ASPG

Identify and Remove Duplicated Records Using Q-gram and Statistical Techniques from the Data Warehouse

Sura Mahroos , Rihab Hazim , Yaqeen Saad , Nadia Mohammed

There are several real-world uses for the duplication system or record linkage. In order to help the system make the best judgments, it appears in a broad area of recognizing similar data, joining online papers in the wide web, detecting plagiarism, and allowing several applications to enter it. To improve the financial interest and applicability of logistics project, routing is crucial. The following is the issue with this study: Because duplicate receipts contain the same significant change in data restrictions and limitations, and the data change itself is minor, the duplicate record data is ambiguous to other redacted records that are reassembled with the same customer. The purpose of this study is to use statistical techniques and the Q-gram to discover the best method for the detection and removal of duplicate records. We propose the following goals to help achieve that goal: Reduce the size of the data warehouse (DW) by providing a data warehouse free of duplicates. Decrease the amount of time spent looking for the (DW) and improve the DSS. The approach is divided into two stages: first, identify similarity records based on Q-gram similarity; second, determine whether classification records may be improved by statistical methods. The percentage threshold of 0.68 has been determined. It goes through a statistical process that decides whether this record is duplicated if the key ratio similarity is surpassed. The accuracy of the suggested work is 79%.

Vol. 17 Issue. 1 PP. 01-09, (2026)

Clustering and Classification of IoT-Based Environmental Data Using Machine Learning Techniques

Ali Subhi Alhumaima , Waleed Khalid Al-Zubaidi , El-Sayed M. El-Kenawy , Marwa M. Eid

In this study, we present an integrated approach to IoT-based environmental data analysis using a collection of unsupervised-learning techniques. We employed KMeans clustering in particular to identify natural groupings in environmental and behavioral features such as air quality, noise level, temperature, stress level, sleeping hours, and mood score. We then trained a Decision Tree classifier to predict and interpret cluster membership from raw sensor readings. The data of more than 30,000 observations in indoor school environments has multifaceted relationships between environmental factors and psychological well-being. KMeans consistently detected three environmental-behavioral states, and the Decision Tree classifier performed 87% classification accuracy, which indicated extremely high predictability power in addition to interpretability. The results indicated that sleep duration, air, and stress were the main factors for cluster discrimination. The hybrid model introduces the potential of observing real-time environmental and mental states for applications in smart cities. The approach is scalable, interpretable, and usable in IoT settings for proactivity-enabled wellness management.

Vol. 17 Issue. 1 PP. 10-20, (2026)

A Novel Hybrid CNN-LSTM Framework for Robust DDoS Attack Detection and Classification

Ammar O. K. Al-Hasani , Islam R. Abdelmaksoud , Amira Rezk

Distributed Denial of Service (DDoS) assaults could be the most prevalent and impactful cybersecurity threats, aiming to disrupt networking services and stop legitimate users from getting access to the service. This paper presents a novel hybrid deep learning framework that employs Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) networking to get long-term dependencies within network traffic. In the experiments on the CIC-DDoS-2019 database, a good classification performance of the proposed model is achieved with accurateness of 99.63%, preciseness of 99.24%, recall of 99.22%, F1 score of 99.22%, and Micro-AUC of 99.71%, surpassing traditional machine learning models such as LGBM, DNN, and standalone CNN and LSTM. In addition, Fuzzy Logic was implemented for risk management using three risk categories low, medium, and high .The findings uncovered that the proposed hybrid CNN-LSTM model gives the best evaluation metrics, despite the complexity and imbalance of the dataset classes. This is due to the capability of the model to combine special and non-permanent features out of the data. The proposed model also is proven to support integration in the whole system including time detection, blocking and alerting, such that it is considered a powerful system for network security.

Vol. 17 Issue. 1 PP. 21-34, (2026)

Integration of Information Technology in a Compact Neural Network Model for Real-Time Monitoring of Seagrass

Atyaf Sami Noori

Monitoring seagrass ecosystems offers critical insights into water quality, which is essential for maintaining aquatic biodiversity. Real-time monitoring, however, is hindered by various challenges, including coral reef degradation, habitat deterioration, fishing impacts, seagrass dredging risks, and complex coastal management issues. To overcome these barriers, this study presents an improved neural network model enhanced by Information Technology (IT) and Artificial Intelligence Neural Networks (AINN). Specifically, a recurrent neural network (RNN) has been utilized to address fishing pressures and habitat issues by evaluating sediment stability within seagrass areas. Additionally, a modular neural network (MNN), leveraging IT support, effectively analyzed coral reef deterioration to promote ecological sustainability. A convolutional neural network (CNN) was further implemented to enhance risk assessment and facilitate optimal seagrass growth conditions, thus improving real-time monitoring accuracy. Results indicated that this integrated IT-based neural network significantly surpassed traditional CNN methods, achieving superior performance in seagrass monitoring and coastal ecosystem management.

Vol. 17 Issue. 1 PP. 35-50, (2026)

Using Artificial Intelligence Techniques to Enhance the Performance of Control Systems in Solar Power Plants

Ahmed Abdul Mahdi Alawsi , Ahmed M. Ali Ali

This study examines the potential benefits of AI. It also addressees enhancing the performance of plants powered by solar and defending them against cyberattacks. Old controllers like PID and fuzzy logic work well in old places, and have no built in protection against cyber hackers that want to steal data, get into your control system, or obtain system access credentials. Artificial Neural Networks (ANN) and Reinforcement Learning (RL) are instances of AI-driven pattern stick to establishing fast adjustments on the fly, thus inducing non-normal behavior in controllers. This work uses AI to build models that predict solar flux on a surface and adjust input parameters in real time. In addition, it delivers security sensitive capabilities through pattern-driven analysis and alerting. MATLAB/Simulink simulations are used to demonstrate the efficacy of the approach, and it is compared with different methods in terms of power generation, time of response, power loss, stability, and quality of control. The ANN model made very good predictions, and the RL methods increased the flexibility and security of the system. According to the outcomes, the inclusion of AI into the system not only makes it more efficient in terms of producing energy but also renders it invulnerable to hackers or any other operational risks. This blog post discusses the need to secure AI-based energy systems with intelligent security. It also adds that future studies should explore the convergence of AI and cyber security in safeguarding critical infrastructure.

Vol. 17 Issue. 1 PP. 51-61, (2026)

Machine Learning Model in Satellite Data Security Analysis using Remote Sensing Network

Gagan Kumar Koduru , P. Chinnasamy , S. Kalaimagal , Karri Nagaraju , V. Bhaskara Murthy , Shivanadhuni Spandana , M. Rajesh

Over uncovered and under-covered areas, satellite communication provides the potential for ubiquity, scalability, and service continuity. However, before these benefits may be fully realized, a number of obstacles need to be overcome. Satellite networks present more difficulties than terrestrial networks in terms of spectrum management, energy consumption, network control, resource management, and network security. The goal of this research is to create a novel way to remote sensing network security modelling by utilizing machine-learning techniques to analyses the security of satellite data. In order to provide an intrusion detection technique for the modern network environment, this study considers data from both terrestrial and satellite networks. Here the remote sensing network security analysis is carried out using quantum federated encryption algorithm and data security has been analysis by quantile regression adversarial convolutional neural networks. Experimental analysis has been carried out in terms of data integrity, latency, random accuracy, QoS, AUC. Proposed technique Data integrity of 93%, LATENCY of 95%, QOS of 96%, random accuracy of 98%, AUC of 92%.

Vol. 17 Issue. 1 PP. 62-70, (2026)

Secure Honeynet Cloud IoT Model and Machine Learning based Smart Healthcare System with Urban Management

S. Pavithra , Venkatesan S. , Yerragudipadu subbarayudu , Keshav Sinha , Rayavarapu Sridivya , Munugapati Bhavana

Smart health is becoming an increasingly sensitive field because to the growing use of a variety of Internet of Medical Things (IoMT) devices as well as apps. IoMT is a well-liked technique for developing smart city solutions that eventually improve critical infrastructures, such smart healthcare. Numerous IoMT devices in smart cities employ Bluetooth technology for short-range communication because it is adaptable and resource-efficient. This research proposes novel method in urban planning in smart public healthcare system utilizing ML algorithms. The smart healthcare system is developed based on secure honeynet cloud IoT model. Here the input smart healthcare-based health monitoring data is collected and processed for missing value removal and noise removal. Then this data classified and optimized using recurrent Bi-LSTM temporal Gaussian model with whale swarm particle colony optimization. Experimental analysis is carried out in terms of detection accuracy, precision, data integrity, throughput, recall, latency. Proposed technique obtained 96% of Detection    accuracy, 97% of Precision, 95% of Throughput, 88% of RECALL, 94% of LATENCY.

Vol. 17 Issue. 1 PP. 71-80, (2026)

Journal of Cybersecurity and Information Management

Journal DOI

Journal Menu

Journal Volumes

Volume 0

Volume 1

Volume 2

Volume 3

Volume 4

Volume 5

Volume 6

Volume 7

Volume 8

Volume 9

Volume 10

Volume 11

Volume 12

Volume 13

Volume 14

Volume 15

Volume 16

Volume 17