Computer Engineering Commons^™

Investigating Intrusion Detection System Using Federated Learning For Iot Security Challenges, Mohammed Q. Mohammed, Zena Abd Alrahman, Aouf R. Shehab

Iraqi Journal for Computer Science and Mathematics

The Internet of Things (IoT) is a decentralized and ever-changing network, which poses challenges in terms of security. The input highlights the need for robust security measures to protect IoT devices and their data from potential threats. The study focuses on Federated Learning (FL) technology as a potential solution to enhance IoT security. FL models are designed to protect sensitive data while allowing its exchange with other systems, making it a promising approach for securing IoT environments. Additionally, the input suggests the implementation of intrusion detection systems (IDS) as an additional strategy to enhance overall IoT security. By combining FL …

Explainable Machine Learning Approach Enables Computer-Aided Identification System For Children Autism Spectrum Disorder (C-Asd), Karrar Hameed Abdulkareem, Zainab Hussein Arif, Mazin Abed Mohammed

Iraqi Journal for Computer Science and Mathematics

Neurodevelopmental disorders like autism spectrum disorder (ASD) cause significant cognitive, linguistic, object identification, communication, and social skills deficits. Although there is currently no cure for autism spectrum disorder (ASD), early detection can aid in diagnosis and implementing effective preventative measures. Artificial intelligence (AI) tools allow for an earlier diagnosis of ASD than was previously possible. Furthermore, many clinical and not clinical attributes can be used for identification of ASD but select the most proper ones still challenge. Therefore, in this study we propose a Computer-Aided Identification System based on machine learning concept and feature selection methods to diagnosis Children Autism …

Stable Heterogeneous Traffic Flow With Effective Localization And Path Planning In Wireless Network Connected And Automated Vehicles In~Internet Of Vehicular Things (Iovt), Ahmed N. Rashid, Ahmed Mahdi Jubair

Iraqi Journal for Computer Science and Mathematics

The increasing complexity of networks comprising both Connected Autonomous Vehicles (CAVs) and Human-Driven Vehicles (HDVs) presents substantial challenges in achieving accurate positioning, efficient communication, and optimal route planning. Current methodologies fall short in enhancing vehicular network efficiency and reliability due to noise interference, inefficient data transmission, and unstable data transfer. This study aims to improve localization accuracy, reduce communication noise, and enhance path planning efficiency in mixed CAV and HDV environments through the Stable Heterogeneous Traffic Flow using Deep Reinforcement Learning and Effective Path Planning (SHTDR-EPP) approach. The primary goals are to ensure dependable localization, efficient communication, and reliable route …

A Comprehensive Analysis Of Partition Dimensions In Efavirenz Abacavir Lamivudine Doravirine Of Anti-Hiv Drug Structures, R. Nithya Raj, R. Sundara Rajan, Hijaz Ahmad

Iraqi Journal for Computer Science and Mathematics

The partition dimension of a graph in chemical graph theory refers to a graph invariant used to analyze the structural properties of molecules. It represents the minimum number of clusters or resolving partition set required to uniquely identify each vertex in the graph based on the neighborhoods within their respective clusters. In the context of chemical graph theory, the vertices of the graph correspond to atoms, and edges represent bonds between these atoms in a molecular structure. Determining the partition dimension of a chemical graph helps in understanding the relationships between molecular components and their spatial arrangements. It assists in …

Embedded Schemes Of The Runge-Kutta Type For The Direct Solution Of Fourth-Order Ordinary Differential Equations, F. A. Fawzi, Nizam G. Ghawadri

Iraqi Journal for Computer Science and Mathematics

This paper introduces an innovative approach for solving fourth-order ordinary differential equations (ODEs) of the form. We present the embedded Runge-Kutta (RK) Direct Explicit (ERKDGF) method, a family of embedded direct explicit RK type methods tailored specifically for this purpose. Through meticulous application of Taylor expansion, we have derived algebraic equations with order conditions up to the sixth order, ensuring the accuracy and reliability of our proposed integrator. We have developed two key variants within this method, namely RKDF5(4) and ERKDGF5(4), with orders five and four, respectively. Our approach is strategically designed, with the higher-order method ensuring exceptional accuracy, and …

Robust-Fragile Watermarking Using Integer Wavelet Transform For Tampered Detection And Copyright Protection, Hendra Budi, Ferda Ernawan, Agit Amrullah

Iraqi Journal for Computer Science and Mathematics

The use of the internet and advanced technologies enables the distribution of information and data through diverse digital images. Nevertheless, this ease of use comes with the potential risk of data misappropriation, encompassing unauthorized alterations, duplications, and reproductions of digital images. Ongoing research is being conducted in the field of watermarking to enhance the capabilities of protecting digital images. The objective of this work is to enhance the strength of copyright protection and the vulnerability of watermarking for authentication in digital images by utilizing the Integer Wavelet Transform (IWT). The watermarking approach involves embedding a durable watermark in the red …

Modelling Security Factors Influencing E-Wallet Adoption In Malaysia, Adi Badiozaman Ruhani, Nur Suhaili Mansor, Hapini Awang, Mohamad Fadli Zolkipli, Khuzairi Mohd Zaini, Abderrahmane Benlahcene

Iraqi Journal for Computer Science and Mathematics

This study aims to develop an effective framework that addresses the security concerns and user behavior related to e-wallet adoption. The research methodology entails quantitative data collection through a literature review and surveys of e-wallet users using convenience sampling, and the proposed model is tested using the Partial Least Squares Structural Equation Modelling (PLS-SEM). The proposed security factors in this study include phone stolen protection, app security performance, secure authentication, data privacy protection, secure online transaction and banking info security. The online survey form was disseminated to Malaysian citizens, and 186 respondents participated in the survey. Using a two-step approach, …

Robust Image Watermarking Based On Schur Decomposition, Ahmad Toha, Ferda Ernawan, Agit Amrullah

Iraqi Journal for Computer Science and Mathematics

The advanced of internet technology allows unauthorized people to distribute multimedia data. Copyright protection for digital images is needed to protect the intellectual properties of the digital image. This study presents a colour image watermarking using schur decomposition for protecting the digital copyright. This study investigates the significant contribution of the orthogonal U of schur decomposition with the size of 8´8 pixels. The proposed scheme embeds a watermark on the (U₂, U₆) of the U matrix to achieve high invisibly and robustness of the embedded watermark. The relationship of each coefficient on the U matrix …

Image Watermarking Using Firefly Algorithm–Iwt-Svd For Copyright Protection, Anjahul Khuluq, Ferda Ernawan, Agit Amrullah, Mohd Arfian Ismail

Iraqi Journal for Computer Science and Mathematics

Image watermarking is a technique used to ensure the legitimacy of ownership by safeguarding images. This research presented the Firefly algorithm–IWT-SVD to enhance resistance and robustness performance against different type of attacks. The cover image is split into blocks of 4×4 pixels, and each block is then computed by IWT-SVD. The Firefly algorithm is used to determine the appropriate scaling factor to incorporate the watermark using a predefined set of principles. The watermarked images have been evaluated under various attacks such as noise addition, filtered image, compressed image and scaled image. The experimental results demonstrate exceptional imperceptibility, with an average …

Robust Image Watermarking Based On Iwt-Dct-Svd For Copyright Protection, Syafiqul Shubuh, Ferda Ernawan, Agit Amrullah, Prajanto Wahyu

Iraqi Journal for Computer Science and Mathematics

The rapid advancement of technology has resulted in many intellectual works, in the form of images requiring copyright protection to prevent unauthorized use by irresponsible parties. This research examines the hybrid watermarking method that utilises IWT-DCT-SVD domain to enhance the durability of the embedded watermark. The host image is used as the input for the R-Level process, if the watermark logo is small, then the cover image is computed by 3-level of IWT. Whereas, the watermark logo has a large size, the cover image is then computed by 1-level of IWT. The watermark logo is embedded into the singular value …

Automated Fake News Detection System, Saja A. Al-Obaidi, Tuba Çağlıkantar

Iraqi Journal for Computer Science and Mathematics

Online news has been the majority of people’s information source in recent decades. However, a lot of the information that is accessible online is fake and sometimes even designed to mislead. It might be difficult for individuals to distinguish between certain false newspaper items and the real ones since they are so similar. Deep learning (DL) and machine learning (ML) models, among other automated false news detection (FND) techniques, are quickly becoming essential. A comparative study was conducted to analyze the performance of five prominent deep learning models across four distinct datasets, namely ISOT, FakeNewsNet, Dataset1, and Dataset2. Results indicated …

Posinormality Of Operators Treated By Weyl's Theorem On Unbounded Hilbert Space, Abbas G. Rajij, Dalia S. Ali, Huseyin Cakalli, Nadia M. G. Al-Saidi

Iraqi Journal for Computer Science and Mathematics

Hamiltonians, momentum operators, and other quantum-mechanical perceptible take the form of self-adjoint operators when understood in quantized physical schemes. Unbounded and self-adjoint recognition are required in the situation of positive measurements. The selection of the proper Hilbert space(s) and the selection of the self-adjoint extension must be made in order for this to operate. In this effort, we define a new extension positive measure depending on the measurable field of nonzero positive self-adjoint operator in unbounded Hilbert space of analytic functions of complex variables. Consequently, we define an extension norm in the same space. We show several new properties of …

Uniform 3d Scattering Point Model For Simulating The Dynamic Radar Echo From Wind Farm, Bo Tang, Zhendong Zhu, Zhiyu Shang, Huanghai Xie, Feng Wang, Jiaxu Chen

Turkish Journal of Electrical Engineering and Computer Sciences

The calculation scale of simulating wind farm dynamic radar echo is gradually growing with the increasing scale of wind farms, which can hardly meet the requirements of real-time radar echo simulation. Considering that the method of surface element division can greatly influence the result of simulation, uniform surface element division is applied to accelerate the traditional simulation algorithm based on the refined 3D scattering point model and enhance the main characteristics of the radar echo. The solution time of dynamic radar echoes from 1-8 wind turbines is calculated to test the average speed that the uniform 3D scattering point model …

An Improved Conditional Integrator Sliding Mode Controller Based On Swarm Intelligence For A Magnetic Levitation System, Abdelkader Kerraci, Mohamed Fayçal Khelfi, Zoubir Ahmed-Foitih

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposes an enhanced Conditional Integrator Sliding Mode Controller using Particle Swarm Optimization (CISMCPSO) for a magnetic levitation system (MLS). The main advantage of this controller is its robustness to uncertainties and disturbances, which also avoids chattering and ensures zero static steady-state error. The main idea of CISMCPSO is to activate its integral action only when the sliding surface reaches the boundary layer while it is reduced to zero or close to zero elsewhere, which avoids destroying the transient response caused by the conventional integral sliding-mode controller. A particle swarm optimization algorithm schedules the conditional integral term parameter of …

In-Situ Superconductor Temperature Sensor For Cryogenic Integrated Circuits, Emre Küçükyilmaz, Nazi̇f Orhun Tekci̇, Sasan Razmkhah, Ali̇ Bozbey

Turkish Journal of Electrical Engineering and Computer Sciences

Cryogenic circuits, such as those based on single flux quantum (SFQ) logic, function at extremely low temperatures. Therefore, the designs target the utilization of liquid helium (LHe) temperatures, maintaining them at 4.2 K. These specialized circuits can be subjected to measurement either within liquid helium (LHe) baths or enclosed within closed-cycle cryocoolers.However, when utilizing LHe in cryocooler systems, inherent weak thermal contact can lead to temperature gradients between the circuit chip and the cold head, where conventional temperature sensors are typically placed. To address this challenge, this study introduces an innovative on-chip temperature sensing approach that capitalizes on the temperature …

A Surface-Based Approach For 3d Approximate Convex Decomposition, Onat Zeybek Kuşkonmaz, Yusuf Sahi̇lli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Approximate convex decomposition enables the simplification of complex shapes into manageable convex components. In this work, we propose a novel surface-based method to achieve this which leads to efficient computation times and sufficiently convex results while avoiding over-approximating the input model. We start approximation using mesh simplification. Then we iterate over the surface polygons of the mesh and divide them into convex groups. We utilize planar and angular equations to determine suitable neighboring polygons for inclusion in forming convex groups. To ensure our method outputs a sufficient result for a wide range of input shapes, we run multiple iterations of …

A New Dxccdita Based Meminductor Emulator And Its Application In Chaotic Oscillator, Bhawna Aggarwal, Shireesh Kumar Rai, Harsh Jain

Turkish Journal of Electrical Engineering and Computer Sciences

This work introduces a new dual-X current conveyor differential input transconductance amplifier (DXCCDITA) based meminductor emulator, alongside its application in chaotic oscillator has also been presented. To realize the designed meminductor emulator, one DXCCDITA, two resistors, and two capacitors are employed. Pinched hysteresis loops are achieved across a wide frequency range spanning from 100 Hz to 1.5 MHz, encompassing both decremental and incremental topologies. Additionally, the proposed circuit offers the flexibility to switch between incremental and decremental configurations using a simple switch. Through examination of non-volatility and transient responses, the efficiency of the presented emulator is evidently demonstrated. To further …

Fault Diagnosis Of Photovoltaic Array Based On Gated Residual Network With Multi-Head Self Attention Mechanism, Ahmed Mesai Belgacem, Mounir Hadef, Abdesslem Djerdir

Turkish Journal of Electrical Engineering and Computer Sciences

Effective fault identification and diagnosis in photovoltaic (PV) arrays is vital for improving the effectiveness, and safety of solar energy systems. While various artificial intelligence methods have successfully established fault detection and diagnosis models, introducing inefficiencies and potentially overlooking useful features. Moreover, these methods often employ neural networks with limited performance capabilities. In response to these challenges, this paper introduces an innovative intelligent model that integrates a combination of a gated residual neural network (GRN) and a multi-head self-attention mechanism (MHSA). To evaluate the proposed fault diagnosis model, the small-scale PV grid system is implemented, and fault simulation experiments, including …

Developing Linguistic Patterns To Mitigate Inherent Human Bias In Offensive Language Detection, Toygar Tanyel, Besher Alkurdi, Serkan Ayvaz

Turkish Journal of Electrical Engineering and Computer Sciences

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is crucial to prevent offensive language from being widely shared on social media. However, the accurate detection of irony, implication, and various forms of hate speech on social media remains a challenge. Natural language-based deep learning models require extensive training with large, comprehensive, and labeled datasets. Unfortunately, manually creating such datasets is both costly and error-prone. Additionally, the presence of human-bias in offensive language datasets is a major …

A Cascade Genetic Algorithm Based Adaptive Backstepping Impedance Control For Upper Limb Rehabilitation Robot, Mawloud Aichaoui, Ameur Ikhlef

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposes a novel cascade impedance control architecture designed for the upper limb exoskeleton rehabilitation robot. The proposed architecture comprises two parts: Firstly, the impedance reference trajectory is shaped from the desired trajectory utilizing the desired impedance model and feedback contact torques. The second part of the proposed controller is an adaptive backstepping control, responsible for tracking the generated impedance reference trajectory. Notably, the proposed adaptive backstepping impedance controller is non-model-based control approach, eliminating the need for the robot's model. Furthermore, a genetic algorithm is employed as an offline tuning method for the inner position loop controller, namely the …

Lgformer: Informer-Based Personalized Modeling For Blood Glucose Prediction, Xue Yuewei, Shaopeng Guan, Jia Wanhai

Turkish Journal of Electrical Engineering and Computer Sciences

Effective diabetes management relies on precise prediction of blood glucose levels to minimize complications. However, the patterns and fluctuations in blood glucose vary significantly among patients, posing a challenge for existing prediction methods. Many current approaches fail to accommodate these individual differences, leading to less reliable predictions. In response to this challenge, we present LGformer, a novel prediction model based on the Informer architecture, designed to enhance both flexibility and accuracy. LGformer improves upon Informer by integrating LSTM and GRU layers into its probSparse Self-attention mechanism, allowing for personalized processing of blood glucose data tailored to each patient's unique profile. …

Towards Human-Machine Collaboration In Autonomous Material Handling On Construction Sites, Jyrki Oraskari, Lukas Kirner, Marit Zöcklein, Sigrid Brell-Cokcan

Human-Machine Communication

In the contemporary construction industry, the shortage of skilled labor has prompted the exploration of automation as a remedy and machine autonomy as a potential solution to the environmental conditions at the site. This research explores the balance between human oversight and the independent decision-making capabilities of robots for material delivery on construction sites. Using a scenario-based approach, autonomy in construction robotics is evaluated across four human-machine interaction cases with spatial and temporal dimensions. The expected outcomes revolve around improved safety through better human-machine communication and establishing an interoperable data model to enhance robot autonomy. This aims to automate tasks …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

Model-Based Navigation And Control Of Multirotor Uavs: A Machine Learning Approach, Serhat Sönmez

Electronic Theses and Dissertations

In recent decades, unmanned systems, particularly Unmanned Aerial Vehicles (UAVs), have seen significant advancement and unprecedented growth in military, civilian and public domain applications. Scientists have focused on enhancing UAV navigation and control through cutting-edge technologies and support tools. UAVs find applications in many fields, except military, such as agriculture, infrastructure inspection, wildlife monitoring, search and rescue, emergency response, border protection, to name but a few relevant civilian applications. Given the faster-than-exponential increase of available computational power, learning-based algorithms have emerged as a prominent tool for (real-time) multirotor UAV navigation and control. This dissertation centers around the fusion of conventional …

Security Vulnerabilities In Mobile Operating Systems Used In Iot Devices: An Examination Of Current Challenges And Countermeasures, Isain Cortes Jr.

Cybersecurity Undergraduate Research Showcase

No abstract provided.

Utilizing A Hybrid Apprach To Link Maternal And Neonatal Records, Vidhani S. Goel, Ana Reyes, Bertille Assoumou, Dodds P. Simangan, Farooq Abdulla, Megumi Akiyama, Deborah A. Kuhls, Kavita Batra

Undergraduate Research Symposium Posters

Linkage of independent datasets allows comprehensive and robust analysis. This study aims to utilize a hybrid strategy to link maternal records with neonatal data with an overarching goal of investigating correlates of adverse birth outcomes.

To link 126,757 records from Nevada Medicaid with 249,181 maternal records from Birth Registry, a hybrid linkage approach was utilized. Data normalization was first performed for the standardization of linkage keys. First, a deterministic approach was used to link these records using a unique identifier followed by a fuzzy or probabilistic algorithm using a set of block variables. These block variables included date of birth, …

Transferred-Learning Intrusion Detection System For Internet Of Vehicles, Tan Nguyen

Undergraduate Research Symposium Posters

The growing connectivity of modern vehicles, particularly within the Internet of Vehicles (IoV), has significantly increased the need for robust cybersecurity solutions. Building upon the work of Yang and Shami (2022), who proposed a transfer learning and optimized convolutional neural network (CNN)-based Intrusion Detection System (IDS) for IoV, this research seeks to validate their results and explore potential enhancements. The original IDS demonstrated exceptional performance, with detection rates surpassing 99.25% on benchmark datasets. In this study, we first replicate their experiments using the Car-Hacking dataset to confirm the effectiveness of the proposed model and then evaluate its ability to detect …

Integrating Humanities Into Cybersecurity Education: Enhancing Ethical, Historical, And Sociopolitical Understanding In Technical Training, Joseph Frusci

Journal of Cybersecurity Education, Research and Practice

The increasing complexity of cybersecurity challenges necessitates a holistic educational approach that integrates both technical skills and humanistic perspectives. This article examines the importance of infusing humanities disciplines such as history, ethics, political science, sociology, law, and anthropology—into cybersecurity education. Through a pilot course developed for Staten Island Technical High School, aligned with the New York State K-12 Computer Science and Digital Fluency Standards, students were introduced to an interdisciplinary curriculum that combined technical cybersecurity training with historical analysis, ethical reasoning, and sociopolitical context. The results of pre- and post-course assessments demonstrated significant improvements in critical thinking, ethical decision-making, and …

Forensicllm: A Local Large Language Model For Digital Forensics, Binaya Sharma

LSU Master's Theses

Large Language Models (LLMs) excel in diverse natural language tasks but often lack specialization in fields like digital forensics. Their reliance on cloud-based APIs or high-performance computers restricts their use in resource-limited environments, and response hallucinations could compromise their applicability in forensic contexts. We introduce ForensicLLM, a 4-bit quantized LLaMA-3.1-8B model fine-tuned using Retrieval Augmented Fine-tuning (RAFT) on 6,739 Q&A samples extracted from 1,082 digital forensic research articles and curated digital artifacts. Evaluation on 2,244 Q&A samples showed that ForensicLLM outperformed the base LLaMA-3.1-8B model by 4.06%, 5.43%, and 15.79% on BERTScore F1, BGE-M3 cosine similarity, and G-Eval, respectively. Compared …

Robotic Multi-Object Grasping From A Pile: Techniques And Algorithms For Enhanced Dexterity, Tianze Chen

USF Tampa Graduate Theses and Dissertations

As robots become increasingly integrated into real-world applications such as warehousing, fulfillment centers, and manufacturing, the need for efficient and adaptable robotic systems grows. One of the key challenges is enabling robots to grasp multiple objects simultaneously, as this significantly boosts the efficiency of tasks like batch picking, sorting, and object transferring, reducing both time and energy consumption. This dissertation presents a comprehensive multi-object grasping (MOG) pipeline that includes pre-grasp selection, end-pose selection, grasping synergy calculation, and a data-driven model for estimating the number of objects being grasped. Central to this work is the development of the Experience Forest structure, …