In the age of mobile technology, the demand for seamless access to educational resources has become essential. This abstract presents a project proposal for developing a mobile application aimed at integrating with the Sakai Learning Management System (LMS). The application seeks to enhance the learning experience by providing students, instructors, and administrators with anytime, anywhere access to Sakai's core functionalities. The proposed mobile application will serve as a comprehensive extension to the Sakai LMS, extending its capabilities to mobile devices such as smartphones and tablets. Leveraging the ubiquity and convenience of mobile devices, students will be empowered to engage in learning activities beyond the traditional classrooms. As principal features we identify the following: Seamless Access, users will be able to log in securely to the Sakai LMS from their mobile devices, accessing their course materials, assignments, discussion boards, and grades effortlessly; Course Notifications, push notifications will alert students to new announcements, upcoming assignments, and other important events reducing the risk of missed deadlines; Content Consumption, students will have the ability to access diverse learning materials, including documents, multimedia files, and interactive content, optimizing their learning experience on mobile devices and Progress Tracking, the mobile application will provide students with a comprehensive overview of their academic progress, including grades, attendance records, and completion status for assignments, empowering them to stay organized and motivated. The development process was done with continuous feedback from educators and students. With different testing and quality assurance measures implemented to ensure the security, reliability, and performance.

Terrestrial locomotion of robots employs two main methods: the use of wheels or tracks, and the use of articulated joints. Articulated locomotion offers advantages over wheels, such as lower energy consumption, access to irregular and rough terrains, better maneuverability in homes by climbing and descending stairs, and improved planning. Additionally, articulated robots are lighter, can be produced and prototyped with 3D printers, and offer greater flexibility in various environments. However, they also present some disadvantages, including complex mechanical structures, increased control complexity, and expensive actuators. This work presents the design and implementation of a reinforcement learning model based on Proximal Policy Optimization (PPO) for the locomotion of a 12-degrees-of-freedom quadruped robot that ensures stable trajectory. For this purpose, a reinforcement learning model based on TensorFlow and Gym was implemented and tested in the Pybullet simulation environment. With the correct adjustment of the model's hyperparameters, maximum stability in the robot's walking trajectory is achieved. During walking, the robot attains a smooth response curve when measuring its center of gravity. The application of reinforcement learning in this context shows the potential for advanced control techniques to address the complexities of articulated robots. By optimizing control strategies and leveraging modern simulation tools, this study demonstrates improvements in the stability and performance of quadruped robots, contributing to the development of more efficient and versatile robotic systems.

Precision and efficacy are vital in the constantly advancing field of food image identification, particularly in the domains of medicine and healthcare. Transfer learning and deep ensemble learning techniques are employed to enhance the accuracy and efficiency of the Indian Food Classification System. The ensemble model effectively captures various patterns and correlations within the information by employing many machine learning techniques. The ensemble method we employ utilizes the MobileNetV3 and DenseNet-121 transfer learning models to construct a robust model. The ensemble model benefits from the integration of model predictions, resulting in enhanced recognition of Indian food. The study utilized a dataset consisting of 6000 photographs of Indian cuisine, categorized into 26 distinct groups. The picture dataset is divided into two subsets: 80% is allocated for training and 20% is reserved for testing. The experimental results demonstrate that DenseNet-121 surpasses MobileNetv3 in terms of testing accuracy, achieving a rate of 90%. The MobileNetV3 model achieves an accuracy of 87.64% on the Indian food image dataset. The integration of both models in ensemble learning yields a model accuracy of 92.38%, surpassing the performance of each individual model. This research revolutionizes our food relationship with the use of state-of-the-art technologies. By utilizing the most advanced transfer learning algorithm specifically designed for the precise classification of Indian cuisine, our aim is to establish a new standard in both technology and gastronomy. This will facilitate innovation in food perception, comprehension, and engagement.

With the intensification of information technology usage and the emergence of artificial intelligence, data protection has become a topic of debate in academia, spanning from the business context to the political sphere. In Brazil, from a legal perspective, data protection is not a new topic; it has been the subject of court rulings and jurisprudence long before the enactment of the Brazilian General Data Protection Law (GDPL). This work aims to present the analytical process and the outcomes of analyzing jurisprudence regarding data protection and relates issues. To achieve this, search strings and data acquisition agents were developed for use on a portal dedicated to Brazilian legal texts, creating a corpus containing 10,009 documents. Through this, an exploratory analysis of the texts from Courts of Justice was conducted considering the types of jurisprudence and case summaries. The main results in the current research phase demonstrate the evolution of associated texts before and after GDPL, based on the date of promulgation of the law. It is also possible to visualize how the cases are distributed among each state court, highlighting the states of the southeast and south regions, as well as the main occurrences within each Brazilian state. By analyzing the legal levels at which decisions have been made, we can also understand the extent of these cases that have been aggravated.

Introduction

Managing bank queues efficiently is crucial for maintaining customer satisfaction, operational efficiency, and compliance with regulations. Nevertheless, it involves overcoming significant challenges related to demand variability, resource constraints, and the need for technological and procedural adaptations. During emergency crises such as the COVID-19 pandemic, offering robust measures for discrete simulations becomes challenging due to significant and unexpected variations in customer arrival rates. This study proposes computing discrete event simulations based on queuing theory and tests of the empirical probability distribution for each particularity to support improvements in waiting times for segments of Caixa Econômica Federal (CEF) responsible for financial aid services (Express, Tellers, and Gov-Social sectors).

Methods

The methodology involves conducting discrete event simulations (DES) using real-time data collection to accurately model customer arrival and service rates. Key parameters included the expected queue length, waiting time, and number of arrivals per unit time, based on service time, the number of servers, the number of clients, and the average waiting time per month. We apply the Kolmogorov-Smirnov test to identify the most fitting probability distributions for these rates, adjusting them as needed on each scenario.

Results

The computing simulations indicated a potential reduction in queue size by approximately 45%. Specifically, hiring at least one more employee for the Express sector in some specific production scenarios could decrease the average waiting time from 36 minutes to 17 minutes, thereby increasing the capacity to serve more customers. In extreme pandemic scenarios, six more employees are necessary to maintain reasonable service times.

Conclusions

The study's findings suggest that strategic employee allocation can significantly improve service efficiency in high-demand sectors at CEF. By implementing the recommended staffing changes, financial institutions can offer satisfactory service, enhance business profitability, and better manage the effects of the pandemic or similar public emergency contexts.

Spam email detection is essential for maintaining cybersecurity, protecting user privacy, and reducing security risks. The persistent activity of spammers necessitates continuous advancements in spam filtering methods. This study introduces an automated spam filtering system using an optimized soft voting ensemble classifier to address this challenge. Initially, the process employs the Grid Search Optimizer to fine-tune the parameters of four distinct classifiers: Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), and XGBoost. Subsequently, the final classification is performed using a soft voting ensemble method, combining the optimised classifiers' outputs to enhance overall accuracy in detecting and classifying spam emails. This study evaluates the proposed model using the Spam_Mails Dataset and Enron1 Dataset. The experimental results demonstrate that the proposed ensemble model, which integrates hyperparameter tuning with soft voting, significantly outperforms existing approaches. Specifically, the model achieved accuracies of 99.22% and 99.12% on the Spam_Mails and Enron1 datasets, respectively. Additionally, the ensemble model attained an AUC of 1.00 on both datasets, indicating its high effectiveness in distinguishing between spam and legitimate emails (ham). The ensemble model exhibits superior accuracy, generalization, and robustness compared to individual classifiers. This innovative combination of Grid Search and soft voting results in a highly effective and efficient spam email detection model. The findings underscore the importance of hyperparameter tuning and ensemble learning in enhancing the performance of spam detection systems, setting a new benchmark for future research in this domain.

Plant diseases pose a significant threat to global food security, particularly affecting tomato crops that are vulnerable to various pathogens. Despite advancements in disease identification methods, farmers continue to experience substantial decreases in yield due to delayed and imprecise diagnoses, along with inadequate treatment recommendations. This research aims to address this critical issue by developing an innovative Artificial Intelligence (AI)-based system that can detect tomato plant diseases and provide effective treatment suggestions. To achieve this, a Convolutional Neural Network (CNN) based on the InceptionV3 architecture has been trained using a comprehensive dataset of 11,000 tomato leaf images representing nine different diseases and healthy samples. The approach combines deep learning techniques for accurate image classification with natural language processing, leveraging OpenAI's GPT-3.5 Turbo model to generate customized treatment recommendations. The results demonstrate the exceptional performance of the model, with a training accuracy of 99.85% and a validation accuracy of 88.75%. Rigorous evaluation using confusion matrices and assessment metrics further confirms the model's high precision and recall rates for different disease categories, showcasing its robust generalization capabilities. Furthermore, the inclusion of an intuitive Streamlit interface enhances user experience and ensures practical applicability in real-world scenarios. This study makes a significant contribution to agricultural technology by providing a comprehensive solution that integrates precise disease detection with actionable treatment guidance. The developed system holds immense potential to revolutionize tomato crop management practices, potentially minimizing financial losses and promoting sustainable agriculture through targeted disease management strategies.

The growing world population is increasing the demand for food, and climate change is causing erratic rainfall patterns. This has led to greater reliance on irrigation, especially in the Sahel and arid regions, to sustain food production. As freshwater resources become scarce, farmers are utilizing various water sources to keep their crops irrigated, aiming to ensure food availability and profitability. However, the rise in industrial activity is increasing pollution, which affects water quality, making its monitoring time-consuming and extensive. The aim of this study is to develop a machine learning approach for predicting irrigation water quality. To achieve this, a large dataset consisting of 1750 water samples was curated. The data were preprocessed, and Sodium Adsorption Ratio (SAR) and Irrigation Water Quality Index (IWQI) were computed. Five machine learning models (XGBoost, K-Nearest Neighbors, Support Vector Machine and Random Forest) were trained using the following parameters: Sodium(Na), Calcium(Ca²⁺), Bicarbonate (HCO3^-), Electical Conductivity (EC), and SAR. The results revealed that XGBoost outperformed the other algorithms, achieving a mean absolute error (MAE) of 0.90, a mean squared error (MSE) of 3.26, a root mean squared error (RMSE) of 1.81, and an R² of 0.96. The use of machine learning algorithms in predicting irrigation water quality is essential for farmers and crop planning, as it can save costs and time while ensuring healthy food production.

Abstract

Emotion recognition, particularly through facial expressions, has become vital across diverse domains like healthcare, entertainment, and education, providing insights into user experiences and guiding decision-making processes. However, the realm of education, particularly in online learning environments, presents distinct challenges. Traditional emotion recognition approaches are insufficient to capture the emotional states expressed by students during the learning process. This research addresses this gap by introducing the concept of learning emotions, specifically emotions like interest, boredom, and confusion, exhibited by learners during online lectures. This research presents a novel approach for recognizing learners' emotions in online learning environments using a deep learning architecture combining convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. The proposed model aims to improve emotion recognition accuracy and enhance the online learning experience. A custom dataset was created by mapping action units from existing emotions in the FER2013 dataset to new emotion categories (interested, confused, and bored). The model was trained and evaluated on this dataset, achieving an accuracy of 98.0%, precision of 97%, recall of 98%, and F1-score of 98%. These results surpass existing approaches for emotion recognition, demonstrating the effectiveness of the CNN-LSTM model in recognizing learners' emotions. This research contributes to the development of affective computing in online learning environments, enabling personalized support and improved learning outcomes. The proposed model has potential applications in various fields, including education, psychology, and human–computer interaction.

Businesses need good defenses against any number of incidents during the continually evolving area of Cybersecurity. SIEM (Security Information and Event Management) systems are now the important tools between them. The current study offers a comprehensive analysis of SIEM solu-tions, such as their key features, benefits, installation issues, and suggested procedures. Security Information and Event Management (SIEM) systems effectively store security event data, giving continuous tracking, interaction, and exam-ination to recognize and deal with threats rapidly. The advantages of this technology include enhanced operating efficiency, streamlined compliance with laws, expedited response to events, and heightened threat detection capabilities. However, the implementation of SIEM systems has many challenges that must be overcome, including intricacies, cognitive exhaustion, data inte-gration complications, and restrictions. To effectively handle these issues, businesses are advised to develop objectives, properly schedule, attend school, and periodically review and enhance their SIEM goals. In addition, organizations may use the complete capabilities of SIEM systems to en-hance their cybersecurity stance and mitigate the risks posed by cyber-attacks by staying updated with the most recent developments. This study aims to provide a comprehensive examination of Security Information and Event Management (SIEM) systems, with a specific emphasis on important features, benefits, implementation challenges, and suggestions.