Computer Research Articles

Comparative Analysis of DNN, GBT, and KNN Models for Network Intrusion Detection

Network intrusion detection is critical to cybersecurity, aiming to identify and mitigate unauthorized access and attacks on computer systems and networks. This study evaluates the effectiveness of three machine learning techniques—deep neural networks (DNN), gradient boost trees (GBT), and k-nearest neighbors (KNN)—in detecting network intrusions. The performance of these models was assessed using a comprehensive dataset of 2,540,047 records encompassing 49 features across nine attack categories. The results indicate that GBT outperforms DNN and KNN in accuracy and robustness. These findings highlight the potential of GBT for enhancing intrusion detection systems and contribute valuable insights into the comparative performance of different machine learning algorithms in cybersecurity applications.

Development of Learning Management Model of Collaborative Learning and Positive Coaching on Cloud Computing System

This study aims to systematically review the learning management model on cloud computing system using collaborative learning and positive coaching. The author uses the literature review to synthesize research as the main process to study related documents, books, research studies, and articles both domestically and internationally. They are selected by purposive sampling for 69 topics. The documents are analyzed by systematic review. This study is a qualitative study and uses content analysis by using keywords to discover three issues as follows: Cloud computing, Collaborative learning, and Positive coaching. From the results of this study, Cloud computing comprises six components: Cloud learning content, Cloud collaboration, Cloud communication, Cloud creation, Cloud presentation, and Cloud evaluation. The collaborative learning process has five steps as follows: Engagement phase, Exploration phase, Transformation phase, Presentation phase, and Reflection phase. Positive coaching comprises five process as follows: Construct the positive relation, Set a clear and challenging goal, Implement a challenging goal to smooth practice, Set a more challenging goal and practice smoothly, and Evaluate and expand the experience, reward the outcome and discovery.

Overview of knowledge graph construction in the field of fully electronic computer interlocking systems

As a core technology in railway signal control, the fully electronic computer interlocking system achieves the control of railway signals and switches through computerization, ensuring the safety and efficiency of train operations. With the increasing complexity of railway systems, traditional management and maintenance face significant challenges. Knowledge graphs, as an advanced data management and representation method, can effectively organize and utilize large-scale domain knowledge, enhancing the system's intelligence. This paper introduces the construction methods, core concepts, and applications of knowledge graphs in the field of fully electronic computer interlocking systems, providing references for research and practice in this area.

PhotoSolver: A bidirectional photonic solver for systems of linear equations

Solving systems of linear equations is one of the most fundamental challenges in computing, with ubiquitous applications in science and engineering. Solving large-scale linear equations is particularly challenging, requiring tremendous computing expenses. However, conventional solvers in electronic digital computers face inevitable physical bottlenecks that hinder further advancements in electronic chips. Unlike the electronic architectures, optical computing harnesses the inherent advantages of lights, such as ultimately high speed, negligible energy consumption, and high parallelism, making optical architectures attractive sources for ultra-high speed analog computing. Especially, recent advances in integrated photonic circuits bring exciting new possibilities for high performance computing based on photonic chips. In this work, we propose a bidirectional PhotoSolver using the propagation of optical signals in different directions on a single integrated photonic chip to perform multiple operations in solving systems of linear equations, scalable to solve large-scale systems. Specifically, we propose an in situ approach to iteratively update solutions by performing the forward and backward propagations within a single photonic chip. Furthermore, we propose a partitioning approach to solve large-scale systems using arrays of photonic chips. Numerical experiments demonstrate these capabilities with representative systems of linear equations. By utilizing lights propagating in integrated photonic chips, our PhotoSolvers provide a promising computing architecture to solve large systems of linear equations, with potentials in wide computational applications.

Crossmodal sensory neurons based on high-performance flexible memristors for human-machine in-sensor computing system

Constructing crossmodal in-sensor processing system based on high-performance flexible devices is of great significance for the development of wearable human-machine interfaces. A bio-inspired crossmodal in-sensor computing system can perform real-time energy-efficient processing of multimodal signals, alleviating data conversion and transmission between different modules in conventional chips. Here, we report a bio-inspired crossmodal spiking sensory neuron (CSSN) based on a flexible VO2 memristor, and demonstrate a crossmodal in-sensor encoding and computing system for wearable human-machine interfaces. We demonstrate excellent performance in the VO2 memristor including endurance (>1012), uniformity (0.72% for cycle-to-cycle variations and 3.73% for device-to-device variations), speed (<30 ns), and flexibility (bendable to a curvature radius of 1 mm). A flexible hardware processing system is implemented based on the CSSN, which can directly perceive and encode pressure and temperature bimodal information into spikes, and then enables the real-time haptic-feedback for human-machine interaction. We successfully construct a crossmodal in-sensor spiking reservoir computing system via the CSSNs, which can achieve dynamic objects identification with a high accuracy of 98.1% and real-time signal feedback. This work provides a feasible approach for constructing flexible bio-inspired crossmodal in-sensor computing systems for wearable human-machine interfaces.

Optimizing the individual technique of veteran Sambo wrestlers using modern technical training tools

Analytical reports of leading martial arts analysts indicate that today there is a positive trend in increasing the popularization of single combat among veteran athletes, especially Sambo wrestling. It is necessary to highlight that according to its essential and substantive characteristics (internal philosophy), Sambo wrestling is a living matter that has absorbed the best techniques of modern martial arts, and which is in a constant process of transformation in accordance with the requirements and realities of today. Taking into account the above, it is appropriate to summarize that the scientific and methodical (technical) support of the key components of the professional activity of veteran athletes who specialize in Sambo wrestling (other martial arts) acquires a dominant role. According to the results of the analysis of scientific and methodological and special literature, it was established that complex studies that reveal the peculiarities of the organization of the system of long-term training of sportsmen-veterans who specialize in Sambo wrestling are rare. In the process of research and analytical work, we used the following methods: axiomatic, idealization, historical and logical, descent from the concrete, formalization. As a result of a theoretical study, the members of the research group developed a program for improving the Sambo fighting technique of veteran athletes with an emphasis on the use of the video computer system "Katsumoto" (at the stage of direct preparation for the main competitions). Prospects for further research in the chosen direction of scientific research include conducting a pedagogical experiment to test the effectiveness of our proposed experimental program for improving the technical skills of veteran Sambo wrestlers with an emphasis on the use of modern technical training tools.

Research on Electro-Optic Hybrid Multidigit Digital Multiplier Based on Surface Plasmon Polariton Technology

Digital multipliers are the core components of digital computers, and improving the speed of transistor electronic computers during computation has almost reached its limit, with high power consumption. In this paper, we proposed an electro-optic hybrid multidigit digital multiplier based on SPP technology, which has the advantages of high speed and low power consumption in optical logic, as well as flexible electrical operation and easy storage. The electro-optic hybrid digital multiplier mainly consists of an electrical AND logic gate, an electro-optic hybrid half adder, and an electro-optic hybrid full adder. The optical logic unit is controlled by activated ITO materials to achieve optical-domain operations, and then the multiplication calculation results are converted into electrical signals through photoelectric conversion. The experimental results show that when the scale is 64 × 64 bits, compared with transistor digital multiplication, the energy consumption is reduced by 48.8%; the speed is increased by a factor of 28; and the volume of the electro-optic hybrid digital multiplier device is larger than that of the transistor multiplier, saving 59.9% of the area. For optical transmission loss, a single adder outputs 0.31 dB at different device scales, while the carry output continuously increases with device scale. At scales of 8 × 8 bits, 16 × 16 bits, and 64 × 64 bits, the insertion losses at the sum output ports are 1.03 dB/μm and 1.87 dB/μm, respectively.

Forensic Investigation, Challenges, and Issues of Cloud Data: A Systematic Literature Review

Cloud computing technology delivers services, resources, and computer systems over the internet, enabling the easy modification of resources. Each field has its challenges, and the challenges of data transfer in the cloud pose unique obstacles for forensic analysts, making it necessary for them to investigate and adjust the evolving landscape of cloud computing. This is where cloud forensics emerges as a critical component. Cloud forensics, a specialized field within digital forensics, focuses on uncovering evidence of exploitation, conducting thorough investigations, and presenting findings to law enforcement for legal action against perpetrators. This paper examines the primary challenges encountered in cloud forensics, reviews the relevant literature, and analyzes the strategies implemented to address these obstacles.

Цифровизация международных связей российских регионов (на примере Республики Татарстан)

Being involved in complex processes of global politics, subnational actors face a lot of challenges, including the growing impact of global digitalization of international relations. The subject of this study are issues of practical use of information technologies in paradiplomacy and adequate response by regional authorities to digital transformation of international relations. Studying the case of the Republic of Tatarstan which systematically applies digital technologies in the field of international relations contributed to identifying priority areas for digitalization of paradiplomacy. The study used regulations and state origin documents of federal and regional levels, and materials produced by international organizations. Basic trends of digitalization of paradiplomacy include issues of development and implementation of management decisions based on the interaction of remote partners together with information support for international cooperation. The work considers the variety of implementation of digital technologies, identifies status of communication members in paradiplomacy, and different forms of communication. The importance of integrating electronic document management with information systems to support decision making is substantiated. The issues of creating special purpose information services for participants in foreign economic activity, cultural and humanitarian relations are considered. The experience of the Republic of Tatarstan testifies the need of legal regulation at the regional level to provide efficient use of information technologies by government authorities. Actual areas of digitalization include development of feedback forms with participants in external relations and creating computer systems of processing data sets to substantiate decision-making.

Radio U-Net: a convolutional neural network to detect diffuse radio sources in galaxy clusters and beyond

ABSTRACT The forthcoming generation of radio telescope arrays promises significant advancements in sensitivity and resolution, enabling the identification and characterization of many new faint and diffuse radio sources. Conventional manual cataloguing methodologies are anticipated to be insufficient to exploit the capabilities of new radio surveys. Radio interferometric images of diffuse sources present a challenge for image segmentation tasks due to noise, artifacts, and embedded radio sources. In response to these challenges, we introduce Radio U-Net, a fully convolutional neural network based on the U-Net architecture. Radio U-Net is designed to detect faint and extended sources in radio surveys, such as radio haloes, relics, and cosmic web filaments. Radio U-Net was trained on synthetic radio observations built upon cosmological simulations and then tested on a sample of galaxy clusters, where the detection of cluster diffuse radio sources relied on customized data reduction and visual inspection of Low-Frequency Array Two metre Sky Survey (LoTSS) data. The 83 per cent of clusters exhibiting diffuse radio emission were accurately identified, and the segmentation successfully recovered the morphology of the sources even in low-quality images. In a test sample comprising 246 galaxy clusters, we achieved a 73 per cent accuracy rate in distinguishing between clusters with and without diffuse radio emission. Our results establish the applicability of Radio U-Net to extensive radio survey data sets, probing its efficiency on cutting-edge high-performance computing systems. This approach represents an advancement in optimizing the exploitation of forthcoming large radio surveys for scientific exploration.

Role of HSP90 in Type 2 Diabetes Mellitus and Its Association with Liver Diseases.

Non-alcoholic fatty acid liver disease (NAFLD), non-alcoholic steatohepatitis (NASH) and hepatocellular carcinoma (HCC) are the fatal liver diseases which encompass a spectrum of disease severity associated with increased risk of type 2 diabetes mellitus (T2DM), a metabolic disorder. Heat shock proteins serve as markers in early prognosis and diagnosis of early stages of liver diseases associated with metabolic disorder. This review aims to comprehensively investigate the significance of HSP90 isoforms in T2DM and liver diseases. Additionally, we explore the collective knowledge on plant-based drug compounds that regulate HSP90 isoform targets, highlighting their potential in treating T2DM-associated liver diseases. Furthermore, this review focuses on the computational systems' biology and next-generation sequencing technology approaches that are used to unravel the potential medicine for the treatment of pleiotropy of these 2 diseases and to further elucidate the mechanism.

Advanced image analysis for medical diagnostics: a system for segmentation and classification using level set methods and AI algorithms

This work aims to implement and utilize an advanced computer system for image analysis and processing through artificial intelligence. The system will evaluate images from multiple sources. As a result, a comprehensive e-Medicus system will be developed to capture and analyze X-ray data and classify cancer cells. This innovative tool, with its unique features tailored for medical facilities, will assist them in capturing and analyzing X-ray images and CT scan results. The e-Medicus system offers several benefits for medical facilities, including efficient automation of photo analysis, tracking changes in a patient's condition over time, and facilitating the identification of medical changes and data classification. A multimedia presentation of the change process will use the contour set function, allowing for topological changes in solution properties. The system integrates novel procedures and algorithms from theoretical computer science and numerical mathematics, leveraging neural networks, genetic algorithms, semantic networks, image ontology, rough set theory, contour set methods, and hybrid algorithms. These developed algorithms enhance methods and concepts in image segmentation, gathering, transmitting, storing, extracting, and effectively presenting information.

Exploring The Horizon of Neuromorphic Computing: Research Progress of Synaptic Transistor Materials

In recent years, with the rapid development of integrated circuits, Moore's law has become more and more difficult to maintain. The brain-like neuromorphic computing system based on the new brain-like device synaptic transistor provides an alternative way for future computers. At present, a large number of studies have tried to fabricate synaptic transistors with different materials, and simulated synaptic behavior successfully. In this review, the basic structure and function of synaptic transistors are described, and three kinds of materials for fabricating synaptic transistors are classified: organic and non-solid electrolyte materials, inorganic solid materials and organic flexible materials, and their current research is reviewed. The purpose of this review is to provide more research directions for the research in the field by summarizing the current research on the fabrication materials of synaptic transistors. At present, there are still many new materials that have not been tried in the research field of synaptic transistors. Trying to use composite materials and two-dimensional materials is a noteworthy research direction, which is expected to promote the development of a new generation of memory technology and the application in the field of artificial intelligence.

An Efficient Computational System For Defect Prediction through Neural Network And Bio-inspired Algorithms

Detecting and locating damage is essential in maintaining structural integrity. While Artificial Neural Networks (ANNs) are effective for this purpose, their performance can be significantly improved through advanced optimization techniques. This study introduces a novel approach using the Grasshopper Optimization Algorithm (GOA) to enhance ANN capabilities for predicting defect aluminum plates. The methodology begins by deriving input parameters from natural frequencies, with defect locations as the output. A Finite Element Model (FEM) is used to simulate data by varying defect locations, creating a comprehensive dataset. To validate this approach, experimental data from vibration analyses of plates with different defect locations is collected. We then compare the performance of our GOA-optimized ANN against other metaheuristic algorithms, such as Cuckoo Search Algorithm (CSA), Bat Algorithm (BA), and Firefly Algorithm (FA). Notably, CSA's performance is slightly close to GOA. The results show that our GOA-based method outperforms these traditional algorithms, demonstrating superior accuracy in damage prediction. This advancement holds significant potential for applications in structural integrity monitoring and maintenance.

The Role of Semiconductor Devices in the Development of High-Performance Computing Systems: Challenges in Scaling and Heat Dissipation

The Role of Semiconductor Devices in the Development of High-Performance Computing Systems: Challenges in Scaling and Heat Dissipation

PERFORMANCE ANALYSIS OF TASK SCHEDULING USING HYBRID GENETIC MODIFIED WHALE OPTIMIZATION ALGORITHM IN CLOUD COMPUTING

Cloud computing plays a vital role, which is used to access computing resources and information online. There are a lot of challenges in accessing cloud computing systems. One of the major challenges among these is resource Management which includes scheduling, allocation, and sharing. In this paper, the Hybrid Genetic Modified Whale optimization algorithm which is a combined Genetic and Modified Whale optimization algorithm to analyze the performance of the cloud computing system such as task completion time, execution cost, speedup, and efficiency with proper allocation and sharing of resources The performance of the proposed algorithm is compared with Genetic algorithm and Whale optimization algorithm. The main target of this Proposed system is to reduce the completion time of the task by increasing the speed. Cloud Sim environment tool kit is used for the testing of the proposed system.

The political economy of digital government: How Silicon Valley firms drove conversion to data science and artificial intelligence in public management

IMPACT The relationships between digital governments and private digital technology corporations shape investments that endure for years, even decades. Yet recent changes have been under-researched in public management and accountability studies. Until the 2010s systems integrators (SIs) were dominant, producing proprietary legacy computer systems that still shape government technologies today. Since that time, governments have become increasingly reliant on the online tools and cloud technologies developed by Silicon Valley (SV) firms and platform corporations. To keep digital investments in line with business and civil society progress, governments have had to catch up and innovate with the latest generation of data-intensive technologies, such as artificial intelligence (AI), and to adopt some SV organizational culture and practices in government. However, previous long time-lags in public sector responses highlight many lessons for today’s digital government change pioneers. In particular, the article illustrates the importance for digital managers of accelerating change in government organizational cultures, and developing the expertise to manage contractual diversity.

PERFORMANCE ANALYSIS OF TASK SCHEDULING USING HYBRID GENETIC MODIFIED WHALE OPTIMIZATION ALGORITHM IN CLOUD COMPUTING

Cloud computing plays a vital role, which is used to access computing resources and information online. There are a lot of challenges in accessing cloud computing systems. One of the major challenges among these is resource Management which includes scheduling, allocation, and sharing. In this paper, the Hybrid Genetic Modified Whale optimization algorithm which is a combined Genetic and Modified Whale optimization algorithm to analyze the performance of the cloud computing system such as task completion time, execution cost, speedup, and efficiency with proper allocation and sharing of resources The performance of the proposed algorithm is compared with Genetic algorithm and Whale optimization algorithm. The main target of this Proposed system is to reduce the completion time of the task by increasing the speed. Cloud Sim environment tool kit is used for the testing of the proposed system.

A Novel Method of Using Machine Learning Techniques to Protect Clouds Against Distributed Denial of Service (DDoS) Attacks.

The term "cloud computing" describes a method of providing hardware- and software-based services over the internet. This allows users to access their data and apps from any device. The benefits of cloud computing include scalability, virtualization, access to user assets, lower infrastructure costs, and flexibility. However, one drawback is that it is susceptible to distributed denial of service attacks, which occur when multiple computer systems collaborate to target a particular resource, website, or server. Distributed denial of service (DDoS) attacks present a serious risk to computer networks and constitute a major cyber security challenge. This results in a denial of service for end users, as a result of false connection requests, a flood of messages, and twisted packets causing the system to slow down or even crash. Real people and services cannot access cloud computing. The issue of machine learning algorithms for identifying distributed denial of service (DDoS) attacks is explored in this article. In order to identify and defend cloud systems from harmful assaults, we developed a new machine learning approach in this work that is based on transfer learning. This study offers NSL-KDD datasets and two methodologies. There are two types of filters available: the Learning Vector Quantization (LVQ) Filters and the Principal Component Analysis (PCA) method, which reduces dimensionality. The features selected from each method were pooled using Decision Tree (DT), Naïve Bayes (NB), and Support Vector Machine (SVM) to detect distributed denial of service attacks (DDoS). We contrasted the results of several classifications. In terms of attack detection, LVQ-based DT performed better results as compared to other methods.

Profit Comparison of Computer System with Hardware Redundancy Subject to Different Repair Activities

In this research paper, main concentrate of the authors on the profit comparison of computer system with hardware redundancy by introducing the concept of priority to software up-gradation, hardware preventive maintenance (PM) and hardware maximum repair time (MRT). The system fails independently from normal mode. All the repair activities such as hardware repair, software up-gradation, hardware preventive maintenance before failure and hardware replacement after maximum repair time are carried out by a single server immediately on need basis. All random variables are statistically independent. The negative exponential distribution is taken for the failure time of the component while the distributions of repair time, up-gradation time, preventive maintenance and replacement time are assumed arbitrary with different probability density functions. Semi-Markov process and regenerative point technique are used. The behaviour of profits of the system models have been examined for different parameters and costs.