Wasit Journal of Computer and Mathematics Science

Fraud is an ancient yet ever-changing profession. Because of the digitization of money, financial transactions, banks, fraudsters now have a limitless number of possibilities to perpetrate crime from behind a screen, anywhere around the world. Fraud has a broad influence, with direct ramifications for business and the economy. It is of great worry to cybercrime organizations as recent studies have proven that ML algorithms may successfully be utilized to identify fraudulent transactions in massive amounts of payment data. Such techniques may identify fraudulent transactions in real time, which human auditors may miss. In this research, we apply supervised ML algorithms to the issue of fraud identification by analyzing simulated financial transaction data that is available to the public. Our aim is to show how supervised ML methods may be utilized to successfully identify data with extreme class disproportion. By way of example, we show how exploratory analysis may be utilized to identify fraudulent from real purchases. We also show that Random Forest outperform Logistic Regression when applied to a clearly distinguished dataset.

In healthcare, medical image processing is considered one of the most significant procedures used in diagnosing pathological conditions. Magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and X-ray visualization have been used. Health institutions are seeking to use artificial intelligence techniques to develop medical image processing and reduce the burden on physicians and healthcare workers. Deep learning has occupied an important place in the healthcare field, supporting specialists in analysing and processing medical images. This article will present a comprehensive survey on the significance of deep learning in the areas of segmentation, classification, disease diagnosis, image generation, image transformation, and image enhancement. This survey seeks to provide an overview of the significance of deep learning in the early detection of diseases, studying tumor localization behaviors, predicting malignant diseases, and determining the suitable treatment for a patient. This article concluded that deep learning is of great significance in improving healthcare, enabling healthcare workers to make diagnoses quickly and more accurately, and improving patient outcomes by providing them with appropriate treatment strategies.

Fraudulent internet transactions have caused considerable harm and losses for both people and organizations over time. The growth of cutting-edge technology and worldwide connectivity has exacerbated the rise in online fraud instances. To offset these losses, robust fraud detection systems must be developed. ML and statistical approaches are critical components in properly recognizing fraudulent transactions. However, implementing fraud detection models presents challenges such as limited data availability, data sensitivity, and imbalanced class distributions. The confidentiality of records adds complexity to drawing inferences and constructing improved models in this domain. This research explores multiple algorithms suitable for classifying transactions as either genuine or fraudulent using the Credit Card Fraud dataset. Given the extremely unbalanced nature of the dataset, the SMOTE approach was used for oversampling to alleviate the class distribution imbalance. In addition, feature selection was carried out, and the dataset was divided into training and test data. The experiments utilized NB, RF, and MLP algorithms, all of which demonstrated high accuracy in detecting credit card fraud. MLP method achieved 99.95% accuracy as compared to other methods

The growing use of digital technologies across various sectors and daily activities has made handwriting recognition a popular research topic. Despite the continued relevance of handwriting, people still require the conversion of handwritten copies into digital versions that can be stored and shared digitally. Handwriting recognition involves the computer's strength to identify and understand legible handwriting input data from various sources, including document, photo-graphs and others. Handwriting recognition pose a complexity challenge due to the diversity in handwriting styles among different individuals especially in real time applications. In this paper, an automatic system was designed to handwriting recognition using the recent artificial intelligent algorithms, the conventional neural network (CNN).

This study offers a new adjustment to the Advanced Encryption Standard (AES) in order to assure a high degree of security. This is achieved by replacing the binary (XOR) operation with a new (Xo) operation in each add-round-key stage. The Xo operation generated an extra six randomly selected control keys determined by six state tables (2, 4, 6, 8, 10, and 12) produced from the addition operation in the Galois Field GF (2^2 ,2^4 ,2^6 , 2^8, 2^10 and 2^12 ) in order to boost the algorithm's unpredictability. In the suggested method, an adversary requires at least probabilities of keys to break the message; hence, it improves the difficulty of the original AES against brute force attacks. also enhances the performance of additional security metrics, such as NIST tests, compared to the original AES. Consequently, this replacement, including the use of six keys in both the encryption and decryption processes, offers a new level of security and a higher degree of resistance to data breaches. The novelty of the proposed (Xo) technique lies in the construction of GF tables ( 2^6 , 2^10 and 2^12) to be used in the encryption and decryption process for the first time, as well as the approach utilized to create the code for it.

Humans can understand their surroundings clearly because they regularly notice objects in their environment. It is essential for the machine to perceive the surroundings similarly to how humans do in order to make it autonomous and capable of navigating in the human world. The machine can assess its surroundings and identify objects using object detection. This can simplify a number of tasks and enable the machine to recognize its surroundings. Making bounding boxes that surround the objects is essentially how object detection systems work to locate objects in an image. Object detection has applications such as autonomous robot navigation, surveillance, face detection, and vehicle

Intrusion detection systems (IDS) have been developed to identify and classify these attacks in order to prevent them from occurring. However, the accuracy and efficiency of these systems are still not satisfactory. In previous research, most of the methods used were based on ordinary neural networks, which had low accuracy. Therefore, this thesis, with the aim of presenting a new approach to intrusion detection and improving its accuracy and efficiency, uses long-term memory (LSTM) optimized with the Penguin optimization algorithm (EPO). In the proposed approach, first, the features were pre-processed by normalization, cleaning, and formatting in number format. In the next step, the linear discriminant analysis (LDA) method was used to reduce the dimensions of the processed features, and after that, the EPO algorithm was used to optimize the size of the hidden unit of the LSTM network. Finally, the optimized network was evaluated using the NSL-KDD dataset, which is a widely used benchmark dataset in the field of intrusion detection. The results obtained for the training and test datasets were 99.4 and 98.8%, respectively. These results show that the proposed approach can accurately identify and classify network intrusions and outperform many existing approaches.

The system might include a turn-by-turn route highlight to prevent fake preferences that check if the user has taken the course. A larger customer overview with more participants is required to acquire more insightful client feedback. Our ex-amination was designed as a lab experiment to gather initial data straight absent. While making fun of other clients and their system comments, we looked at a few initial objective mixtures. Doing field research with actual clients using our suggested model in real-world situations (such as when looking for a course online to work from home) is crucial. This will help us better understand how effective our approach is. In this article, we developed a creative method for recommending multimodal travel routes. In a client survey with 20 participants, we evaluated the applicability of our cross-breed computation and its usability. The results show that CF, in-formation-based, and well-liked course concepts complement one more successfully than cutting-edge course organizer advances. Thanks to the Google Guides Programming interface, our application can give seven different elective trip options.

In this work, the cellular network performance based on other cell interference predictions is presented. It presents a mathematical model of co-channel interference analysis in hexagonal and linear cell shapes through a log-distance propagation model to investigate the effect of path loss exponent value on the received signal quality of the downlink. Simulation results obtained show that as the power exponent value increase, the interfering signals attenuation is increased resulting in received signal quality improvement. The signal-to-interference ratio (SIR) received by subscribers close to the cell edge will be less due to the contribution of the near-interfering cells especially when multiple layers of interfering cells are considered. The simulations confirmed that the impact of multi tiers of interfering cells cannot be ignored in systems of small cluster size as they may contribute to system performance degradation.

It has become increasingly apparent that bandwidth scarcity is an issue as wireless communications advance. Alternatively, spectrum sensing techniques are used to detect licensed users. A spectrum sensor can detect energy, matched filters, and cyclostationary features. There are, however, some drawbacks to these methods. Energy detector performance is affected by noise power uncertainty. Every primary user needs a dedicated receiver for matched filter spectrum sensing. Computational effort and observation time are required for cyclo-stationary feature detection. Spectrum use is determined using particle swarm optimization (PSO), an algorithm for determining the best frequency allocation and highest accuracy. Using PSO operations, this paper proposes an improved energy detection method compared to conventional energy detection methods. Detecting energy and using the PSO channel allocation technique to detect fading channels is also mathematically described.

The Apriori algorithm creates all possible association rules between items in the database using the Association Rule Mining and Apriori Algorithm. Using Ant Colony Optimization, a new algorithm is proposed for improving association rule mining results. Using ant colony behaviour as a starting point, an optimization of ant colonies (ACO) is developed. The Apriori algorithm creates association rules. Determine the weakest rule set and reduce the association rules to find rules of higher quality than apriori based on the Ant Colony algorithm's threshold value. Through optimization and improvement of rules generated for ACO, the proposed research work aims to reduce the scanning of datasets.

Image processing is an interesting area where noisy images can be restored from salt and pepper noise. Various filtering algorithms can be used in the restoration process. Pixels in the original image should not be affected by the restoration process. Despite changes in dimensions and image format, the problem of the existing work persists. A hybrid technique used Ant colony Optimization to remove high-density salt and pepper noise from images. This hybrid technique would remove salt and pepper noise in corrupted images. Ant Colony Optimization (ACO) identifies and selects noisy pixels from corrupted images. It eliminates salt and pepper noise (SP Noise), which causes black and white spots in the original image. All the processes are explained to prove the theory, and the simulation results are presented.

In this paper, we focus on the "Artificial Neural Network (ANN) based PWM-AC chopper". This system is based on the PWM AC chopper-encouraged single-phase induction motor. The main purpose of this paper is to design and implement an ideal technique regarding speed control. Here analyzed PWM-based AC-AC converter with resistive load, R-L load and finally, the PWM AC chopper is fed to single phase induction for speed control. Using other soft computing and optimization techniques such as Artificial Neural Networks, Fuzzy Logic, Convolution algorithm, PSO, and Neuro Fuzzy can control the Speed. We used Artificial Neural Network to control the Speed of the PWM-AC Single phase induction motor drive. The Neural Network toolbox has been further used for getting desired responses. Neural system computer programs are executed in MATLAB. The performance of the proposed method of ANN system of PWM AC Chopper fed single phase induction motor drive is better than other traditional and base methods for controlling the Speed, based on the MOSFET.

In this paper, we defined new triple transformation, which is called the fractional triple g-transformation of the order αl ,0<α≤1 for fractional of differentiable functions. This transformation is generalized to double g-transformation. Which has the following form;
Tg_α (u(ξ,τ,μ)=p(s)∫_0^∞▒∫_0^∞▒∫_0^∞▒〖E_α 〖(-(q_1 (s)ξ+q_2 (s)τ+q_3 (s)μ)〗^α 〖(dξ)〗^α 〖(dτ)〗^α 〖(dμ)〗^α 〗

This paper discussed the analytic methods to solve Second order Volterra integral equations form using different methods. The domain decomposition method is the first technique. Depending on the hypothesis, the solution is by sequence. The second method is the successive approximation technique, which is used Picard iteration method. The third method used Laplace transformation. The modified decomposition technique is used as the fourth method. Depending on the Taylor series, the fifth method is called the series method. The last method solves the VIE using the functional correction technique called the variational iteration method. We introduce some examples to illustrate these methods.