Wasit Journal of Computer and Mathematics Science

Although liver biopsy is the gold standard for identifying diffuse liver disorders, it is an intrusive procedure with a host of negative side effects. Physician subjectivity may affect the ultrasonography diagnosis of diffuse liver disease. As a result, there is still a clear need for an appropriate classification of liver illnesses. In this article, an unique deep classifier made up of deep convolutional neural networks (CNNs) that have already been trained is proposed to categories the liver condition. The variants of ResNet and AlexNet are a few networks that are combined with fully connected networks (FCNs). Transfer learning can be used to extract deep features that can offer adequate categorization data. Then, an FCN can depict images of the disease in its many stages, including tissue, liver hepatitis, and hepatitis. To discriminate between these liver images, three different (normal/cirrhosis, perfectly natural, and cirrhosis/hepatitis) and 3 (normal/cirrhosis/hepatitis) models were trained. A hybrid classifier is presented in order to integrate the graded odds of the classes produced by each individual classifier since two-class classifiers performed better than three-class classifiers. The class with the highest score is then chosen using a majority voting technique. The experimental results demonstrate an high accuracy when liver images were divided into three classes using ResNet50 and a hybrid classifier.

Online examination is an integral and vital component of online learning. Student authentication is going to be widely seen when one of these major challenges within the online assessment. This study aims to investigate potential threats to student authentication in the online examinations. Adopting cheating in E-learning in a university of Iraq brings essential security issues for e-exam . In this document, these analysts suggested a model making use of a quantitative research style to confirm the suggested aspects and create this relationship between these. The major elements that might impact universities to adopt cheating electronics were declared as Educational methods, Organizational methods, Teaching methods, Technical methods. In order to verify that the design of the questionnaire, has been followed up with two steps of verification. First of all, a approval stage within that , the list of questions examined by the section of specialists in this subject in computer technology and teaching in universities, the feedback received was implemented before proceeding in order in order to this second stage . Second of all, the pilot research has been carried out to check the dependability of the factors . The gathered data has been examined using the Cronbach’s Alpha coefficient dependability test in SPSS 18 software package. This final results demonstrated this all factors are dependable as they acquired a value of 0.9126 and above inside test.

Natural language processing has developed significantly recently, which has progressed the text summarization task. It is no longer limited to reducing the text size or obtaining helpful information from a long document only. It has begun to be used in getting answers from summarization, measuring the quality of sentiment analysis systems, research and mining techniques, document categorization, and natural language Inference, which increased the importance of scientific research to get a good summary. This paper reviews the most used datasets in text summarization in different languages and types, with the most effective methods for each dataset. The results are shown using text summarization matrices. The review indicates that the pre-training models achieved the highest results in the summary measures in most of the researchers' works for the datasets. Dataset English made up about 75% of the databases available to researchers due to the extensive use of the English language. Other languages such as Arabic, Hindi, and others suffered from low resources of dataset sources, which limited progress in the academic field.

This study investigated the approach of extracting features from single EEG channels when the minimum number of features in Electroencephalogram (EEG) channels, hence the visibility of using sets of features extracted from a single channel. The feature sets considered in previous studies are utilized to establish a combined set of features extracted from one channel. The feature is the set of statistical moments. Publicly available EEG datasets like the Dryad dataset, obtained from 15 participants, are tested into a support vector machine classifier. The 12 channels were trained separately, where each channel was divided into a different number of blocks, and the results indicated that some channels were bad. Some were very encouraging, reaching 100% in the number of blocks 16 in channels 8 and 12. In this article, the comparison of ANN algorithm test results published in a previous article with SVM algorithm test results for the same tested features and channels will be presented.

The necessities of steganography methods for hiding secret message into images have been ascend. Thereby, this study is to generate a practical steganography procedure to hide text into image. This operation allows the user to provide the system with both text and cover image, and to find a resulting image that comprises the hidden text inside. The suggested technique is to hide a text inside the header formats of a digital image. Least Significant Bit (LSB) method to hide the message or text, in order to keep the features and characteristics of the original image are used. A new method is applied via using the whole image (header formats) to hide the image. From the experimental results, suggested technique that gives a higher embedding of several stages of complexity. Also, LSB method via using the whole image is to increase the security and robustness of the proposed method as compared to state-of the-art methods.

In the presence of technology and taking into account the concept of globalization, the application of chat is one of the most important aspects of our daily life to use different purposes that meet the needs of education, business and personal communication where the barrier is the language in most cases. Although we can send text using the chat app but there is still no known chat app where people can chat in different languages with the help of automatic translation system. Here the author decided to develop a mobile application with a chat and translation system in which users can chat in their preferred language for the translation system. Businessmen will help to facilitate communication with their foreign partners and students can talk to their friends abroad. It is useful to learn different languages and is useful to communicate with each other. Users only need to select the language they want to chat from the specified system. The system will use the Microsoft Translator API to translate in different languages.

Data hiding is the art of hiding data for various purposes such as; to maintain private data, secure confidential data and so on. Securely exchange the data over the internet network is very important issue. So, in order to transfer the data securely to the destination, there are many approaches like cryptography and steganography. In this research we propose an AES algorithm for embedding the data into the images which is implemented through the Microsoft .NET framework using the C#.NET.

Data breaches are perhaps the single most significant risk that banks face today. In the financial industry. Aside from the direct costs involved in these breaches, like lost funds, increased insurance expenses and fines, and penalties, institutions also must contend with the indirect costs. Loss of reputation and consumer trust are not easy to quantitatively measure, but it’s guaranteed the price is very high.

Unfortunately, banks need to face an ever-evolving set of threats because of the nature of their business. They hold sensitive financial records that bad actors are known to target, and with methods that are always shifting. Consequently, security cannot be static to meet these threats. It must be a continuous process to monitor and respond to new risks as they emerge. Also, compliance needs to be built into the overall process to meet the stringent privacy regulations for the financial industry. Data security for banks is undoubtedly a challenge, but a holistic approach may make it easier to manage.

the smart robot is an important part of the smart homes system, in this research the Arduino Vacuum Cleaner we built is very compact and practical for potential office and home use. The developed robot is disk-shaped, equipped with vacuuming and cleaning technology and controlled by Arduino nano.

It sucks dirt via a retractable dustbin, using a fan within a motor. the device will be deployed for office and home use thereby making cleaning a fully autonomous duty. This robot will have ultrasonic sensors and an IR proximity sensor. The ultrasonic sensor will allow the robot to avoid obstacles so that it can move freely until the room is properly cleaned, and the proximity sensor will help it to avoid falling from stairs.

One of the most important features of our floor cleaning robot is that it is fast and flexible in movement, able to deal with all dirt and stains on floors without human intervention. It is also characterized by the fact that it can be disassembled and installed with ease and simplicity, so that in the event of a malfunction, any malfunction will be repaired at the same time. It is also characterized by possessing sensors, so it can identify the .It is possible to develop this technique to become more used in various fields. Because we are in the world of technology development, it becomes very easy to develop such projects to benefit from them in daily life.

DNA sequencing, imaging procedures, and wireless healthcare monitoring devices are all examples of high-throughput, data-intensive precision medicine assays and technologies that have necessitated new methods for analysing, integrating, and interpreting the enormous volumes of data they produce. While several statistical approaches have been developed to deal with the "big data" generated by such tests, previous experience with artificial intelligence (AI) techniques suggests that they may be especially well-suited. Furthermore, data-intensive biomedical technologies applied to study have shown that people differ greatly at the genetic, biochemical, physiological, exposure, and behavioural levels, particularly with regards to disease processes and treatment receptivity. This indicates the need to 'personalise' medications so that they better suit the complex and often individual needs of each patient. AI can play a significant role in the clinical research and development of new personalised health products, from selecting relevant contribute to sustainable to testing their utility, because of the importance of data-intensive assays in revealing appropriate intervention objectives and approaches for personalising medicines. The work here presents a variety of ways in which AI can contribute to the progress of personalised medicine, and we argue that the success of this endeavour is critically dependent on the improvement of appropriate assays and methods for storing, aggregating, accessing, and ultimately combining the data they generate. In addition, the manuscript also discusses the potential future research directions and highlights the shortcomings of various AI methods.

Cyber crime was a major problem even before the epidemic, and it skyrocketed as the globe became increasingly digital after the pandemic began. It is crucial to think about how to make the web safer in the post-pandemic period, since the number of cyber scams is rising rapidly. With more people doing remote work and more people quickly embracing new technology, as well as with decreased monitoring and controls, hackers have more opportunities to attack weaknesses in the system. Individuals and businesses were rendered more vulnerable to cyber fraud as a result of each of these developments brought on by the epidemic. Since cybercriminals are just as technically savvy as their cyber security counterparts, a lot of effort and money must be spent on prevention. Professionals in the field of cyber security and cybercriminals nowadays share many of the same skills and use many of the same tools. Both cyber security experts and cybercriminals rely on them, but the former to protect their systems from the latter.

During the past recent years, there has been tremendous development reaming the concept of digital libraries-a knowledge base that can be stored and retrieved through online networks. Digital libraries are the most complex form of information systems that support digital document preservation, distributed database management, hypertext, filtering, information retrieval, and selective dissemination of information. This has really overcome geographical barriers offering a wide range of academic, research, and cultural resources with multimedia effects that can be accessed around the world over the distributed networks. The paper examines the concept of Digital library, the technology that has enabled its emergence & architecture of the digital library system. It also highlights the digital library projects undertaken in USA, UK, and India. Here the authors explored the unique feature of digital library and possible challenges ahead for library and information professionals in the digital environment.

By the virtue of blooming automation industry and wireless connectivity, all the devices within the home can be connected. Today's World is moving to digitalization where everything is made easy and comfortable for people i.e., young youth as well as senior citizen. Smart Automated House Application using IOT (Internet of Thing) is a system where basic house facility can be handled by device from any place such as ON and Off of Light, Fan, AC, Water pump, Gardening of Water. One can handle all these things with help of device NodeMCU ESP8266, Android Application, Internet Connection. This paper include functionality of node esp8266 are connected with either of above given house application like fan, light, water pump, gardening with help of coding and hosting online with web server. All the functionality is handled by Mobile App created in android application, from which house application are controlled with help of internet. This paper is clarifying that monitoring of circuit devices through wireless using Node MCU and controlling using App Blynk. According to requirement of need one can connect multiple device like sensors, appliance and many more till 8.

The introduction of microprocessors had created a number of product options that were just not there before. These clever processors have infiltrated and dispersed themselves across every aspect of our life, whether it be in the office (fax machines, pagers, laser printers, credit card readers), living rooms (televisions, air conditioners), or kitchens (food processors, microwave ovens). The usage of an operating system has many benefits as distributed applications get more complicated. The real-time demands of the majority of distributed systems need the usage of Real Time Operating Systems (RTOS) that can fulfill the needs of distributed systems. Real-time applications can be readily built and expanded thanks to RTOS. Through the division of the application code into different files, the use of RTOS streamlines the design process.

Fake images are one of the most widespread phenomena that have a significant influence on our social life, particularly in the world of politics and celeb. Nowadays, generating fake images has become very easy due to the powerful yet simple applications in mobile devices that navigate in the social media world and with the emergence of the Generative Adversarial Network (GAN) that produces images which are indistinguishable to the human eye. Which makes fake images and fake videos easy to perform, difficult to detect, and fast to spread. As a result, image processing and artificial intelligence play an important role in solving such issues. Thus, detecting fake images is a critical problem that must be controlled and to prevent these numerous harmful effects. This research proposed utilizing the most popular algorithm in deep learning is (Convolution Neural Network) to detect the fake images.

The first steps includes a preprocessing which start with converting images from RGB to YCbCr color space, after that entering the Gamma correction. finally extract edge detection by entering the Canny filter on them. After that, utilizing two different method of detection by applying (Convolution Neural Network with Principal Component Analysis) and (Convolution Neural Network without Principal Component Analysis) as a classifiers.

The results reveal that the use of CNN with PCA in this research results in acceptable accuracy. In contrast, using CNN only gave the highest level of accuracy in detecting manipulated images.

The main challenges in routing protocols are node mobility, resource constraints, error-prone channel states, and problems with hidden and unprotected terminals. This article provides an overview of the main protocols, their problems, and ways to improve them. The cell phone allows communication between two moving units via mobile stations (MS), mobile units, and landing units. The term "mobile ad hoc network" (MANET) refers to a group of devices connecting and communicating. The military, law enforcement, and emergency services have quickly become interested in MANETS because they provide a high quality of service. Path loss (PL), one of the biggest problems in wireless communications, can be caused by multiple reflections from an obstacle or by the source of the signal being far from the destination on the network. Multipath propagation, path loss, and interference reduce the network's quality of service (QoS). The best route is added to a router's routing table using a dynamic routing protocol, and an alternate path is chosen when the primary route is unavailable.

The objective of hiding text in an image is hiding text without raising suspicions that the image contains a hidden message or text, which leads to protecting and maintaining text confidentiality. The previous hiding methods have problems in capacity, randomization, and imperceptibility. This paper will be solved some of these problems; we suggested a new method for hiding text in an image. Firstly, encrypting the text by the AES-192 bit algorithm for obtaining a secret message. When the initial key of the AES-192 (bit) algorithm is generated by a chaotic system for randomness purposes, secondly, hiding the secret message is into a gray image for obtaining a stego-image. The hiding step is based on a proposed map that chooses from the last round of key expansion in the AES-192 algorithm. This map represented random positions of LSB in each byte of the gray image. The experimental result of this method proved a successful method based on metric criteria. Also, this method is the very speed for hiding ciphertext in the gray image as well as extracting ciphertext from the gray image. Also, it is very safe because it is difficult for attackers to distinguish between the original image and the stego image therefore the correlation between the original image and the stego- image is very close to 1.

Data transmission classification is an important issue in networks communications, since the data classification process has the ultimate impact in organizing and arranging it according to size and area to prepare it for transmission to minimize the transmission bandwidth and enhancing the bit rate. There are several methods and mechanisms for classifying the transmitted data according to the type of data and to the classification efficiency. One of the most recent classification methods is the classification of artificial neural networks (ANN). It is considered one of the most dynamic and up-to-date research in areas of application. ANN is a branch of artificial intelligence (AI). The neural network is trained by backpropagation algorithm. Various combinations of functions and their effect while utilizing ANN as a file, classifier was studied and the validity of these functions for different types of datasets was analyzed. Back propagation neural university (BPNN) supported with Levenberg Marqurdte (LM) activation function might be utilized with as a successful data classification tool with a suitable set of training and learning functions which operates, when the probability is maximum. Whenever the maximum likelihood method was compared with backpropagation neural network method, the BPNN supported with Levenberg Marqurdte (LM) activation function was further accurate than maximum likelihood method. A high predictive ability against stable and well-functioning BPNN is possible. Multilayer feed-forward neural network algorithm is also used for classification. However BPNN supported with Levenberg Marqurdte (LM) activation function proves to be more effective than other classification algorithms.

This work is aimed to introduce a new topology on a graph, namely the degree topology. This topology is defined by the degree of the vertices of the graphs. We find the degree topology for certain types of graphs and determine their types. The degree topology for the complete graph is an indiscrete topology. While The degree topology is generated by a complete bipartite graph with is a quasi-discrete topology. In addition, a new property is initiated namely set- space and discussed the link between it and space. We verify that every degree topology is a set- space.

Blood diseases are considered one of the most common diseases in the world for humans, which occurs as a result of abnormal growth on the artery wall, which leads to strokes and heart attacks, given that the artery is a tube. There are many types of narrowing of the arteries that can be described mathematically. In this research, we will explain again considering the overlapping stenosis of the artery and describing it mathematically.

The aim of this paper to study the existence solution of some types of hyperbolic differential equation with periodicity of some controls function as nonlocal initial condition for the equation and the technical and used depended on some interest iniquities.