Iraqi Journal for Computers and Informatics

One of the most important prognostic factors for all lung cancer patients is the accurate detection of metastases.
Pathologists, as we all know, examine the body and its tissues. On the existing clinical method, they have a tedious and manual task. Recent analysis has been inspired by these aspects. Deep Learning (DL) algorithms have been used to identify lung cancer. The developed cutting-edge technologies beat pathologists in terms of cancer identification and localization inside pathology images. These technologies, though, are not medically feasible because they need a massive amount of time or computing capabilities to perceive high-resolution images. Image processing techniques are primarily employed for lung cancer prediction and early identification and therapy to avoid lung cancer. This research aimed to assess lung cancer diagnosis by employing DL algorithms and low-resolution images. The goal would be to see if Machine Learning (ML) models might be created that generate higher confidence conclusions while consuming fractional resources by comparing low and high-resolution images. A DL pipeline has been built to a small enough size from compressing high-resolution images to be fed into an or before CNN (Convolutional Neural Network) for binary classification i.e. cancer or normal. Numerous enhancements have been done to increase overall performance, providing data augmentations, including augmenting training data and
implementing tissue detection. Finally, the created lowresolution models are practically incapable of handling
extremely low-resolution inputs i.e. 299 x 299 to 2048 x 2048 pixels. Considering the lack of classification ability, a
substantial reduction in models’ predictable times is only a marginal benefit. Due to an obvious drawback with the
methodology, this is disheartening but predicted finding: very low resolutions, essentially expanding out on a slide, preserve only data about macro-cellular structures, which is usually insufficient to diagnose cancer by itself.
Index items: Convolutional Neural Networks, Deep Learning, Image Processing, Lung Cancer Detection, Machine Learning, Medical Image Analysis

The data deduplication technique efficiently reduces and removes redundantdata in big data storage systems.The main issue is that thedata deduplication requires expensive computational effort to remove duplicate data due to the vast size of big data.Thepaper attempts to reduce the time and computationrequired fordata deduplicationstages.The chunkingand hashingstageoften requires a lot of calculations and time.This paper initiallyproposes an efficient new method to exploit the parallel processing of deduplication systems with the best performance. The proposed systemis designed to use multicore computing efficiently. First, The proposed method removes redundant data by making a rough classification for the input into several classes using the histogram similarity and k-mean algorithm.Next, a new method for calculating the divisor list for each class was introduced to improve the chunking method and increase the data deduplication ratio. Finally, the performance of the proposed method was evaluated using three datasets as test examples. The proposed method proves thatdata deduplication based on classes and a multicore processor is much faster than a single-core processor.Moreover, the experimental results showed that the proposed method significantly improved the performance of Two Threshold Two Divisors (TTTD) and Basic Sliding Window BSW algorithms

The popularity of massive open online courses (MOOCs) and other forms of distance learning has increased recently. Schools and institutions are going online to serve their students better. Exam integrity depends on the effectiveness of proctoring remote online exams. Proctoring services powered by computer vision and artificial intelligence have also gained popularity. Such systems should employ methods to guarantee an impartial examination. This research demonstrates how to create a multi-model computer vision system to identify and prevent abnormal student behaviour during exams. The system uses You only look once (YOLO) models and Dlib facial landmarks to recognize faces, objects, eye, hand, and mouth opening movement, gaze sideways, and use a mobile phone. Our approach offered a model that analyzes student behaviour using a deep neural network model learned from our newly produced dataset" StudentBehavioralDS." On the generated dataset, the "Behavioral Detection Model" had a mean Average Precision (mAP) of 0.87, while the "Mouth Opening Detection Model" and "Person and Objects Detection Model" had accuracies of 0.95 and 0.96, respectively. This work demonstrates good detection accuracy. We conclude that using computer vision and deep learning models trained on a private dataset, our idea provides a range of techniques to spot odd student behaviour during online tests.

The most important cereal crop in the world is rice (Oryza sativa). Over half of the world's population uses it as a staple food and energy source. Abiotic and biotic factors such as precipitation, soil fertility, temperature, pests, bacteria, and viruses, among others, impact the yield production and quality of rice grain. Farmers spend a lot of time and money managing diseases, and they do so using a bankrupt "eye" method that leads to unsanitary farming practices. The development of agricultural technology is greatly conducive to the automatic detection of pathogenic organisms in the leaves of rice plants. Several deep learning algorithms are discussed, and processors for computer vision problems such as image classification, object segmentation, and image analysis are discussed. The paper showed many methods for detecting, characterizing, estimating, and using diseases in a range of crops. The methods of increasing the number of images in the data set were shown. Two methods were presented, the first is traditional reinforcement methods, and the second is generative adversarial networks. And many of the advantages have been demonstrated in the research paper for the work that has been done in the field of deep learning.

Internet-based programs and communication techniques have become widely used and respected in the IT industry recently. A persistent source of "big data," or data that is enormous in volume, diverse intype, and has a complicated multidimensional structure, is internet applications and communications. Today, several measures are routinely performed with no assurance that any of them will be helpful in understanding the phenomenon of interest in an era of automatic, large-scale data collection. Online transactions that involve buying, selling, or even investing are all examples of e-commerce. As a result, they generate data that has a complex structure and a high dimension. The usual data storage techniques cannot handle those enormous volumes of data. There is a lot of work being done to find ways to minimize the dimensionality of big data in order to provide analytics reports that are even more accurate and data visualizations that are more interesting. As a result, the purpose of this survey study is to give an overview of big data analytics along with related problems and issues that go beyond technology.

There is growing interestin automating crime detection and prevention for large populations as a result of the increased usage of social media for victimization and criminal activities. This area is frequently researched due to its potential for enabling criminals to reach a large audience. While several studies have investigated specific crimes on social media, a comprehensive review paper that examines all types of social media crimes, their similarities, and detection methods is still lacking. The identification of similarities among crimes and detection methods can facilitate knowledge and data transfer across domains. The goal of this study is to collect a library of social media crimes and establish their connections using a crime taxonomy. The survey also identifies publicly accessible datasets and offers areas for additional study in this area.

With technological advancements and the development of robots have begun to be utilized in numerous sectors, including industrial, agricultural, and medical. Optimizing the path planning of robot manipulators is a fundamental aspect ofrobot research with promising future prospects. The precise robot manipulator tracks can enhance the efficacy of a variety of robot duties, such as workshop operations, crop harvesting, and medical procedures, among others. Trajectory planning for robot manipulators is one of the fundamental robot technologies, and manipulator trajectory accuracy can be enhanced by the design of their controllers. However, the majority of controllers devised up to this point were incapable of effectively resolving the nonlinearity and uncertainty issues of high-degree freedom manipulators in order to overcome these issues and enhance the track performance of high-degree freedom manipulators. Developing practical path-planning algorithms to efficiently complete robot functions in autonomous robotics is critical. In addition, designing a collision-free path in conjunction with the physical limitations of the robot is a very challenging challenge due to the complex environment surrounding the dynamics and kinetics of robots with different degrees of freedom (DoF) and/or multiple arms. The advantages and disadvantages of current robot motion planning methods, incompleteness, scalability, safety, stability, smoothness, accuracy, optimization, and efficiency are examined in this paper.

The COVID-2019 virus, which was discovered for the first time in December 2019 in the city of Wuhan, China, went on to become a pandemic after rapidly spreading around the globe. As there are currently no reliable automated toolkits on the market, there has been an increase in the demand for supplementary diagnostic tools for COVID19 patients. It may be possible to improve the accuracy of the diagnosis of covid19 disease by making use of more recent developments in artificial intelligence (AI) approaches and radiological imaging. In this research, three different convolution neural networks were applied to raw chest x-rays before the histogram filter was used for the basic pre-processing. The goal was to automatically detect COVID-19. The results that we obtained using the three suggested models indicate that the ResNet50 model provides the greatest classification performance with 96% accuracy , while the InceptionV3 model only achieves 95% accuracy, and the Inception-ResNetV2 model only achieves 82% accuracy

The development of wheeled ground robots has enabled them to be used for a variety of tasks. These robots must be able to move with accuracy and precision, especially when faced with obstacles or inclines. To improve the movement of these robots on a slope,lidar data can be used to detect the location and shape of obstacles. In recent years, Lidar technology has become an essential tool for various robotic applications. It has proven to be a game-changer in the field of autonomous navigation, especially in situations where robots have to operate in unknown environments. Lidar technology provides a high-resolution 3D map of the environment around the robot, enabling it to navigate autonomously while avoiding obstacles. In this paper, wediscuss the use of Lidar technology in improving the movement of a wheeled ground robot on a slope. Wedescribe the steps involved in obtaining Lidar data, processing the data to create a 3D map of the environment, and using the map to plan more efficient movement of the robot. Wepresent an applied example of how Lidar data improves the movement of a ground robot with wheels on a slope, calculating the inclination of the ground, calculating the force required for the movement of the robot, creating three-dimensional models of the terrain to be navigated, creating plans for more efficient movement,and reducing damage and wear of the robot.