To provide the best possible performance in precisely segmenting clinical images, several approaches are used. Convolutional neural networks are one method used in it to extract its features, which combine several models with several additional methods. It also improves the efficiency of generalisation between categorised and uncategorized image categories. The method proposed combines multi-style image fusion with two-dimensional fracture image representation. The photographs on this page have been updated with a variety of images to improve concentration sharing and achieve the desired visual look. The border detection algorithm is then used to extract the exact border of the image from the contrast extended images. It will then be divided into basic and comprehensive layers. The fused image was then created using augmented end layers.
{"title":"BISFT- two-dimensional breakdown clinical image seperation and fusion technique using CNN","authors":"G. Pradeepkumar, S. Kavitha","doi":"10.3233/jifs-239695","DOIUrl":"https://doi.org/10.3233/jifs-239695","url":null,"abstract":"To provide the best possible performance in precisely segmenting clinical images, several approaches are used. Convolutional neural networks are one method used in it to extract its features, which combine several models with several additional methods. It also improves the efficiency of generalisation between categorised and uncategorized image categories. The method proposed combines multi-style image fusion with two-dimensional fracture image representation. The photographs on this page have been updated with a variety of images to improve concentration sharing and achieve the desired visual look. The border detection algorithm is then used to extract the exact border of the image from the contrast extended images. It will then be divided into basic and comprehensive layers. The fused image was then created using augmented end layers.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140215310","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}
M. A. Ganesh, S. Saravana Perumaal, S.M. Gomathi Sankar
The current framework for detecting Fake License Plates (FLP) in real-time is not robust enough for patrol teams. The objective of this paper is to develop a robust license plate authentication framework, based on the Vehicle Make and Model Recognition (VMMR) and the License Plate Recognition (LPR) algorithms that is implementable at the edge devices. The contributions of this paper are (i) Development of license plate database for 547 Indian cars, (ii) Development of an image dataset with 3173 images of 547 Indian cars in 8 classes, (iii) Development of an ensemble model to recognize vehicle make and model from frontal, rear, and side images, and (iv) Development of a framework to authenticate the license plates with frontal, rear, and side images. The proposed ensemble model is compared with the state-of-the-art networks from the literature. Among the implemented networks for VMMR, the Ensembling model with a size of 303.2 MB achieves the best accuracy of 89% . Due to the limited memory size, Easy OCR is chosen to recognize license plate. The total size of the authentication framework is 308 MB. The performance of the proposed framework is compared with the literature. According to the results, the proposed framework enhances FLP recognition due to the recognition of vehicles from side images. The dataset is made public at https://www.kaggle.com/ganeshmailecture/datasets.
{"title":"Automated license plate authentication framework using multi-view vehicle images","authors":"M. A. Ganesh, S. Saravana Perumaal, S.M. Gomathi Sankar","doi":"10.3233/jifs-230607","DOIUrl":"https://doi.org/10.3233/jifs-230607","url":null,"abstract":"The current framework for detecting Fake License Plates (FLP) in real-time is not robust enough for patrol teams. The objective of this paper is to develop a robust license plate authentication framework, based on the Vehicle Make and Model Recognition (VMMR) and the License Plate Recognition (LPR) algorithms that is implementable at the edge devices. The contributions of this paper are (i) Development of license plate database for 547 Indian cars, (ii) Development of an image dataset with 3173 images of 547 Indian cars in 8 classes, (iii) Development of an ensemble model to recognize vehicle make and model from frontal, rear, and side images, and (iv) Development of a framework to authenticate the license plates with frontal, rear, and side images. The proposed ensemble model is compared with the state-of-the-art networks from the literature. Among the implemented networks for VMMR, the Ensembling model with a size of 303.2 MB achieves the best accuracy of 89% . Due to the limited memory size, Easy OCR is chosen to recognize license plate. The total size of the authentication framework is 308 MB. The performance of the proposed framework is compared with the literature. According to the results, the proposed framework enhances FLP recognition due to the recognition of vehicles from side images. The dataset is made public at https://www.kaggle.com/ganeshmailecture/datasets.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140217651","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}
Video anomaly detection (VAD) has garnered substantial attention from researchers due to its broad applications, including fire detection, drop detection, and vibration detection. In the current context of VAD, existing methods prioritize detection efficiency but overlook the impact of motion and appearance information. Additionally, achieving accurate predictions while retaining motion and appearance information poses a significant challenge. This paper proposes a novel semi-supervised method for VAD based on Generative Adversarial Network (GAN) structures with dual generators and dual discriminators, namely Dual-GAN. The future frame generator utilizes an improved encoder-decoder network to preserve more spatial information. Motion information for the future flow generator is obtained by estimating optical flow between reconstruction frames, complementing the optical flow between prediction frames. The introduction of a frame discriminator and a motion discriminator against the frame generator enhances the realism of prediction frames, which facilitates the identification of unexpected abnormal events. This method significantly outperforms comparative approaches in synthesizing video frames and predicting future flows, showcasing its effectiveness in handling diverse video data. Extensive experiments are performed on four publicly available datasets to ensure a comprehensive evaluation of the model performance. Further exploration could include refining the model architecture, exploring additional datasets, and adapting the methodology to specific application domains.
视频异常检测（VAD）因其广泛的应用而备受研究人员的关注，包括火灾检测、跌落检测和振动检测。在当前的 VAD 环境下，现有方法优先考虑检测效率，却忽视了运动和外观信息的影响。此外，在保留运动和外观信息的同时实现准确预测也是一个巨大的挑战。本文提出了一种基于具有双生成器和双判别器的生成对抗网络（GAN）结构的新型半监督 VAD 方法，即 Dual-GAN。未来帧生成器利用改进的编码器-解码器网络来保留更多的空间信息。未来流生成器的运动信息是通过估计重建帧之间的光流获得的，这是对预测帧之间光流的补充。针对帧生成器引入的帧判别器和运动判别器增强了预测帧的真实性，从而有助于识别意外异常事件。该方法在合成视频帧和预测未来流量方面明显优于其他方法，展示了其处理各种视频数据的有效性。我们在四个公开数据集上进行了广泛的实验，以确保对模型性能进行全面评估。进一步的探索可包括完善模型架构、探索其他数据集，以及将该方法调整到特定应用领域。
{"title":"Dual generators and dual discriminators generative adversarial network for video anomaly detection","authors":"Kang Chen, Changming Song, Dongxu Cheng, Hao Li","doi":"10.3233/jifs-237831","DOIUrl":"https://doi.org/10.3233/jifs-237831","url":null,"abstract":"Video anomaly detection (VAD) has garnered substantial attention from researchers due to its broad applications, including fire detection, drop detection, and vibration detection. In the current context of VAD, existing methods prioritize detection efficiency but overlook the impact of motion and appearance information. Additionally, achieving accurate predictions while retaining motion and appearance information poses a significant challenge. This paper proposes a novel semi-supervised method for VAD based on Generative Adversarial Network (GAN) structures with dual generators and dual discriminators, namely Dual-GAN. The future frame generator utilizes an improved encoder-decoder network to preserve more spatial information. Motion information for the future flow generator is obtained by estimating optical flow between reconstruction frames, complementing the optical flow between prediction frames. The introduction of a frame discriminator and a motion discriminator against the frame generator enhances the realism of prediction frames, which facilitates the identification of unexpected abnormal events. This method significantly outperforms comparative approaches in synthesizing video frames and predicting future flows, showcasing its effectiveness in handling diverse video data. Extensive experiments are performed on four publicly available datasets to ensure a comprehensive evaluation of the model performance. Further exploration could include refining the model architecture, exploring additional datasets, and adapting the methodology to specific application domains.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140215329","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}
A real-time stable multi-target tracking method based on the enhanced You Only Look Once-v8 (YOLOv8) and the optimized Simple Online and Realtime Tracking with a Deep association metric (DeepSORT) for multi-target tracking (S-YOFEO) is proposed with the aim of addressing the issue of target ID transformation and loss caused by the increase of practical background complexity. For the purpose of further enhancing the representation of small-scale features, a small target detection head is first introduced to the detection layer of YOLOv8 in this paper with the aim of collecting more detailed information by increasing the detection resolution of YOLOv8. Secondly, the Omni-Scale Network (OSNet) feature extraction network is implemented to enable accurate and efficient fusion of the extracted complex and comparable feature information, taking into account the restricted computational power of DeepSORT’s original feature extraction network. Again, a novel adaptive forgetting Kalman filter algorithm (FSA) is devised to enhance the precision of model prediction and the effectiveness of parameter updates to adjust to the uncertain movement speed and trajectory of pedestrians in real scenarios. Following that, an accurate and stable association matching process is obtained by substituting Efficient-Intersection over Union (EIOU) for Complete-Intersection over Union (CIOU) in DeepSORT to boost the convergence speed and matching effect during association matching. Last but not least, One-Shot Aggregation (OSA) is presented as the trajectory feature extractor to deal with the various noise interferences in the complex scene. OSA is highly sensitive to information of different scales, and its one-time aggregation property substantially decreases the computational overhead of the model. According to the trial results, S-YOFEO has made some developments as its precision can reach 78.2% and its speed can reach 56.0 frames per second (FPS).
{"title":"Pedestrian tracking method based on S-YOFEO framework in complex scene","authors":"Wenshun Sheng, Jiahui Shen, Qiming Huang, Zhixuan Liu, Zihao Ding","doi":"10.3233/jifs-237208","DOIUrl":"https://doi.org/10.3233/jifs-237208","url":null,"abstract":"A real-time stable multi-target tracking method based on the enhanced You Only Look Once-v8 (YOLOv8) and the optimized Simple Online and Realtime Tracking with a Deep association metric (DeepSORT) for multi-target tracking (S-YOFEO) is proposed with the aim of addressing the issue of target ID transformation and loss caused by the increase of practical background complexity. For the purpose of further enhancing the representation of small-scale features, a small target detection head is first introduced to the detection layer of YOLOv8 in this paper with the aim of collecting more detailed information by increasing the detection resolution of YOLOv8. Secondly, the Omni-Scale Network (OSNet) feature extraction network is implemented to enable accurate and efficient fusion of the extracted complex and comparable feature information, taking into account the restricted computational power of DeepSORT’s original feature extraction network. Again, a novel adaptive forgetting Kalman filter algorithm (FSA) is devised to enhance the precision of model prediction and the effectiveness of parameter updates to adjust to the uncertain movement speed and trajectory of pedestrians in real scenarios. Following that, an accurate and stable association matching process is obtained by substituting Efficient-Intersection over Union (EIOU) for Complete-Intersection over Union (CIOU) in DeepSORT to boost the convergence speed and matching effect during association matching. Last but not least, One-Shot Aggregation (OSA) is presented as the trajectory feature extractor to deal with the various noise interferences in the complex scene. OSA is highly sensitive to information of different scales, and its one-time aggregation property substantially decreases the computational overhead of the model. According to the trial results, S-YOFEO has made some developments as its precision can reach 78.2% and its speed can reach 56.0 frames per second (FPS).","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140213096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the context of the digital era, the factors influencing the cognitive load of the full ecological smart home on the elderly are mostly interconnected. Most existing studies have conducted single correlation analyses, ignoring the fact that cognitive load is the result among multiple interactions of multiple factors. Furthermore, the color, material and Finishing of the product design can also impact on the user’s perceptual needs. Therefore, exploring the grouping dynamics of cognitive load and users’ perceptual needs for color (C), material (M), and Finishing (F) of smart products can provide insights for inclusive design of smart homes. The article analyzes the asymmetric multiple concurrent causal effects of full ecological smart homes on the cognitive load of the elderly from a histological perspective using fuzzy set Qualitative Comparative Analysis (fsQCA) based on the four elements of Innovation Diffusion Theory. At the same time, principal component analysis and quantitative theory I class method are used to explore the quantitative relationship between color, material, Finishing and users’ perceptual imagery of the product. The results of the study showed that there were no necessary conditions leading to high or low cognitive load in the fsQCA analysis, indicating that the problem was the result of the interaction of multiple conditions, and the final analysis yielded three histological pathways leading to low cognitive load and one pathway leading to high load in older adults. Moreover, the study identifies the combination of colors, materials, and finishes that best represent user preferences. This study establishes a dialogue between theory, results, and cases in analyzing of the group dynamics of the impact of full ecological smart homes on the cognitive load of the elderly. It provides a theoretical basis for the development of digital inclusion enhancement strategies.
{"title":"A study on the impact of full eco-smart home on the cognitive load and perceptual needs of elderly users","authors":"Jinsong Huang, Hecheng Hou, Xiaoying Li, Ziyi Zhang, Qi Jia","doi":"10.3233/jifs-237212","DOIUrl":"https://doi.org/10.3233/jifs-237212","url":null,"abstract":"In the context of the digital era, the factors influencing the cognitive load of the full ecological smart home on the elderly are mostly interconnected. Most existing studies have conducted single correlation analyses, ignoring the fact that cognitive load is the result among multiple interactions of multiple factors. Furthermore, the color, material and Finishing of the product design can also impact on the user’s perceptual needs. Therefore, exploring the grouping dynamics of cognitive load and users’ perceptual needs for color (C), material (M), and Finishing (F) of smart products can provide insights for inclusive design of smart homes. The article analyzes the asymmetric multiple concurrent causal effects of full ecological smart homes on the cognitive load of the elderly from a histological perspective using fuzzy set Qualitative Comparative Analysis (fsQCA) based on the four elements of Innovation Diffusion Theory. At the same time, principal component analysis and quantitative theory I class method are used to explore the quantitative relationship between color, material, Finishing and users’ perceptual imagery of the product. The results of the study showed that there were no necessary conditions leading to high or low cognitive load in the fsQCA analysis, indicating that the problem was the result of the interaction of multiple conditions, and the final analysis yielded three histological pathways leading to low cognitive load and one pathway leading to high load in older adults. Moreover, the study identifies the combination of colors, materials, and finishes that best represent user preferences. This study establishes a dialogue between theory, results, and cases in analyzing of the group dynamics of the impact of full ecological smart homes on the cognitive load of the elderly. It provides a theoretical basis for the development of digital inclusion enhancement strategies.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140212405","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}
Zhiwei Lin, Songchuan Zhang, Yiwei Zhou, Haoyu Wang, Shilei Wang
Current mainstream deep learning optimization algorithms can be classified into two categories: non-adaptive optimization algorithms, such as Stochastic Gradient Descent with Momentum (SGDM), and adaptive optimization algorithms, like Adaptive Moment Estimation with Weight Decay (AdamW). Adaptive optimization algorithms for many deep neural network models typically enable faster initial training, whereas non-adaptive optimization algorithms often yield better final convergence. Our proposed Adaptive Learning Rate Burst (Adaburst) algorithm seeks to combine the strengths of both categories. The update mechanism of Adaburst incorporates elements from AdamW and SGDM, ensuring a seamless transition between the two. Adaburst modifies the learning rate of the SGDM algorithm based on a cosine learning rate schedule, particularly when the algorithm encounters an update bottleneck, which is called learning rate burst. This approach helps the model to escape current local optima more effectively. The results of the Adaburst experiment underscore its enhanced performance in image classification and generation tasks when compared with alternative approaches, characterized by expedited convergence and elevated accuracy. Notably, on the MNIST, CIFAR-10, and CIFAR-100 datasets, Adaburst attained accuracies that matched or exceeded those achieved by SGDM. Furthermore, in training diffusion models on the DeepFashion dataset, Adaburst achieved convergence in fewer epochs than a meticulously calibrated AdamW optimizer while avoiding abrupt blurring or other training instabilities. Adaburst augmented the final training set accuracy on the MNIST, CIFAR-10, and CIFAR-100 datasets by 0.02%, 0.41%, and 4.18%, respectively. In addition, the generative model trained on the DeepFashion dataset demonstrated a 4.62-point improvement in the Frechet Inception Distance (FID) score, a metric for assessing generative model quality. Consequently, this evidence suggests that Adaburst introduces an innovative optimization algorithm that simultaneously updates AdamW and SGDM and incorporates a learning rate burst mechanism. This mechanism significantly enhances deep neural networks’ training speed and convergence accuracy.
{"title":"Learning rate burst for superior SGDM and AdamW integration","authors":"Zhiwei Lin, Songchuan Zhang, Yiwei Zhou, Haoyu Wang, Shilei Wang","doi":"10.3233/jifs-239157","DOIUrl":"https://doi.org/10.3233/jifs-239157","url":null,"abstract":"Current mainstream deep learning optimization algorithms can be classified into two categories: non-adaptive optimization algorithms, such as Stochastic Gradient Descent with Momentum (SGDM), and adaptive optimization algorithms, like Adaptive Moment Estimation with Weight Decay (AdamW). Adaptive optimization algorithms for many deep neural network models typically enable faster initial training, whereas non-adaptive optimization algorithms often yield better final convergence. Our proposed Adaptive Learning Rate Burst (Adaburst) algorithm seeks to combine the strengths of both categories. The update mechanism of Adaburst incorporates elements from AdamW and SGDM, ensuring a seamless transition between the two. Adaburst modifies the learning rate of the SGDM algorithm based on a cosine learning rate schedule, particularly when the algorithm encounters an update bottleneck, which is called learning rate burst. This approach helps the model to escape current local optima more effectively. The results of the Adaburst experiment underscore its enhanced performance in image classification and generation tasks when compared with alternative approaches, characterized by expedited convergence and elevated accuracy. Notably, on the MNIST, CIFAR-10, and CIFAR-100 datasets, Adaburst attained accuracies that matched or exceeded those achieved by SGDM. Furthermore, in training diffusion models on the DeepFashion dataset, Adaburst achieved convergence in fewer epochs than a meticulously calibrated AdamW optimizer while avoiding abrupt blurring or other training instabilities. Adaburst augmented the final training set accuracy on the MNIST, CIFAR-10, and CIFAR-100 datasets by 0.02%, 0.41%, and 4.18%, respectively. In addition, the generative model trained on the DeepFashion dataset demonstrated a 4.62-point improvement in the Frechet Inception Distance (FID) score, a metric for assessing generative model quality. Consequently, this evidence suggests that Adaburst introduces an innovative optimization algorithm that simultaneously updates AdamW and SGDM and incorporates a learning rate burst mechanism. This mechanism significantly enhances deep neural networks’ training speed and convergence accuracy.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140212067","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}
To solve the problem of lack of practice in Japanese teaching, a design of a Japanese remote interactive practical teaching platform based on the modern edge computing-based wireless sensor network is proposed. In terms of hardware, it mainly refits interactive mobile edge computing, wireless sensor networks, microprocessors, and other equipment, and adjusts the interface circuit. The Japanese teaching data and relevant Japanese teaching resources generated in the process of Japanese Teaching of practical courses are stored in the corresponding database table according to a certain format, and the logical relationship between database tables is used to update the database. The software function of the platform is designed with the support of a database and hardware equipment. It consists of multiple modules, including platform user roles, interactive practical teaching and management, practical resource management and distribution, practice project information release, practice investigation statistics, and platform operation safety. Through the above design, the operation of a Japanese remote interactive practical teaching platform is realized. The test results show that there is no significant difference in the function realization of the design platform, but when multiple users are online at the same time, the interaction performance of the design platform is stronger, that is, the operation performance of the platform has obvious advantages.
{"title":"Next generation mobile edge computing wireless sensor network based Japanese remote interactive practical teaching platform","authors":"HongJu Yan","doi":"10.3233/jifs-238196","DOIUrl":"https://doi.org/10.3233/jifs-238196","url":null,"abstract":"To solve the problem of lack of practice in Japanese teaching, a design of a Japanese remote interactive practical teaching platform based on the modern edge computing-based wireless sensor network is proposed. In terms of hardware, it mainly refits interactive mobile edge computing, wireless sensor networks, microprocessors, and other equipment, and adjusts the interface circuit. The Japanese teaching data and relevant Japanese teaching resources generated in the process of Japanese Teaching of practical courses are stored in the corresponding database table according to a certain format, and the logical relationship between database tables is used to update the database. The software function of the platform is designed with the support of a database and hardware equipment. It consists of multiple modules, including platform user roles, interactive practical teaching and management, practical resource management and distribution, practice project information release, practice investigation statistics, and platform operation safety. Through the above design, the operation of a Japanese remote interactive practical teaching platform is realized. The test results show that there is no significant difference in the function realization of the design platform, but when multiple users are online at the same time, the interaction performance of the design platform is stronger, that is, the operation performance of the platform has obvious advantages.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140216292","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}
Legal judgment prediction(LJP) has achieved remarkable results. However, existing methods still face problems such as difficulties in obtaining key feature words for charges, which impose limitations on the improvement of prediction results. To this end, we propose a legal judgment prediction model with legal feature Word subgraph Label-Embedding and Dual-knowledge Distillation(WLEDD). Compared with traditional methods, our method has two contributions: (1) To mitigate the impact of overly sparse tail class data and high similarity text representations, we capture the critical features related to the charges by fusing LDA and legal feature word subgraphs. Then we encode them as label information to obtain highly distinguished representations of legal documents. (2) To solve the problem of high difficulty in some subtasks in LJP, we perform subtask-oriented compression of models to construct a student model with lower complexity and higher accuracy through dual knowledge distillation. Moreover, we exploit the logical association between the subtasks to constrain the labels of articles by charge prediction results. It greatly reduces the difficulty of article prediction. Experimental results on four datasets show that our approach significantly outperforms the baseline models. Compared with the state-of-art method, the F1 value of WLEDD for charge prediction has increased by an average of 2.57% . For article prediction, the F1 value has increased by an average of 1.09% . In addition, we demonstrate its effectiveness through ablation experiments and analytical experiments.
{"title":"WLEDD: Legal judgment prediction with legal feature word subgraph label-embedding and dual-knowledge distillation","authors":"Xiao Wei, Yidian Lin","doi":"10.3233/jifs-237323","DOIUrl":"https://doi.org/10.3233/jifs-237323","url":null,"abstract":"Legal judgment prediction(LJP) has achieved remarkable results. However, existing methods still face problems such as difficulties in obtaining key feature words for charges, which impose limitations on the improvement of prediction results. To this end, we propose a legal judgment prediction model with legal feature Word subgraph Label-Embedding and Dual-knowledge Distillation(WLEDD). Compared with traditional methods, our method has two contributions: (1) To mitigate the impact of overly sparse tail class data and high similarity text representations, we capture the critical features related to the charges by fusing LDA and legal feature word subgraphs. Then we encode them as label information to obtain highly distinguished representations of legal documents. (2) To solve the problem of high difficulty in some subtasks in LJP, we perform subtask-oriented compression of models to construct a student model with lower complexity and higher accuracy through dual knowledge distillation. Moreover, we exploit the logical association between the subtasks to constrain the labels of articles by charge prediction results. It greatly reduces the difficulty of article prediction. Experimental results on four datasets show that our approach significantly outperforms the baseline models. Compared with the state-of-art method, the F1 value of WLEDD for charge prediction has increased by an average of 2.57% . For article prediction, the F1 value has increased by an average of 1.09% . In addition, we demonstrate its effectiveness through ablation experiments and analytical experiments.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140218545","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}
Shahnaz N. Shahbazova, Ab.G. Rzayev, R. Asadova, K.M. Jabiyev
The paper gives a systems analysis in the field of heat transfer and temperature distribution (TD) along the length of oil production wells (OPW). The analysis shows that the existing mathematical models are suitable only for determining TD along the length of casing string (CS) and are not suitable for determining TD along the length of the tubing run, since the existence of the interfacial (between the CS and the tubing) annulus of the fluid and gas layers with heat capacity and thermal conductivity that differ significantly from the heat capacity and thermal conductivity of rocks surrounding the CS. Given the above, mathematical models taking into account the impact of the fluid and gas layers in the annulus on the heat transfer from the upward fluid flow to the tubing wall and from the wall to the interfacial annulus are developed. To ensure the technological effectiveness of the obtained model, formulas for quantitative estimation of the heat transfer of the fluid flow into the surrounding environment are given.
{"title":"A mathematical model of temperature distribution along the length of the oil production well","authors":"Shahnaz N. Shahbazova, Ab.G. Rzayev, R. Asadova, K.M. Jabiyev","doi":"10.3233/jifs-219366","DOIUrl":"https://doi.org/10.3233/jifs-219366","url":null,"abstract":"The paper gives a systems analysis in the field of heat transfer and temperature distribution (TD) along the length of oil production wells (OPW). The analysis shows that the existing mathematical models are suitable only for determining TD along the length of casing string (CS) and are not suitable for determining TD along the length of the tubing run, since the existence of the interfacial (between the CS and the tubing) annulus of the fluid and gas layers with heat capacity and thermal conductivity that differ significantly from the heat capacity and thermal conductivity of rocks surrounding the CS. Given the above, mathematical models taking into account the impact of the fluid and gas layers in the annulus on the heat transfer from the upward fluid flow to the tubing wall and from the wall to the interfacial annulus are developed. To ensure the technological effectiveness of the obtained model, formulas for quantitative estimation of the heat transfer of the fluid flow into the surrounding environment are given.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140211561","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 paper focuses on how to improve the prediction accuracy of time series and the interpretability of prediction results. First, a novel Prophet model based on Gaussian linear fuzzy approximate representation (GF-Prophet) is proposed for long-term prediction, which uniformly predicts the data with consistent trend characteristics. By taking Gaussian linear fuzzy information granules as inputs and outputs, GF-Prophet predicts with significantly smaller cumulative error. Second, noticing that trend extraction affects prediction accuracy seriously, a novel granulation modification algorithm is proposed to merge adjacent information granules that do not have significant differences. This is the first attempt to establish Prophet based on fuzzy information granules to predict trend characteristics. Experiments on public datasets show that the introduction of Gaussian linear fuzzy information granules significantly improves prediction performance of traditional Prophet model. Compared with other classical models, GF-Prophet has not only higher prediction accuracy, but also better interpretability, which can clearly give the change information, fluctuation amplitude and duration of a certain trend in the future that investors actually pay attention to.
{"title":"A novel Prophet model based on Gaussian linear fuzzy information granule for long-term time series prediction1","authors":"Hong Yang, Lina Wang","doi":"10.3233/jifs-230313","DOIUrl":"https://doi.org/10.3233/jifs-230313","url":null,"abstract":"The paper focuses on how to improve the prediction accuracy of time series and the interpretability of prediction results. First, a novel Prophet model based on Gaussian linear fuzzy approximate representation (GF-Prophet) is proposed for long-term prediction, which uniformly predicts the data with consistent trend characteristics. By taking Gaussian linear fuzzy information granules as inputs and outputs, GF-Prophet predicts with significantly smaller cumulative error. Second, noticing that trend extraction affects prediction accuracy seriously, a novel granulation modification algorithm is proposed to merge adjacent information granules that do not have significant differences. This is the first attempt to establish Prophet based on fuzzy information granules to predict trend characteristics. Experiments on public datasets show that the introduction of Gaussian linear fuzzy information granules significantly improves prediction performance of traditional Prophet model. Compared with other classical models, GF-Prophet has not only higher prediction accuracy, but also better interpretability, which can clearly give the change information, fluctuation amplitude and duration of a certain trend in the future that investors actually pay attention to.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140211536","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：