Pub Date : 2023-07-20DOI: 10.20965/jaciii.2023.p0673
Pengtao Wang, Lihong Li, Feiyang Pan, L. Wang
Herein, a dual-branch semantic segmentation model based on depth-separable convolution and attention mechanism is proposed for the real-time and accuracy requirement of semantic segmentation. The proposed approach overcomes the problems of poor segmentation effect and over-simplification of feature fusion arising from the constant downsample operations in semantic segmentation. The network is divided into spatial detail and semantic information paths. The spatial detail path utilizes a smaller downsample multiplier to maintain resolution and efficiently extract spatial information. The semantic information path is constructed by a non-bottleneck residual unit with dilated convolution; it extracts semantic features. For the feature aggregation problem, the feature-guided fusion module is designed to assign different weights to the parts of the two paths and fuse them to obtain the final output. The proposed algorithm achieves a segmentation accuracy of 69.6% and speed of 70 fps on the Cityscapes dataset, with a model parameter count of only 0.76 M, thus indicating some advantages over recent real-time semantic segmentation algorithms. The proposed method with depth separable convolution and attention mechanism can effectively extract features and compensate for the loss of accuracy caused by downsampling. The experiments demonstrate that the proposed fusion module outperforms other methods in fusing different features.
{"title":"Lightweight Bilateral Network for Real-Time Semantic Segmentation","authors":"Pengtao Wang, Lihong Li, Feiyang Pan, L. Wang","doi":"10.20965/jaciii.2023.p0673","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0673","url":null,"abstract":"Herein, a dual-branch semantic segmentation model based on depth-separable convolution and attention mechanism is proposed for the real-time and accuracy requirement of semantic segmentation. The proposed approach overcomes the problems of poor segmentation effect and over-simplification of feature fusion arising from the constant downsample operations in semantic segmentation. The network is divided into spatial detail and semantic information paths. The spatial detail path utilizes a smaller downsample multiplier to maintain resolution and efficiently extract spatial information. The semantic information path is constructed by a non-bottleneck residual unit with dilated convolution; it extracts semantic features. For the feature aggregation problem, the feature-guided fusion module is designed to assign different weights to the parts of the two paths and fuse them to obtain the final output. The proposed algorithm achieves a segmentation accuracy of 69.6% and speed of 70 fps on the Cityscapes dataset, with a model parameter count of only 0.76 M, thus indicating some advantages over recent real-time semantic segmentation algorithms. The proposed method with depth separable convolution and attention mechanism can effectively extract features and compensate for the loss of accuracy caused by downsampling. The experiments demonstrate that the proposed fusion module outperforms other methods in fusing different features.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"15 1","pages":"673-682"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90222657","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0638
Wenshuo Song, Weihua Cao, Wenkai Hu, Min Wu
This study proposes a cloud-edge collaboration framework for temperature regulation in continuous annealing processes. A multiobjective optimization is formulated by ensuring the control accuracy of the temperature to reduce energy consumption and increase efficiency with cloud computing. Based on process analytics, a framework for clustering operating conditions with high real-time requirements is proposed. Further, a recommendation mechanism for furnace temperatures with low real-time requirements is developed in the cloud. Compared with traditional architectures, the cloud-edge collaboration approach improves energy savings and control stability, which demonstrates its effectiveness and practicality.
{"title":"Cloud-Edge Cooperative Control System in Continuous Annealing Processes","authors":"Wenshuo Song, Weihua Cao, Wenkai Hu, Min Wu","doi":"10.20965/jaciii.2023.p0638","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0638","url":null,"abstract":"This study proposes a cloud-edge collaboration framework for temperature regulation in continuous annealing processes. A multiobjective optimization is formulated by ensuring the control accuracy of the temperature to reduce energy consumption and increase efficiency with cloud computing. Based on process analytics, a framework for clustering operating conditions with high real-time requirements is proposed. Further, a recommendation mechanism for furnace temperatures with low real-time requirements is developed in the cloud. Compared with traditional architectures, the cloud-edge collaboration approach improves energy savings and control stability, which demonstrates its effectiveness and practicality.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"34 3","pages":"638-644"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72475738","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0603
Enna Hirata, Takahiro Yamashita, Seiichi Ozawa
In this study, we introduce a system called Matrix Researcher2vec (MResearcher2vec) which generates researcher embedding vectors from their papers and research projects in researchmap and KAKENHI databases. The system includes data on 276,841 researchers, 6,161,592 papers, and research projects. Utilizing natural language processing techniques, the MResearcher2vec model extracts researcher vectors from the papers and research project summaries of KAKENHI grant recipients. The similarity between reseachers is then computed to visualize inter-researcher relationships. The machine learning results have been integrated into a web service, providing a novel approach for academic relationship mining. It can be applied in the matching of research contents and researchers in evaluation of industry-government-academia collaboration and joint research. It contributes in four aspects: (1) exchanges between researchers, (2) creation of opportunities for researchers and companies to connect, (3) further promotion of interdisciplinary research, and (4) reduction of lost opportunities for research institutions to acquire talents.
{"title":"Researcher Network Visualization Using Matrix Researcher2vec","authors":"Enna Hirata, Takahiro Yamashita, Seiichi Ozawa","doi":"10.20965/jaciii.2023.p0603","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0603","url":null,"abstract":"In this study, we introduce a system called Matrix Researcher2vec (MResearcher2vec) which generates researcher embedding vectors from their papers and research projects in researchmap and KAKENHI databases. The system includes data on 276,841 researchers, 6,161,592 papers, and research projects. Utilizing natural language processing techniques, the MResearcher2vec model extracts researcher vectors from the papers and research project summaries of KAKENHI grant recipients. The similarity between reseachers is then computed to visualize inter-researcher relationships. The machine learning results have been integrated into a web service, providing a novel approach for academic relationship mining. It can be applied in the matching of research contents and researchers in evaluation of industry-government-academia collaboration and joint research. It contributes in four aspects: (1) exchanges between researchers, (2) creation of opportunities for researchers and companies to connect, (3) further promotion of interdisciplinary research, and (4) reduction of lost opportunities for research institutions to acquire talents.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"16 1","pages":"603-608"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88607022","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0622
Ryotaro Harada, T. Oyama, Kenji Fujimoto, T. Shimizu, Masayoshi Ozawa, Julien Samuel Amar, Masahiko Sakai
The illegal dumping of aluminum and plastic into cities and marine areas leads to negative impacts on the ecosystem and contributes to increased environmental pollution. Although volunteer trash pickup activities have increased in recent years, they require significant effort, time, and money. Therefore, we propose automated trash pickup robot, which incorporates autonomous movement and trash pickup arms. Although these functions have been actively developed, relatively little research has focused on trash detection. As such, we have developed a trash detection function by using deep learning models to improve the accuracy. First, we created a new trash dataset that classifies four types of trash with high illegal dumping volumes (cans, plastic bottles, cardboard, and cigarette butts). Next, we developed a new you only look once (YOLO)-based model with low parameters and computations. We trained the model on a created dataset and a dataset consisting of marine trash created during previous research. In consequence, the proposed models achieve the same detection accuracy as the existing models on both datasets, with fewer parameters and computations. Furthermore, the proposed models accelerate the edge device’s frame rate.
{"title":"Trash Detection Algorithm Suitable for Mobile Robots Using Improved YOLO","authors":"Ryotaro Harada, T. Oyama, Kenji Fujimoto, T. Shimizu, Masayoshi Ozawa, Julien Samuel Amar, Masahiko Sakai","doi":"10.20965/jaciii.2023.p0622","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0622","url":null,"abstract":"The illegal dumping of aluminum and plastic into cities and marine areas leads to negative impacts on the ecosystem and contributes to increased environmental pollution. Although volunteer trash pickup activities have increased in recent years, they require significant effort, time, and money. Therefore, we propose automated trash pickup robot, which incorporates autonomous movement and trash pickup arms. Although these functions have been actively developed, relatively little research has focused on trash detection. As such, we have developed a trash detection function by using deep learning models to improve the accuracy. First, we created a new trash dataset that classifies four types of trash with high illegal dumping volumes (cans, plastic bottles, cardboard, and cigarette butts). Next, we developed a new you only look once (YOLO)-based model with low parameters and computations. We trained the model on a created dataset and a dataset consisting of marine trash created during previous research. In consequence, the proposed models achieve the same detection accuracy as the existing models on both datasets, with fewer parameters and computations. Furthermore, the proposed models accelerate the edge device’s frame rate.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"12 1","pages":"622-631"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83565967","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0700
Malak Abid Ali Khan, Hongbin Ma, Z. Rehman, Ying Jin, A. Rehman
To overcome the previous challenges and to mitigate the retransmission and acknowledgment of LoRa for electric shelf labels, the data parallelism model is used for transmitting the concurrent data from the network server to end devices (EDs) through gateways (GWs). The EDs are designated around the GWs based on machine clustering to minimize data congestion, collision, and overlapping during signal reception. Deployment and redeployment of EDs in the defined clusters depend on arithmetic distribution to reduce the near-far effect and the overall saturation in the network. To further improve the performance and analyze the behavior of the network, constant uplink power for signal-to-noise (SNR) while dynamic for received signal strength (RSS) has been proposed. In contrast to SNR, the RSS indicator estimates the actual position of the ED to prevent the capture effect. In the experimental implementation, downlink power at the connected EDs in the clusters illustrates higher values than the defined threshold.
{"title":"Evaluation of Distributed Machine Learning Model for LoRa-ESL","authors":"Malak Abid Ali Khan, Hongbin Ma, Z. Rehman, Ying Jin, A. Rehman","doi":"10.20965/jaciii.2023.p0700","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0700","url":null,"abstract":"To overcome the previous challenges and to mitigate the retransmission and acknowledgment of LoRa for electric shelf labels, the data parallelism model is used for transmitting the concurrent data from the network server to end devices (EDs) through gateways (GWs). The EDs are designated around the GWs based on machine clustering to minimize data congestion, collision, and overlapping during signal reception. Deployment and redeployment of EDs in the defined clusters depend on arithmetic distribution to reduce the near-far effect and the overall saturation in the network. To further improve the performance and analyze the behavior of the network, constant uplink power for signal-to-noise (SNR) while dynamic for received signal strength (RSS) has been proposed. In contrast to SNR, the RSS indicator estimates the actual position of the ED to prevent the capture effect. In the experimental implementation, downlink power at the connected EDs in the clusters illustrates higher values than the defined threshold.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"1 1","pages":"700-709"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89521738","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0632
Jinseok Woo, Minoru Hara, Y. Ohyama
Experimental education imparted at universities is essential for students to confirm their theoretical knowledge. Experiments, in general, can deal with real-world data that theory or simulation cannot handle. However, there are experimental subjects where it is difficult to obtain results according to the theory. Among them, heat conduction is a subject wherein it is difficult to obtain theoretical results because it is difficult to establish an experimental environment. Therefore, it is highly important to design experimental content using students’ perspectives, such as theory and practical experiments. Therefore, this study investigates the impact of education on the design and application of experimental apparatus for a heat-transfer experiment, which is a part of an experiment conducted by the Department of Mechanical Engineering, Tokyo University of Technology. Furthermore, we discuss the effectiveness of the proposed experimental system based on students’ behavior, comprehension, satisfaction, and subsequent results.
{"title":"Development and Application of a Heat-Transfer Experimental System for the Mechanical Engineering Applied Experiment","authors":"Jinseok Woo, Minoru Hara, Y. Ohyama","doi":"10.20965/jaciii.2023.p0632","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0632","url":null,"abstract":"Experimental education imparted at universities is essential for students to confirm their theoretical knowledge. Experiments, in general, can deal with real-world data that theory or simulation cannot handle. However, there are experimental subjects where it is difficult to obtain results according to the theory. Among them, heat conduction is a subject wherein it is difficult to obtain theoretical results because it is difficult to establish an experimental environment. Therefore, it is highly important to design experimental content using students’ perspectives, such as theory and practical experiments. Therefore, this study investigates the impact of education on the design and application of experimental apparatus for a heat-transfer experiment, which is a part of an experiment conducted by the Department of Mechanical Engineering, Tokyo University of Technology. Furthermore, we discuss the effectiveness of the proposed experimental system based on students’ behavior, comprehension, satisfaction, and subsequent results.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"43 1","pages":"632-637"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88956308","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0720
Fang Gao, Wenbin Chen
In this study, for a linear singular system, the dissipativity and disturbance-rejection problems are considered simultaneously. An improved equivalent-input-disturbance (IEID) method has shown good disturbance-rejection performance for linear systems. Therefore, the objective of this study is to obtain a satisfactory disturbance-rejection performance and dissipativity performance level based on the IEID method for singular systems. First, the influence of exogenous disturbances on the system is estimated based on the IEID method. The estimate is added to the control input channel to offset this influence. A necessary and sufficient condition is obtained to ensure that the singular system is admissible and satisfies dissipativity performance level. Subsequently, a state-feedback controller is designed based on the admissibility condition. Finally, a numerical example is used to demonstrate the validity of the proposed method.
{"title":"Mixed Dissipativity Control and Disturbance Rejection for Singular Systems","authors":"Fang Gao, Wenbin Chen","doi":"10.20965/jaciii.2023.p0720","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0720","url":null,"abstract":"In this study, for a linear singular system, the dissipativity and disturbance-rejection problems are considered simultaneously. An improved equivalent-input-disturbance (IEID) method has shown good disturbance-rejection performance for linear systems. Therefore, the objective of this study is to obtain a satisfactory disturbance-rejection performance and dissipativity performance level based on the IEID method for singular systems. First, the influence of exogenous disturbances on the system is estimated based on the IEID method. The estimate is added to the control input channel to offset this influence. A necessary and sufficient condition is obtained to ensure that the singular system is admissible and satisfies dissipativity performance level. Subsequently, a state-feedback controller is designed based on the admissibility condition. Finally, a numerical example is used to demonstrate the validity of the proposed method.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"54 1","pages":"720-725"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78032088","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0594
Yuan Xu, Di Zhang, Tianlang Xian, Zhizhang Ma, Hui Gao, Yuanyuan Ma
In this study, a drilling fluid prediction method based on an online sequential extreme learning machine (OS-ELM) is proposed, which is prepared for water well drilling on the muddy clay formation of Tarim Basin, Qinghai Province. First, we investigated the mechanism linking mix ratio to fluid performance, allowing us to employ an OS-ELM algorithm derived from the extreme learning machine. Particularly, the proposed prediction method is bidirectional to identify an appropriate slurry formulation. The forward prediction model is established to predict the fluid performance, where the mud additive contents are inputs, and the drilling fluid properties parameters are outputs. Correspondingly, the backward prediction model is established to modify the slurry formula, where differences in the drilling fluid properties are inputs and percentages of slurry additives amount are output. The simulation results show that the two-direction OS-ELM prediction model can better predict the drilling fluid properties in water well drilling.
{"title":"Two-Direction Prediction Method of Drilling Fluid Based on OS-ELM for Water Well Drilling","authors":"Yuan Xu, Di Zhang, Tianlang Xian, Zhizhang Ma, Hui Gao, Yuanyuan Ma","doi":"10.20965/jaciii.2023.p0594","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0594","url":null,"abstract":"In this study, a drilling fluid prediction method based on an online sequential extreme learning machine (OS-ELM) is proposed, which is prepared for water well drilling on the muddy clay formation of Tarim Basin, Qinghai Province. First, we investigated the mechanism linking mix ratio to fluid performance, allowing us to employ an OS-ELM algorithm derived from the extreme learning machine. Particularly, the proposed prediction method is bidirectional to identify an appropriate slurry formulation. The forward prediction model is established to predict the fluid performance, where the mud additive contents are inputs, and the drilling fluid properties parameters are outputs. Correspondingly, the backward prediction model is established to modify the slurry formula, where differences in the drilling fluid properties are inputs and percentages of slurry additives amount are output. The simulation results show that the two-direction OS-ELM prediction model can better predict the drilling fluid properties in water well drilling.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"14 1","pages":"594-602"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82852667","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0616
T. Ohkubo, E. Matsunaga
Numerical calculations are used in various situations. However, to achieve accurate numerical calculations, accuracy in the calculation method and initial values with high spatial resolution are necessary. Therefore, we propose a new method for estimating spatial values that considers characteristic theory but does not use interpolation. We consider the treatment of the curved characteristic line, which implies that the characteristic speed is altered locally. In the new method named averaging inverse characteristics method (AICM), the locally changing characteristic speed is averaged with the characteristic speed of the previous steps. We calculated the spatial values of the shock tube problem, described by the Euler equation, and examined the accuracy of the AICM by comparing the results of the inverse characteristics method (ICM) proposed in the previous study and the traditional interpolating methods. Compared to other methods, AICM reduced the error to less than 1/10 for all parameters. We determined from these results that the AICM accurately estimates the spatial distribution of problems where characteristic speed has significantly changed.
{"title":"New Spatial Value Estimation Method for Curved Characteristic Line","authors":"T. Ohkubo, E. Matsunaga","doi":"10.20965/jaciii.2023.p0616","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0616","url":null,"abstract":"Numerical calculations are used in various situations. However, to achieve accurate numerical calculations, accuracy in the calculation method and initial values with high spatial resolution are necessary. Therefore, we propose a new method for estimating spatial values that considers characteristic theory but does not use interpolation. We consider the treatment of the curved characteristic line, which implies that the characteristic speed is altered locally. In the new method named averaging inverse characteristics method (AICM), the locally changing characteristic speed is averaged with the characteristic speed of the previous steps. We calculated the spatial values of the shock tube problem, described by the Euler equation, and examined the accuracy of the AICM by comparing the results of the inverse characteristics method (ICM) proposed in the previous study and the traditional interpolating methods. Compared to other methods, AICM reduced the error to less than 1/10 for all parameters. We determined from these results that the AICM accurately estimates the spatial distribution of problems where characteristic speed has significantly changed.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"102 1","pages":"616-621"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75796113","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0576
Changfan Zhang, Yifu Xu, Zhenwen Sheng
The activation function introduces nonlinearity into convolutional neural network, which greatly promotes the development of computer vision tasks. This paper proposes elastic adaptively parametric compounded units to improve the performance of convolutional neural networks for image recognition. The activation function takes the structural advantages of two mainstream functions as the function’s fundamental architecture. The SENet model is embedded in the proposed activation function to adaptively recalibrate the feature mapping weight in each channel, thereby enhancing the fitting capability of the activation function. In addition, the function has an elastic slope in the positive input region by simulating random noise to improve the generalization capability of neural networks. To prevent the generated noise from producing overly large variations during training, a special protection mechanism is adopted. In order to verify the effectiveness of the activation function, this paper uses CIFAR-10 and CIFAR-100 image datasets to conduct comparative experiments of the activation function under the exact same model. Experimental results show that the proposed activation function showed superior performance beyond other functions.
{"title":"Elastic Adaptively Parametric Compounded Units for Convolutional Neural Network","authors":"Changfan Zhang, Yifu Xu, Zhenwen Sheng","doi":"10.20965/jaciii.2023.p0576","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0576","url":null,"abstract":"The activation function introduces nonlinearity into convolutional neural network, which greatly promotes the development of computer vision tasks. This paper proposes elastic adaptively parametric compounded units to improve the performance of convolutional neural networks for image recognition. The activation function takes the structural advantages of two mainstream functions as the function’s fundamental architecture. The SENet model is embedded in the proposed activation function to adaptively recalibrate the feature mapping weight in each channel, thereby enhancing the fitting capability of the activation function. In addition, the function has an elastic slope in the positive input region by simulating random noise to improve the generalization capability of neural networks. To prevent the generated noise from producing overly large variations during training, a special protection mechanism is adopted. In order to verify the effectiveness of the activation function, this paper uses CIFAR-10 and CIFAR-100 image datasets to conduct comparative experiments of the activation function under the exact same model. Experimental results show that the proposed activation function showed superior performance beyond other functions.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"37 1","pages":"576-584"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79239479","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：