In this parper, a 4D absolute memristor Jerk chaotic system is proposed. Firstly, complex dynamics are studied by phase diagram, Poincaré section, power spectrum, bifurcation diagram, 0-1 test, and Lyapunov exponent spectrum. Then, the period doubling bifurcation, degradation, and offset boosting are revealed. For the feasibility of practical application, the analog circuit and FPGA digital circuit are designed. Finally, a simplified predefined time synchronization scheme is proposed; comparing with the full control input synchronization scheme, the simplified predefined time synchronization scheme can not only reduce the controller inputs but also predefine the synchronization time.
{"title":"Complex Dynamic Analysis, Circuit Design and Simplified Predefined Time Synchronization for a Jerk Absolute Memristor Chaotic System","authors":"Jindong Liu, Zhen Wang, Huaigu Tian, F. Xie","doi":"10.1155/2023/5912191","DOIUrl":"https://doi.org/10.1155/2023/5912191","url":null,"abstract":"In this parper, a 4D absolute memristor Jerk chaotic system is proposed. Firstly, complex dynamics are studied by phase diagram, Poincaré section, power spectrum, bifurcation diagram, 0-1 test, and Lyapunov exponent spectrum. Then, the period doubling bifurcation, degradation, and offset boosting are revealed. For the feasibility of practical application, the analog circuit and FPGA digital circuit are designed. Finally, a simplified predefined time synchronization scheme is proposed; comparing with the full control input synchronization scheme, the simplified predefined time synchronization scheme can not only reduce the controller inputs but also predefine the synchronization time.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"28 1","pages":"5912191:1-5912191:22"},"PeriodicalIF":0.0,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76724876","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}
Dimitrios Kagkas, Despina Karamichailidou, A. Alexandridis
The game of chess is the most widely examined game in the field of artificial intelligence and machine learning. In this work, we propose a new method for obtaining the evaluation of a chess position without using tree search and examining each candidate move separately, like a chess engine does. Instead of exploring the search tree in order to look several moves ahead, we propose to use the much faster and less computationally demanding estimations of a properly trained neural network. Such an approach offers the benefit of having an estimation for the position evaluation in a matter of milliseconds, while the time needed by a chess engine may be several orders of magnitude longer. The proposed approach introduces models based on the radial basis function (RBF) neural network architecture trained with the fuzzy means algorithm, in conjunction with a novel set of input features; different methods of network training are also examined and compared, involving the multilayer perceptron (MLP) and convolutional neural network (CNN) architectures and a different set of input features. All methods were based upon a new dataset, which was developed in the context of this work, derived by a collection of over 1500 top-level chess games. A Java application was developed for processing the games and extracting certain features from the arising positions in order to construct the dataset, which contained data from over 80,000 positions. Various networks were trained and tested as we considered different variations of each method regarding input variable configurations and dataset filtering. Ultimately, the results indicated that the proposed approach was the best in performance. The models produced with the proposed approach are suitable for integration in model-based decision-making frameworks, e.g., model predictive control (MPC) schemes, which could form the basis for a fully-fledged chess-playing software.
{"title":"Chess Position Evaluation Using Radial Basis Function Neural Networks","authors":"Dimitrios Kagkas, Despina Karamichailidou, A. Alexandridis","doi":"10.1155/2023/7143943","DOIUrl":"https://doi.org/10.1155/2023/7143943","url":null,"abstract":"The game of chess is the most widely examined game in the field of artificial intelligence and machine learning. In this work, we propose a new method for obtaining the evaluation of a chess position without using tree search and examining each candidate move separately, like a chess engine does. Instead of exploring the search tree in order to look several moves ahead, we propose to use the much faster and less computationally demanding estimations of a properly trained neural network. Such an approach offers the benefit of having an estimation for the position evaluation in a matter of milliseconds, while the time needed by a chess engine may be several orders of magnitude longer. The proposed approach introduces models based on the radial basis function (RBF) neural network architecture trained with the fuzzy means algorithm, in conjunction with a novel set of input features; different methods of network training are also examined and compared, involving the multilayer perceptron (MLP) and convolutional neural network (CNN) architectures and a different set of input features. All methods were based upon a new dataset, which was developed in the context of this work, derived by a collection of over 1500 top-level chess games. A Java application was developed for processing the games and extracting certain features from the arising positions in order to construct the dataset, which contained data from over 80,000 positions. Various networks were trained and tested as we considered different variations of each method regarding input variable configurations and dataset filtering. Ultimately, the results indicated that the proposed approach was the best in performance. The models produced with the proposed approach are suitable for integration in model-based decision-making frameworks, e.g., model predictive control (MPC) schemes, which could form the basis for a fully-fledged chess-playing software.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"22 1","pages":"7143943:1-7143943:16"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84359789","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}
S. Agyei, A. Bossman, Joseph Kofi Obeng Benchie, Oliver Asiamah, Emmanuel Yaw Arhin
In a time-frequency biwavelet framework, we analysed the short-, medium-, and long-term impacts of COVID-19-related shocks on ten energy commodities (i.e., Brent, crude oil, coal, heating oil, natural gas, gasoline, ethanol, naphtha, propane, and uranium) from January 2020 to April 2022. We document intervals of high and low coherence between COVID-19 cases and the returns on energy commodities across the short-, medium-, and long-term horizons. Low coherence at high frequencies indicated weak correlation and signified diversification, hedging, and safe-haven potentials in the short term of the pandemic. Our findings suggest that energy markets’ dynamics were highly driven by the pandemic, causing significant changes in market returns, particularly across the medium- and low-frequency bands. Furthermore, the empirical results indicate dynamic lead-lag relationships between COVID-19 cases and energy returns between the medium- and long-term horizons, signifying that diversification could be sought through crossinvestment in different energy commodities. The results have significant implications for market participants, regulators, and practitioners.
{"title":"Time-Frequency Analysis of COVID-19 Shocks and Energy Commodities","authors":"S. Agyei, A. Bossman, Joseph Kofi Obeng Benchie, Oliver Asiamah, Emmanuel Yaw Arhin","doi":"10.1155/2023/3982443","DOIUrl":"https://doi.org/10.1155/2023/3982443","url":null,"abstract":"In a time-frequency biwavelet framework, we analysed the short-, medium-, and long-term impacts of COVID-19-related shocks on ten energy commodities (i.e., Brent, crude oil, coal, heating oil, natural gas, gasoline, ethanol, naphtha, propane, and uranium) from January 2020 to April 2022. We document intervals of high and low coherence between COVID-19 cases and the returns on energy commodities across the short-, medium-, and long-term horizons. Low coherence at high frequencies indicated weak correlation and signified diversification, hedging, and safe-haven potentials in the short term of the pandemic. Our findings suggest that energy markets’ dynamics were highly driven by the pandemic, causing significant changes in market returns, particularly across the medium- and low-frequency bands. Furthermore, the empirical results indicate dynamic lead-lag relationships between COVID-19 cases and energy returns between the medium- and long-term horizons, signifying that diversification could be sought through crossinvestment in different energy commodities. The results have significant implications for market participants, regulators, and practitioners.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"22 1","pages":"3982443:1-3982443:16"},"PeriodicalIF":0.0,"publicationDate":"2023-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82751604","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}
After excavation of the weakly cemented roadway adjacent to the chambers, deformation characteristics such as roof subsidence, roadway extrusion, and floor heave appear, showing the characteristics of large deformation of surrounding rock, long deformation duration, and serious damage, which are not conducive to guaranteeing safety mining. Based on the technical means of the rock mechanical property test, mineral composition analysis, in situ stress test, and surrounding rock deformation monitoring of 2# coal roadway in Hongqingliang coal mine, a numerical simulation study on the influence of surrounding rock stress on adjacent chamber groups was carried out. The physical and mechanical properties of the weakly cemented rock were obtained, the stress distribution law of the 2# coal roadway was mastered, the deformation characteristics of the surrounding rock of the weakly cemented roadway were obtained, and the deformation and failure mechanism of the weakly cemented roadway adjacent to the chambers were revealed. The relationship between the regional stress increment of the chambers and the failure range of the surrounding rock of the roadway is revealed, establishing a mechanical model of allowable deformation + stress release + controlled form with U-shaped steel as the main structure. The roadway support countermeasures were given and applied in engineering practice.
{"title":"Study on Stress Disturbed Mechanism and Supporting Method of Weakly Cemented Roadway near Chambers","authors":"W. Zhang","doi":"10.1155/2023/7775116","DOIUrl":"https://doi.org/10.1155/2023/7775116","url":null,"abstract":"After excavation of the weakly cemented roadway adjacent to the chambers, deformation characteristics such as roof subsidence, roadway extrusion, and floor heave appear, showing the characteristics of large deformation of surrounding rock, long deformation duration, and serious damage, which are not conducive to guaranteeing safety mining. Based on the technical means of the rock mechanical property test, mineral composition analysis, in situ stress test, and surrounding rock deformation monitoring of 2# coal roadway in Hongqingliang coal mine, a numerical simulation study on the influence of surrounding rock stress on adjacent chamber groups was carried out. The physical and mechanical properties of the weakly cemented rock were obtained, the stress distribution law of the 2# coal roadway was mastered, the deformation characteristics of the surrounding rock of the weakly cemented roadway were obtained, and the deformation and failure mechanism of the weakly cemented roadway adjacent to the chambers were revealed. The relationship between the regional stress increment of the chambers and the failure range of the surrounding rock of the roadway is revealed, establishing a mechanical model of allowable deformation + stress release + controlled form with U-shaped steel as the main structure. The roadway support countermeasures were given and applied in engineering practice.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"60 1","pages":"7775116:1-7775116:12"},"PeriodicalIF":0.0,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91100037","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}
Supply chain management (SCM) is deeply affected by the COVID-19 pandemic besides breakdowns occurred in all sectors. Nowadays, managers need techniques for protecting supply chains from serious and costly disruptions, establishing permanent relationships with the customers and partners and preventing breakdowns throughout the process. Each firm needs to determine SCM strategies to be prepared for breakdowns in an intense competitive environment. With COVID-19, the change in business and trade environments has taken a different dimension, and it has revealed a new relationship between the efforts to perpetuate supply chains and strategies for supply chain management and enabled new models. In this study, it is aimed to prioritize the factors that lead to SCM breaks needed in project management and the realization of projects, and to choose the most successful SCM strategy considering COVID-19. For this purpose, rough SWARA was used for weighting factors and rough MARCOS was used for the alternative selection. According to the findings, the transportation capacity factor was found to be the most important factor leading to SCM breakdowns. The most ideal supply chain management strategy has been the “collaborative supply chain management strategy.” In the food manufacturing sector, the study can be considered as a roadmap in terms of preventing supply chain management breaks during the COVID-19 process and helping to ensure a sustainable production. As another theoretical and practical importance of the study, it is aimed to propose a robust, powerful, and practical decision-making model that can cope with the current uncertainties.
{"title":"Supply Chain Management (SCM) Breakdowns and SCM Strategy Selection during the COVID-19 Pandemic Using the Novel Rough MCDM Model","authors":"Željko Stević, A. Ulutaş, Selçuk Korucuk, Saliha Memiş, Ezgi Demir, Ayşe Topal, Çağlar Karamaşa","doi":"10.1155/2023/3478719","DOIUrl":"https://doi.org/10.1155/2023/3478719","url":null,"abstract":"Supply chain management (SCM) is deeply affected by the COVID-19 pandemic besides breakdowns occurred in all sectors. Nowadays, managers need techniques for protecting supply chains from serious and costly disruptions, establishing permanent relationships with the customers and partners and preventing breakdowns throughout the process. Each firm needs to determine SCM strategies to be prepared for breakdowns in an intense competitive environment. With COVID-19, the change in business and trade environments has taken a different dimension, and it has revealed a new relationship between the efforts to perpetuate supply chains and strategies for supply chain management and enabled new models. In this study, it is aimed to prioritize the factors that lead to SCM breaks needed in project management and the realization of projects, and to choose the most successful SCM strategy considering COVID-19. For this purpose, rough SWARA was used for weighting factors and rough MARCOS was used for the alternative selection. According to the findings, the transportation capacity factor was found to be the most important factor leading to SCM breakdowns. The most ideal supply chain management strategy has been the “collaborative supply chain management strategy.” In the food manufacturing sector, the study can be considered as a roadmap in terms of preventing supply chain management breaks during the COVID-19 process and helping to ensure a sustainable production. As another theoretical and practical importance of the study, it is aimed to propose a robust, powerful, and practical decision-making model that can cope with the current uncertainties.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"161 1","pages":"3478719:1-3478719:20"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85166788","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 : 2023-04-11eCollection Date: 2023-01-01DOI: 10.1159/000530223
Huseyin Gedik, Roseann E Peterson, Brien P Riley, Vladimir I Vladimirov, Silviu-Alin Bacanu
Background: The genome-wide association study (GWAS) is a common tool to identify genetic variants associated with complex traits, including psychiatric disorders (PDs). However, post-GWAS analyses are needed to extend the statistical inference to biologically relevant entities, e.g., genes, proteins, and pathways. To achieve this goal, researchers developed methods that incorporate biologically relevant intermediate molecular phenotypes, such as gene expression and protein abundance, which are posited to mediate the variant-trait association. Transcriptome-wide association study (TWAS) and proteome-wide association study (PWAS) are commonly used methods to test the association between these molecular mediators and the trait.
Summary: In this review, we discuss the most recent developments in TWAS and PWAS. These methods integrate existing "omic" information with the GWAS summary statistics for trait(s) of interest. Specifically, they impute transcript/protein data and test the association between imputed gene expression/protein level with phenotype of interest by using (i) GWAS summary statistics and (ii) reference transcriptomic/proteomic/genomic datasets. TWAS and PWAS are suitable as analysis tools for (i) primary association scan and (ii) fine-mapping to identify potentially causal genes for PDs.
Key messages: As post-GWAS analyses, TWAS and PWAS have the potential to highlight causal genes for PDs. These prioritized genes could indicate targets for the development of novel drug therapies. For researchers attempting such analyses, we recommend Mendelian randomization tools that use GWAS statistics for both trait and reference datasets, e.g., summary Mendelian randomization (SMR). We base our recommendation on (i) being able to use the same tool for both TWAS and PWAS, (ii) not requiring the pre-computed weights (and thus easier to update for larger reference datasets), and (iii) most larger transcriptome reference datasets are publicly available and easy to transform into a compatible format for SMR analysis.
{"title":"Integrative Post-Genome-Wide Association Study Analyses Relevant to Psychiatric Disorders: Imputing Transcriptome and Proteome Signals.","authors":"Huseyin Gedik, Roseann E Peterson, Brien P Riley, Vladimir I Vladimirov, Silviu-Alin Bacanu","doi":"10.1159/000530223","DOIUrl":"10.1159/000530223","url":null,"abstract":"<p><strong>Background: </strong>The genome-wide association study (GWAS) is a common tool to identify genetic variants associated with complex traits, including psychiatric disorders (PDs). However, post-GWAS analyses are needed to extend the statistical inference to biologically relevant entities, e.g., genes, proteins, and pathways. To achieve this goal, researchers developed methods that incorporate biologically relevant intermediate molecular phenotypes, such as gene expression and protein abundance, which are posited to mediate the variant-trait association. Transcriptome-wide association study (TWAS) and proteome-wide association study (PWAS) are commonly used methods to test the association between these molecular mediators and the trait.</p><p><strong>Summary: </strong>In this review, we discuss the most recent developments in TWAS and PWAS. These methods integrate existing \"omic\" information with the GWAS summary statistics for trait(s) of interest. Specifically, they impute transcript/protein data and test the association between imputed gene expression/protein level with phenotype of interest by using (i) GWAS summary statistics and (ii) reference transcriptomic/proteomic/genomic datasets. TWAS and PWAS are suitable as analysis tools for (i) primary association scan and (ii) fine-mapping to identify potentially causal genes for PDs.</p><p><strong>Key messages: </strong>As post-GWAS analyses, TWAS and PWAS have the potential to highlight causal genes for PDs. These prioritized genes could indicate targets for the development of novel drug therapies. For researchers attempting such analyses, we recommend Mendelian randomization tools that use GWAS statistics for both trait and reference datasets, e.g., summary Mendelian randomization (SMR). We base our recommendation on (i) being able to use the same tool for both TWAS and PWAS, (ii) not requiring the pre-computed weights (and thus easier to update for larger reference datasets), and (iii) most larger transcriptome reference datasets are publicly available and easy to transform into a compatible format for SMR analysis.</p>","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"9 1-4","pages":"130-144"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425719/pdf/cxp-2023-0009-01-4-530223.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10193463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Salman Ali, Muhammad Sadiq Khan, Habib Shah, Harish Garg, Abdullah Alsheddy
A Boolean-valued information system (BIS) is an application of a soft set in which the data are mapped in a binary form and used in making applications not limited to decision-making, medical diagnoses, game theory, and economics. BIS may be lost for several reasons including virus attacks, improper entry, and machine errors. A concept was presented that the entire lost BIS can be regenerated from four aggregate sets through supposition. Based on that concept, this paper presents an algorithm to recalculate the entire BIS through a genetic algorithm (GA), named BISGA which is more general and easy to implement than the supposition method. A solved example is presented which explains how BISGA works. Furthermore, BISGA is implemented in Python and evaluated on both UCI benchmark datasets and randomized datasets for checking its efficiency and accuracy. Results show that the lost BIS is recovered significantly and accurately; however, the efficiency drops when the size of the BIS increases. This novel approach may help practitioners recalculate the entire lost BIS, which in turn helps in the decision-making process and conclusions.
{"title":"BISGA: Recalculating the Entire Boolean-Valued Information System from Aggregates Using a Genetic Algorithm","authors":"Salman Ali, Muhammad Sadiq Khan, Habib Shah, Harish Garg, Abdullah Alsheddy","doi":"10.1155/2023/1539563","DOIUrl":"https://doi.org/10.1155/2023/1539563","url":null,"abstract":"A Boolean-valued information system (BIS) is an application of a soft set in which the data are mapped in a binary form and used in making applications not limited to decision-making, medical diagnoses, game theory, and economics. BIS may be lost for several reasons including virus attacks, improper entry, and machine errors. A concept was presented that the entire lost BIS can be regenerated from four aggregate sets through supposition. Based on that concept, this paper presents an algorithm to recalculate the entire BIS through a genetic algorithm (GA), named BISGA which is more general and easy to implement than the supposition method. A solved example is presented which explains how BISGA works. Furthermore, BISGA is implemented in Python and evaluated on both UCI benchmark datasets and randomized datasets for checking its efficiency and accuracy. Results show that the lost BIS is recovered significantly and accurately; however, the efficiency drops when the size of the BIS increases. This novel approach may help practitioners recalculate the entire lost BIS, which in turn helps in the decision-making process and conclusions.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"5 1","pages":"1539563:1-1539563:11"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90149165","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}
Abdulmalik Aldawsari, S. Yusuf, R. Souissi, Muhammad Al-Qurishi
Automated assessment of car damage is a major challenge in the auto repair and damage assessment industries. The domain has several application areas, ranging from car assessment companies, such as car rentals and body shops, to accidental damage assessment for car insurance companies. In vehicle assessment, the damage can take many forms, from scratches, minor dents, and major dents to missing parts. Often, the assessment area has a significant level of noise, such as dirt, grease, oil, or rush, which makes accurate identification challenging. Moreover, in the repair industry, identifying a particular part is the first step in obtaining an accurate labor and part assessment, where the presence of different car models, shapes, and sizes makes the task even more challenging for a machine-learning model to perform well. To address these challenges, this study explores and applies various instance segmentation methodologies to determine the best-performing models. This study focuses on two genres of real-time instance segmentation models, namely, SipMask and YOLACT, owing to their industrial significance. These methodologies were evaluated against a previously reported car parts dataset (DSMLR) as well as an internally curated dataset extracted from local car repair workshops. The YOLACT-based part localization and segmentation method outperformed other real-time instance mechanisms with an mAP of 66.5. For the workshop repair dataset, SipMask++ reported better accuracy for object detection with a mAP of 57.0, with outcomes for A P I o U = . 50 and A P I o U = . 75 reporting 72.0 and 67.0, respectively, whereas YOLACT was observed to be a better performer for A P s with 44.0 and 2.6 for object detection and segmentation categories, respectively.
汽车损伤的自动评估是汽车修理和损伤评估行业面临的主要挑战。该领域有几个应用领域，从汽车评估公司(如汽车租赁和车身商店)到汽车保险公司的意外损害评估。在车辆评估中，损坏可以采取多种形式，从划痕，小凹痕，大凹痕到缺失的部件。通常，评估区域具有显著的噪声水平，例如污垢、油脂、油或冲流，这使得准确识别具有挑战性。此外，在维修行业，识别特定零件是获得准确劳动力和零件评估的第一步，而不同车型、形状和尺寸的存在使得机器学习模型的任务更加具有挑战性。为了应对这些挑战，本研究探索并应用了各种实例分割方法来确定性能最佳的模型。鉴于实时实例分割模型的工业意义，本研究重点研究了两种类型的实时实例分割模型，即SipMask和YOLACT。这些方法是根据先前报告的汽车零件数据集(DSMLR)以及从当地汽车维修车间提取的内部策划数据集进行评估的。基于yolact的零件定位与分割方法的mAP值为66.5，优于其他实时实例机制。对于车间维修数据集，SipMask++报告的目标检测精度更高，mAP为57.0，结果为a P I o U =。50 A P I o U =。75人分别报告72.0和67.0，而YOLACT在对象检测和分割类别方面的表现分别为44.0和2.6。
{"title":"Real-Time Instance Segmentation Models for Identification of Vehicle Parts","authors":"Abdulmalik Aldawsari, S. Yusuf, R. Souissi, Muhammad Al-Qurishi","doi":"10.1155/2023/6460639","DOIUrl":"https://doi.org/10.1155/2023/6460639","url":null,"abstract":"Automated assessment of car damage is a major challenge in the auto repair and damage assessment industries. The domain has several application areas, ranging from car assessment companies, such as car rentals and body shops, to accidental damage assessment for car insurance companies. In vehicle assessment, the damage can take many forms, from scratches, minor dents, and major dents to missing parts. Often, the assessment area has a significant level of noise, such as dirt, grease, oil, or rush, which makes accurate identification challenging. Moreover, in the repair industry, identifying a particular part is the first step in obtaining an accurate labor and part assessment, where the presence of different car models, shapes, and sizes makes the task even more challenging for a machine-learning model to perform well. To address these challenges, this study explores and applies various instance segmentation methodologies to determine the best-performing models. This study focuses on two genres of real-time instance segmentation models, namely, SipMask and YOLACT, owing to their industrial significance. These methodologies were evaluated against a previously reported car parts dataset (DSMLR) as well as an internally curated dataset extracted from local car repair workshops. The YOLACT-based part localization and segmentation method outperformed other real-time instance mechanisms with an mAP of 66.5. For the workshop repair dataset, SipMask++ reported better accuracy for object detection with a mAP of 57.0, with outcomes for \u0000 \u0000 A\u0000 \u0000 \u0000 P\u0000 \u0000 \u0000 I\u0000 o\u0000 U\u0000 =\u0000 .\u0000 50\u0000 \u0000 \u0000 \u0000 and \u0000 \u0000 A\u0000 \u0000 \u0000 P\u0000 \u0000 \u0000 I\u0000 o\u0000 U\u0000 =\u0000 .\u0000 75\u0000 \u0000 \u0000 \u0000 reporting 72.0 and 67.0, respectively, whereas YOLACT was observed to be a better performer for \u0000 \u0000 A\u0000 \u0000 \u0000 P\u0000 \u0000 \u0000 s\u0000 \u0000 \u0000 \u0000 with 44.0 and 2.6 for object detection and segmentation categories, respectively.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"25 1","pages":"6460639:1-6460639:16"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76308352","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 this paper, we develop an efficient numerical method to approximate the solution of fractional integro-differential equations (FI-DEs) of mixed Volterra−Fredholm type using spectral collocation method with shifted Chebyshev polynomials of the third kind (S-Cheb-3). The fractional derivative is described in the Caputo sense. A Chebyshev−Gauss quadrature is involved to evaluate integrals for more precision. Two types of equations are studied to obtain algebraic systems solvable using the Gauss elimination method for linear equations and the Newton algorithm for nonlinear ones. In addition, an error analysis is carried out. Six numerical examples are evaluated using different error values (maximum absolute error, root mean square error, and relative error) to compare the approximate and the exact solutions of each example. The experimental rate of convergence is calculated as well. The results validate the numerical approach’s efficiency, applicability, and performance.
{"title":"Theoretical and Numerical Study for Volterra-Fredholm Fractional Integro-Differential Equations Based on Chebyshev Polynomials of the Third Kind","authors":"Zineb Laouar, N. Arar, A. B. Makhlouf","doi":"10.1155/2023/6401067","DOIUrl":"https://doi.org/10.1155/2023/6401067","url":null,"abstract":"In this paper, we develop an efficient numerical method to approximate the solution of fractional integro-differential equations (FI-DEs) of mixed Volterra−Fredholm type using spectral collocation method with shifted Chebyshev polynomials of the third kind (S-Cheb-3). The fractional derivative is described in the Caputo sense. A Chebyshev−Gauss quadrature is involved to evaluate integrals for more precision. Two types of equations are studied to obtain algebraic systems solvable using the Gauss elimination method for linear equations and the Newton algorithm for nonlinear ones. In addition, an error analysis is carried out. Six numerical examples are evaluated using different error values (maximum absolute error, root mean square error, and relative error) to compare the approximate and the exact solutions of each example. The experimental rate of convergence is calculated as well. The results validate the numerical approach’s efficiency, applicability, and performance.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"1 1","pages":"6401067:1-6401067:13"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79853413","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}
The article outlines an approach to computer modelling called “human simulation,” whose development has been explicitly oriented towards addressing societal problems through transdisciplinary efforts involving stakeholders, change agents, policy professionals, subject matter experts, and computer scientists. It describes the steps involved in the creation and exploration of the “insight space” of policy-oriented artificial societies, which include both analysing societal problems and designing societal solutions. A case study is provided, based on an (ongoing) research project studying “emotional contagion” related to misinformation, stigma, and anxiety in the wake of the COVID-19 pandemic, along with lessons learned about some of the challenges and opportunities facing scientists and stakeholders trying to simulate solutions to complex societal problems.
{"title":"Simulation, Science, and Stakeholders: Challenges and Opportunities for Modelling Solutions to Societal Problems","authors":"F. Shults","doi":"10.1155/2023/1375004","DOIUrl":"https://doi.org/10.1155/2023/1375004","url":null,"abstract":"The article outlines an approach to computer modelling called “human simulation,” whose development has been explicitly oriented towards addressing societal problems through transdisciplinary efforts involving stakeholders, change agents, policy professionals, subject matter experts, and computer scientists. It describes the steps involved in the creation and exploration of the “insight space” of policy-oriented artificial societies, which include both analysing societal problems and designing societal solutions. A case study is provided, based on an (ongoing) research project studying “emotional contagion” related to misinformation, stigma, and anxiety in the wake of the COVID-19 pandemic, along with lessons learned about some of the challenges and opportunities facing scientists and stakeholders trying to simulate solutions to complex societal problems.","PeriodicalId":72654,"journal":{"name":"Complex psychiatry","volume":"98 1","pages":"1375004:1-1375004:10"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73597356","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：