Structured Query Language injection (SQLi) remains one of the most pervasive and dangerous threats to web-based systems, capable of compromising databases and bypassing authentication protocols. Despite advancements in machine learning for cybersecurity, many models rely on static detection rules or require extensive labeled datasets, making them less adaptable to evolving threats. Addressing this limitation, the present study aimed to design, implement, and evaluate a Deep Q-Network (DQN) model capable of detecting SQLi attacks using reinforcement learning. The research employed a Design and Development Research (DDR) methodology, supported by an evolutionary prototyping framework, and utilized a dataset of 30,919 labeled SQL queries, balanced between malicious and safe inputs. Preprocessing involved query normalization and vector encoding into fixed-length ASCII representations. The DQN model was trained over 2,000 episodes, using experience replay and an epsilon-greedy strategy. Key evaluation metrics—accuracy, cumulative reward, and epsilon decay—showed performance improvements, with accuracy increasing from 52% to 82% and stabilizing between 65% and 73% in later episodes. The agent demonstrated consistent adaptability by successfully generalizing across various injection patterns. This outcome suggests that reinforcement learning, particularly using DQN, provides a viable alternative to traditional models, with superior resilience and dynamic learning capabilities. The model's convergence trend highlights its practical application in real-time SQLi detection systems, contributing significantly to cybersecurity measures for database-driven applications.

Cross-site scripting (XSS) attacks remained among the most persistent threats in web-based systems, often bypassing traditional input validation techniques through obfuscated or embedded scripting payloads. Existing detection models typically relied on static rules or shallow learning techniques, limiting their ability to adapt to evolving attack vectors. This research addressed that gap by developing a hybrid detection framework that integrated natural language processing (NLP) and reinforcement learning (RL) techniques to classify and interpret malicious web inputs. The study aimed to design, develop, and evaluate a system that transformed raw input strings into structured features, trained a deep neural network (DNN) for binary classification, and simulated agent-based learning through policy-driven feedback. The methodology followed the Design Development Research (DDR) framework. Preprocessing involved lowercasing, lemmatization, stopword removal, and TF-IDF vectorization. The trained DNN achieved high accuracy and demonstrated clear boundary separability through PCA and t-SNE visualizations. In the simulation phase, the RL agent optimized its classification policy using cumulative rewards, Q-value heatmaps, and decision contour projections. Results confirmed the system’s capability to generalize across input variations while maintaining interpretability and precision. This framework provided a scalable solution for web application security and demonstrated the effectiveness of semantically guided and policy-aware models for detecting XSS threats.

This study addresses the challenges of administrative tasks and communication tracking at Visayas State University Alangalang (VSUA), highlighting the inefficiencies in the current manual processes. The objective is to develop an Integrated Communication Tracking Management Information System (iCTMIS) that enhances operational efficiency by integrating Optical Character Recognition (OCR) and Lempel-Ziv-Welch (LZW) Lossless and Zlib compression algorithms. By employing a developmental research design and ADDIE model, the system proves that there is an improvement on data analysis and reduces disk space through efficient compression. Significant findings reveal that OCR achieves up to 90% accuracy in text conversion, while LZW compressions substantially deflate data sizes. This was evaluated against ISO 9126 Software Quality Characteristics, the iCTMIS has shown to optimize storage and address VSUA's operational challenges effectively. This research therefore concludes that the systematic integration of advanced algorithmic frameworks in iCTMIS significantly enhances organizational communication and administrative workflows efficiency.

SQL injections remain one of the most persistent security risks in systems that rely heavily on database-driven operations. This study developed a compact neural-network classifier capable of distinguishing malicious SQL patterns from legitimate traffic by converting more than 30,000 labeled queries into 100-dimensional TF-IDF representations. The final model reached 98.8 % accuracy on the held-out test set, with a 97.3 % detection rate for malicious inputs and a 0.15 % false-positive rate, indicating strong generalization despite the moderate class imbalance in the dataset. To make the model's decisions easier to interpret, the framework includes several visual analytical tools—word frequency mapping, query-length distribution, PCA projection of embeddings, and a confusion-matrix display. In addition, the system introduces a reinforcement-learning-inspired decision diagram, not as a trained RL agent but as a conceptual visualization to illustrate how the classifier evaluates an incoming query. The results show that high detection accuracy can be paired with clear interpretability, making the approach suitable for institutions with limited cybersecurity resources.

Structured Query Language Injection (SQLi) attacks continue to pose a serious threat to web applications, especially those hosted in cloud-based environments. Traditional detection methods, such as signature-based and rule-based systems, often fail to detect obfuscated or evolving injection patterns. Despite the increasing use of deep learning techniques for SQLi detection, which are particularly effective in recognizing complex, obfuscated, and evolving SQL injection patterns. However, most studies remain limited to offline experiments without real-time system deployment. This research addresses that gap by developing and operationalizing a deep learning-based SQLi detection model integrated with FastAPI. The study aimed to design a classification model capable of distinguishing malicious from safe SQL queries using numerically encoded inputs. Following the Evolutionary Prototyping Model, the system was developed through data preprocessing, model training using TensorFlow-Keras, and deployment as an API. A total of 30,919 SQL queries were used, and the model achieved 97% training accuracy and 94.5% validation accuracy, supported by strong precision, recall, and F1-scores above 93%. Findings confirm the model’s high reliability and real-time responsiveness, with an average detection response under 50 milliseconds. The research demonstrates that integrating deep learning with lightweight API frameworks can result in a scalable and accurate solution suitable for web security systems. These results suggest practical implications for deploying intelligent cybersecurity tools in real-world cloud applications.

This research presents the development and implementation of MIS-GeoMAPA, a comprehensive Management Information System utilizing geospatial modeling and predictive algorithms for forest fire readiness and early warning in Leyte's Sab-a Basin Peatland (LSBP). Employing an iterative-waterfall development approach, we integrated real-time environmental sensor data, including temperature, humidity, wind speed, and soil moisture, with advanced geospatial analysis. Predictive models, particularly linear and logistic regression, were developed to forecast fire risks, achieving high accuracy validated through statistical tests like the Wilcoxon signed-rank test. The system’s performance, reflected in a Mean Squared Error (MSE) of 0.25 and an 88% accuracy rate, underscores its potential in enhancing fire preparedness and response. This study highlights the critical role of environmental monitoring and predictive analytics in mitigating forest fire impacts, offering a scalable solution for environmental management and disaster readiness.