Pub Date : 2023-03-20DOI: 10.20965/jaciii.2023.p0271
Tsung-Yin Ou, Yi-Chen Lee, Tien-Hsiang Chang, S. Lee, W. Tsai
As shopping patterns have gradually shifted from offline to online mode, and with recent lockdowns during the coronavirus disease 2019 (COVID-19) pandemic restricting foreign trade and accelerating the growth of the domestic economy, digital transformation has become a major strategy for many retailers to support and expand their businesses. With the pandemic becoming a turning point, the business of major e-commerce companies in Taiwan in the retail of dry goods has grown significantly, and it has driven the online sales of fresh products as well. In this era of fierce competition, it is especially important to find a way that enables consumers to quickly find ideal fresh products on multiple platforms, shortens the time for price comparison, and improves the efficiency of online shopping. This study uses the Python programming language to write a web crawler program that captures product information from fresh food e-commerce platforms, including product introduction, price, origin, and sales volume, and then defines the relevant status of the product, such as product popularity. Accordingly, through Chinese text segmentation and term-frequency calculation, it aims to classify the product names and introductions into frequently occurring words and use them as product-related labels. Finally, the program combines the product information processing results and product-related labels to construct an online fresh food recommendation system. The results of the proposed system show that it reduces the time and energy spent comparing prices. It can also guide consumers to browse products that may be of interest using relevant tags and increase consumption efficiency by helping them find the ideal item when shopping.
{"title":"Design and Implementation of a Recommendation System for Buying Fresh Foods Online Based on Web Crawling","authors":"Tsung-Yin Ou, Yi-Chen Lee, Tien-Hsiang Chang, S. Lee, W. Tsai","doi":"10.20965/jaciii.2023.p0271","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0271","url":null,"abstract":"As shopping patterns have gradually shifted from offline to online mode, and with recent lockdowns during the coronavirus disease 2019 (COVID-19) pandemic restricting foreign trade and accelerating the growth of the domestic economy, digital transformation has become a major strategy for many retailers to support and expand their businesses. With the pandemic becoming a turning point, the business of major e-commerce companies in Taiwan in the retail of dry goods has grown significantly, and it has driven the online sales of fresh products as well. In this era of fierce competition, it is especially important to find a way that enables consumers to quickly find ideal fresh products on multiple platforms, shortens the time for price comparison, and improves the efficiency of online shopping. This study uses the Python programming language to write a web crawler program that captures product information from fresh food e-commerce platforms, including product introduction, price, origin, and sales volume, and then defines the relevant status of the product, such as product popularity. Accordingly, through Chinese text segmentation and term-frequency calculation, it aims to classify the product names and introductions into frequently occurring words and use them as product-related labels. Finally, the program combines the product information processing results and product-related labels to construct an online fresh food recommendation system. The results of the proposed system show that it reduces the time and energy spent comparing prices. It can also guide consumers to browse products that may be of interest using relevant tags and increase consumption efficiency by helping them find the ideal item when shopping.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"1 1","pages":"271-280"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85962541","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0215
Hsiao-Chi Juan
Following the education reform occurring worldwide, the professional learning community has been seen as a crucial factor in changing the teaching practice on site. However, empirical research has failed to deal with multicollinearity under a social context. This study examines the effect of curriculum development policy and leadership on the professional learning community of teachers. The regularized linear regression method is used to identify the precise effect on the professional learning community in two ways, i.e., ridge and least absolute shrinkage and selection operator regressions. The results show that the main variance comes from teacher actions at the school level and that the collaborative sense of teachers has the most significant effect. This study contributes to existing knowledge on the professional learning of teachers by providing distinguished view of governance model.
{"title":"Relations Among Curriculum Governance Model, Teacher Work Settings, and Teacher Perceptions on the Professional Learning Community","authors":"Hsiao-Chi Juan","doi":"10.20965/jaciii.2023.p0215","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0215","url":null,"abstract":"Following the education reform occurring worldwide, the professional learning community has been seen as a crucial factor in changing the teaching practice on site. However, empirical research has failed to deal with multicollinearity under a social context. This study examines the effect of curriculum development policy and leadership on the professional learning community of teachers. The regularized linear regression method is used to identify the precise effect on the professional learning community in two ways, i.e., ridge and least absolute shrinkage and selection operator regressions. The results show that the main variance comes from teacher actions at the school level and that the collaborative sense of teachers has the most significant effect. This study contributes to existing knowledge on the professional learning of teachers by providing distinguished view of governance model.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"71 1","pages":"215-222"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85883197","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0292
Jianbin He, W. Qiu, Jianping Cai
The synchronization of master-slave hyperchaotic systems is investigated by intermittent control and proved by the Lyapunov stable theory. Meanwhile, a new secure communication scheme is designed for the continuous and digital information. The encrypted information is transmitted to receiver through the intermittent controller, which reduces the disturbance to the synchronization of master-slave systems and improves the security and reliability of secure communication. Before transmitting to the receiver, the continuous signal is firstly modulated and masked by the chaotic signals. Furthermore, an encryption algorithm for the digital information of color image is proposed by the pseudo-random sequences of Chen hyperchaotic system, and then the encrypted image is modulated and masked by the variables of the master system. The original image can be decrypted successfully at the receiving end after the slave system is synchronized with the master system. Finally, the feasibility and effectiveness of this scheme are verified by simulation experiments. In addition, the security analysis of the image encryption algorithm is also discussed, such as key sensitivity, correlation coefficient, NIST test, and return map.
{"title":"Synchronization of Hyperchaotic Systems Based on Intermittent Control and its Application in Secure Communication","authors":"Jianbin He, W. Qiu, Jianping Cai","doi":"10.20965/jaciii.2023.p0292","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0292","url":null,"abstract":"The synchronization of master-slave hyperchaotic systems is investigated by intermittent control and proved by the Lyapunov stable theory. Meanwhile, a new secure communication scheme is designed for the continuous and digital information. The encrypted information is transmitted to receiver through the intermittent controller, which reduces the disturbance to the synchronization of master-slave systems and improves the security and reliability of secure communication. Before transmitting to the receiver, the continuous signal is firstly modulated and masked by the chaotic signals. Furthermore, an encryption algorithm for the digital information of color image is proposed by the pseudo-random sequences of Chen hyperchaotic system, and then the encrypted image is modulated and masked by the variables of the master system. The original image can be decrypted successfully at the receiving end after the slave system is synchronized with the master system. Finally, the feasibility and effectiveness of this scheme are verified by simulation experiments. In addition, the security analysis of the image encryption algorithm is also discussed, such as key sensitivity, correlation coefficient, NIST test, and return map.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"39 1","pages":"292-303"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90041546","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0251
Shuping Lin, Wenhui Ma
Compared with traditional finance, digital inclusive finance involves particular policies, different targeting, and wider coverage, plays a positive role in promoting the development of the real economy, and upgrades to industrial facilities. Based on the panel data of 288 prefecture-level cities in China from 2011 to 2019, in this study, we empirically examined the impact of digital inclusive finance on upgrades to industrial structures. The experimental results showed a “U”-shaped nonlinear relationship between the development of digital inclusive finance and the upgrades to industrial structure. In particular, this conclusion remained valid after citing instrumental variables, replacing core explanatory variables, and performing other robustness tests. Furthermore, we used the threshold model to test the influence of digital inclusive finance on industrial structure upgrade, and observed a double threshold effect based on digital inclusive finance and local levels of economic development. Therefore, in the dynamic transformation towards digital inclusive finance and continuing economic development, the role of digital inclusive finance in promoting industrial structure upgrade continues to strengthen.
{"title":"Digital Inclusive Finance and Industrial Structure Upgrade - Based on Nonlinear Relationship Perspective","authors":"Shuping Lin, Wenhui Ma","doi":"10.20965/jaciii.2023.p0251","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0251","url":null,"abstract":"Compared with traditional finance, digital inclusive finance involves particular policies, different targeting, and wider coverage, plays a positive role in promoting the development of the real economy, and upgrades to industrial facilities. Based on the panel data of 288 prefecture-level cities in China from 2011 to 2019, in this study, we empirically examined the impact of digital inclusive finance on upgrades to industrial structures. The experimental results showed a “U”-shaped nonlinear relationship between the development of digital inclusive finance and the upgrades to industrial structure. In particular, this conclusion remained valid after citing instrumental variables, replacing core explanatory variables, and performing other robustness tests. Furthermore, we used the threshold model to test the influence of digital inclusive finance on industrial structure upgrade, and observed a double threshold effect based on digital inclusive finance and local levels of economic development. Therefore, in the dynamic transformation towards digital inclusive finance and continuing economic development, the role of digital inclusive finance in promoting industrial structure upgrade continues to strengthen.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"357 1","pages":"251-258"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76507921","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0259
Tao He, Hui Li, Zhe Cheng
Underdetermined blind source separation has received increasing attention in recent years as an effective method for speech-signal processing. Hence, a self-organizing mapping-density peak clustering and compressed sensing approach, which is a two-step approach, is proposed herein to improve the accuracy of underdetermined blind source separation. The approach features the following two aspects: (1) A mixing matrix estimation method based on self-organizing mapping and density peak clustering, which can intuitively determine the number of source signals, remove outliers, and determine the column vector of the mixing matrix based on local density; (2) a compressed sensing-based source signal reconstruction method, which can exploit the sparsity of signals in the frequency domain and use a hierarchical coupling method to reconstruct the source signal accurately and efficiently under the premise that the prior knowledge of the signal is unknown. The proposed method does not require the number of source signals and exhibits excellent performance under different noise conditions. Theoretical analysis and experimental results demonstrate the effectiveness of the proposed method.
{"title":"Underdetermined Blind Source Separation Method for Speech Signals Based on SOM-DPC and Compressed Sensing","authors":"Tao He, Hui Li, Zhe Cheng","doi":"10.20965/jaciii.2023.p0259","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0259","url":null,"abstract":"Underdetermined blind source separation has received increasing attention in recent years as an effective method for speech-signal processing. Hence, a self-organizing mapping-density peak clustering and compressed sensing approach, which is a two-step approach, is proposed herein to improve the accuracy of underdetermined blind source separation. The approach features the following two aspects: (1) A mixing matrix estimation method based on self-organizing mapping and density peak clustering, which can intuitively determine the number of source signals, remove outliers, and determine the column vector of the mixing matrix based on local density; (2) a compressed sensing-based source signal reconstruction method, which can exploit the sparsity of signals in the frequency domain and use a hierarchical coupling method to reconstruct the source signal accurately and efficiently under the premise that the prior knowledge of the signal is unknown. The proposed method does not require the number of source signals and exhibits excellent performance under different noise conditions. Theoretical analysis and experimental results demonstrate the effectiveness of the proposed method.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"38 1","pages":"259-270"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80734382","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0243
Lei Li, Yuemei Ren, Jinming Ma
It has been demonstrated that nuclear-norm-based low-rank representation is capable of modeling cluttered backgrounds in hyperspectral images (HSIs) for robust anomaly detection. However, minimizing the nuclear norm regularizes each singular value equally during rank reduction, which restricts the capacity and flexibility of modeling the major structures of the background. To address this problem, we propose detection of anomaly pixels in HSIs using the weighted nuclear norm, which can preserve the major singular values during rank reduction. We present a down-up sampling scheme to remove plausible anomaly pixels from the image as much as possible and learn a robust principal component analysis (PCA) background dictionary. From a dictionary, we develop a weighted nuclear-norm minimization model to represent the background with a low-rank coefficients matrix that can be effectively optimized using the standard alternating direction method of multipliers (ADMM). Due to the flexible modeling capacity using the weighted nuclear norm, anomaly pixels can be distinguished from the background with the reconstruction error. The experimental results on two real HSIs datasets demonstrate the effectiveness of the proposed method for anomaly detection.
{"title":"Flexible Hyperspectral Anomaly Detection Using Weighted Nuclear Norm","authors":"Lei Li, Yuemei Ren, Jinming Ma","doi":"10.20965/jaciii.2023.p0243","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0243","url":null,"abstract":"It has been demonstrated that nuclear-norm-based low-rank representation is capable of modeling cluttered backgrounds in hyperspectral images (HSIs) for robust anomaly detection. However, minimizing the nuclear norm regularizes each singular value equally during rank reduction, which restricts the capacity and flexibility of modeling the major structures of the background. To address this problem, we propose detection of anomaly pixels in HSIs using the weighted nuclear norm, which can preserve the major singular values during rank reduction. We present a down-up sampling scheme to remove plausible anomaly pixels from the image as much as possible and learn a robust principal component analysis (PCA) background dictionary. From a dictionary, we develop a weighted nuclear-norm minimization model to represent the background with a low-rank coefficients matrix that can be effectively optimized using the standard alternating direction method of multipliers (ADMM). Due to the flexible modeling capacity using the weighted nuclear norm, anomaly pixels can be distinguished from the background with the reconstruction error. The experimental results on two real HSIs datasets demonstrate the effectiveness of the proposed method for anomaly detection.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"61 1","pages":"243-250"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81062016","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0314
Jie Hu, Chengda Lu, Luefeng Chen, Quanxin Li, Wangnian Li, Hongchao Wei, Min Wu
During the drilling process, horizontal drill strings are often subject to stick-slip and back-pressure phenomena, which undermine drilling safety and affect drilling costs. However, most of the models proposed in the existing literature apply only to the analysis of the drill string motion state and are irrelevant to the rotary drilling process in coal mines. This paper presents a lumped-mass model of a drill string in a horizontal coal mine well. First, based on reasonable assumptions, the drill-string system was considered as four lumped-mass units. The lateral-torsional dynamics model was established based on the Lagrange dynamics theory. Further, combined with lateral movement, the intermittent contact between the drill string and borehole wall is described, and the friction torque due to this intermittent contact is calculated. Combined with the Karnopp bit-rock interaction, a drill-string dynamics model of horizontal wells that considers intermittent contact friction was developed. The proposed horizontal well drill-string model is more suitable for rotary drilling in a coal mine, and the nonlinear influencing factors are considered more comprehensive.
{"title":"Drill-String Dynamics Model of Horizontal Coal Mine Wells Considering Intermittent Borehole Wall Contact","authors":"Jie Hu, Chengda Lu, Luefeng Chen, Quanxin Li, Wangnian Li, Hongchao Wei, Min Wu","doi":"10.20965/jaciii.2023.p0314","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0314","url":null,"abstract":"During the drilling process, horizontal drill strings are often subject to stick-slip and back-pressure phenomena, which undermine drilling safety and affect drilling costs. However, most of the models proposed in the existing literature apply only to the analysis of the drill string motion state and are irrelevant to the rotary drilling process in coal mines. This paper presents a lumped-mass model of a drill string in a horizontal coal mine well. First, based on reasonable assumptions, the drill-string system was considered as four lumped-mass units. The lateral-torsional dynamics model was established based on the Lagrange dynamics theory. Further, combined with lateral movement, the intermittent contact between the drill string and borehole wall is described, and the friction torque due to this intermittent contact is calculated. Combined with the Karnopp bit-rock interaction, a drill-string dynamics model of horizontal wells that considers intermittent contact friction was developed. The proposed horizontal well drill-string model is more suitable for rotary drilling in a coal mine, and the nonlinear influencing factors are considered more comprehensive.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"49 1","pages":"314-321"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72543566","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0154
Ming-Yun Kuo, Tsung-Kuo Tien-Liu, Wen-Lin Chang
This study investigated the relationship between passion for exercise, self-esteem, and well-being of participants of jogging activities. Purpose: The purpose of this study was to explore the relationship between passion for exercise, self-esteem, and psychological well-being of participants with different backgrounds and determine whether self-esteem affects the relationship between participants’ passion for exercise and well-being. Design/methodology/approach: A total of 344 valid questionnaires were employed, which included 164 males and 180 females of the jogging activities held by Fu Jen Catholic University. Descriptive statistics, independent sample t-test, one-way analysis of variance, Pearson product-difference correlation, regression, and other statistical methods were performed on the questionnaire to test the correlation between variables. Findings: (1) Different sexes had differences in obsessive passion, (2) different jogging groups had differences in obsessive passion, (3) different grades had differences in negative self-esteem, (4) different ages had harmonious passion, and there were differences in positive self-esteem, (5) the frequency of exercising with peers exhibited differences in psychological well-being and positive self-esteem, (6) there was a correlation between passion, psychological well-being, and self-esteem, and (7) positive self-esteem had a mediating effect on harmonious passion and psychological well-being. Conclusions: Participants of jogging activities are willing to spend time and effort in jogging activities, participate with an open and flexible attitude, and enjoy the process, thus improving positive self-evaluation and achieving a satisfied self-feel. Originality/value: There is less research on the relationship between passion and self-esteem in Taiwan. In addition, the authors not only found the relationship between passion, self-esteem, and psychological well-being from the data, but also found that self-esteem has a mediating effect on the relationship between passion and psychological well-being. Therefore, when organizing similar activities in the future, in addition to using attractive conditions that are more favorable to the participants, attention should be given to conditions that can enhance the self-worth of participants and increase the motivation and number of participants. In addition, participants performing activities with their peers will have more positive self-evaluations and feelings and happier and more satisfied.
{"title":"Mediating Role of Self-Esteem in Activity Participants' Passion for Exercise and Psychological Well-Being by Jogging in Fu Jen Catholic University","authors":"Ming-Yun Kuo, Tsung-Kuo Tien-Liu, Wen-Lin Chang","doi":"10.20965/jaciii.2023.p0154","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0154","url":null,"abstract":"This study investigated the relationship between passion for exercise, self-esteem, and well-being of participants of jogging activities. Purpose: The purpose of this study was to explore the relationship between passion for exercise, self-esteem, and psychological well-being of participants with different backgrounds and determine whether self-esteem affects the relationship between participants’ passion for exercise and well-being. Design/methodology/approach: A total of 344 valid questionnaires were employed, which included 164 males and 180 females of the jogging activities held by Fu Jen Catholic University. Descriptive statistics, independent sample t-test, one-way analysis of variance, Pearson product-difference correlation, regression, and other statistical methods were performed on the questionnaire to test the correlation between variables. Findings: (1) Different sexes had differences in obsessive passion, (2) different jogging groups had differences in obsessive passion, (3) different grades had differences in negative self-esteem, (4) different ages had harmonious passion, and there were differences in positive self-esteem, (5) the frequency of exercising with peers exhibited differences in psychological well-being and positive self-esteem, (6) there was a correlation between passion, psychological well-being, and self-esteem, and (7) positive self-esteem had a mediating effect on harmonious passion and psychological well-being. Conclusions: Participants of jogging activities are willing to spend time and effort in jogging activities, participate with an open and flexible attitude, and enjoy the process, thus improving positive self-evaluation and achieving a satisfied self-feel. Originality/value: There is less research on the relationship between passion and self-esteem in Taiwan. In addition, the authors not only found the relationship between passion, self-esteem, and psychological well-being from the data, but also found that self-esteem has a mediating effect on the relationship between passion and psychological well-being. Therefore, when organizing similar activities in the future, in addition to using attractive conditions that are more favorable to the participants, attention should be given to conditions that can enhance the self-worth of participants and increase the motivation and number of participants. In addition, participants performing activities with their peers will have more positive self-evaluations and feelings and happier and more satisfied.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"46 1","pages":"154-164"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73770112","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0223
Akinobu Sakata, Takamasa Kikuchi, M. Kunigami, Atsushi Yoshikawa, M. Yamamura, T. Terano
This study proposes a method for analyzing gaming simulation results. The gaming simulation we focus on intends to be played by both human and computer agent players. To extract the knowledge of what and how they have played, we must determine what type of decision-making process leads to specific scenarios. Such simulation results, however, tend to have so many branch factors of scenarios that it is hard to understand by manual operations. To deal with the issues, we have developed a method for obtaining the branch factors of scenarios from gaming simulation results. We have demonstrated the effectiveness of the proposed method by identifying the branching factors of scenarios as follows. First, software agents were asked to play a gaming simulation for career education. Next, logs acquired through gaming were classified into multiple scenarios using machine learning techniques. Finally, decision-making factors separating the scenarios were identified using a decision tree.
{"title":"Extracting Branch Factors of Scenarios from a Gaming Simulation Using Log-Cluster Analysis","authors":"Akinobu Sakata, Takamasa Kikuchi, M. Kunigami, Atsushi Yoshikawa, M. Yamamura, T. Terano","doi":"10.20965/jaciii.2023.p0223","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0223","url":null,"abstract":"This study proposes a method for analyzing gaming simulation results. The gaming simulation we focus on intends to be played by both human and computer agent players. To extract the knowledge of what and how they have played, we must determine what type of decision-making process leads to specific scenarios. Such simulation results, however, tend to have so many branch factors of scenarios that it is hard to understand by manual operations. To deal with the issues, we have developed a method for obtaining the branch factors of scenarios from gaming simulation results. We have demonstrated the effectiveness of the proposed method by identifying the branching factors of scenarios as follows. First, software agents were asked to play a gaming simulation for career education. Next, logs acquired through gaming were classified into multiple scenarios using machine learning techniques. Finally, decision-making factors separating the scenarios were identified using a decision tree.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"27 1","pages":"223-234"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88172291","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 : 2023-03-20DOI: 10.20965/jaciii.2023.p0182
V. Vijayan, K. Pushpalatha
Drowsy driving is more hazardous than reckless driving. This study concentrates on capturing the behavioral features of drowsiness from facial images of a driver. The methodology considers scale invariant feature transform matched with the fast library for approximate nearest neighbors for low-level drowsy features extraction. These features are fused with the high-level features extracted from the convolutional layers of a convolutional neural network (CNN). The convolution operation incorporates a model parallelization technique to increase the efficiency of the training and improve the feature identification. Further classification is performed by considering the occurrences of visual words using the softmax layers of the CNN. In contrast to existing state-of-the-art models which require a few seconds to detect drowsiness, this model detects drowsiness in milliseconds. With the model parallelization approach, this model exhibits a high accuracy rate of 83.8% relative to normal CNNs.
{"title":"Fused Architecture with Enhanced Bag of Visual Words for Efficient Drowsiness Detection","authors":"V. Vijayan, K. Pushpalatha","doi":"10.20965/jaciii.2023.p0182","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0182","url":null,"abstract":"Drowsy driving is more hazardous than reckless driving. This study concentrates on capturing the behavioral features of drowsiness from facial images of a driver. The methodology considers scale invariant feature transform matched with the fast library for approximate nearest neighbors for low-level drowsy features extraction. These features are fused with the high-level features extracted from the convolutional layers of a convolutional neural network (CNN). The convolution operation incorporates a model parallelization technique to increase the efficiency of the training and improve the feature identification. Further classification is performed by considering the occurrences of visual words using the softmax layers of the CNN. In contrast to existing state-of-the-art models which require a few seconds to detect drowsiness, this model detects drowsiness in milliseconds. With the model parallelization approach, this model exhibits a high accuracy rate of 83.8% relative to normal CNNs.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"21 1","pages":"182-189"},"PeriodicalIF":0.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87513491","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：