Computer Hardware Research Articles

A Scalable Sorting Network Based on Hybrid Algorithms for Accelerating Data Sorting

Sorting in sequential data mining is significantly improved through hardware acceleration, which becomes essential as data volume and complexity increase. This paper presents a scalable hybrid sorting network that maintains or improves performance while reducing computational load and hardware requirements. The network is composed of the pre-comparison odd–even sorting network (P-OESN) and the bidirectional insertion sorting network (BISN). A pre-comparison layer is introduced to the original OESN. This layer aims to place larger values in the first half of the input sequence and smaller values in the latter half. The number of iterations is reduced when the P-OESN transitions from fully parallel execution to iterative execution. A novel pipelined BISN architecture is proposed, which leads to enhanced operating frequency and throughput. The experimental results show that the pre-comparison layer reduces the number of iterations by 6% to 50%. Throughput is improved by more than four times, and operating frequency is increased by more than two times due to the pipelined BISN. The proposed hybrid sorting network reduces sorting time or resource usage, while enabling the sorting of large-scale data sets that other methods cannot support.

Advances in Artificial Intelligence and Computational Methods: Enhancing Modeling, Prediction, and Optimization

bstract: This area of artificial intelligence and computational methods has witnessed tremendous development, especially with the solution of highly complex problems across scientific disciplines. This review brings together the latest advancements in the integration of AI with traditional computational techniques, focusing on their applications in numerical simulations, system optimization, and predictive modeling. Key contributions include AI-augmented finite difference methods for solving partial differential equations, advancements in material and energy systems optimization, and innovative approaches to highperformance computing. Future directions emphasize scalability, interdisciplinary applications, and the integration of emerging technologies such as quantum computing and reconfigurable hardware.

MESSI: Task Mapping and Scheduling Strategy for FPGA-based Heterogeneous Real-Time Systems

Continuous demands for improved performance within constrained resource budgets are driving a move from homogeneous to heterogeneous processing platforms for the implementation of today’s Real-Time (RT) embedded systems. The applications executing on such systems are typically represented as a Precedence Task Graph (PTG), where a node represents a task or algorithm for one functionality and edges represent the complex interactions between multiple functionalities. Due to RT constraints, the task graph needs to be executed within a specified deadline. Although some existing studies have looked into solving this challenge, comprehensive studies that combine the theoretical features of RT task-graph mapping and scheduling with practical runtime architectural characteristics have mostly been ignored to date. Hence, in this paper, we consider the challenge of scheduling a RT application modelled as a single PTG, with the objective of minimizing the overall execution time under Hardware (HW) resource and deadline constraints for heterogeneous Central Processing Unit (CPU) + Field Programmable Gate Array (FPGA) architectures. First, we introduce an optimal solution using Integer Linear Programming (ILP). However, this ILP-based optimal solution suffers from computational complexity and does not scale well even for moderately large problem sizes. Hence, we additionally propose heuristic algorithms for task mapping and scheduling. The efficiency of the proposed scheme, named MESSI, has been evaluated through experiments using PTGs on a practical CPU+FPGA system regarding current technology restrictions. Our experiments demonstrate that performance gains of 55.6 % and area usage reductions of 46.3 % are possible compared to full Software SW and HW execution, respectively.

Development of Learning Videos on Computer Hardware Materials

This study aimed to develop a learning video on computer hardware material at SMP Negeri 8 Jangkang using the ADDIE development method. This study involved 32 grade VII students as test subjects and six validators consisting of material, design, and media experts. Qualitative and quantitative data analysis showed that the developed learning video had a very high feasibility level, with an average percentage of 96% in the material, design, and media aspects. Empirical tests on 32 students showed similar results, with a feasibility level reaching 98% and positive responses from students to the learning media. Statistical tests using the Mann-Whitney method showed a significant difference between the experimental and control groups, with a substantial effect value of 5.44. These findings indicate that learning videos have a very considerable influence on student learning outcomes. Based on the study results, learning videos are categorized as very effective media and positively impact student learning outcomes on computer hardware material. In addition, student responses to the use of this media were very positive, which confirmed its effectiveness and usefulness in supporting a more interactive and enjoyable learning process.

Comparative Aerodynamic Analysis and Parallel Performance of 2D CFD Simulations of a VAWT Using Sliding Mesh Interface Method

ABSTRACTWith rapid advancements in computer hardware and numerical modeling methods, Computational Fluid Dynamics (CFD) has gained prominence in simulating complex flows. As parallel computation becomes an industry standard, the computational efficiency of simulations has become critical. The flow around a Vertical Axis Wind Turbine (VAWT), characterized by complex dynamics and challenging rotating geometry, serves as an intriguing case for CFD studies. This study employs the open‐source CFD solvers SU2 and OpenFOAM to simulate the incompressible, unsteady, and turbulent flow around an H‐type Darrieus VAWT in two dimensions. Spatial and temporal discretization parameters are examined to balance computational cost and accuracy, revealing notable effects on power predictions. Simulations conducted under identical conditions allow for a comparison of the predictions and parallel performances of SU2 and OpenFOAM across three distinct tip speed ratios (TSRs). The findings show that discretization parameters behave differently at various TSRs. While power predictions from SU2 and OpenFOAM generally align with experimental data and with each other, discrepancies arise at lower TSRs, with thrust predictions showing better consistency. Although OpenFOAM provides a faster solution across all parallel configurations, SU2 demonstrates superior parallel scalability, achieving higher speedup and efficiency.

Efficient optical trapping force tuning for cusp-catastrophe autofocusing beams using deep neural networks

Structured light adjusts optical trapping forces through flexible structure design. However, it is challenging to evaluate optical forces on microscopic particles in structured light due to high computational hardware requirements, prolonged computation times, and data inefficiencies associated with solving optical trapping forces using generalized Lorenz–Mie theory. We propose the use of deep neural networks for predicting and tuning the optical trapping force of cusp-catastrophe autofocusing beams on Mie particles. Inputs include beam's structural parameters, laser power, and the size of captured particle, while the output is the optical trapping force. Following iterative training, the neural network achieved a mean square error of 1.5×10−5. Evaluation using 150 sets of test data revealed that 95.3% of the predictions had a relative error of less than 1.8%, indicating a high prediction accuracy. In contrast to traditional computational methods, the neural network model demonstrates a remarkable efficiency improvement—104 times faster in optimizing beams for optical trapping. This advancement demonstrates the advantage of deep learning neural networks for the application of structured light including autofocusing beams in optical tweezers.

Numerical Analysis of the Magnetic Moment in S/F/S-Josephson Junction

One particularly intriguing object in superconductivity is the Josephson junction, which is an integral part of quantum computer hardware. Analysing this object requires solving differential equations. Such problems often cannot be solved with analytical methods; therefore, numerical methods and computational mathematics must be utilized. This article explores a fundamental model of the Josephson junction. The model presents the spatial coordinates of the magnetic moment as unknown functions dependent on time in a system of three ordinary differential equations with initial conditions. Comparative analysis of various methods is conducted for different sets of parameters. Optimal numerical methods for these particular instances of the problem are found. Visual results are also presented.

Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing.

Large language models (LLMs), with their remarkable generative capacities, have greatly impacted a range of fields, but they face scalability challenges due to their large parameter counts, which result in high costs for training and inference. The trend of increasing model sizes is exacerbating these challenges, particularly in terms of memory footprint, latency and energy consumption. Here we explore the deployment of 'mixture of experts' (MoEs) networks-networks that use conditional computing to keep computational demands low despite having many parameters-on three-dimensional (3D) non-volatile memory (NVM)-based analog in-memory computing (AIMC) hardware. When combined with the MoE architecture, this hardware, utilizing stacked NVM devices arranged in a crossbar array, offers a solution to the parameter-fetching bottleneck typical in traditional models deployed on conventional von-Neumann-based architectures. By simulating the deployment of MoEs on an abstract 3D AIMC system, we demonstrate that, due to their conditional compute mechanism, MoEs are inherently better suited to this hardware than conventional, dense model architectures. Our findings suggest that MoEs, in conjunction with emerging 3D NVM-based AIMC, can substantially reduce the inference costs of state-of-the-art LLMs, making them more accessible and energy-efficient.

Two-Dimensional Materials for Brain-Inspired Computing Hardware.

Recent breakthroughs in brain-inspired computing promise to address a wide range of problems from security to healthcare. However, the current strategy of implementing artificial intelligence algorithms using conventional silicon hardware is leading to unsustainable energy consumption. Neuromorphic hardware based on electronic devices mimicking biological systems is emerging as a low-energy alternative, although further progress requires materials that can mimic biological function while maintaining scalability and speed. As a result of their diverse unique properties, atomically thin two-dimensional (2D) materials are promising building blocks for next-generation electronics including nonvolatile memory, in-memory and neuromorphic computing, and flexible edge-computing systems. Furthermore, 2D materials achieve biorealistic synaptic and neuronal responses that extend beyond conventional logic and memory systems. Here, we provide a comprehensive review of the growth, fabrication, and integration of 2D materials and van der Waals heterojunctions for neuromorphic electronic and optoelectronic devices, circuits, and systems. For each case, the relationship between physical properties and device responses is emphasized followed by a critical comparison of technologies for different applications. We conclude with a forward-looking perspective on the key remaining challenges and opportunities for neuromorphic applications that leverage the fundamental properties of 2D materials and heterojunctions.

Application of Discrete Event Simulation to Enhance the Efficiency of the Ant Colony Optimization Algorithm

The application of the Ant Colony Optimization (ACO) algorithm to solve the the Traveling Salesman Problem (TSP) has been extensively studied by scientists worldwide. However, implementing the algorithm faces challenges due to the randomness in the departure and movement times of ants, as well as the limitations of computer hardware. These factors reduce the algorithm's convergence ability and overall effectiveness. This paper proposes an approach to implement the algorithm by utilizing discrete event simulation (DES). Artificial ants are modeled to depart and move completely randomly, closely mimicking the behavior of natural ants. This approach accelerates the algorithm's convergence, minimizes the likelihood of falling into local optima, and enhances overall performance. The simulation results clearly demonstrate the advantages of this method.

Exploration of image processing in various domains: A review

Interest in digital image processing methods stems from two principal application areas: improvement of pictorial information for human interpretation; and processing of image data for storage, transmission, and representation for autonomous machine perception. Computer digital image technology is a very important branch of the computer application discipline, and its application areas include measurement, computer-aided design, physics, three-dimensional simulation and other industries. Moreover, with the improvement of computer hardware performance, image processing algorithms have improved the application of digital image processing technology. This Review article focuses on the current digital image processing technology and its application in Medical, forest protection and other fields of today’s interest.

Pelatihan Pengenalan Dasar-Dasar Komputer Hardware dan Software

Training in introducing computer basics is one of the trainings that students can develop because the acquisition of excess competencies from this training is quite promising. If students, after becoming alumni, can develop these competencies, it will be very profitable. Partners in this PKM activity are students from MTs Pembangunan Nurul Islam, Sarimulya Setu, South Tangerang. The introductory training on the basics of computer hardware and software was carried out in stages: introduction, counseling and assistance in using it. Based on the results of observations and discussions with partners, there were several problems faced by the introductory training on computer basics, namely students' lack of operating computer technology perfectly, lack of Student motivation when studying computer technology. One of the causes is a lack of awareness of how important it is to study computer technology. The solutions proposed or offered in this PKM activity are as follows: 1. Facilitate and provide direction to MTs students at the school, it is hoped that they can understand the basics of computers more freely without fear. 2. Provide computer basics learning according to level. for junior high school level, they are given advanced material from what they learn formally in school informatics lessons. During training activities, students are encouraged to be able to understand the basics of computers with the aim of raising their self-confidence in learning. For this reason, the PKM team will help to solve problems in the management aspect using training methods

USING FACIAL EXPRESSIONS FOR CUSTOM ACTIONS: DEVELOPMENT AND EVALUATION OF A HANDS-FREE INTERACTION METHOD

This study explores a novel facial expression-based interaction method designed to provide an accessible and hands-free alternative for performing precision tasks. Traditional input devices, such as keyboards and mice, are often unsuitable for individuals with limited mobility or for hands-free environments. The proposed system leverages standard computer hardware and machine learning-based facial landmark detection to map customizable facial expressions to specific actions, making it a low-cost and adaptable solution. This study evaluates the usability, learnability, and potential applications of this interaction method through a task-based user study. Sixteen participants aged 19–34 completed a series of five trials, performing the same color and number-matching task on an interactive grid. This approach allowed the evaluation of the learning curve by analyzing how participants improved their skills and reduced task completion times with each subsequent trial. Participants also provided feedback on challenging facial expressions to identify usability challenges. The evaluation focused on task completion time, participant-reported challenging actions, and qualitative feedback to assess system usability, user adaptability, and potential applications. The results indicate a clear learning curve, with participants improving task completion times over repeated trials. Feedback highlighted the potential of this interaction method for assistive technologies, gamified facial exercises, and as a supplementary input tool, while also identifying challenges such as facial fatigue and action complexity. The findings demonstrate the system's promise as an accessible and adaptable alternative interaction method, with opportunities for future refinement and broader application.

Dynamic Comfort Considerations in the Design of High-rise Buildings

<p>The following paper provides research analysis on the influence of wind on a building, considering the regional and local climate conditions, to improve dynamic stability and reduce wind disruption effects on high-rise reinforced concrete buildings. The main aspect of disturbance in living conditions is caused by wind loads on the building. The data is based on structural analysis, generated by the “Lira CAD 2013” ​​software, for a construction project of a 19-story residential building, completed in Georgia’s capital Tbilisi, 58 Kavtaradze St., in accordance with the given necessary requirements and restrictions by general terms and conditions of the Georgian state law. Computer aided modeling provides the ability to simulate and define parameters caused by the wind disruption on an actual site. Calculation process is based on variables specified by state law for each region of the country. Modified accelerations which have been caused by wind in multi-story, high-rise buildings have significantly greater values on upper floors, and reaching the edges ​​​​of the minimum living comfort criteria. The given study features the estimation for high-rise buildings under various combinations of loads. High-rise buildings have gone under significant restrictions due to use of conventional rigid frames as structural elements in the construction process. That process tends to develop a series of new research and findings for proper architectural forms, which became possible using the new generation of fast digital computing software and hardware.</p>

Spiking Flip-Flop Memory in Resonant Tunneling Diode Neurons.

We report a spiking flip-flop memory mechanism that allows controllably switching between neural-like excitable spike-firing and quiescent dynamics in a resonant tunneling diode (RTD) neuron under low-amplitude (<150 mV pulses) and high-speed (ns rate) inputs pulses. We also show that the timing of the set-reset input pulses is critical to elicit switching responses between spiking and quiescent regimes in the system. The demonstrated flip-flop spiking memory, in which spiking regimes can be controllably excited, stored, and inhibited in RTD neurons via specific low-amplitude, high-speed signals (delivered at proper time instants) offers high promise for RTD-based spiking neural networks, with the potential to be extended further to optoelectronic implementations where RTD neurons and RTD memory elements are deployed alongside for fast and efficient photonic-electronic neuromorphic computing and artificial intelligence hardware.

Pixel‐Level Hardware Strategy for Large‐Scale Convolution Calculation in Neuromorphic Devices

AbstractFor convolution neural networks, increasing the performance of hardware computer systems is crucial in the era of big data. Benefiting from the neuromorphic devices, producing the convolutional calculation at the crossbar array circuit has become a promising approach for high‐performance hardware computer systems. However, as computation scales, this hardware system faces the challenge of low resource utilization efficiency and low power efficiency. Here, a novel pixel‐level strategy, leveraging the dynamic change of electron concentration as the process of convolution calculation, is proposed for high‐performance hardware computer systems. Compared with the crossbar array circuit‐based strategy, instead of at least four devices, raised the power efficiency to 413% and decreased the training epochs to 38%. This work presents a novel physics‐based approach that enables highly efficient convolutional calculation, improves power efficiency, speeds up convergency, and paves the way for building complex convolution neural networks with large‐scale convolutional computation capabilities.

Navigating Computing Device Requirements: A systematic review and guide for healthcare administrators

Background: The transition from paper-based to electronic-based processes is an ongoing issue in all health systems with varying levels throughout the world. Hospitals are increasingly transitioning to digital medical records and paperless workflows. As medical administrators tackle the challenge of ensuring computer systems and hardware meet the needs of the staff hospital environment, it is essential to adopt a systematic and well-informed approach to allocate different wards with computing devices based on staffing numbers, patient occupancy, and patient flow requirements. Goal: To review existing literature and develop a framework for determining the necessary computing resources for a hospital ward to operate effectively. Methods: A systematic review was conducted using the PRISMA process and relevant publications were identified, covering data from 1946 to January 2022. Only English articles were included, and any articles relating to software development and digital medical records were excluded. The quality of the studies included was assessed using the Johanna Briggs Institute (JBI) Checklist for Qualitative Research. A search of grey literature was also conducted due to the paucity of search results, for a total of 14 included studies. Additionally, we mapped the workflow in clinical wards. Drawing insights from a multivariate analysis based on this mapping and literature review, we formulated and validated a framework for hospitals to strategically plan computer usage and optimise ward workflows. Principal Findings: We propose a framework based on the number and skills of a mix of staff, patient turnover and the extent of computerised tasks. Whilst individual hospitals will differ in computing and technology utilisation, our proposed framework can be adapted to suit unique needs. Practical Applications: A similar framework can be used to implement computers across various health services. It can also be adapted for sporting organisations, where multiple health professionals need computers to manage athletes' health and performance.

Investigating the policies, the resources and gaps in the competencies of Bachelor of Technical-Vocational Teacher Education (BTVTEd) prescribed by: TESDA and K to 12 Basic Education Curriculum and a proposed curriculum revision for Bachelor of Technical -Vocational Teacher Education in the Philippines

In response to evolving societal needs and educational goals, this study aimed to revise the Bachelor of Technical-Vocational Teacher Education (BTVTEd) Program at Mariano Marcos State University. Utilizing a research and development framework, the study incorporated document analysis, focus group discussions with selected stakeholders, and validation by curriculum experts. Findings revealed significant gaps in resources and curriculum content, including inadequate teaching facilities, unqualified faculty, insufficient funding, and misaligned competencies with TESDA and K to 12 standards in areas like Computer Hardware Servicing and Electrical Technology. Stakeholders highlighted the need for improved course organization, alignment with program objectives, relevant skill integration, faculty development, and a supportive learning environment. To address these issues, a revised BTVTEd curriculum was developed and validated as highly acceptable for implementation. It is recommended that this proposed curriculum be adopted to effectively bridge the identified competency gaps and better serve the needs of students, educational institutions, and industry partners.

Development of Augmented Reality Based Learning Media for Computer Hardware Materials at SMP Santa Monika

This study aims to develop augmented reality-based learning media for computer hardware materials for Grade VII students at SMP Santa Monika. The research method employed is Research and Development (R&amp;D) using the ADDIE design model, which consists of Analysis, Design, Development, Implementation, and Evaluation. The product development subjects include expert validators in media and material: two lecturers in Information Technology Education, one lecturer in Information Technology Education, and an informatics subject teacher. The small-scale and large-scale product testing subjects consist of Grade VII students at SMP Santa Monika, with a total of 40 students. Data collection techniques used in the study include direct communication, indirect communication, and data collection tools such as unstructured interviews, questionnaires, and documentation. Based on the results obtained, the conclusion of this study is that the augmented reality-based learning media developed is feasible for use in the learning process. The validation results from media and material experts achieved an average percentage of 89.75%, categorized as highly feasible. Additionally, the student response questionnaire results in the small-scale trial showed a percentage of 80.33%, while the large-scale trial achieved 89.74%, both categorized as excellent.

The Application of Machine Learning on Antibody Discovery and Optimization

Antibodies play critical roles in modern medicine, serving as diagnostics and therapeutics for various diseases due to their ability to specifically bind to target antigens. Traditional antibody discovery and optimization methods are time-consuming and resource-intensive, though they have successfully generated antibodies for diagnosing and treating diseases. The advancements in protein data, computational hardware, and machine learning (ML) models have the opportunity to disrupt antibody discovery and optimization research. Machine learning models have demonstrated their abilities in antibody design. These machine learning models enable rapid in silico design of antibody candidates within a few days, achieving approximately a 60% reduction in time and a 50% reduction in cost compared to traditional methods. This review focuses on the latest machine learning-based antibody discovery and optimization developments. We briefly discuss the limitations of traditional methods and then explore the machine learning-based antibody discovery and optimization methodologies. We also focus on future research directions, including developing Antibody Design AI Agents and data foundries, alongside the ethical and regulatory considerations essential for successfully adopting machine learning-driven antibody designs.