Authors - Nelson Herrera Herrera, Estevan Gomez-Torres, Paul Baldeon-Egas, Renato Toasa Abstract - The Context-Aware Mobile Systems (CAMS) framework simplifies the development of context-aware mobile applications using Model-Driven Development (MDD). CAMS incorporates a Domain-Specific Language (DSL) built with Xtext, enabling developers to model contextual information, define business rules, and establish event-driven behaviors. The generation of Android applications is automated via Acceleo, supporting the seamless integration of cloud services such as Azure Maps for geolocation, IoT Hub for sensor data management, and Twilio for contextual notifications. To enhance scalability and deployment efficiency, CAMS leverages Infrastructure-as-Code (IaC) solutions through Pulumi and Terraform, automating cloud resource provisioning. This approach reduces development complexity, minimizes manual configurations, and accelerates deployment cycles. A case study on package tracking showcases CAMS' ability to dynamically adjust application behavior in real time based on contextual data from IoT sensors and geolocation services. Evaluation results demonstrate a 40% reduction in development time compared to traditional methods, alongside improved scalability, supporting up to 10,000 IoT devices simultaneously. CAMS offers an innovative framework for developing intelligent mobile applications across various sectors, including logistics, smart cities, and real-time monitoring. Its modular architecture and automated deployment processes enable rapid prototyping and efficient scaling, making it adaptable to diverse application scenarios. Future enhancements include expanding support for iOS applications, integrating additional IoT capabilities, and incorporating AI-driven decision-making tools to enhance real-time responsiveness. CAMS positions itself as a robust and flexible solution for next-generation mobile applications, bridging the gap between contextual awareness and scalable cloud-based infrastructures.
Authors - Thavaprakash Arulsivakumar, Senthil Veerasamy Abstract - The perspectives and insights of sentiments on destinations are important for tourism stakeholders. Purpose of this research work is to understand tourist behaviour with the help of Electronic Word of Mouth (eWOM) and to bring out the cognitive insights using TripAdvisor for Asian destinations. A well-established Stimulus Organism Response (SOR) theory is used as a thematic foundation in this research and ChatGPT based content analysis is conducted using traveler reviews. Sample size of 151872 TripAdvisor review comments from 90 Asian destinations are analyzed in this research. Logistic regression and Structural equation modelling are used to examine the sample data. Empirical findings highlighted that travelers have unique sentiments on each destination and moderate positive sentiments influence the intention to visit. Macro and micro analysis is used in this research, its findings are re-shaping the demand and supply and is helpful for the decision makers to promote destinations.
Authors - Tihomir Dovramadjiev, Petya Manolova, Rozalina Dimova, Dimo Dimov, Vasil Gatev Abstract - This article investigates the interplay between human factors and criminology in identifying both the techniques and motivations behind cyber threats. By analyzing the psychological, social, and environmental drivers of cybercriminals, as well as the methods they employ, this study proposes a comprehensive framework for detecting and mitigating cyber threats. The integration of criminological theories and human factors research offers a novel approach to understanding and countering the evolving tactics of cyber attackers. In the era of Society 5.0, where human-centric technologies and artificial intelligence (AI) are deeply integrated into daily life, the role of human factors becomes even more critical. Human factors research helps uncover how cognitive biases, emotional states, and social influences shape both the behavior of cybercriminals and the effectiveness of defenders. For instance, AI-driven cybersecurity systems, while powerful, still rely on human oversight and decision-making, making it essential to address human vulnerabilities such as fatigue, stress, and misjudgment. Furthermore, as Society 5.0 emphasizes the fusion of cyber and physical spaces, understanding human behavior is key to designing systems that are resilient to social engineering, phishing, and other human-exploitative techniques. By combining main cybersecurity layers insights with human factors, this study not only addresses the technical aspects of cyber threats but also highlights the importance of human-centered design in cybersecurity of data assets.
Authors - Yuki Shirahama, Kayoko Yamamoto Abstract - In order to help yourself, it is necessary for the general public to keep adequate stockpiles in their homes that will be useful at the disaster outbreak times. Additionally, in order to provide mutual aid from the normal times, it is important for local residents to accumulate and share necessary information in a local community without relying on the government to provide information. Against such a backdrop, the purpose of the present study is to design, develop, operate and evaluate an original disaster information system to support self-help and mutual aid from the normal times to the disaster outbreak times, by integrating a stockpiling improvement support system, a local social network service (SNS) and web-geographic information systems (Web-GIS). Chofu City, Tokyo, was selected as the operation target area for the system. During the operation period of the system, the number of users was 57, and the number of information submitted by users was 25. From the result of the online questionnaire survey for users, it is evident that the system was useful in terms of improving the stockpiling situations in their homes at normal times, and in supporting the accumulation and sharing of disaster information among them from the normal times to the disaster outbreak times.
Authors - Marwan Babiker, Eda Merisalu, Zenija Roja, Henrijs Kalkis Abstract - A Health Information System (HIS) is an electronic database of managerial and clinical information, which allows physicians to utilize quality improvement processes in clinical practice and support multiple services in healthcare organizations. According to research, physician satisfaction varies greatly and is frequently correlated with particular features and the ease of exchanging information. The study aimed to identify the traits of doctors' acceptability of using a hospital information system (HIS) and their degree of satisfaction with it. It is a cross-sectional study that used an online self-administered survey, which was conducted among all 56 physicians working in family medicine centers in the Royal Commission health service program, Saudi Arabia. The questionnaire was used to assess the physician’s satisfaction level about the two structures that will be examined: system quality and satisfaction level. The findings showed that the physicians in the family medicine centers have a high agreement proportion about the use and satisfaction of the use of HIS, which indicates a high quality of the HIS. The outcomes measure system excellence and user satisfaction when assessing the effectiveness of HIS in several domains. The participating physicians expressed satisfaction with the way HIS improved their clinical processes and how reliable it was for patient care. More longitudinal studies are required to understand the indicator of physician satisfaction with the HIS use.
Authors - Rehab Hassan Bader, Issa A. Abed, Bayadir A.Isaa Abstract - Multi-Robot Systems (MRS) have developed as a disruptive technology in robotics, allowing multiple autonomous robots to work together to execute complex tasks. Multi-Robot Task Allocation (MRTA) is an important component of MRS since it involves distributing tasks to robots in a way that maximizes performance, efficiency, and resource use. Effective scheduling is crucial in MRTA because it determines the order and timing of task execution, which has a significant impact on overall system performance. This paper investigates current MRTA and scheduling strategies and algorithms, with an emphasis on the challenges raised by dynamic environments and the requirement for flexibility in task allocation. They discuss numerous approaches, including centralized and decentralized methods, constraint-based models, and reinforcement learning techniques, emphasizing the benefits and drawbacks. The combination of reallocation and rescheduling approaches is also being researched as a means of boosting system responsiveness to unanticipated changes. The findings suggest that future research should focus on developing hybrid models that take advantage of existing approaches to create more resilient and efficient multi-robot systems capable of operating in real-world scenarios.
Authors - Victoria Orozco Arias, Ernesto Rivera Alvarado Abstract - Data protection on websites is a common objective for entities and organizations, so new security strategies are constantly being sought. This research evaluates the effectiveness of using security metadata in HTML structures to protect sensitive data. To achieve this, a website scraping experiment will be conducted on sites that include authentication, to verify on which sites this type of fraud can be performed and to identify the use of security metadata. Our results show that 25% of the websites selected for the experiment could be extracted from the database, and the remaining sites have different settings, such as metadata, robots.txt file, and others, to protect and prevent data extraction. This proves that metadata is the first step of website security.
Authors - Ossman Lopez, Joan Alvarado, Juan Diaz-Gonzalez, Elisa Rendon-Cadavid, Sara Lopez, Mikel Maiza, Juan Felipe Restrepo-Arias, David Velasquez Abstract - This study presents the design and development of a non-invasive sensor for measuring the capacitance of cocoa fruits to detect ripening stages and the onset of fungal disease caused by Moniliophthora roreri. Capacitance is recognized in the state of the art as an effective physiological indicator due to its correlation with moisture content, cell development, and glucose levels in fruit. Based on this premise, the hypothesis was that capacitance measurements are directly related to fruit ripening and fungal infection. The sensor system features an electronic circuit that generates a 10V peak output at a frequency of 1 kHz, integrated with a Sauty Bridge for real-time capacitance measurements without harming the fruit. The device is lightweight, user-friendly, and energy-efficient. The experiments were carried out under controlled conditions using the CNCH13 cocoa variety to standardize the measurements. The preliminary results confirm a strong correlation between capacitance levels, ripening stages in healthy fruits, and the presence of fungal disease. The prototype developed effectively measures capacitance, providing a reliable method for assessing the physiological state of cocoa fruits.
Lecturer, Lecturer, University of Botswana, Botswana
Mrs Tsholofetso Taukobong is a Lecturer with the Department of Computer Science, University of Botswana. She hold an MSc and BSc in Computer Science, both from the University of Botswana and is currently pursuing her PhD studies in Computer Science specializing in Computer Vision... Read More →
Authors - Ernesto Rivera-Alvarado, Saul Guadamuz Abstract - Predatory journals are characterized by publishing research articles without the proper peer-review process. They are mainly focused on getting money from authors, regardless of the quality of the article being submitted, in a scenario where academics and researchers are usually incentivized to create a high volume of research to advance their career paths. While publishing in a predatory journal is easier than in a reputable publisher, the author’s credibility could be tarnished. The rise of large language models has provided a new danger for this scenario. It is now easier to create low-quality research papers using IA tools that could be sent to predatory publishers that fail to perform a rigorous peer-review process. A bad combination of fast and poorly created research papers with highly available pay-to-publish journals provides an unsafe scenario for science publishing and unaware scientists. This paper aims to warn researchers about the dangers of generating low-quality research and publishing in predatory journals.
Authors - Mohammadmahdi Ghobadi, Renee Bryce Abstract - Modern applications are built from many small services that work together. In these systems, an API gateway plays a key role in routing requests, balancing the load, and processing events. Most API gateways use fixed rules that do not change with shifting workloads, causing delays as high-priority events may be blocked by less critical tasks. In this paper, we propose a new method that uses reinforcement learning to create adaptive API gateways. Our system learns from real-time performance data such as CPU usage, memory usage, event latency, arrival rates of high-priority events, and throughput of low-priority events. By using multiple metrics, the system adjusts its settings to respond to changing conditions. It processes high-priority events immediately while grouping low-priority events into batches for efficient processing. We use the Proximal Policy Optimization (PPO) algorithm because it is stable and effective for learning the best settings. We evaluated our method using simulations that mimic real-world conditions. The results show that our approach reduces the delay for highpriority events by about 41% and significantly lowers the delay for lowpriority events. The system also uses fewer resources than rule-based gateways. These improvements demonstrate that considering multiple performance metrics can lead to smarter, more adaptive API gateways. Our approach adapts very quickly to varying workloads, ensuring remarkably reliable operation during sudden spikes. Our work shows that reinforcement learning can improve API gateway performance for modern applications. This is important for fields such as finance, healthcare, and emergency systems, where fast and reliable responses are critical.
Authors - Paula Poveda-Sotomayor, Henry N. Roa, Edison Loza-Aguirre, Javier Guana-Moya, Nelson Salgado-Reyes Abstract - Water treatment facilities require efficient and continuous monitoring to ensure safe drinking water. Traditional Supervisory Control and Data Acquisition (SCADA) systems often face limitations in scalability, cost-effectiveness, and real-time data accessibility, prompting interest in alternative technologies such as the Internet of Things (IoT). This study proposes a cloud-integrated IoT framework explicitly designed for real-time monitoring of key water quality parameters, including pH, turbidity, and flow rate. The framework securely transmits data using MQTT protocol to AWS IoT Core, leveraging AWS Timestream and Grafana dashboards for advanced analytics, visualization, and proactive anomaly detection. The system's feasibility and performance were validated through simulation, guided by the Design Science Research (DSR) methodology. Results indicate significant potential benefits, including improved real-time responsiveness, reduced manual monitoring requirements and enhanced operational decision-making. This framework provides a scalable and secure solution that addresses existing SCADA limitations, laying the groundwork for future integration into smart water management practices.
Authors - S. M. Mizanoor Rahman Abstract - We proposed and investigated a bidirectional trust-triggered cyber-physical-human (CPH) system framework for human-robot collaborative assembly in flexible manufacturing. For this purpose, we developed a one human-one robot hybrid cell where the human and the robot collaborated with each other to perform the assembly operation of different manufacturing components in a flexible manufacturing setup. In the proposed framework, we configured the human-robot collaborative system in three interconnected components of a CPH system: cyber system (software system), physical system (the robot, sensors and necessary hardware), and human system (the human co-worker, supervisor and work environment). We divided the functions of the CPH framework into three interconnected modules: computing or computation, communication and control. We used a model to compute the human and robot’s bidirectional trust in real-time to monitor the performance of the CPH framework. We evaluated the performance of the CPH framework implementing it on an actual human-robot collaborative assembly setup considering systematic variations in the complexity levels of the computing module. The overall results revealed that variations in computing complexity significantly impacted the performance of the CPH framework in terms of human-robot interactions and task efficiency and quality. The results thus proved that it became easy and effective to monitor the performance and interactional effectiveness of a human-robot collaborative system modularly when the system was configured in the form of a CPH system. The results can transform the design, development, analysis and control of human-robot collaborative systems for various applications such as industrial manufacturing and assembly, military operations, transportation, healthcare and rehabilitation, construction, social services, etc.
Authors - Oleksandr M. Khimich, Elena A. Nikolaevskaya, Pavlo S. Yershov Abstract - Virtual assistants (VAs) are becoming an increasingly popular tool that helps users find information faster and more accurately. This paper proposes a new AI-powered Virtual Travel Guide (GuideAI) system. The concept, architecture, and implementation of a microservice for intelligent travel search are explored in detail. The study focuses on technical aspects, particularly the integration of GPT for analysis and personalization. It highlights how geolocation and personalization can be combined to create more adaptive, user-responsive systems. The proposed approach enhances travel experiences by providing real-time, tailored recommendations based on user preferences and location. The scientific contribution of this research lies in the development of a novel AI-driven approach to travel assistance, demonstrating how advanced natural language processing and contextual data analysis can improve recommendation accuracy. By leveraging machine learning techniques, GuideAI refines search results, enhances decision-making processes, and optimizes user interactions. This work contributes to the field of intelligent information retrieval and personalized AI systems, offering insights for future applications in tourism and beyond.
Authors - Alvaro A. Casanova, Elvis E. Gaona, Oscar Acosta Abstract - This paper introduces a stochastic modeling framework for analyzing binaural urban noise in Bogotá, Colombia. A total of 4,200 five-minute audio recordings were collected using binaural sensors placed at seven urban locations over 47 days. To analyze the data, we utilized cloud-based tools, including Inferencer app for machine-learning-based sound classification and Soundmetrics app for extracting acoustic parameters such as LEQ (equivalent continuous sound level), IACC (inter-aural cross-correlation coefficient), and WIACC (weighted inter-aural cross-correlation coefficient). The probabilistic analysis revealed instances of extreme noise events exceeding 85 dB. We identified correlation patterns that informed the development of a predictive model based on discrete-time Markov chains. Which incorporated both noise intensity and sound source classification into composite acoustic states. The simulated trajectories effectively captured the temporal dynamics of urban acoustic conditions, successfully meeting the study’s objective of modeling future noise dynamics. This approach demonstrates a scalable solution for real-time monitoring, statistical characterization, and predictive modeling of complex urban soundscapes, providing actionable insights that support data-driven decision-making in smart city planning.
Authors - Ramiro Ramirez, Yasmany Garcia-Ramirez, Jandry Jaramillo Abstract - This research explores the potential of mobile applications in improving road safety education and driver behavior. Road traffic crashes, particularly those involving vulnerable road users, continue to represent a significant global public health issue. Traditional road safety education methods often lack engagement and immediate feedback, limiting their effectiveness in promoting long-term behavioral change. This study introduces SafeJourney, a mobile application developed to enhance road safety learning through real-time feedback, location-based alerts, and personalized progress tracking. The application integrates GPS technology and mobile sensors to monitor driving, cycling, and pedestrian behavior, providing users with timely feedback to reinforce safe practices. The development of SafeJourney followed a modified SCRUM methodology, ensuring iterative and efficient progress. Key features include real-time alerts, integration with traffic law databases, and a user-friendly interface designed with Figma and React Native. Testing and validation confirmed the application's functionality, including low-latency tracking, device compatibility, and seamless integration with a cloud-based database. SafeJourney represents a promising innovation in road safety education, offering an interactive and scalable solution to reduce traffic-related injuries and fatalities.
Authors - Gery Prasetyo, Tanty Oktavia, Mohammad Ichsan Abstract - This research presents the current state of development and implementation of AI predictive analytics for project management support through the lens of Indonesian financial projects, highlighting a practical implementation gap and its impacts towards the fulfilment of enhancements in the core project management aspects of risk prediction, budget and resource estimation, deliverables quality monitoring, and automation of project financial processes. A qualitative methodology is applied to explore the various field experiences and sentiments of five financial project professionals in individual financial firms through direct semi-structured interviews. Analysis of the findings affirms the implementation of machine learning predictive analytics in the four key project areas, with tasks in risk strategy implementation, budget estimation, and resource allocation management revealed as the prominent applications utilized by respondent financial companies. Benefits in streamlining tasks and improvements towards project efficiency are noted by the respondents, along with enhancing team awareness against unseen risks and resource issues, setting new standards for quality management, and reducing human errors in rapid financial processing. The findings further uncovered key barriers in predictive analytics implementation success stemming from system maturity and accuracy issues, and moreover the influence of intangible human factors towards the financial sector business environment and practices. Improving the synergy of the technical capabilities predictive AI systems with human subjectivity and intuition is paramount to ensure successful implementations of predictive project support tools in the Indonesian finance sector.
Lecturer, Lecturer, University of Botswana, Botswana
Mrs Tsholofetso Taukobong is a Lecturer with the Department of Computer Science, University of Botswana. She hold an MSc and BSc in Computer Science, both from the University of Botswana and is currently pursuing her PhD studies in Computer Science specializing in Computer Vision... Read More →
Authors - Ezhilmathi Krishnasamy, Pascal Bouvry Abstract - The ongoing development in architecture and programming models, particularly regarding GPUs, significantly influences the landscape of high-performance computing. Presently, nearly all supercomputers worldwide are equipped with GPU compute nodes, promoting advancements in architecture that emphasize heterogeneity. Concurrently, there is a parallel evolution in programming models designed to effectively harness the potential of this diverse architecture for executing scientific applications. Notable architectures, longing trends in Nvidia GPUs, such as Grace Hopper and the AMD Mi300 series, alongside programming paradigms like SYCL, OpenCL, and various library-based models, including Kokos and StarPU, illustrate this trend. The primary motivation is to establish an appropriate programming model that targets modern architectures, essential for maximizing computational efficiency across specific applications. A multitude of programming models exist, each offering the potential for optimal utilization of advanced architectural capabilities. However, a critical question arises regarding the ease of adoption and the user-friendliness of these models for existing large-scale scientific codes. This study focuses on OpenMP Offloading, examining its application on Nvidia to ensure a unified source code compatible with various GPU architectures. Identifying an optimal programming model for effective OpenMP Offloading usage is of paramount importance. This paper conducts a comparative analysis of the OpenMP Offloading programming model against CUDA for Nvidia GPUs, facilitating a comprehensive performance evaluation. The analysis employs key BLAS operations to assess the performance characteristics of OpenMP Offloading in relation to CUDA, thereby elucidating the advantages and limitations associated with leveraging OpenMP Offloading.
Authors - Yury Zontov, Alexander Derendyaev, Daniil Tkachev, Arkady Vaynshtok, Vyacheslav Yakuba Abstract - A consulting system for development and adoption of high-quality decisions by territorial governments should provide tools for accessing relevant and reliable information about processes and results of population's life, as well as tools for analyzing socio-economic indicators and infrastructure functioning. Analysis tools should help identify problem situations ("bottlenecks") in ensuring the quality of life of population and to form a "tree" of management goals for the development of territory and improvement of life of population. The solution of these problems is possible by creating a human-machine platform for scenario analysis of the development of territories for numerous aspects of management. The decision-making process based on the representation, calculation and interpretation of current observed and predicted parameters is effective for both operational management and strategic planning. The information and analytical system under development is intended to become a convenient and powerful tool for analyzing the level of development of a region, scenario analysis, planning support and making high-quality management decisions.
Authors - Sunday Omotoye, Weifeng Chen Abstract - The escalation of insider threats poses significant harm to organizations and businesses, necessitating a thorough understanding of their nature and the associated threat landscape to develop effective Insider Threat Programs (ITP). This paper delves into the pervasive issue of insider threats within the retail industry, examining the applicability of the Cyber Kill Chain (CKC) to comprehend these threats. The retail sector, with its diverse and dispersed workforce, faces unique vulnerabilities that require organized strategies and proactive measures. By strategically integrating the CKC framework, the ITP systematically identifies and prevents insider threats at every stage of their lifecycle. This comprehensive approach serves as an indispensable element in fortifying the security framework of both the retail industry and broader economic landscape.
Authors - Sarmad K.D. Alkhafaji, Shahab Abdulla, Haydar Abdulameer Marhoon, Mohammed Diykh, Mustafa Ali Majed, Jafar Sadiq, Ali Aqeel Saleh, Aqeel Sahi, Hussein Alabdally Abstract - Chest radiography is a technique based on medical imaging that is employed to detect thoracic diseases. In this paper, we designed an intelligent method to diagnose thorax disease from chest X-ray (CXR) images. A novel empirical curvelet transform, coupled with a deep learning model, is proposed. The collected images are analysed using the proposed empirical curvelet transform (ECT) model. Then, the outputs of ECT model are sent to DenseNet. The proposed model is assessed using several statistical metrics. The proposed model achieves an accuracy of 98%. The results demonstrated the ability of the proposed model to detect Thoracic Disease.
Authors - Elias Tabane, Zenghui Wang, Ernest Mnkandla Abstract - In this paper, we present a comprehensive analysis of ensemble deep learning models for DNA sequence classification. We explore the performance of three standalone models: Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Units (GRU), along with an ensemble approach that combines all three. Our study evaluates the models based on four performance metrics: accuracy, precision, recall, and F1 score. The ensemble model achieved an accuracy of 90.6%, with precision, recall, and F1 score all at 0.91. We compare these results to the standalone models and demonstrate that ensemble learning significantly improves classification performance in the context of DNA sequence data. Additionally, we review relevant studies that have applied deep learning models to similar tasks and discuss the advantages of combining CNN, BiLSTM, and GRU for sequence classification tasks.
Authors - Indibar Debnath, Om Prakash Abstract - For a prime p and ℓ ∈ N with gcd(ℓ, p) = 1, this work explores the hulls of ℓ-length cyclic codes over Zp3 . We establish the form of the generators of the hulls and provide a characterization of the hulls. Further, we present a condition for these codes to be LCD. To formulate the p-dimensions of the hulls, first, we find the types of the hulls and then use them to come up with an expression for the p-dimensions of the hulls. Moreover, for a fixed p-dimension of the hull, we count all the cyclic codes.
Authors - Shahriar Sultan Ramit, Nayeem Ahmed, Md Fatin Ishrak, Md Ruhul Amin, Alaya Parven Alo, Md. Sadekur Rahman Abstract - Oral Squamous Cell Carcinoma (OSCC) is among the most frequent cancer death causes, and early detection plays a vital role in improving patient survival. The traditional histopathological diagnosis is subjective and labor-intensive which necessitates an automated and standardized classification methods. This study has used a publicly available dataset comprising a total of 10,000 histopathological images. This paper evaluates four CNN architectures ResNet101, InceptionV3, MobileNetV2 and Xception to classify OSCC and normal cells. For better accuracy Hyperparameter Tuning was done on MobileNetV2. Tuned MobileNetV2 achieved the best performance with accuracy, recall, and F1-score of 0.99, demonstrating its efficacy in classifying malignant vs. normal tissues. To further enhance interpretability Explainable AI techniques were employed, including LIME and Saliency Maps, enabling visual comprehension of model predictions. Our results demonstrate the importance of deep learning for OSCC detection overcoming the "black-box" issue of CNNs by explain ability. This study contributes to AI-driven diagnostic innovation through a more accurate and interpretable approach to OSCC classification.
Authors - Nelson Salgado-Reyes, Jorge Rivera-Guaman Abstract - This proposal outlines the establishment of a Computer Security Incident Response Team (CSIRT) at the Central University of Ecuador (UCE) with a focus on training, awareness, and a hybrid model adapted to the academic environment. The study utilizes a mixed qualitative-quantitative approach to analyze international best practices, diagnose cybersecurity vulnerabilities at UCE, and design the proposed model. The findings emphasize the importance of strengthening security culture, reducing incidents caused by human error, and integrating cybersecurity into the university curriculum. The model includes an organizational structure, educational services, and assessment metrics that adhere to standards such as ISO/IEC 27035 and NIST SP 800-61. This research contributes to the field of CSIRTs in educational institutions with limited resources, providing a replicable framework specifically tailored for Latin American contexts.
Authors - Syed Muhammad Raza Abidi, David C. Henshall,Gabriel-Miro Muntean Abstract - The weak electromagnetic signals originating from the brain’s neu-ronal activities can be assessed by electroencephalography (EEG) and magne-toencephalography (MEG). Due to the continuous time series data of EEG and low amplitude and nonstationary characteristics, it is difficult to achieve a con-sistent and satisfactory diagnosis outcome. It is hard to use these signals to identify and describe neuronal activation in the brain and adequate knowledge of signal processing, statistics, and numerical techniques are required. This paper introduces an innovative hybrid approach using machine learning, i.e., Modality Integration for Neuro Signals to Enhance Accuracy (MINE-Acc) which com-bines EEG and MEG data to increase brain activity prediction accuracy. This approach leverages the complementary strengths of both modalities to improve the accuracy and robustness of prediction. We employed the machine learning pipeline and used a Logistic Regression (LR) classifier in the research, performed a 5-fold cross-validation on sample dataset given by MNE-Python and by com-bining modalities together the findings provide a prediction accuracy of 99.8%. Traditional methods, such as functional magnetic resonance imaging (fMRI) and Positron Emission Tomography (PET) etc. are available to use these signals to characterize normal and pathological brain activity but there remain difficulties with integration and interpretation. They have high spatial resolution but lack real-time capabilities. The study determines the improved prediction accuracy of the activity participants engage with based on combined analysis of EEG and MEG data. We used the MNE-Python, a software package to test this novel approach.
Authors - Ahmed Noorim, Raina Nusrat Jahan, Md. Sabbir Al Ahsan, Sourav Adhikary, Md. Jamil Uddin Abstract - Early detection of Diabetic Retinopathy (DR) remains essential due to its status as a leading cause of vision loss along with severe complications. Ever increasing worldwide diabetes situation makes it necessary to develop an automated diagnosis system for detecting DR at an early stage precisely. The research proposes a weighted average ensemble deep learning architecture to perform two stages of DR diagnosis along with severity classification from fundus images. The first stage identifies cases of the presence of DR by applying a binary classifier followed by a multiclass classifier in the second stage to evaluate severity levels. This model is trained and evaluated on a merged dataset which amalgamates APTOS 2019, MESSIDOR 2, and IDRiD with three different preprocessing to boost its generalized application capabilities. DenseNet121, EfficientNetB1 and Xception models complement each other for optimal feature extraction and classification task thus utilized in the development of ensemble model. Outperforming several state-of-the-art models, 97% recall with 92% accuracy was achieved in determining the existence of DR, while severity classification reaches 93% accuracy and 94% recall. The research shows promising assistance for ophthalmologists in becoming an essential diagnostic screening instrument for the early detection of DR in resource limited areas.
Authors - Dario Galic, Dejan Stosovic, Elvir Cajic, Anita Katic Abstract - This paper explores numerical methods for solving partial differential equations (PDEs) using the method of nets. The focus is on hyperbolic equations, such as the wave equation, and the application of net methods in solving problems with boundary conditions. The process of solving these equations using computational tools is illustrated, and the accuracy of the results is analyzed. The iterative Gauss-Seidel method is applied to solve systems of algebraic equations generated by the net method.
Authors - Kamil Samara, Syed Rizwan Abstract - Mental health challenges, particularly anxiety and stress, are prevalent among students due to academic pressures, social expectations, and personal struggles. Traditional mental health support systems often fail to provide timely interventions, leading to severe consequences such as depression or suicidal ideation. This study presents an Early Detection and Support System for Student Mental Health, integrating machine learning models to proactively assess and predict student anxiety levels. The system utilizes data from activity logs, and survey responses to classify students into different anxiety categories and provide personalized support recommendations. Multiple machine learning algorithms, including Logistic Regression, Decision Tree, and Random Forest, were employed to optimize prediction accuracy. The results demonstrate that Logistic Regression achieved the highest accuracy (89.1%) in predicting stress levels, while the Random Forest model performed best in stress reduction prediction. The system's predictive capabilities extend beyond anxiety detection, enabling multi-feature mental health analysis, including depression, self-esteem, and stress levels. By integrating an automated alert mechanism and real-time monitoring, this framework offers a proactive solution for universities to support student mental well-being.
Authors - Alaya Parven Alo, Md Ruhul Amin, Md Imran Kabir Joy, Kazi Rezwana Alam, Shahriar Sultan Ramit, Md. Sadekur Rahman Abstract - Cervical cancer is a leading cause of cancerrelated deaths among women, and early detection is crucial for improving patient prognosis. Traditional diagnostic methods, while effective, are often timeconsuming and prone to subjectivity. This paper explores the use of deep learning techniques for automating cervical cancer diagnosis, employing five distinct models MobileNetV2, VGG19, Xception, ConvNeXtBase, and InceptionV3 along with a tuned version of MobileNetV2. A secondary dataset with five classes of cervical cell images were utilized to build the models and the performance of each model was evaluated with precision, recall and F1score. The tuned MobileNetV2 model achieved the highest accuracy and robustness in classification.TunedMobileNetV2 provided an accuracy of 0.99, with precision and recall values of 0.99.To address the "blackbox" nature of deep learning models, Explainable AI (XAI) techniques were incorporated, including LIME and Saliency Maps, to improve model interpretability. The use of XAI in the tuned MobileNetV2 model enhances transparency, allowing for visual interpretation of model predictions. Findings of the research suggests that deep learning, coupled with XAI, offers a promising and more explainable approach to cervical cancer diagnosis, advancing both accuracy and interpretability in automated clinical decisionmaking.
Authors - Katleho Seatlolo, Khutso Lebea Abstract - This paper investigates the potential of Retrieval Augmented Generation (RAG) technology to enhance the effectiveness of Intrusion Detection Systems (IDS) in the energy sector. By leveraging vast amounts of historical data, real-time threat intelligence, and advanced natural language processing techniques, RAG can significantly improve IDS capabilities in detecting and responding to cyber threats. The paper addresses the limitations of traditional IDS, such as their reliance on predefined signatures and vulnerability databases. It explores how RAG can overcome these limitations by analysing network traffic patterns, identifying anomalies, and correlating them with known attack vectors. The paper discusses the potential benefits of RAG in terms of improved threat detection accuracy, reduced false positives, and enhanced response times. Case studies and research findings are presented to support the argument. Challenges and considerations related to data quality, privacy, and ethical implications are also addressed. The conclusion emphasises the importance of RAG technology in safeguarding smart grids from evolving cyber threats and highlights potential future directions for research and development. The paper aims to explore the potential of RAG technology to enhance IDS in smart grids and contribute to Sustainable Development Goal 9: Industry, Innovation, and Infrastructure. It describes the limitations of traditional IDS, the benefits of RAG technology, and the potential applications of RAG in the energy sector.
Authors - Aditi Choudhary, Aditya Gupta, Pulkit Jain, Nikunj Agarwal, Mukund Wagh Abstract - We present a novel programming-by-example (PBE) approach that synthesizes natural and human-readable code by integrating higher-order functions with standard and third- party libraries in Haskell. This technique leverages refinement types to efficiently prune the search space, ensuring scalability while preserving soundness. Using Liquid Haskell, we extend support for complex data structures, enabling the synthesis of reusable and idiomatic code. Our evaluation demonstrates the tool’s versatility across lists, trees, maps, and domain-specific languages, including musical scores. The results highlight that our method generates concise, interpretable programs, bridging the gap between formal verification and practical usability in functional programming. Index Terms—Programming-by-Example (PBE), Haskell, Higher-Order Functions, Refinement Types, Liquid Haskell, Code Synthesis, Functional Programming, Search Space Pruning, Domain-Specific Languages (DSLs), Formal Verification, Scalability, Reusable Code, Idiomatic Programming.
Authors - Wanda Syauqi Mikola, Tiurida Lily Anita Abstract - This Research looks at how Customer’s Intentions to Buy from Fast-Food Restaurants are influenced by Online Reviews, Brand Images, and Menu Visuals. Understanding the factors that influence Customer’s Purchase Decisions is of business interest due to the impact of technology and the evolution of services. The objective is to empirically ascertain how these three factors increase Customer’s Intentions to Buy for sustainability in The Restaurant Industry. Structural Equation Modeling-Partial Least Squares (SEM-PLS), A Quantitative Method, is used in this study to examine the connection between variables. Data was gathered by randomly selecting 200 Customer’s Fast-Food Restaurants in The Jakarta Region. The Results indicate that while Online Reviews do not significantly affect Customer’s Intentions to Buy, Brand Images and Menu Visuals do. This implies that when it comes to Fast-Food Restaurants, Customers are more swayed by The Reputation of A Well-Known of Brand Images and Menu Visuals than by Online Reviews. For Restaurant Businesses looking to improve their Brand Images and optimize Their Menu Visuals to draw in and keep Customers, This Research offers Insightful Information.
