Parallel Processing Techniques Research Articles

Parallel translation process in consecutive interpreting: Differences between beginning and advanced interpreting students

This study examines the parallel translation process of 30 beginning and 30 advanced consecutive interpreting students (BISs and AISs). It investigates the characteristics and efficiency of parallel translation processing employed during the comprehension phase across proficiency levels. Quantitative and qualitative analyses reveal AISs demonstrated superior information reformulation capabilities, particularly for high-density content, along with more efficient note-taking and utilization compared to BISs. A key finding is that AISs interpreted more propositions than they recorded in their notes, reflecting stronger encoding and memory retention. In contrast, BISs relied heavily on external notation instead of internal memory retrieval, only interpreting a portion of their notes while failing to decipher the rest. These findings uncover complex yet differentiated parallel processing approaches across skill levels, with more successful comprehension-to-production strategies utilized by AISs. Enhancing students’ metacognitive awareness regarding parallel processing techniques may improve information processing efficiency during source language comprehension, ultimately enhancing target language reformulation accuracy and completeness.

HPB3C-3PG algorithm: A new hybrid global optimization algorithm and its application to plant classification

This paper proposes a hybrid bio-inspired search and optimization algorithm that combines the strengths of the PB3C (Parallel Big Bang Big Crunch) and 3PGA (3 Parent Genetic Algorithm) algorithms. The hybrid algorithm employs a single population-based evolutionary search coupled with multi-population parallel processing techniques to address optimization problems. The proposed algorithm is implemented in MATLAB software. We evaluate the performance of the proposed algorithm on the CEC2021 standard test bench suite. The performance of the proposed approach is compared with that of the other nine algorithms. The comparative analysis shows that the proposed hybrid PB3C and 3PGA algorithms performed better than the other nine optimization algorithms. Furthermore, this chapter proposes an HPB3C-3PGA-based approach to evolve the near-optimal architecture of CNN. The proposed plant image classification approach is implemented in Python and compared with 12 other approaches. The proposed approach achieved an accuracy of 98.96% on the Mendeley dataset and 98.97% on the CVIP100 dataset. The proposed approach outperforms all other approaches for the plant leaf classification problem. This research significantly contributes to overcoming limitations in existing approaches, providing a robust solution for optimization problems and image classification tasks.

Mathematical modeling and problem solving: from fundamentals to applications

The rapidly advancing fields of machine learning and mathematical modeling, greatly enhanced by the recent growth in artificial intelligence, are the focus of this special issue. This issue compiles extensively revised and improved versions of the top papers from the workshop on Mathematical Modeling and Problem Solving at PDPTA'23, the 29th International Conference on Parallel and Distributed Processing Techniques and Applications. Covering fundamental research in matrix operations and heuristic searches to real-world applications in computer vision and drug discovery, the issue underscores the crucial role of supercomputing and parallel and distributed computing infrastructure in research. Featuring nine key studies, this issue pushes forward computational technologies in mathematical modeling, refines techniques for analyzing images and time-series data, and introduces new methods in pharmaceutical and materials science, making significant contributions to these areas.

Parallel Fractional Stochastic Gradient Descent With Adaptive Learning for Recommender Systems

The structural change toward the digital transformation of online sales elevates the importance of parallel processing techniques in recommender systems, particularly in the pandemic and post-pandemic era. Matrix factorization (MF) is a popular and scalable approach in collaborative filtering (CF) to predict user preferences in recommender systems. Researchers apply Stochastic Gradient Descent (SGD) as one of the most famous optimization techniques for MF. Paralleling SGD methods help address Big Data challenges due to the wide range of products and the sparsity in user ratings. However, these methods’ convergence rate and accuracy are affected by the dependency between the user and item latent factors, specifically in large-scale problems. Besides, the performance is sensitive to the applied learning rates. This paper proposes a new parallel method to remove dependencies and boost speed-up by using fractional calculus to improve accuracy and convergence rate. We also apply adaptive learning rates to enhance the performance of our proposed method. The proposed method is based on Compute Unified Device Architecture (CUDA) platform. We evaluate the performance of our proposed method using real-world data and compare the results with the close baselines. The results show that our method can obtain high accuracy and convergence rate in addition to high parallelism.

GPU-Based Parallel Processing Techniques for Enhanced Brain Magnetic Resonance Imaging Analysis: A Review of Recent Advances.

The approach of using more than one processor to compute in order to overcome the complexity of different medical imaging methods that make up an overall job is known as GPU (graphic processing unit)-based parallel processing. It is extremely important for several medical imaging techniques such as image classification, object detection, image segmentation, registration, and content-based image retrieval, since the GPU-based parallel processing approach allows for time-efficient computation by a software, allowing multiple computations to be completed at once. On the other hand, a non-invasive imaging technology that may depict the shape of an anatomy and the biological advancements of the human body is known as magnetic resonance imaging (MRI). Implementing GPU-based parallel processing approaches in brain MRI analysis with medical imaging techniques might be helpful in achieving immediate and timely image capture. Therefore, this extended review (the extension of the IWBBIO2023 conference paper) offers a thorough overview of the literature with an emphasis on the expanding use of GPU-based parallel processing methods for the medical analysis of brain MRIs with the imaging techniques mentioned above, given the need for quicker computation to acquire early and real-time feedback in medicine. Between 2019 and 2023, we examined the articles in the literature matrix that include the tasks, techniques, MRI sequences, and processing results. As a result, the methods discussed in this review demonstrate the advancements achieved until now in minimizing computing runtime as well as the obstacles and problems still to be solved in the future.

A Systematic Survey of Multilingual Speech Transcription and Translation

This paper presents an innovative initiative dedicated to revolutionizing multilingual communication by leveraging state-of-the-art technologies such as Artificial Intelligence (AI), NLP, or natural language processing and Machine Learning. With a primary focus on Indian languages, the research aims to develop an advanced system capable of seamlessly transcribing speech across diverse linguistic landscapes. Through the incorporation of cutting-edge algorithms and parallel processing techniques, the proposed system facilitates real-time transcription and translation of multiple languages concurrently. Rigorous experimentation and analysis demonstrate the efficiency of the developed framework in breaking down language barriers and fostering inclusive communication. Furthermore, the paper emphasizes the cultural significance of this technology in promoting global connectivity and celebrating linguistic diversity. Ultimately, this research underscores the transformative potential of technology in facilitating cross-cultural understanding and enabling meaningful interactions within a multilingual society

SWOT Analysis of Parallel Processing APIs - CUDA, OpenCL, OpenMP and MPI and their Usage in Various Companies

Purpose: Parallel Processing is the technique of achieving High Performance Computing (HPC) with parallel execution of programs that are synchronized during the execution time. This research paper studied the companies which use Parallel Processing techniques in their projects and products along with the identification of major Application Program Interfaces (APIs) that are used to achieve parallelism. The major aim of this research work is to perform the SWOT analysis of Parallel Processing APIs to identify the importance of each one from the company perspective. Design/Methodology/Approach: The research method adopted to accomplish the SWOT Analysis of Parallel Processing APIs - CUDA, OpenCL, OpenMP and MPI and their Usage in Various Companies is qualitative and exploratory in nature. Systematic literature review of different companies that use Parallel Processing techniques to build and develop parallel programs is done during this research work. Findings/Results: Parallel Processing constructs can be used to solve various problems in the six major application domains as: - Computational Finance & Business Economics, Artificial Intelligence, Machine Learning (ML), Data Science, Numerical Analysis and Design of Algorithms. Major Parallel Processing APIs used in companies are: - CUDA, OpenCL, OpenMP and MPI for implementing the problems with parallel execution. Foremost companies that use Parallel Processing APIs are studied and various applications, systems, models, and projects that are developed using Parallel Processing techniques are listed. SWOT Analysis is performed on all four Parallel Processing APIs and its SWOT(Strengths-Weaknesses-Opportunities-Threats) are identified. Originality/Value: Listing of SWOT Analysis (Strengths-Weaknesses-Opportunities-Threats) of Parallel Processing APIs - CUDA, OpenCL, OpenMP and MPI. Paper Type: Company Analysis research paper

Promoting Sustainable Travel Experiences: A Weighted Parallel Hybrid Approach for Personalized Tourism Recommendations and Enhanced User Satisfaction

With the growing significance of the tourism industry and the increasing desire among travelers to discover new destinations, there is a need for effective recommender systems that cater to individual interests. Existing tourism mobile applications incorporate recommendation systems to alleviate information overload. However, these systems often overlook the varying importance of different items, resulting in suboptimal recommendations. In this research paper, a novel approach is proposed: a weighted parallel hybrid recommendation system. By considering item weights and leveraging parallel processing techniques, this method significantly enhances the accuracy of the similarity between items, leading to improved recommendation quality and precision. With this approach, users can efficiently and effectively explore new destinations that align with their unique preferences and interests, thereby enhancing their overall tourism experience and satisfaction. To evaluate the effectiveness of the proposed weighted parallel hybrid recommendation system, we conducted experiments using a dataset consisting of 20 users. The results demonstrated that the proposed approach achieved an impressive classification accuracy of 80%. A comparative analysis revealed that the proposed approach outperformed that of existing systems and achieved the best results in terms of classification accuracy. This finding highlights the effectiveness and efficiency of the proposed method in generating and promoting sustainable travel experiences by developing a personalized recommendations system for the unique preferences and interests of individual users.

Machine Learning Model Using Extreme Gradient Boosting (XGBoost) Feature Importance and Light Gradient Boosting Machine (LightGBM) to Improve Accurate Prediction of Bankruptcy

Abstract. Humans have limitations in processing and analyzing large amounts of data in a short time, including in terms of analyzing bankruptcy data. Bankruptcy data is one of the data that has complex information, so it requires technology that can assist in the process of analyzing and processing data more quickly and efficiently. Data science technology enables data processing and analysis on a large scale, using parallel processing techniques. Parallel processing can be implemented in machine learning models.
 Purpose: Using parallel processing techniques, data science technologies enable data processing and analysis at scale. Parallel processing can be implemented in machine learning models. Therefore, this study aims to implement a machine learning model using the Light Gradient Boosting Machine (LightGBM) classification algorithm which is optimized using Extreme Gradient Boosting (XGBoost) Feature Importance to increase the accuracy of bankruptcy prediction.
 Methods/Study design/approach: Bankruptcy prediction is carried out by applying LightGBM as a classification model and optimized using the XGBoost algorithm as a Feature Importance technique to improve model accuracy. the dataset used is the Taiwanese Bankruptcy dataset collected from the Taiwan Economic Journal for 1999 to 2009 and has 6,819 data. Taiwanese Bankruptcy is unbalanced data, so this study applies random oversampling.
 Result/Findings: The results obtained after going through the model testing process using the confusion matrix obtained an accuracy of the performance of LightGBM+XGBoost Feature Importance of 99.227%.
 Novelty/Originality/Value: So it can be concluded that the implementation of XGBoost Feature Importance can be used to improve LightGBM's performance in bankruptcy prediction.

A parallel optimization and transfer learning approach for summarization in electrical power systems

Transfer learning approaches in natural language processing have been explored and evolved as a potential solution for solving many problems in recent days. The current research on aspect-based summarization shows unsatisfactory accuracy and low-quality generated summaries. Additionally, the potential advantages of combining language models with parallel processing have not been explored in the existing literature. This paper aims to address the problem of aspect-based extractive text summarization using a transfer learning approach and an optimization method based on map reduce. The proposed approach utilizes transfer learning with language models to extract significant aspects from the text. Subsequently, an optimization process using map reduce is employed. This optimization framework includes an in-node mapper and reducer algorithm to generate summaries for important aspects identified by the language model. This enhances the quality of the summary, leading to improved accuracy, particularly when applied to electrical power system documents. By leveraging the strengths of natural language models and parallel data processing techniques, this model presents an opportunity to achieve better text summary generation. The performance metric used is accuracy, measured with the ROUGE tool, incorporating precision, recall and f-measure. The proposed model demonstrates a 6% improvement in scores compared to state-of-the-art techniques.

Analyzing the Impact of C-ITS Services on Driving Behavior: A Case Study of the Daejeon–Sejong C-ITS Pilot Project in South Korea

This paper analyzes the impact of C-ITS service on driving behavior, focusing on a pilot project in Daejeon–Sejong, South Korea. C-ITS, an advanced technology, enables bidirectional wireless communication between vehicles or infrastructure, allowing for real-time traffic data collection and dissemination. The study uses a unique analytical method, employing parallel processing techniques for variable extraction and a paired t-test to examine the short-term effects of C-ITS on driving behavior. Findings indicate a significant change in drivers’ behavior, particularly in average speed, hard braking rate, severe deceleration rate, speeding rate, and excessive speeding rate, towards safer trends after receiving C-ITS warning services. Reductions in hard braking and severe deceleration were immediate after C-ITS service initiation, while a decrease in excessive speeding was observed after four months. Further research is needed to identify other potential influencing variables and provide an unbiased evaluation of C-ITS effectiveness. The study’s implications highlight its role in promoting public acceptance of C-ITS-service-based cooperative autonomous driving strategies.

Hyperchaotic Maps and the Single Neuron Model: A Novel Framework for Chaos-Based Image Encryption

With the explosion of the generation, transmission and sharing of image data over the Internet and other unsecured networks, the need for and significance of the development of novel image encryption algorithms are unprecedented. In this research work, we propose a novel framework for image encryption that is based on two hyperchaotic maps utilized in conjunction with the single neuron model (SNM). The framework entails three successive stages, where in every stage a substitution box (S-box) is applied, then XORing with an encryption key is carried out. The S-boxes and the encryption keys are generated from the numerical solutions of the hyperchaotic maps and the SNM. The performance of the proposed framework is gauged through a number of metrics, reflecting superior performance and complete asymmetry between the plain images and their encrypted versions. The main advantages of this work are (1) vast key space and (2) high encryption efficiency. The superior key space of 22551 is the result of employing the two hyperchaotic maps, while the improved efficiency, resulting in an average encryption rate of 8.54 Mbps, is the result of using the SNM as well as the employment of optimized parallel processing techniques. In addition, the proposed encryption framework is shown to output encrypted images that pass the NIST SP 800 suite. Average achieved values for the metrics include MSE of 9626, PSNR of 8.3 dB, MAE of 80.99, entropy of 7.999, NPCR of 99.6% and UACI of 31.49%.

MRI Brain Tumor Classification Using Computational Intelligence Technique

We proposed a method for detecting and classifying tumors using parallel processing, soft computing, and machine learning techniques. Due to the augmented size and capacity of medical images, the medical imaging field must need an automatic diagnosis process for tumor classification for improved treatment. Initially, we pre-process Magnetic Resonance Imaging (MRI) brain tumor images using non-local adaptive means filter and contrast enhancement in the proposed system. We use a Fuzzy Clustering Means (FCM) algorithm to segment the tumors from the preprocessed MRI brain images. The significant features are obtained from the segmented tumor images by using Discrete Wavelet Transform (DWT), Principal Components Analysis (PCA), and the gray level co-occurrence matrix (GLCM). Machine learning classifiers are peerless techniques for classifying tumors. The classification of tumor grade is done through the Multiclass Support vector machine (MCSVM) classifier. The entire proposed work is implemented on the NVIDIA GeForce GTX parallel processing environment. The innovative final result of our approach was assessed by the Kaggle dataset with the performance metrics and achieved 98.056 % Sensitivity, 100 % Specificity, and 98.139 % Accuracy in 0.3337 computational times

PARALLEL FUZZY FREQUENT ITEMSET MINING USING CELLULAR AUTOMATA

Finding frequent fuzzy itemsets in operational quantitative databases is a significant challenge for fuzzy association rule mining in the context of data mining. If frequent fuzzy itemsets are detected, the decision-making process and formulating strategies in businesses will be made more precise. Because the characteristic of these data models is a large number of transactions and unlimited and high-speed productions. This leads to limitations in calculating the support for itemsets containing fuzzy attributes. As a result, mining using parallel processing techniques has emerged as a potential solution to the issue of slow availability. This study presents a reinforced technique for mining frequent fuzzy sets based on cellular learning automata (CLA). The results demonstrate that frequent set mining can be accomplished with less running time when the proposed method is compared to iMFFP and NPSFF methods.

Modernization of Legacy Batch Processes: An Upgrade to Prolonged Batch Runs with Advanced Computing and Parallel Processing Techniques

In an era dominated by the need for speed and efficiency, long-running batch jobs in legacy systems significantly hinder organizational performance and scalability. This article explores the transformation of these batch jobs through the use of advanced computing and parallel processing techniques. We delve into the challenges posed by outdated batch processing methods and present solutions that leverage modern technology to enhance execution speed, reduce resource consumption, and improve overall system responsiveness.

Design of low latency asynchronous arbiter based on standard cell library

In this paper, a low-latency asynchronous arbiter based on standard cell library was proposed. The circuit which was implemented based on standard cell library, could be synthesized by mainstream EDA tools and suitable for being part of large-scale digital designs. With the employment of parallel processing techniques, Quick Request Forward and Quick Acknowledgement Release, which were able to reduce the release time by shortening the long feedback delay, the proposed asynchronous arbiter could provide a low latency. Post-layout simulations showed that the cycle time of the proposed arbiter was 7.3-40% better than existing arbiters in terms of latency in a simple communication model and 35.26-81.84% better in a complex communication model. In addition, the advantage became distinct as N increased.

A parallel rule-based approach to compute rough approximations of dominance based rough set theory

In many datasets, conditional attributes and decision classes are preference-ordered, however, the classical Rough Set Theory (RST) does not consider the preference order between the values of the attributes. An extension of RST known as a Dominance-based Rough Set Approach (DRSA) provides dominance relation in this regard. In DRSA, data analysis mainly depends on the calculations of lower and upper approximations and these two measures are computationally utilizing many resources i.e., time and memory, due to the consideration of preference order. In this paper, we have proposed a parallel technique for calculating DRSA approximation sets. The proposed method directly computes approximations by following heuristic rules without calculating dominance positive or negative relations. The proposed parallel approach is then compared with the conventional method of calculation of DRSA approximations and a recent another technique of parallel processing using ten UCI publicly available datasets. Results validated the efficiency and effectiveness of the proposed model. An average reduction of 83% was observed in execution time and 86% in memory consumption. The structural complexity of the algorithm also considerably reduced.

Lightweight distributed computing framework for orchestrating high performance computing and big data

In recent years, the need for the ability to work remotely and subsequently the need for the availability of remote computer-based systems has increased substantially. This trend has seen a dramatic increase with the onset of the 2020 pandemic. Often local data is produced, stored, and processed in the cloud to remedy this flood of computation and storage needs. Historically, HPC (high performance computing) and the concept of big data have been utilized for the storage and processing of large data. However, both HPC and Hadoop can be utilized as solutions for analytical work, though the differences between these may not be obvious. Both use parallel processing techniques and offer options for data to be stored in either a centralized or distributed manner. Recent studies have focused on using a hybrid approach with both technologies. Therefore, the convergence between HPC and big data technologies can be filled with distributed computing machines at the layer described. This paper results from the motivation that there exists a necessity for a distributed computing framework that can scale from SOC (system on chip) boards to desktop computers and servers. For this purpose, in this article, we propose a distributed computing environment that can scale up to devices with heterogeneous architecture, where devices can set up clusters with resource-limited nodes and then run on top of. The solution can be thought of as a minimalist hybrid approach between HPC and big data. Within the scope of this study, not only the design of the proposed system is detailed, but also critical modules and subsystems are implemented as proof of concept.

Fully-Decentralized Optimal Power Flow of Multi-Area Power Systems Based on Parallel Dual Dynamic Programming

In this paper, we propose a parallel dual dynamic programming (PDDP)-based decentralized algorithm for the multi-area optimal power flow (MAOPF), which can preserve the information privacy and operational independence of each area. The MAOPF problem is decomposed into a series of subproblems for individual areas by the dual dynamic programming (DDP) algorithm, and the Benders cut-based value functions are used to reflect the impacts of one area’s decisions to the subsequent areas. The optimal solution of MAOPF can be obtained in a decentralized fashion, requiring only a limited amount of information exchange among neighbor areas. Moreover, a parallel processing technique is designed to avoid the waiting process of the basic DDP algorithm, thus accelerating the computing speed of the proposed decentralized algorithm. Compared with the existing decentralized algorithms, the proposed algorithm has better performance in terms of convergence and computational efficiency. In addition, there is no need for parameter tuning. Case studies on several IEEE test systems and a real 2298-bus system demonstrate the effectiveness of the proposed algorithm.

Highly Vectorized SIKE for AVX-512

It is generally accepted that a large-scale quantum computer would be capable to break any public-key cryptosystem used today, thereby posing a serious threat to the security of the Internet’s public-key infrastructure. The US National Institute of Standards and Technology (NIST) addresses this threat with an open process for the standardization of quantum-safe key establishment and signature schemes, which is now in the final phase of the evaluation of candidates. SIKE (an abbreviation of Supersingular Isogeny Key Encapsulation) is one of the alternate candidates under evaluation and distinguishes itself from other candidates due to relatively short key lengths and relatively high computing costs. In this paper, we analyze how the latest generation of Intel’s Advanced Vector Extensions (AVX), in particular AVX-512IFMA, can be used to minimize the latency (resp. maximize the hroughput) of the SIKE key encapsulation mechanism when executed on Ice Lake CPUs based on the Sunny Cove microarchitecture. We present various techniques to parallelize and speed up the base/extension field arithmetic, point arithmetic, and isogeny computations performed by SIKE. All these parallel processing techniques are combined in AvxSike, a highly optimized implementation of SIKE using Intel AVX-512IFMA instructions. Our experiments indicate that AvxSike instantiated with the SIKEp503 parameter set is approximately 1.5 times faster than the to-date best AVX-512IFMA-based SIKE software from the literature. When executed on an Intel Core i3-1005G1 CPU, AvxSike outperforms the x64 assembly implementation of SIKE contained in Microsoft’s SIDHv3.4 library by a factor of about 2.5 for key generation and decapsulation, while the encapsulation is even 3.2 times faster.