检索结果-内蒙古大学图书馆

Parallel Seeds:From Foundation Models to Foundation Intelligence for Agricultural Sustainability

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 481-484页

作者： Laiyi Fu Shunkang Ling Danyang Wu Mengzhen Kang Fei-Yue Wang Hequan Sun the Shool of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University the College of Information Engineering Northwest A&F University IEEE the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences

THE development of agriculture faces significant challenges due to population growth, climate change, land depletion, and environmental pollution, threatening global food security [1]. This necessitates the development of sustainable agriculture, where a fundamental step is crop breeding to improve agronomic or economic traits, e.g., increasing yields of crops while decreasing resource usage and minimizing pollution to the environment [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting the Future: Using AdaBoost to Forecast Food Commodity Prices Across Indonesian Markets

Predicting the Future: Using AdaBoost to Forecast Food Commo...

引用

2025 International Conference on Advancement in Data Science, E-learning and information System, ICADEIS 2025

作者： Haerani, Erna Aulia, Selmi Dina Darmawan, Irfan Rahmatulloh, Alam Rizal, Randi Gunawan, Rohmat Siliwangi University Faculty of Engineering Department of Information Systems Tasikmalaya Indonesia Siliwangi University Faculty of Engineering Tasikmalaya Indonesia Telkom University Faculty of Industrial Engineering Department of Information Systems Bandung Indonesia

ISBN: (纸本)9798331513320

Rice prices play a crucial role in Indonesia's food security, making accurate predictions essential for effective decision-making in price stabilization and policy planning. This study aims to predict rice prices in various markets across Indonesia by applying the Adaptive Boosting (AdaBoost) algorithm. Eight modeling schemes were explored using a combination of AdaBoost and Decision Tree Regression, with coefficient of determination (R-pag 1-1) and Mean Absolute Percentage Error (MAPE) as evaluation metrics. The dataset, comprising 35,107 data points, was obtained from the Strategic Food Price information Center (PIHPS) and covers the period from May 2023 to April 2024. The results indicate that Scheme 5, utilizing a 90:10 data split scenario, achieved the best performance with an R2 value of 99.72% and a MAPE of 0.14%. This significantly outperforms previous research employing the Gradient Boosted Trees Regression algorithm, which achieved an R2 of 90.47% and a MAPE of 12.41%. These findings demonstrate the superiority of the AdaBoost algorithm in modeling food commodity prices, particularly in forecasting rice prices in Indonesia. This study contributes to the advancement of more accurate price prediction methods, which can be leveraged by policymakers, market stakeholders, and the agricultural sector to support price stabilization and food security management in Indonesia. © 2025 IEEE.

关键词： AdaBoost food commodity modelling schemes PIHPS price prediction

来源：评论

学校读者我要写书评

暂无评论

Classification of human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the spotted hyena algorithm

引用

Alexandria engineering Journal 2025年 126卷 116-130页

作者： Ragab, Mahmoud Ashary, Ehab Bahaudien Kateb, Faris Hakeem, Abeer Mosli, Rayan Albogami, Nasser N. Nooh, Sameer Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Electrical and Computer Engineering Department Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

The rapid advancement of artificial intelligence (AI) in generating human-like text poses significant challenges in distinguishing between human-written and AI-generated content. Recent advancements in natural language generation have significantly enhanced the quality and variety of AI-generated text, making it almost indistinguishable from human-written content. ChatGPT, a popular AI model, belongs to the generative pre-trained transformer family. While human content is created with a clear intent to convey meaning, AI-generated text aims to replicate human-like language. Classifying human-written and AI-generated sentences is crucial for addressing issues like fake news, plagiarism, and spamming. AI text often follows repetitive patterns, while human writing is more creative and original, making detection significant for combating misinformation. Therefore, this study proposes to classify human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the Spotted Hyena Algorithm (CHWAIG-DLSHO) approach. The approach involves preprocessing text data through tokenization, lemmatization, and data splitting, followed by word embedding using Latent Dirichlet Allocation (LDA). A hybrid convolutional neural network (CNN) and gated recurrent unit (GRU) model is employed for sentence classification. The spotted hyena optimizer (SHO) model is utilized to fine-tune the hyperparameters of the CNN-GRU model, enhancing its performance. The analysis of the CHWAIG-DLSHO method takes place utilizing AI vs. human text dataset. The performance validation of the CHWAIG-DLSHO method portrayed a superior accuracy value of 99.17 % over existing techniques. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hands-On Gaming: Real-Time Gesture Detection in Rock-Paper-Scissors Using Mediapipe and CNN

Hands-On Gaming: Real-Time Gesture Detection in Rock-Paper-S...

引用

2025 International Conference on Advancement in Data Science, E-learning and information System, ICADEIS 2025

作者： Darmawan, Irfan Meldiawati, Aulia Melda Rizal, Randi Rahmatulloh, Alam Haerani, Erna Gunawan, Rohmat Telkom University Department of Information Systems Faculty of Industrial Engineering Bandung Indonesia Siliwangi University Faculty of Engineering Departement of Informatics Tasikmalaya Indonesia Siliwangi University Faculty of Engineering Department of Information Systems Tasikmalaya Indonesia

ISBN: (纸本)9798331513320

Real-time hand gesture detection enables intuitive non-verbal communication between humans and devices. In gaming, using hand gestures as a control mechanism enhances user engagement and provides a more immersive experience. This research implements a real-time hand gesture detection system for the Rock-Paper-Scissors game by combining Mediapipe for feature extraction and a Convolutional Neural Network (CNN) for gesture classification. Mediapipe detects and extracts key hand landmarks in real-time, while the CNN classifies the gestures into three categories: rock, paper, and scissors. The proposed system demonstrates high performance, achieving an impressive classification accuracy of 98.12% after 500 training epochs. Furthermore, it ensures adequate detection speed for seamless real-time interaction in gameplay. Future improvements to this system include utilizing a larger and more diverse dataset to enhance the model's ability to recognize a broader range of hand gesture patterns. This approach could improve robustness across different lighting conditions, hand sizes, and variations in gesture execution. Additionally, refining the CNN model architecture could lead to further performance gains in both accuracy and speed. The findings of this research highlight the potential for hand gesture detection to enhance interactivity in gaming and beyond. Applications such as augmented reality (AR), virtual reality (VR), and other interactive systems could benefit from this technology. This study demonstrates that integrating Mediapipe and CNNs can provide an accurate, responsive, and engaging user experience, paving the way for further advancements in gesture-based interaction technologies. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance *** Comparative Analysis of Multimodal Bilinear Pooling Fusion Approaches for Deep Learning-Based Visual Arabic-Question Answering systems

引用

Computer Modeling in engineering & Sciences 2025年第4期143卷 373-411页

作者： Sarah M.Kamel Mai A.Fadel Lamiaa Elrefaei Shimaa I.Hassan Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer and Systems Engineering Faculty of Engineering and TechnologyBadr University in Cairo(BUC)Cairo11829Egypt Communication Systems Engineering Department Faculty of EngineeringBenha National UniversityObour11846QalyubiaEgypt

Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate *** this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in *** support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the *** the model complexity and the overall model *** fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA *** far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no ***,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA *** indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that *** the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model *** Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.

关键词： Arabic-VQA deep learning-based VQA deep multimodal information fusion multimodal representation learning VQA of yes/no questions VQA model complexity VQA model performance performance-complexity trade-off

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection in surveillance videos through LSTM auto-encoding and local minima assistance

引用

Discover Internet of Things 2025年第1期5卷 1-25页

作者： Sengonul, Erkan Samet, Refik Abu Al-Haija, Qasem Alqahtani, Ali Alsemmeari, Rayan A. Alghamdi, Bandar Alturki, Badraddin Alsulami, Abdulaziz A. Department of Computer Engineering Ankara University Ankara06100 Turkey Department of Cybersecurity Faculty of Computer & Information Technology Jordan University of Science and Technology PO Box 3030 Irbid22110 Jordan Department of Networks & Communications Engineering College of Computer Science & Information Systems Najran University Najran61441 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Abnormal event detection in video surveillance is critical for security, traffic management, and industrial monitoring applications. This paper introduces an innovative methodology for anomaly detection in video data, encompassing three primary stages: preprocessing, feature learning, and anomaly detection. We employ background subtraction and noise reduction during preprocessing to refine the data. The feature-learning stage involves training an LSTM autoencoder to capture the essential features of normal video sequences. For anomaly detection, we map video data to a lower-dimensional space (latent code) and compare it against the distribution of codes from normal sequences. We determine regularity scores and identify local minima points exceeding a specified threshold while scrutinizing shadows between adjacent maxima to confirm and pinpoint anomalies. When tested on the CUHK Avenue and UMN datasets, our methodology demonstrated performance with AUCs of 93.8% and 94.1%, respectively, outperforming several baseline models. Our results show the high precision of our method that can detect anomalies, highlighting its potential advantages that it can achieve for enhancing systems of surveillance. © The Author(s) 2025.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Truth: Detecting Fake News Using SVM and TF-IDF

Unveiling the Truth: Detecting Fake News Using SVM and TF-ID...

引用

2025 International Conference on Advancement in Data Science, E-learning and information System, ICADEIS 2025

作者： Rizal, Randi Faturahman, Ade Impron, Ali Darmawan, Irfan Haerani, Erna Rahmatulloh, Alam Faculty of Engineering Siliwangi University Department of Informatics Tasikmalaya Indonesia Universitas Muhammadiyah Sampit Faculty of Engineering and Agriculture Departement of Informatics Central Kalimantan Indonesia Telkom University Faculty of Industrial Engineering Department of Information Systems Bandung Indonesia Faculty of Engineering Siliwangi University Department of Information Systems Tasikmalaya Indonesia

ISBN: (纸本)9798331513320

The spread of fake news on social media platforms such as Facebook, Instagram, and X has become a significant issue in the digital era due to its negative societal and informational impacts. The rapid dissemination of unverified information often leads to misinformation and confusion, highlighting the critical need for reliable detection methods. This study aims to classify and detect fake news by optimizing the Support Vector Machine (SVM) machine learning algorithm using the Term Frequency-Inverse Document Frequency (TFIDF) technique. Two publicly available Kaggle datasets, containing labeled fake and real news, were utilized as the foundation for this research. The research results demonstrate that the SVM algorithm, when optimized with TF-IDF, achieved the highest accuracy of 99.6% compared to other commonly used machine learning algorithms such as Random Forest and Logistic Regression. This highlights the effectiveness of TF-IDF in improving the feature extraction process, enabling the model to better differentiate between fake and real news. These findings underscore the potential of SVM as a reliable tool for combating misinformation. To further enhance fake news detection, future research should explore the use of more comprehensive, multilingual, and complex datasets to better reflect real-world scenarios. Additionally, employing transformer-based approaches, such as BERT, GPT, or similar models, could provide a deeper understanding of linguistic context and semantic relationships, ultimately improving the robustness and accuracy of fake news detection systems. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Supervisory Control of Discrete Event systems Modeled With Labeled Petri Nets for Diagnosability Enforcement

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 13855-13870页

作者： Li, Chengzong Chen, Yufeng Mostafa, Almetwally M. Khalgui, Mohamed Qinghai University School of Energy and Electrical Engineering Xining810000 China Macau University of Science and Technology Institute of Systems Engineering Taipa China King Saud University College of Computer and Information Sciences Department of Information Systems Riyadh11543 Saudi Arabia German International University Faculty of Engineering Berlin13507 Germany

This paper proposes an active fault diagnosis method to enforce the diagnosability of discrete event systems using labeled Petri nets by constructing a diagnostic supervisor. For a non-diagnosable net model, its diagnosability is viewed as a control specification and addressed by using supervisory control techniques. First, an event-based monitor and a Petri net structure, referred to as data isolation arcs, are introduced to apply control specifications for labeled Petri nets. Then, a diagnostic supervisor reachability graph is generated to estimate the current state of the diagnoser. By analyzing the diagnostic supervisor reachability graph, an integer linear programming model is formulated to design a diagnostic supervisor, which can prevent the system from entering into any indeterminate cycle only by observing the occurrence of events. Finally, by the obtained diagnostic supervisor, the resulting net model is shown to be diagnosable. Some examples are presented to demonstrate the proposed method. © 2004-2012 IEEE.

关键词： Supervisory personnel

来源：评论

学校读者我要写书评

暂无评论

Experiments on Taking Loss Methods in Imitation Learning With Bilateral Control

Experiments on Taking Loss Methods in Imitation Learning Wit...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Tagashira, Yusuke Okamura, Kazuya Akagawa, Tetsuro Sakaino, Sho National Institute of Technology Hachinohe College Electrical and Information Engineering Course Aomori Japan University of Tsukuba Faculty of Engineering Information and Systems Tsukuba Japan

ISBN: (纸本)9798331533892

Recently, motion generation technology using deep learning has been attracting attention as a method for robots to acquire motions adapted to their environment. The combination of imitation learning and bilateral control enables imitation of movements at speeds comparable to those of humans. Previous studies have investigated learning that inputs external information, such as one-hot vectors or image features, but learning to choose actions based on dynamic external information is still being studied. If a camera is used to collect external information, high-level image processing is required, resulting in heavy processing. We thought that the robot's motion generation could cover the problem without high-level image processing. Therefore, this paper examines the task of grasping an object that moves autonomously, independent of the robot, using low-resolution images. We first tried a model that takes loss based on the transformation of angle information into arm hand coordinates, whereas the previous learning model takes loss based on angle information. The results showed that, in imitation learning based on bilateral control, using hand coordinate loss caused a bias in learning the joint angle responses. It also became clear that it is important to learn the joint angle responses with equal weights. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Robotic artistic writing — reproduction of signs drawn on the surface of plastically deformable materials

引用

IEEE Sensors Journal 2025年第10期25卷 18090-18105页

作者： He, Xin Zielinska, Teresa Matsumaru, Takafumi Dutta, Vibekananda Waseda University Graduate School of Information Production and Systems Fukuoka Kitakyushu Japan Warsaw University of Technology Faculty of Power and Aeronautical Engineering Warsaw Poland Warsaw University of Technology Faculty of Mechatronics Warsaw Poland

Existing surface shaping methods focus on hard materials with stable physical properties. This means that the approaches developed are insufficient for shaping soft materials. The article describes a cheap method of reproducing plastic deformations using a robotic manipulator. The shape recording and reproduction system consists of two RGB-D cameras, two containers with kinetic sand, and a manipulator with 6 degrees of freedom. Volunteers create templates by drawing on the surface of kinetic sand with a wooden stylus or finger. Some pressure is exerted while writing. The resulting shapes recorded by the RGB-D camera have the form of ribbon ditches (grooves). The obtained point cloud is processed to create a sand deformation model. In the first stage, a dedicated local smoothing technique is used. Then, special algorithms are implemented to create a description of the main curvatures and key dimensions of recorded signs. A spline-based approach is used. The method allows for the representation of various shapes in a unified form. In the final stage, modulated sinusoidal functions define the robot’s trajectory. The effects of the robot’s operation are recorded to assess the reproduction quality. The Point Cloud Structural Similarity Measure (PointSSIM) evaluates the results. Experimental research takes into account many different shapes. Copies of shapes created by humans and robots are compared with the originals. The outcomes show that the quality of reproduction achieved by humans and robots is comparable. The median-based curvature similarity measure obtained for the human was only 1.92% higher than the robot’s result, and the covariance-based geometric similarity measure was only 0.74% higher than the robot’s score. The system can be used to mass-produce souvenirs or special implants. © 2001-2012 IEEE.

关键词： Wooden containers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：