River channel boundaries were delineated for the years 2002, 2012, and 2022, and polygon overlay techniques were applied to quantify changes for the periods 2002-2012, 2012-2022, and the cumulative period 2002-2022. Results reveal that bank erosion remained the dominant process throughout the study period, accounting for 54.79% of the total bank area over two decades. However, a noticeable shift from erosion-dominated conditions (2002-2012) to enhanced accretion (2012-2022) was observed, indicating partial channel adjustment in recent years. The spatial patterns highlight intense erosion along outer meander bends and downstream reaches, while accretion is concentrated along inner bends, point bars, and abandoned channels. The findings emphasize sustained lateral channel migration and long-term bank instability in the Prayagraj city, with important implications for floodplain management, infrastructure planning, and riverbank protection strategies.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bank erosion, Accretion, Channel migration, River Ganga, Prayagraj, GIS, Remote sensing

  License

Creative Commons Attribution 4.0 and The Open Definition