Pub Date : 2023-12-16DOI: 10.3390/computers12120261
Vangelis Sarlis, George Papageorgiou, Christos Tjortjis
Injuries are an unfortunate part of professional sports. This study aims to explore the multi-dimensional impact of injuries in professional basketball, focusing on player performance, team dynamics, and economic outcomes. Employing advanced machine learning and text mining techniques on suitably preprocessed NBA data, we examined the intricate interplay between injury and performance metrics. Our findings reveal that specific anatomical sub-areas, notably knees, ankles, and thighs, are crucial for athletic performance and injury prevention. The analysis revealed the significant economic burden that certain injuries impose on teams, necessitating comprehensive long-term strategies for injury management. The results provide valuable insights into the distribution of injuries and their varied effects, which are essential for developing effective prevention and economic strategies in basketball. By illuminating how injuries influence performance and recovery dynamics, this research offers comprehensive insights that are beneficial for NBA teams, healthcare professionals, medical staff, and trainers, paving the way for enhanced player care and optimized performance strategies.
伤病是职业体育的一个不幸组成部分。本研究旨在探索职业篮球运动中伤病的多维影响，重点关注球员表现、球队动态和经济效益。在对 NBA 数据进行适当预处理后，我们采用了先进的机器学习和文本挖掘技术，研究了伤病与表现指标之间错综复杂的相互作用。我们的研究结果表明，特定的解剖亚区域，尤其是膝盖、脚踝和大腿，对于运动表现和伤害预防至关重要。分析表明，某些伤病给球队带来了巨大的经济负担，因此有必要制定全面的长期伤病管理策略。研究结果为了解伤病的分布及其不同影响提供了宝贵的见解，这对于制定有效的篮球运动预防和经济策略至关重要。通过阐明伤病如何影响表现和恢复动态，这项研究提供了全面的见解，有利于 NBA 球队、医疗保健专业人员、医务人员和训练员，为加强球员护理和优化表现策略铺平了道路。
{"title":"Sports Analytics and Text Mining NBA Data to Assess Recovery from Injuries and Their Economic Impact","authors":"Vangelis Sarlis, George Papageorgiou, Christos Tjortjis","doi":"10.3390/computers12120261","DOIUrl":"https://doi.org/10.3390/computers12120261","url":null,"abstract":"Injuries are an unfortunate part of professional sports. This study aims to explore the multi-dimensional impact of injuries in professional basketball, focusing on player performance, team dynamics, and economic outcomes. Employing advanced machine learning and text mining techniques on suitably preprocessed NBA data, we examined the intricate interplay between injury and performance metrics. Our findings reveal that specific anatomical sub-areas, notably knees, ankles, and thighs, are crucial for athletic performance and injury prevention. The analysis revealed the significant economic burden that certain injuries impose on teams, necessitating comprehensive long-term strategies for injury management. The results provide valuable insights into the distribution of injuries and their varied effects, which are essential for developing effective prevention and economic strategies in basketball. By illuminating how injuries influence performance and recovery dynamics, this research offers comprehensive insights that are beneficial for NBA teams, healthcare professionals, medical staff, and trainers, paving the way for enhanced player care and optimized performance strategies.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"162 8‐12","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138966841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-15DOI: 10.3390/computers12120260
Arnab Biswas, Kiki Adhinugraha, David Taniar
With urban areas facing rapid population growth, public transport plays a key role to provide efficient and economic accessibility to the residents. It reduces the use of personal vehicles leading to reduced traffic congestion on roads and reduced pollution. To assess the performance of these transport systems, prior studies have taken into consideration the blank spot areas, population density, and stop access density; however, very little research has been performed to compare the accessibility between cities using a GIS-based approach. This paper compares the access and performance of public transport across Melbourne and Sydney, two cities with a similar size, population, and economy. The methodology uses spatial PostGIS queries to focus on accessibility-based approach for each residential mesh block and aggregates the blank spots, and the number of services offered by time of day and the frequency of services at the local government area (LGA) level. The results of the study reveal an interesting trend: that with increase in distance of LGA from city centre, the blank spot percentage increases while the frequency of services and stops offering weekend/night services declines. The results conclude that while Sydney exhibits a lower percentage of blank spots and has better coverage, performance in terms of accessibility by service time and frequency is better for Melbourne’s LGAs, even as the distance increases from the city centre.
{"title":"Comparative GIS Analysis of Public Transport Accessibility in Metropolitan Areas","authors":"Arnab Biswas, Kiki Adhinugraha, David Taniar","doi":"10.3390/computers12120260","DOIUrl":"https://doi.org/10.3390/computers12120260","url":null,"abstract":"With urban areas facing rapid population growth, public transport plays a key role to provide efficient and economic accessibility to the residents. It reduces the use of personal vehicles leading to reduced traffic congestion on roads and reduced pollution. To assess the performance of these transport systems, prior studies have taken into consideration the blank spot areas, population density, and stop access density; however, very little research has been performed to compare the accessibility between cities using a GIS-based approach. This paper compares the access and performance of public transport across Melbourne and Sydney, two cities with a similar size, population, and economy. The methodology uses spatial PostGIS queries to focus on accessibility-based approach for each residential mesh block and aggregates the blank spots, and the number of services offered by time of day and the frequency of services at the local government area (LGA) level. The results of the study reveal an interesting trend: that with increase in distance of LGA from city centre, the blank spot percentage increases while the frequency of services and stops offering weekend/night services declines. The results conclude that while Sydney exhibits a lower percentage of blank spots and has better coverage, performance in terms of accessibility by service time and frequency is better for Melbourne’s LGAs, even as the distance increases from the city centre.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"121 14","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138999726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-13DOI: 10.3390/computers12120259
Yongseok Lee, Jonghee Youn, Kevin Nam, Hyunyoung Oh, Y. Paek
This paper focuses on enhancing the performance of the Nth-degree truncated-polynomial ring units key encapsulation mechanism (NTRU-KEM) algorithm, which ensures post-quantum resistance in the field of key establishment cryptography. The NTRU-KEM, while robust, suffers from increased storage and computational demands compared to classical cryptography, leading to significant memory and performance overheads. In environments with limited resources, the negative impacts of these overheads are more noticeable, leading researchers to investigate ways to speed up processes while also ensuring they are efficient in terms of area utilization. To address this, our research carefully examines the detailed functions of the NTRU-KEM algorithm, adopting a software/hardware co-design approach. This approach allows for customized computation, adapting to the varying requirements of operational timings and iterations. The key contribution is the development of a novel hardware acceleration technique focused on optimizing bus utilization. This technique enables parallel processing of multiple sub-functions, enhancing the overall efficiency of the system. Furthermore, we introduce a unique integrated register array that significantly reduces the spatial footprint of the design by merging multiple registers within the accelerator. In experiments conducted, the results of our work were found to be remarkable, with a time-area efficiency achieved that surpasses previous work by an average of 25.37 times. This achievement underscores the effectiveness of our optimization in accelerating the NTRU-KEM algorithm.
{"title":"Optimizing Hardware Resource Utilization for Accelerating the NTRU-KEM Algorithm","authors":"Yongseok Lee, Jonghee Youn, Kevin Nam, Hyunyoung Oh, Y. Paek","doi":"10.3390/computers12120259","DOIUrl":"https://doi.org/10.3390/computers12120259","url":null,"abstract":"This paper focuses on enhancing the performance of the Nth-degree truncated-polynomial ring units key encapsulation mechanism (NTRU-KEM) algorithm, which ensures post-quantum resistance in the field of key establishment cryptography. The NTRU-KEM, while robust, suffers from increased storage and computational demands compared to classical cryptography, leading to significant memory and performance overheads. In environments with limited resources, the negative impacts of these overheads are more noticeable, leading researchers to investigate ways to speed up processes while also ensuring they are efficient in terms of area utilization. To address this, our research carefully examines the detailed functions of the NTRU-KEM algorithm, adopting a software/hardware co-design approach. This approach allows for customized computation, adapting to the varying requirements of operational timings and iterations. The key contribution is the development of a novel hardware acceleration technique focused on optimizing bus utilization. This technique enables parallel processing of multiple sub-functions, enhancing the overall efficiency of the system. Furthermore, we introduce a unique integrated register array that significantly reduces the spatial footprint of the design by merging multiple registers within the accelerator. In experiments conducted, the results of our work were found to be remarkable, with a time-area efficiency achieved that surpasses previous work by an average of 25.37 times. This achievement underscores the effectiveness of our optimization in accelerating the NTRU-KEM algorithm.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"36 12","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-10DOI: 10.3390/computers12120258
Sunghae Jun
In big data analysis, various zero-inflated problems are occurring. In particular, the problem of inflated zeros has a great influence on text big data analysis. In general, the preprocessed data from text documents are a matrix consisting of the documents and terms for row and column, respectively. Each element of this matrix is an occurred frequency of term in a document. Most elements of the matrix are zeros, because the number of columns is much larger than the rows. This problem is a cause of decreasing model performance in text data analysis. To overcome this problem, we propose a method of zero-inflated text data analysis using generative adversarial networks (GAN) and statistical modeling. In this paper, we solve the zero-inflated problem using synthetic data generated from the original data with zero inflation. The main finding of our study is how to change zero values to the very small numeric values with random noise through the GAN. The generator and discriminator of the GAN learned the zero-inflated text data together and built a model that generates synthetic data that can replace the zero-inflated data. We conducted experiments and showed the results, using real and simulation data sets to verify the improved performance of our proposed method. In our experiments, we used five quantitative measures, prediction sum of squares, R-squared, log-likelihood, Akaike information criterion and Bayesian information criterion to evaluate the model’s performance between original and synthetic data sets. We found that all performances of our proposed method are better than the traditional methods.
{"title":"Zero-Inflated Text Data Analysis using Generative Adversarial Networks and Statistical Modeling","authors":"Sunghae Jun","doi":"10.3390/computers12120258","DOIUrl":"https://doi.org/10.3390/computers12120258","url":null,"abstract":"In big data analysis, various zero-inflated problems are occurring. In particular, the problem of inflated zeros has a great influence on text big data analysis. In general, the preprocessed data from text documents are a matrix consisting of the documents and terms for row and column, respectively. Each element of this matrix is an occurred frequency of term in a document. Most elements of the matrix are zeros, because the number of columns is much larger than the rows. This problem is a cause of decreasing model performance in text data analysis. To overcome this problem, we propose a method of zero-inflated text data analysis using generative adversarial networks (GAN) and statistical modeling. In this paper, we solve the zero-inflated problem using synthetic data generated from the original data with zero inflation. The main finding of our study is how to change zero values to the very small numeric values with random noise through the GAN. The generator and discriminator of the GAN learned the zero-inflated text data together and built a model that generates synthetic data that can replace the zero-inflated data. We conducted experiments and showed the results, using real and simulation data sets to verify the improved performance of our proposed method. In our experiments, we used five quantitative measures, prediction sum of squares, R-squared, log-likelihood, Akaike information criterion and Bayesian information criterion to evaluate the model’s performance between original and synthetic data sets. We found that all performances of our proposed method are better than the traditional methods.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"848 ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138982808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-09DOI: 10.3390/computers12120257
Felix Kahmann, Fabian Honecker, Julian Dreyer, Marten Fischer, Ralf Tönjes
Since the introduction of the first cryptocurrency, Bitcoin, in 2008, the gain in popularity of distributed ledger technologies (DLTs) has led to an increasing demand and, consequently, a larger number of network participants in general. Scaling blockchain-based solutions to cope with several thousand transactions per second or with a growing number of nodes has always been a desirable goal for most developers. Enabling these performance metrics can lead to further acceptance of DLTs and even faster systems in general. With the introduction of directed acyclic graphs (DAGs) as the underlying data structure to store the transactions within the distributed ledger, major performance gains have been achieved. In this article, we review the most prominent directed acyclic graph platforms and evaluate their key performance indicators in terms of transaction throughput and network latency. The evaluation aims to show whether the theoretically improved scalability of DAGs also applies in practice. For this, we set up multiple test networks for each DAG and blockchain framework and conducted broad performance measurements to have a mutual basis for comparison between the different solutions. Using the transactions per second numbers of each technology, we created a side-by-side evaluation that allows for a direct scalability estimation of the systems. Our findings support the fact that, due to their internal, more parallelly oriented data structure, DAG-based solutions offer significantly higher transaction throughput in comparison to blockchain-based platforms. Although, due to their relatively early maturity state, fully DAG-based platforms need to further evolve in their feature set to reach the same level of programmability and spread as modern blockchain platforms. With our findings at hand, developers of modern digital storage systems are able to reasonably determine whether to use a DAG-based distributed ledger technology solution in their production environment, i.e., replacing a database system with a DAG platform. Furthermore, we provide two real-world application scenarios, one being smart grid communication and the other originating from trusted supply chain management, that benefit from the introduction of DAG-based technologies.
自 2008 年第一种加密货币比特币问世以来，分布式账本技术（DLT）越来越受欢迎，导致需求不断增加，网络参与者的数量也随之增加。扩展基于区块链的解决方案，以应对每秒数千次的交易或节点数量的不断增加，一直是大多数开发人员的理想目标。启用这些性能指标可以进一步提高人们对 DLT 的接受度，甚至提高系统的运行速度。引入有向无环图（DAG）作为底层数据结构来存储分布式账本中的交易后，已经实现了重大的性能提升。在本文中，我们回顾了最著名的有向无环图平台，并从交易吞吐量和网络延迟的角度对其关键性能指标进行了评估。评估旨在说明有向无环图在理论上提高的可扩展性在实践中是否也适用。为此，我们为每个 DAG 和区块链框架建立了多个测试网络，并进行了广泛的性能测量，以便为不同解决方案之间的比较提供相互依存的基础。利用每种技术的每秒交易量，我们创建了一个并排评估，可以直接估算系统的可扩展性。我们的研究结果支持这样一个事实，即与基于区块链的平台相比，基于 DAG 的解决方案由于其内部更面向并行的数据结构，可提供更高的交易吞吐量。不过，由于处于相对早期的成熟状态，完全基于 DAG 的平台还需要进一步发展其功能集，才能达到与现代区块链平台相同的可编程性和传播水平。有了我们的研究成果，现代数字存储系统的开发人员就能合理地决定是否在其生产环境中使用基于 DAG 的分布式账本技术解决方案，即用 DAG 平台取代数据库系统。此外，我们还提供了两个现实世界中的应用场景，一个是智能电网通信，另一个源自可信供应链管理，它们都受益于基于 DAG 技术的引入。
{"title":"Performance Comparison of Directed Acyclic Graph-Based Distributed Ledgers and Blockchain Platforms","authors":"Felix Kahmann, Fabian Honecker, Julian Dreyer, Marten Fischer, Ralf Tönjes","doi":"10.3390/computers12120257","DOIUrl":"https://doi.org/10.3390/computers12120257","url":null,"abstract":"Since the introduction of the first cryptocurrency, Bitcoin, in 2008, the gain in popularity of distributed ledger technologies (DLTs) has led to an increasing demand and, consequently, a larger number of network participants in general. Scaling blockchain-based solutions to cope with several thousand transactions per second or with a growing number of nodes has always been a desirable goal for most developers. Enabling these performance metrics can lead to further acceptance of DLTs and even faster systems in general. With the introduction of directed acyclic graphs (DAGs) as the underlying data structure to store the transactions within the distributed ledger, major performance gains have been achieved. In this article, we review the most prominent directed acyclic graph platforms and evaluate their key performance indicators in terms of transaction throughput and network latency. The evaluation aims to show whether the theoretically improved scalability of DAGs also applies in practice. For this, we set up multiple test networks for each DAG and blockchain framework and conducted broad performance measurements to have a mutual basis for comparison between the different solutions. Using the transactions per second numbers of each technology, we created a side-by-side evaluation that allows for a direct scalability estimation of the systems. Our findings support the fact that, due to their internal, more parallelly oriented data structure, DAG-based solutions offer significantly higher transaction throughput in comparison to blockchain-based platforms. Although, due to their relatively early maturity state, fully DAG-based platforms need to further evolve in their feature set to reach the same level of programmability and spread as modern blockchain platforms. With our findings at hand, developers of modern digital storage systems are able to reasonably determine whether to use a DAG-based distributed ledger technology solution in their production environment, i.e., replacing a database system with a DAG platform. Furthermore, we provide two real-world application scenarios, one being smart grid communication and the other originating from trusted supply chain management, that benefit from the introduction of DAG-based technologies.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"232 ","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139010843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-07DOI: 10.3390/computers12120255
Paria Sarzaeim, Q. Mahmoud, Akramul Azim, Gary Bauer, Ian Bowles
Smart policing refers to the use of advanced technologies such as artificial intelligence to enhance policing activities in terms of crime prevention or crime reduction. Artificial intelligence tools, including machine learning and natural language processing, have widespread applications across various fields, such as healthcare, business, and law enforcement. By means of these technologies, smart policing enables organizations to efficiently process and analyze large volumes of data. Some examples of smart policing applications are fingerprint detection, DNA matching, CCTV surveillance, and crime prediction. While artificial intelligence offers the potential to reduce human errors and biases, it is still essential to acknowledge that the algorithms reflect the data on which they are trained, which are inherently collected by human inputs. Considering the critical role of the police in ensuring public safety, the adoption of these algorithms demands careful and thoughtful implementation. This paper presents a systematic literature review focused on exploring the machine learning techniques employed by law enforcement agencies. It aims to shed light on the benefits and limitations of utilizing these techniques in smart policing and provide insights into the effectiveness and challenges associated with the integration of machine learning in law enforcement practices.
{"title":"A Systematic Review of Using Machine Learning and Natural Language Processing in Smart Policing","authors":"Paria Sarzaeim, Q. Mahmoud, Akramul Azim, Gary Bauer, Ian Bowles","doi":"10.3390/computers12120255","DOIUrl":"https://doi.org/10.3390/computers12120255","url":null,"abstract":"Smart policing refers to the use of advanced technologies such as artificial intelligence to enhance policing activities in terms of crime prevention or crime reduction. Artificial intelligence tools, including machine learning and natural language processing, have widespread applications across various fields, such as healthcare, business, and law enforcement. By means of these technologies, smart policing enables organizations to efficiently process and analyze large volumes of data. Some examples of smart policing applications are fingerprint detection, DNA matching, CCTV surveillance, and crime prediction. While artificial intelligence offers the potential to reduce human errors and biases, it is still essential to acknowledge that the algorithms reflect the data on which they are trained, which are inherently collected by human inputs. Considering the critical role of the police in ensuring public safety, the adoption of these algorithms demands careful and thoughtful implementation. This paper presents a systematic literature review focused on exploring the machine learning techniques employed by law enforcement agencies. It aims to shed light on the benefits and limitations of utilizing these techniques in smart policing and provide insights into the effectiveness and challenges associated with the integration of machine learning in law enforcement practices.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"21 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138590351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-05DOI: 10.3390/computers12120254
Baasanjargal Erdenebat, Bayarjargal Bud, Temuulen Batsuren, Tamás Kozsik
DevOps methodology and tools, which provide standardized ways for continuous integration (CI) and continuous deployment (CD), are invaluable for efficient software development. Current DevOps solutions, however, lack a useful functionality: they do not support simultaneous project developments and deployment on the same operating infrastructure (e.g., a cluster of Docker containers). In this paper, we propose a novel approach to address this shortcoming by defining a multi-project, multi-environment (MPME) approach. With this approach, a large company can organize many microservice-based projects operating simultaneously on a common code base, using self-hosted Kubernetes clusters, which helps developers and businesses to better focus on the product they are developing, and to reduce efforts on the management of their DevOps infrastructure.
{"title":"Multi-Project Multi-Environment Approach—An Enhancement to Existing DevOps and Continuous Integration and Continuous Deployment Tools","authors":"Baasanjargal Erdenebat, Bayarjargal Bud, Temuulen Batsuren, Tamás Kozsik","doi":"10.3390/computers12120254","DOIUrl":"https://doi.org/10.3390/computers12120254","url":null,"abstract":"DevOps methodology and tools, which provide standardized ways for continuous integration (CI) and continuous deployment (CD), are invaluable for efficient software development. Current DevOps solutions, however, lack a useful functionality: they do not support simultaneous project developments and deployment on the same operating infrastructure (e.g., a cluster of Docker containers). In this paper, we propose a novel approach to address this shortcoming by defining a multi-project, multi-environment (MPME) approach. With this approach, a large company can organize many microservice-based projects operating simultaneously on a common code base, using self-hosted Kubernetes clusters, which helps developers and businesses to better focus on the product they are developing, and to reduce efforts on the management of their DevOps infrastructure.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"10 5","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138598066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.3390/computers12120253
T. Schindler, Simon Schlicht, K. Thoben
Within the integration and development of data-driven process models, the underlying process is digitally mapped in a model through sensory data acquisition and subsequent modelling. In this process, challenges of different types and degrees of severity arise in each modelling step, according to the Cross-Industry Standard Process for Data Mining (CRISP-DM). Particularly in the context of data acquisition and integration into the process model, it can be assumed with a sufficiently high degree of probability that the acquired data contain anomalies of various kinds. The outliers must be detected in the data preparation and processing phase and dealt with accordingly. If this is sufficiently implemented, it will positively impact the subsequent modelling in terms of accuracy and precision. Therefore, this paper shows how outliers can be identified using the unsupervised machine learning methods autoencoder, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Isolation Forest (iForest), and One-Class Support Vector Machine (OCSVM). Following implementing these methods, we compared them by applying the Numenta Anomaly Benchmark (NAB) and sufficiently presented the individual strengths and disadvantages. Evaluating the correctness, distinctiveness and robustness criteria described in the paper showed that the One-Class Support Vector Machine was outstanding among the methods considered. This is because the OCSVM achieved acceptable anomaly detections on the available process datasets with comparatively little effort.
{"title":"Towards Benchmarking for Evaluating Machine Learning Methods in Detecting Outliers in Process Datasets","authors":"T. Schindler, Simon Schlicht, K. Thoben","doi":"10.3390/computers12120253","DOIUrl":"https://doi.org/10.3390/computers12120253","url":null,"abstract":"Within the integration and development of data-driven process models, the underlying process is digitally mapped in a model through sensory data acquisition and subsequent modelling. In this process, challenges of different types and degrees of severity arise in each modelling step, according to the Cross-Industry Standard Process for Data Mining (CRISP-DM). Particularly in the context of data acquisition and integration into the process model, it can be assumed with a sufficiently high degree of probability that the acquired data contain anomalies of various kinds. The outliers must be detected in the data preparation and processing phase and dealt with accordingly. If this is sufficiently implemented, it will positively impact the subsequent modelling in terms of accuracy and precision. Therefore, this paper shows how outliers can be identified using the unsupervised machine learning methods autoencoder, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Isolation Forest (iForest), and One-Class Support Vector Machine (OCSVM). Following implementing these methods, we compared them by applying the Numenta Anomaly Benchmark (NAB) and sufficiently presented the individual strengths and disadvantages. Evaluating the correctness, distinctiveness and robustness criteria described in the paper showed that the One-Class Support Vector Machine was outstanding among the methods considered. This is because the OCSVM achieved acceptable anomaly detections on the available process datasets with comparatively little effort.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"8 24","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138603433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.3390/computers12120252
Shiyuan Cai, Yuchen Cai, Liu Liu, Haitao Han, Feng Bao
Due to increased traffic pressure, traditional urban rail vehicle–ground communication systems are no longer able to meet the increasing communication requirements. In this paper, ad hoc networks are applied to urban rail transit vehicle–ground communication systems to improve link reliability and reduce transmission delay. In the proposed network, a service-driven routing algorithm is proposed, which considers the distance factor for cluster head selection and optimizes the routing transmission delay by service priority and congestion level. An auxiliary node-based routing maintenance mechanism is also proposed to avoid the problem of frequent breakage of communication links due to the high-speed movement of trains. Through the simulation, the proposed algorithm can effectively reduce the packet loss rate, end-to-end delay, and routing overhead of vehicle–ground communication compared with the traditional routing algorithm, which is more conducive to meeting the next generation of urban rail transit vehicle–ground communication requirements.
{"title":"A Service-Driven Routing Algorithm for Ad Hoc Networks in Urban Rail Transit","authors":"Shiyuan Cai, Yuchen Cai, Liu Liu, Haitao Han, Feng Bao","doi":"10.3390/computers12120252","DOIUrl":"https://doi.org/10.3390/computers12120252","url":null,"abstract":"Due to increased traffic pressure, traditional urban rail vehicle–ground communication systems are no longer able to meet the increasing communication requirements. In this paper, ad hoc networks are applied to urban rail transit vehicle–ground communication systems to improve link reliability and reduce transmission delay. In the proposed network, a service-driven routing algorithm is proposed, which considers the distance factor for cluster head selection and optimizes the routing transmission delay by service priority and congestion level. An auxiliary node-based routing maintenance mechanism is also proposed to avoid the problem of frequent breakage of communication links due to the high-speed movement of trains. Through the simulation, the proposed algorithm can effectively reduce the packet loss rate, end-to-end delay, and routing overhead of vehicle–ground communication compared with the traditional routing algorithm, which is more conducive to meeting the next generation of urban rail transit vehicle–ground communication requirements.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"26 25","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138604078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-03DOI: 10.3390/computers12120251
Martin Wynn, K. Felser
As digitalisation sweeps through industries, companies are having to deal with the resultant changes in business models, core processes and organisational structures. This includes the reassessment of the role of the IT department, traditionally the guardians of technology standards and providers of corporate systems and infrastructure, and their ongoing maintenance. This article investigates this dynamic in two research studies. Study 1 focuses on the German automotive industry and adopts a qualitative inductive approach based on interviews with IT practitioners to ascertain the key aspects of digitalisation impacting the industry and to chart the emergence of a new model for the management of IT. Study 2 then reviews the deployment of digital technologies in other industry sectors via questionnaire responses from senior IT professionals in eight organisations. The results suggest that the transfer of IT roles and responsibilities to business functions, evident in the German automotive industry, is being replicated in other organisations in which digital technologies are now embedded in an organisation’s products or services. This article concludes with a model for cross-referencing the role of the IT function with the impact of digital technologies, representing a contribution to the growing literature on digital technology deployment in organisations.
{"title":"Digitalisation and Change in the Management of IT","authors":"Martin Wynn, K. Felser","doi":"10.3390/computers12120251","DOIUrl":"https://doi.org/10.3390/computers12120251","url":null,"abstract":"As digitalisation sweeps through industries, companies are having to deal with the resultant changes in business models, core processes and organisational structures. This includes the reassessment of the role of the IT department, traditionally the guardians of technology standards and providers of corporate systems and infrastructure, and their ongoing maintenance. This article investigates this dynamic in two research studies. Study 1 focuses on the German automotive industry and adopts a qualitative inductive approach based on interviews with IT practitioners to ascertain the key aspects of digitalisation impacting the industry and to chart the emergence of a new model for the management of IT. Study 2 then reviews the deployment of digital technologies in other industry sectors via questionnaire responses from senior IT professionals in eight organisations. The results suggest that the transfer of IT roles and responsibilities to business functions, evident in the German automotive industry, is being replicated in other organisations in which digital technologies are now embedded in an organisation’s products or services. This article concludes with a model for cross-referencing the role of the IT function with the impact of digital technologies, representing a contribution to the growing literature on digital technology deployment in organisations.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"17 3","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138605850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：