Dynamic multi-objective optimization problems (DMOPs) are optimization problems where elements of the problems, such as the objective functions and/or constraints, change with time. These problems are characterized by two or more objective functions, where at least two objective functions are in conflict with one another. When solving real-world problems, the incorporation of human decision-makers (DMs)’ preferences or expert knowledge into the optimization process and thereby restricting the search to a specific region of the Pareto-optimal Front (POF) may result in more preferred or suitable solutions. This study proposes approaches that enable DMs to influence the search process with their preferences by reformulating the optimization problems as constrained problems. The subsequent constrained problems are solved using various constraint handling approaches, such as the penalization of infeasible solutions and the restriction of the search to the feasible region of the search space. The proposed constraint handling approaches are compared by incorporating the approaches into a differential evolution (DE) algorithm and measuring the algorithm’s performance using both standard performance measures for dynamic multi-objective optimization (DMOO), as well as newly proposed measures for constrained DMOPs. The new measures indicate how well an algorithm was able to find solutions in the objective space that best reflect the DM’s preferences and the Pareto-optimality goal of dynamic multi-objective optimization algorithms (DMOAs). The results indicate that the constraint handling approaches are effective in finding Pareto-optimal solutions that satisfy the preference constraints of a DM.
{"title":"Decision-Maker’s Preference-Driven Dynamic Multi-Objective Optimization","authors":"Adekunle Rotimi Adekoya, Mardé Helbig","doi":"10.3390/a16110504","DOIUrl":"https://doi.org/10.3390/a16110504","url":null,"abstract":"Dynamic multi-objective optimization problems (DMOPs) are optimization problems where elements of the problems, such as the objective functions and/or constraints, change with time. These problems are characterized by two or more objective functions, where at least two objective functions are in conflict with one another. When solving real-world problems, the incorporation of human decision-makers (DMs)’ preferences or expert knowledge into the optimization process and thereby restricting the search to a specific region of the Pareto-optimal Front (POF) may result in more preferred or suitable solutions. This study proposes approaches that enable DMs to influence the search process with their preferences by reformulating the optimization problems as constrained problems. The subsequent constrained problems are solved using various constraint handling approaches, such as the penalization of infeasible solutions and the restriction of the search to the feasible region of the search space. The proposed constraint handling approaches are compared by incorporating the approaches into a differential evolution (DE) algorithm and measuring the algorithm’s performance using both standard performance measures for dynamic multi-objective optimization (DMOO), as well as newly proposed measures for constrained DMOPs. The new measures indicate how well an algorithm was able to find solutions in the objective space that best reflect the DM’s preferences and the Pareto-optimality goal of dynamic multi-objective optimization algorithms (DMOAs). The results indicate that the constraint handling approaches are effective in finding Pareto-optimal solutions that satisfy the preference constraints of a DM.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"2023 7-8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136103636","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}
Alexey Kozin, Anton Gerasimov, Maxim Bakaev, Anton Pashkov, Olga Razumnikova
Brain–computer interfaces (BCIs) based on steady-state visually evoked potentials (SSVEPs) are inexpensive and do not require user training. However, the highly personalized reaction to visual stimulation is an obstacle to the wider application of this technique, as it can be ineffective, tiring, or even harmful at certain frequencies. In our experimental study, we proposed a new approach to the selection of optimal frequencies of photostimulation. By using a custom photostimulation device, we covered a frequency range from 5 to 25 Hz with 1 Hz increments, recording the subjects’ brainwave activity (EEG) and analyzing the signal-to-noise ratio (SNR) changes at the corresponding frequencies. The proposed set of SNR-based coefficients and the discomfort index, determined by the ratio of theta and beta rhythms in the EEG signal, enables the automation of obtaining the recommended stimulation frequencies for use in SSVEP-based BCIs.
{"title":"Automating Stimulation Frequency Selection for SSVEP-Based Brain-Computer Interfaces","authors":"Alexey Kozin, Anton Gerasimov, Maxim Bakaev, Anton Pashkov, Olga Razumnikova","doi":"10.3390/a16110502","DOIUrl":"https://doi.org/10.3390/a16110502","url":null,"abstract":"Brain–computer interfaces (BCIs) based on steady-state visually evoked potentials (SSVEPs) are inexpensive and do not require user training. However, the highly personalized reaction to visual stimulation is an obstacle to the wider application of this technique, as it can be ineffective, tiring, or even harmful at certain frequencies. In our experimental study, we proposed a new approach to the selection of optimal frequencies of photostimulation. By using a custom photostimulation device, we covered a frequency range from 5 to 25 Hz with 1 Hz increments, recording the subjects’ brainwave activity (EEG) and analyzing the signal-to-noise ratio (SNR) changes at the corresponding frequencies. The proposed set of SNR-based coefficients and the discomfort index, determined by the ratio of theta and beta rhythms in the EEG signal, enables the automation of obtaining the recommended stimulation frequencies for use in SSVEP-based BCIs.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"312 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136158114","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}
Md. Ashikur Rahman, Lway Faisal Abdulrazak, Md. Mamun Ali, Imran Mahmud, Kawsar Ahmed, Francis M. Bui
Diabetes is one of the fatal diseases that play a vital role in the growth of other diseases in the human body. From a clinical perspective, the most significant approach to mitigating the effects of diabetes is early-stage control and management, with the aim of a potential cure. However, lack of awareness and expensive clinical tests are the primary reasons why clinical diagnosis and preventive measures are neglected in lower-income countries like Bangladesh, Pakistan, and India. From this perspective, this study aims to build an automated machine learning (ML) model, which will predict diabetes at an early stage using socio-demographic characteristics rather than clinical attributes, due to the fact that clinical features are not always accessible to all people from lower-income countries. To find the best fit of the supervised ML classifier of the model, we applied six classification algorithms and found that RF outperformed with an accuracy of 99.36%. In addition, the most significant risk factors were found based on the SHAP value by all the applied classifiers. This study reveals that polyuria, polydipsia, and delayed healing are the most significant risk factors for developing diabetes. The findings indicate that the proposed model is highly capable of predicting diabetes in the early stages.
{"title":"Machine Learning-Based Approach for Predicting Diabetes Employing Socio-Demographic Characteristics","authors":"Md. Ashikur Rahman, Lway Faisal Abdulrazak, Md. Mamun Ali, Imran Mahmud, Kawsar Ahmed, Francis M. Bui","doi":"10.3390/a16110503","DOIUrl":"https://doi.org/10.3390/a16110503","url":null,"abstract":"Diabetes is one of the fatal diseases that play a vital role in the growth of other diseases in the human body. From a clinical perspective, the most significant approach to mitigating the effects of diabetes is early-stage control and management, with the aim of a potential cure. However, lack of awareness and expensive clinical tests are the primary reasons why clinical diagnosis and preventive measures are neglected in lower-income countries like Bangladesh, Pakistan, and India. From this perspective, this study aims to build an automated machine learning (ML) model, which will predict diabetes at an early stage using socio-demographic characteristics rather than clinical attributes, due to the fact that clinical features are not always accessible to all people from lower-income countries. To find the best fit of the supervised ML classifier of the model, we applied six classification algorithms and found that RF outperformed with an accuracy of 99.36%. In addition, the most significant risk factors were found based on the SHAP value by all the applied classifiers. This study reveals that polyuria, polydipsia, and delayed healing are the most significant risk factors for developing diabetes. The findings indicate that the proposed model is highly capable of predicting diabetes in the early stages.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"59 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136136169","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}
Carmelo Scribano, Danilo Pezzi, Giorgia Franchini, Marco Prato
With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by abstracting away imperceptible image details and introducing substantial spatial compression, renders the learning of the generative process more manageable while significantly reducing computational and memory demands. In this work, we propose to replace autoencoder coding with a model-based coding scheme based on traditional lossy image compression techniques; this choice not only further diminishes computational expenses but also allows us to probe the boundaries of latent-space image generation. Our objectives culminate in the proposal of a valuable approximation for training continuous diffusion models within a discrete space, accompanied by enhancements to the generative model for categorical values. Beyond the good results obtained for the problem at hand, we believe that the proposed work holds promise for enhancing the adaptability of generative diffusion models across diverse data types beyond the realm of imagery.
{"title":"Denoising Diffusion Models on Model-Based Latent Space","authors":"Carmelo Scribano, Danilo Pezzi, Giorgia Franchini, Marco Prato","doi":"10.3390/a16110501","DOIUrl":"https://doi.org/10.3390/a16110501","url":null,"abstract":"With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by abstracting away imperceptible image details and introducing substantial spatial compression, renders the learning of the generative process more manageable while significantly reducing computational and memory demands. In this work, we propose to replace autoencoder coding with a model-based coding scheme based on traditional lossy image compression techniques; this choice not only further diminishes computational expenses but also allows us to probe the boundaries of latent-space image generation. Our objectives culminate in the proposal of a valuable approximation for training continuous diffusion models within a discrete space, accompanied by enhancements to the generative model for categorical values. Beyond the good results obtained for the problem at hand, we believe that the proposed work holds promise for enhancing the adaptability of generative diffusion models across diverse data types beyond the realm of imagery.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136231666","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}
Linear probing continues to be one of the best practical hashing algorithms due to its good average performance, efficiency, and simplicity of implementation. However, the worst-case performance of linear probing seems to degrade with high load factors due to a primary-clustering tendency of one collision to cause more nearby collisions. It is known that the maximum cluster size produced by linear probing, and hence the length of the longest probe sequence needed to insert or search for a key in a hash table of size n, is Ω(logn), in probability. In this article, we introduce linear probing hashing schemes that employ two linear probe sequences to find empty cells for the keys. Our results show that two-way linear probing is a promising alternative to linear probing for hash tables. We show that two-way linear probing has an asymptotically almost surely O(loglogn) maximum cluster size when the load factor is constant. Matching lower bounds on the maximum cluster size produced by any two-way linear probing algorithm are obtained as well. Our analysis is based on a novel approach that uses the multiple-choice paradigm and witness trees.
{"title":"Two-Way Linear Probing Revisited","authors":"Ketan Dalal, Luc Devroye, Ebrahim Malalla","doi":"10.3390/a16110500","DOIUrl":"https://doi.org/10.3390/a16110500","url":null,"abstract":"Linear probing continues to be one of the best practical hashing algorithms due to its good average performance, efficiency, and simplicity of implementation. However, the worst-case performance of linear probing seems to degrade with high load factors due to a primary-clustering tendency of one collision to cause more nearby collisions. It is known that the maximum cluster size produced by linear probing, and hence the length of the longest probe sequence needed to insert or search for a key in a hash table of size n, is Ω(logn), in probability. In this article, we introduce linear probing hashing schemes that employ two linear probe sequences to find empty cells for the keys. Our results show that two-way linear probing is a promising alternative to linear probing for hash tables. We show that two-way linear probing has an asymptotically almost surely O(loglogn) maximum cluster size when the load factor is constant. Matching lower bounds on the maximum cluster size produced by any two-way linear probing algorithm are obtained as well. Our analysis is based on a novel approach that uses the multiple-choice paradigm and witness trees.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"48 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136231798","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}
Stream ciphers usually rely on highly secure Boolean functions to ensure safe communication within unsafe channels. However, discovering secure Boolean functions is a non-trivial optimization problem that has been addressed by many optimization techniques: in particular by evolutionary algorithms. We investigate in this article the employment of Genetic Programming (GP) for evolving Boolean functions with large non-linearity by examining the search space consisting of Walsh transforms. Especially, we build generic Walsh spectra starting from the evolution of Walsh transform coefficients. Then, by leveraging spectral inversion, we build pseudo-Boolean functions from which we are able to determine the corresponding nearest Boolean functions, whose computation involves filling via a random criterion a certain amount of “uncertain” positions in the final truth table. We show that by using a balancedness-preserving strategy, it is possible to exploit those positions to obtain a function that is as balanced as possible. We perform experiments by comparing different types of symbolic representations for the Walsh transform, and we analyze the percentage of uncertain positions. We systematically review the outcomes of these comparisons to highlight the best type of setting for this problem. We evolve Boolean functions from 6 to 16 bits and compare the GP-based evolution with random search to show that evolving Walsh transforms leads to highly non-linear functions that are balanced as well.
{"title":"Discovering Non-Linear Boolean Functions by Evolving Walsh Transforms with Genetic Programming","authors":"Luigi Rovito, Andrea De Lorenzo, Luca Manzoni","doi":"10.3390/a16110499","DOIUrl":"https://doi.org/10.3390/a16110499","url":null,"abstract":"Stream ciphers usually rely on highly secure Boolean functions to ensure safe communication within unsafe channels. However, discovering secure Boolean functions is a non-trivial optimization problem that has been addressed by many optimization techniques: in particular by evolutionary algorithms. We investigate in this article the employment of Genetic Programming (GP) for evolving Boolean functions with large non-linearity by examining the search space consisting of Walsh transforms. Especially, we build generic Walsh spectra starting from the evolution of Walsh transform coefficients. Then, by leveraging spectral inversion, we build pseudo-Boolean functions from which we are able to determine the corresponding nearest Boolean functions, whose computation involves filling via a random criterion a certain amount of “uncertain” positions in the final truth table. We show that by using a balancedness-preserving strategy, it is possible to exploit those positions to obtain a function that is as balanced as possible. We perform experiments by comparing different types of symbolic representations for the Walsh transform, and we analyze the percentage of uncertain positions. We systematically review the outcomes of these comparisons to highlight the best type of setting for this problem. We evolve Boolean functions from 6 to 16 bits and compare the GP-based evolution with random search to show that evolving Walsh transforms leads to highly non-linear functions that are balanced as well.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136235709","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}
In the mathematical discipline of computational geometry (CG), practical algorithms for resolving geometric input and output issues are designed, analyzed, and put into practice. It is sometimes used to refer to pattern recognition and to define the solid modeling methods for manipulating curves and surfaces. CG is a rich field encompassing theories to solve complex optimization problems, such as path planning for mobile robot systems and extension to distributed multi-robot systems. This brief review discusses the fundamentals of CG and its application in solving well-known automated path-planning problems in single- and multi-robot systems. We also discuss three winning algorithms from the CG-SHOP (Computational Geometry: Solving Hard Optimization Problems) 2021 competition to evidence the practicality of CG in multi-robotic systems. We also mention some open problems at the intersection of CG and robotics. This review provides insights into the potential use of CG in robotics and future research directions at their intersection.
{"title":"On the Intersection of Computational Geometry Algorithms with Mobile Robot Path Planning","authors":"Ehsan Latif, Ramviyas Parasuraman","doi":"10.3390/a16110498","DOIUrl":"https://doi.org/10.3390/a16110498","url":null,"abstract":"In the mathematical discipline of computational geometry (CG), practical algorithms for resolving geometric input and output issues are designed, analyzed, and put into practice. It is sometimes used to refer to pattern recognition and to define the solid modeling methods for manipulating curves and surfaces. CG is a rich field encompassing theories to solve complex optimization problems, such as path planning for mobile robot systems and extension to distributed multi-robot systems. This brief review discusses the fundamentals of CG and its application in solving well-known automated path-planning problems in single- and multi-robot systems. We also discuss three winning algorithms from the CG-SHOP (Computational Geometry: Solving Hard Optimization Problems) 2021 competition to evidence the practicality of CG in multi-robotic systems. We also mention some open problems at the intersection of CG and robotics. This review provides insights into the potential use of CG in robotics and future research directions at their intersection.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"15 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136235587","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}
Deep Neural Networks and Optimization Algorithms have many applications in engineering problems and scientific research [...]
深度神经网络和优化算法在工程问题和科学研究中有许多应用。
{"title":"Overview of the Special Issue on “Deep Neural Networks and Optimization Algorithms”","authors":"Jia-Bao Liu, Muhammad Faisal Nadeem, Yilun Shang","doi":"10.3390/a16110497","DOIUrl":"https://doi.org/10.3390/a16110497","url":null,"abstract":"Deep Neural Networks and Optimization Algorithms have many applications in engineering problems and scientific research [...]","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"63 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134906467","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}
Roberto Avilés, Diego Brito de Souza, José Pino-Ortega, Julen Castellano
The development of algorithms applied to new technologies allows a better understanding of many of the movements in team sports. The purpose of this work was to analyze the validity, precision, and reproducibility of an algorithm to detect angulation of changes of direction (CoDs) while running, of between 45° and 180°, both to the left and the right at different speeds, in a standardized context. For this, five participants performed a total of 200 CoDs at 13 km/h and 128 CoDs at 18 km/h while wearing three inertial sensors. The information obtained from the sensors was contrasted with observation and coding using high-resolution video. Agreement between systems was assessed using Bland–Altman 95% limits of agreement as well as effect size (ES) and % difference between means. Reproducibility was evaluated using the standard error (CV%). The algorithm overestimated the angulation of 90° and 135° to the right (Cohen’s d > 0.91). The algorithm showed high precision when the angulations recorded at 13 km/h and 18 km/h were compared, except at 45° to the left (mean bias = −2.6°; Cohen’s d = −0.57). All angulations showed excellent reproducibility (CV < 5%) except at 45° (CV = 11%), which worsened when the pre-CoD speed was 18 km/h (CV < 16%). The algorithm showed a high degree of validity and reproducibility to detect angles during CoDs.
应用于新技术的算法的发展可以更好地理解团队运动中的许多动作。这项工作的目的是分析一种算法的有效性、精度和可重复性，该算法可以检测在45°到180°之间的方向变化(CoDs)，在不同的速度下，在标准化的环境中向左和向右。为此，五名参与者在佩戴三个惯性传感器的情况下，以13公里/小时的速度进行了200次CoDs，以18公里/小时的速度进行了128次CoDs。从传感器获得的信息与高分辨率视频的观察和编码进行对比。采用Bland-Altman 95%一致性限以及效应大小(ES)和均数差异%评估系统间的一致性。用标准误差(CV%)评价重现性。该算法高估了向右90°和135°的角度(Cohen 's d >0.91)。将13 km/h和18 km/h记录的角度进行比较，该算法显示出较高的精度，但向左45°处除外(平均偏差=−2.6°;Cohen’s d = - 0.57)。所有角度均表现出良好的再现性(CV <(CV = 11%)，当预cod速度为18 km/h时(CV <16%)。该算法具有较高的有效性和可重复性，可用于cod过程中的角度检测。
{"title":"Agreement, Accuracy, and Reliability of a New Algorithm for the Detection of Change of Direction Angle Based on Integrating Inertial Data from Inertial Sensors","authors":"Roberto Avilés, Diego Brito de Souza, José Pino-Ortega, Julen Castellano","doi":"10.3390/a16110496","DOIUrl":"https://doi.org/10.3390/a16110496","url":null,"abstract":"The development of algorithms applied to new technologies allows a better understanding of many of the movements in team sports. The purpose of this work was to analyze the validity, precision, and reproducibility of an algorithm to detect angulation of changes of direction (CoDs) while running, of between 45° and 180°, both to the left and the right at different speeds, in a standardized context. For this, five participants performed a total of 200 CoDs at 13 km/h and 128 CoDs at 18 km/h while wearing three inertial sensors. The information obtained from the sensors was contrasted with observation and coding using high-resolution video. Agreement between systems was assessed using Bland–Altman 95% limits of agreement as well as effect size (ES) and % difference between means. Reproducibility was evaluated using the standard error (CV%). The algorithm overestimated the angulation of 90° and 135° to the right (Cohen’s d > 0.91). The algorithm showed high precision when the angulations recorded at 13 km/h and 18 km/h were compared, except at 45° to the left (mean bias = −2.6°; Cohen’s d = −0.57). All angulations showed excellent reproducibility (CV < 5%) except at 45° (CV = 11%), which worsened when the pre-CoD speed was 18 km/h (CV < 16%). The algorithm showed a high degree of validity and reproducibility to detect angles during CoDs.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"21 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135112944","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}
Order scheduling is of a great significance in the internet and communication industries. With the rapid development of the communication industry and the increasing variety of user demands, the number of work orders for communication operators has grown exponentially. Most of the research that tries to solve the order scheduling problem has focused on improving assignment rules based on real-time performance. However, these traditional methods face challenges such as poor real-time performance, high human resource consumption, and low efficiency. Therefore, it is crucial to solve multi-objective problems in order to obtain a robust order scheduling policy to meet the multiple requirements of order scheduling in real problems. The priority dispatching rule (PDR) is a heuristic method that is widely used in real-world scheduling systems In this paper, we propose an approach to automatically optimize the Priority Dispatching Rule (PDR) using a deep multiple-objective reinforcement learning agent and to optimize the weighted vector with a convex hull to obtain the most objective and efficient weights. The convex hull method is employed to calculate the maximal linearly scalarized value, enabling us to determine the optimal weight vector objectively and achieve a balanced optimization of each objective rather than relying on subjective weight settings based on personal experience. Experimental results on multiple datasets demonstrate that our proposed algorithm achieves competitive performance compared to existing state-of-the-art order scheduling algorithms.
{"title":"Multi-Objective Order Scheduling via Reinforcement Learning","authors":"Sirui Chen, Yuming Tian, Lingling An","doi":"10.3390/a16110495","DOIUrl":"https://doi.org/10.3390/a16110495","url":null,"abstract":"Order scheduling is of a great significance in the internet and communication industries. With the rapid development of the communication industry and the increasing variety of user demands, the number of work orders for communication operators has grown exponentially. Most of the research that tries to solve the order scheduling problem has focused on improving assignment rules based on real-time performance. However, these traditional methods face challenges such as poor real-time performance, high human resource consumption, and low efficiency. Therefore, it is crucial to solve multi-objective problems in order to obtain a robust order scheduling policy to meet the multiple requirements of order scheduling in real problems. The priority dispatching rule (PDR) is a heuristic method that is widely used in real-world scheduling systems In this paper, we propose an approach to automatically optimize the Priority Dispatching Rule (PDR) using a deep multiple-objective reinforcement learning agent and to optimize the weighted vector with a convex hull to obtain the most objective and efficient weights. The convex hull method is employed to calculate the maximal linearly scalarized value, enabling us to determine the optimal weight vector objectively and achieve a balanced optimization of each objective rather than relying on subjective weight settings based on personal experience. Experimental results on multiple datasets demonstrate that our proposed algorithm achieves competitive performance compared to existing state-of-the-art order scheduling algorithms.","PeriodicalId":7636,"journal":{"name":"Algorithms","volume":"49 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135266855","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：