AlKadhum Journal of Science
Not a member yet
50 research outputs found
Sort by
LV2PA: A Lightweight Verification with Privacy-Preserving Authentication for Vehicular Communications
No full text Security and privacy must be taken into account for vehicular ad-hoc networks (VANETs) due to the fact that broadcasting occurs through an open communication channel. This work offers a Lightweight Verification with Privacy-Preserving Authentication (LV2PA) approach for vehicular communications to overcome these challenges. To satisfy security and privacy requirements, the proposed LV2PA approach employs not only the cryptographic hash function, but also a Bloom filter and the Chinese remainder theorem. During the mutual authentication of the LV2PA scheme, only the first roadside unit (RSU) and on-board unit are required to communicate with a trusted authority (TA) due to the changeover use, however the other RSUs in vehicular communications do not require TA communication. Consequently, bottleneck problems for the TA are avoided. In addition, the RSU updates the shared group key whenever a vehicle joins or departs the group; hence, the proposed LV2PA provides complete forward secrecy and backward secrecy for vehicular communications. The formal (Burrows–Abadi–Needham (BAN) logic) and informal security analyses demonstrate that the proposed LV2PA scheme is legitimate and meets the security and privacy requirements, respectively. In terms of computing and communication expenses, the performance evaluation of the proposed LV2PA scheme has advantageously low overhead and low latency compared to state-of-the-art scheme
AI- Techniques for Decoding Language Representation from EEG-Based Brain Activity: A Comprehensive Review
No full textتتناول هذه الورقة الشاملة تقنيات الذكاء الاصطناعي لفك تشفير اللغة وتمثيلها اعتمادًا على نشاط الدماغ كما يتم قياسه بواسطة تخطيط كهربية الدماغ (EEG)، وهي طريقة شائعة وغير جراحية وتتميز بدقة زمنية عالية لتسجيل النشاط العصبي في الدماغ أثناء معالجة اللغة. وتواجه هذه التقنية عدة تحديات، أبرزها التعامل مع الضوضاء والتعقيد في الإشارات. كما تستعرض الورقة التقدم الكبير في تحليل هذه الإشارات باستخدام تقنيات التعلم الآلي التقليدية مثل آلات المتجهات الداعمة (SVM) والغابات العشوائية (RF)، بالإضافة إلى تقنيات التعلم العميق مثل الشبكات العصبية الالتفافية (CNN) وشبكات الذاكرة طويلة وقصيرة الأمد (LSTM) والمحوّلات (Transformers). وتناقش الورقة أيضًا التطبيقات الرئيسية لهذه التقنيات، مثل توفير أدوات تواصل للأشخاص ذوي الإعاقات، والتشخيص والعلاج الطبي، وفهم الإدراك اللغوي، إلى جانب التحديات المرتبطة بجودة البيانات وتكلفتها وتعقيدها والقضايا الأخلاقية. كما تقدم الورقة رؤى مستقبلية واعدة حول دمج تقنيات متعددة، والتنبؤ بالحالات العصبية والمعرفية، وتطوير واجهات متقدمة بين الدماغ والحاسوب، مما يمهد الطريق لفهم أعمق لآليات معالجة اللغة في الدماغ.This comprehensive paper examines artificial intelligence techniques for decoding and representing language from brain activity, as measured by electroencephalography (EEG), a common, non-invasive, and high-temporal-resolution method for recording neural activity from the brain during language processing. This technique faces several challenges in dealing with noise and complexity. It also reviews the significant progress in analyzing this signal using traditional machine learning techniques such as SVM, RF, as well as deep learning techniques like CNN, LSTM, and Transformers. This paper also discusses the main applications of these technologies in providing communication tools for people with disabilities, medical diagnosis and treatment, understanding linguistic perception, as well as the challenges related to data quality, cost, complexity, and ethical issues. It also offers promising future insights into the integration of multiple technologies, predicting neurological and cognitive conditions, and developing advanced brain-computer interfaces, paving the way for a deeper understanding of language processing mechanisms in the brain.
 
Medical Image Improvement Using a Proposed Algorithm
No full textThe clarity of medical images is important nowadays because it will be based on the diagnosis of the patient\u27s situation diagnosis, the phase of the disease, and give an appropriate treatment to him. The objective of the present study is to clarify the edges of the colored medical images by boosting thickness to dispose of the soft edges and some places that do not appear when the edge is determined. It can convert from RGB to HSV and then display the resulting image in the color space (HSV)set the edges of this image and add it to the image in space (HSV) then convert the resulting image from the color space (HSV) to RGB). Use this algorithm to optimize images by Matlab2020a. This proposed method can be applied to all types of medical images such as (MRI, Ultrasound, X-ray, ... etc.) colored and gray, with any size and any part of the human body. The results give high resolution in the resulting images if showed an increase in the consistency of the resulting images
A Review of Encryption Algorithms for Enhancing Data Security in Cloud Computing
No full textCloud computing is one of the most rapidly evolving technologies today; it provides numerous advantages that increase its affordability and dependability for use in the company. This paper goes over the concepts of cloud computing, such as its characteristics, deployment model, and service model, discusses the various benefits of cloud computing, and highlights the most pressing issues and security concerns in cloud storage. As a consequence, that leads to a review of distinctive cryptography algorithms that meet the security requirements (CIA: confidentiality, integrity, and availability) that are used to secure communications in cloud computing situations. It also displays many algorithms depending on the previous studies, such as Blowfish, RSA, DES, AES, MD5, Feistel, SP, HIGHT, LED, Cybpher, PRESENT, RC6, Diamond2, mCrypton, SLIM, Klein, PUFFIN-2, SEA, CLEFIA, LBlock, TWINE, 2, ANU, ANU-II, NLBSIT, Piccolo, BORON, RECTANGLE, LICI, QTL, LOGIC, TRIVIUM, Fruit-v2, Fruit-80, A4, the Enocoro family, and Grain family, to make a comparison among them using many measurements. It found that modern and lightweight algorithms are more suitable for use in this field. Furthermore, the purpose of this paper is to make some suggestions for improving the safety and security of cloud computing technologies
Improving Communication Performance Through Fiber Amplifier EDFA
No full textDue to the development of fast and extensive data communication methods, typical erbium-doped fiber amplifiers (EDFA) have recently gained much interest. The main advantage of EDFA is its ability to build a system with a broad band. However, it is evident from documented works that using EDFA results in a gain increase. Nevertheless, the expense, complexity, and subpar effectiveness of these procedures made them ineffective. In this work, the performance of an 8-channel communication system for different distances of 80, 120, and 180 km is enhanced and maximized by applying a simulation model of long distance based on EDFA to reduce the effects of dispersion correction. The effect of the EDFA on three channels was investigated along the three distances by Q Factor and BER. The proposed system achieved good results in enhancing signals due to EDFA. The results of the extraction demonstrate the system\u27s capacity to send large data rates to 180 km with a bit error rate of less than 1×10-14. EDFA shows the best performance in gain differences. The simulation setup and implementation of the work aim to improve communication performance and propose a suitable solution to enhance the Bit Error Rate (BER)
Transmission of High Data Rate Signals over Low-Frequency Passbands Using (DSSS-BPSK) Technique
No full textThis study presents an enhancement to the Direct Sequence Spread Spectrum (DSSS) algorithm aimed at transmitting high data rate signals over low-frequency passbands. By utilizing a random number to generate a new encryption key, the complexity of both encryption and decryption processes is significantly increased. The original signal undergoes multiplication with a spreading code, resulting in a random matrix that obscures the original data and enhances security. The research employs Binary Phase Shift Keying (BPSK) modulation to effectively transmit the spread signal, optimizing bandwidth utilization and mitigating channel impairments. Simulation results conducted using MATLAB demonstrate that the proposed DSSS method achieves low Bit Error Rates (BER) under various conditions, confirming its robustness against interference. Furthermore, the findings indicate that the combination of high data rate transmission and low-frequency passbands using DSSS has promising applications in diverse fields such as industrial automation, remote sensing, and military communications. Overall, this research contributes to advancing secure and efficient communication systems by leveraging DSSS techniques.
Intelligent Agent-Based Architecture for Low-Light Image Enhancement Using an A3C Framework
No full textLow-light image enhancement (LLIE) is an important area of research as many applications such as photography, video surveillance, and security are confronted with image degradation in low-light environments. This paper presents an intelligent agent-based method for LLIE using the Asynchronous Advantage Actor-Critic (A3C) framework. The enhancement task is effectively cast in this work into the framework of a Markov Decision Process. This method enables an agent to learn a policy that successively improves image quality. In the agent, features are extracted by a Fully Convolutional Network (FCN), a policy network for choosing an action, and a value network for estimating the reward. In training, non-reference loss functions are also used to measure image quality without the availability of the reference image or ground truth images. Such functions include spatial consistency loss, exposure control loss, and illumination smoothness loss, and the approach achieves end-to-end enhancement without reference image. The experimental results on LOL and MIT-Adobe dataset also show that the proposed technique enhances image brightness, Contrast, and structure much better as compared to other state-of-the-art methods. Especially, the methodology proposed scored 25.93 PSNR, 0.932 SSIM, and 0.053 LPIPS on the LOL dataset, achieving better results than related strategies. The designed agent-based approach works under a wide range of low-light situations. This approach allows obtaining enhancement results that will be satisfactory in terms of the users’ preferences and needs of the specific applications. The findings highlight the method\u27s robustness and flexibility, making it suitable for various practical applications. This work demonstrates that reinforcement learning agents have promising applications in improved image processing capabilities, and establishes a new record for low-light image improvement.
Diabetes Multiclass Prediction Using Ensemble Learning Techniques
No full textDiabetes is one of the most prevalent diseases in the modern era, leading to a significant number of deaths annually, as reported by the World Health Organization. Early prediction of diabetes can substantially improve patient outcomes and save lives. This study introduces a new model for predicting diabetes using the Random Forest algorithm, known for its powerful ability to split data until reaching an optimal state. Two datasets are utilized: the Multiclass Diabetes dataset and the PIMA Indian Diabetes dataset. The data are preprocessed by removing outliers, handling missing values, and balancing the classes. These preprocessed data are then classified using the Random Forest algorithm through continuous splitting until the stopping criteria are met, aiming to predict diabetic individuals. The proposed model demonstrated superior performance with the Multiclass Diabetes dataset, it achieves a validation accuracy of 100%, a precision of 98.20%, and recall and F1 scores of 98.11% and 98.12%, respectively. With the PIMA dataset, the proposed model achieves a validation accuracy of 85.30%, with precision, recall, and F1 scores of 88.07%, 87.50%, and 87.50%, respectively. In addition to our proposed model, we built many machine learning models with the first dataset such as SVM, logistic regression, logistic regression with L1/ L2 regularization, K-NN, and naïve bayes. Our results indicate that the Random Forest algorithm significantly outperforms other machine learning techniques in predicting diabetes, offering a highly accurate and reliable tool for early diagnosis. This research underscores the potential of ensemble learning in healthcare, particularly in managing chronic diseases like diabetes
ChatGPT and the Crisis of Academic Honesty
No full textChatGPT is one of the conversational AI tools that changed and still change the human life in different aspects wherein the academic and the scientific aspects seem to be affected more seriously. This paper, therefore, is an attempt to delve into some minutes of this influence in these two sensitive aspects. And this can be achieved through pinpoint its aggressions that are mainly caused by its capacities and limitations as far as scientific communication and studies are concerned. On its surface face, this AL seems to enrich scientific texts with clarity and coherence, to have a role in generation of new ideas and research methods, along with the dangers it creates to the honesty of academic efforts. The study, therefore, seems grim and pessimistic in this respect contrary to the immense praise and acceptance it receives at the universal level. It tries to call for a stricter human censorship over academic and scientific works to draw them away, as much as possible, from the injuries of this AI application. And to support this caution, it shows some of ChatGPT features and restrictions that turn it dangerous in the academic fields. And to be objective and accurate, the study refers to some of its positive aspects like its ability to help in creating coherence and clarity to scientific articles, research methods, and use in fighting plagiarism. As thus, the study highlights an urgent need for a necessary methods, restrictions, and strategies that can ensure a safe use of ChatGPT\u27s advantages and avoiding its weaknesses whenever it is used in scientific writing
Survey of SMS Spam Detection Techniques: A Taxonomy
No full textShort Message Service (SMS) spam remains a significant threat to users and businesses, with spammers constantly adopting more sophisticated techniques. This paper comprehensively surveys SMS spam detection methods, categorizing existing approaches into five primary groups: rule-based methods, traditional machine learning techniques, deep learning models, hybrid models, and ensemble methods. Each category is examined in detail, highlighting its strengths, limitations, and evolution. Rule-based methods, though historically significant, are limited by their inability to handle new or evolving spam tactics. Traditional machine learning techniques, such as Naive Bayes and support vector machines (SVM), offer improved accuracy but depend on handcrafted features. In contrast, deep learning models, including recurrent neural networks (RNN) and convolutional neural networks (CNN), excel in feature extraction and adaptability yet face challenges with model complexity and the need for large labeled datasets. Hybrid and ensemble methods combine the benefits of various models to improve performance, reduce bias, and enhance robustness. This review aims to provide a structured overview of the state of SMS spam detection, identify emerging trends, and suggest future research directions, including improving generalization, reducing data dependency, and exploring the integration of contextual information. The findings underscore the need for continued innovation to address the evolving landscape of SMS spam