Efficient Prediction of Judicial Case Decisions Based on State Space Modeling DOI Creative Commons
Yuntao Liu

International Journal of Computational Intelligence Systems, Год журнала: 2024, Номер 17(1)

Опубликована: Ноя. 12, 2024

With the rapid advancement of information technology and artificial intelligence, digitization legal texts has caused a swift increase in volume materials. Judges now face increased professional demands, larger loads, more complex case structures, which heightens their workload demands. To enhance quality efficiency judicial work drive modernization system, application intelligent prediction models become essential. This paper presents MambaEffNet model, integrates multiple modules such as Convolutional Neural Networks (CNN) Multilayer Perceptrons (MLP). The core convolutional structure is improved using state space multi-directional feature fusion designed to performance sequence extraction. Generative Adversarial (GAN) are employed for data augmentation, address issue missing features predictions. EfficientNetV2 architecture used optimize kernel size expansion ratio input output channels. Experimental results demonstrate that model achieves accuracy 92.05% on Nigerian Supreme Court judgment dataset performs excellently other datasets, significantly improving efficiency. Specifically, increases criminal civil judgments by 9.53% 11.57%, respectively. Additionally, excels handling long data, effectively capturing key providing comprehensive decision support.

Язык: Английский

Using machine learning techniques to identify major determinants of electricity usage in residential buildings of Pakistan DOI

Muhammad Sohaib Jarral,

Khuram Pervez Amber, Taqi Ahmad Cheema

и другие.

Journal of Building Engineering, Год журнала: 2025, Номер 100, С. 111800 - 111800

Опубликована: Янв. 7, 2025

Язык: Английский

Процитировано

1

Medical image enhancement using war strategy optimization algorithm DOI
Yusuf UZUN, Mehmet Berat Bilgin

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 106, С. 107740 - 107740

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

1

Off-grid multi-region energy system design based on energy load demand estimation using hybrid nature-inspired optimization algorithms DOI

Ali Alhamami,

Sani I. Abba,

Bashir Musa

и другие.

Energy Conversion and Management, Год журнала: 2024, Номер 315, С. 118766 - 118766

Опубликована: Июль 14, 2024

Язык: Английский

Процитировано

4

Optimized deep neural network architectures for energy consumption and PV production forecasting DOI

Eghbal Hosseini,

Barzan Saeedpour,

Mohsen Banaei

и другие.

Energy Strategy Reviews, Год журнала: 2025, Номер 59, С. 101704 - 101704

Опубликована: Апрель 8, 2025

Язык: Английский

Процитировано

0

War strategy optimization-based methods for pattern synthesis of antenna arrays and optimization of microstrip patch antenna DOI
Renjing Gao, Wei Tong, Mingyue Zhang

и другие.

Journal of Computational Electronics, Год журнала: 2024, Номер 23(5), С. 1125 - 1134

Опубликована: Авг. 8, 2024

Язык: Английский

Процитировано

1

A Novel Neuro-Probabilistic Framework for Energy Demand Forecasting in Electric Vehicle Integration DOI Creative Commons

Miguel Ángel Rojo-Yepes,

Carlos D. Zuluaga, Sergio D. Saldarriaga-Zuluaga

и другие.

World Electric Vehicle Journal, Год журнала: 2024, Номер 15(11), С. 493 - 493

Опубликована: Окт. 29, 2024

This paper presents a novel grid-to-vehicle modeling framework that leverages probabilistic methods and neural networks to accurately forecast electric vehicle (EV) charging demand overall energy consumption. The proposed methodology, tailored the specific context of Medellin, Colombia, provides valuable insights for optimizing infrastructure grid operations. Based on collected local data, mathematical models are developed coded reflect characteristics EV charging. Through rigorous analysis criteria, indices, relationships, most suitable model city is selected. By combining with networks, this study offers comprehensive approach predicting future as penetration increases. effectively captures behavior various types, while network forecasts demand. findings can inform decision-making regarding planning, investment strategies, policy development support sustainable integration vehicles into power grid.

Язык: Английский

Процитировано

1

VoltaVistaMan: Energy Dynamics Intelligent Predictive Analysis Utilizing Bayesian Hyper-Tuned Neural Networks – A Case Study on Switzerland's National Electricity Demand DOI
Ashkan Safari, Hamed Kharrati, Afshin Rahimi

и другие.

Опубликована: Июнь 17, 2024

Язык: Английский

Процитировано

0

Research on the innovation of “four-work synergy” service education system for social work majors in higher vocational colleges and universities under the background of Internet+ DOI Creative Commons

Yulong Wang,

Xiaolei Du

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract This paper puts forward an innovative approach to the service education system of higher vocational colleges and universities constructs a “four-work synergy” from four aspects: integration, construction, revitalization, innovation. Using war strategy optimization algorithm, is optimized adjusted. An artificial neural network-based quality assessment model for “four-industry was established, applied in practice measure research subjects. The students were satisfied with their impression school, value school services, importance work, all which above three points. six dimensions educational services object P high statistics, including highest mean score 3.6496 assurance, except tangible empathy, other similar, distribution range between 3.3-3.5. A pre-and post-test experiment designed examine effect on improvement students’ professional skills. During post-tests, it revealed that average skills increased by 6.0587 points, while overall passing rate 17.83%. Through independent sample t-test, further found t=-4.679, sig=0.000, there significant difference data, shows “four-worker cooperative” proposed this has positive effect.

Язык: Английский

Процитировано

0

Efficient Prediction of Judicial Case Decisions Based on State Space Modeling DOI Creative Commons
Yuntao Liu

International Journal of Computational Intelligence Systems, Год журнала: 2024, Номер 17(1)

Опубликована: Ноя. 12, 2024

With the rapid advancement of information technology and artificial intelligence, digitization legal texts has caused a swift increase in volume materials. Judges now face increased professional demands, larger loads, more complex case structures, which heightens their workload demands. To enhance quality efficiency judicial work drive modernization system, application intelligent prediction models become essential. This paper presents MambaEffNet model, integrates multiple modules such as Convolutional Neural Networks (CNN) Multilayer Perceptrons (MLP). The core convolutional structure is improved using state space multi-directional feature fusion designed to performance sequence extraction. Generative Adversarial (GAN) are employed for data augmentation, address issue missing features predictions. EfficientNetV2 architecture used optimize kernel size expansion ratio input output channels. Experimental results demonstrate that model achieves accuracy 92.05% on Nigerian Supreme Court judgment dataset performs excellently other datasets, significantly improving efficiency. Specifically, increases criminal civil judgments by 9.53% 11.57%, respectively. Additionally, excels handling long data, effectively capturing key providing comprehensive decision support.

Язык: Английский

Процитировано

0