检索结果-内蒙古大学图书馆

World Symposium on Digital Intelligence for Systems and Machines (DISA)

作者： Renát Haluška Michal Popovič Matus Pleva Matthew Frohman Department of Electronics and Multimedia Communications Faculty of Electrical Engineering and Informatics Technical University Kosice Kosice Slovakia Department of computer science Perception and Robotics Group University of Maryland College Park MD United States

The main goal of this paper was to find out how the gender and age group acoustical models behave on audio data that is in no way related to the data corpora used to train and evaluate the models. These models could be used for early predator detection in minors’ audio chats. The datasets used for training were mainly composed of English speakers. One part was made up of speakers whose native language is English and the rest use English as a secondary language.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Descriptive Exam Evaluation through Semantic Mining and Analysis

Descriptive Exam Evaluation through Semantic Mining and Anal...

引用

Human-Centered Cognitive Systems (HCCS)

作者： Raybal Akhtar Muhammad Safyan Muddesar Iqbal Sohail Sarwar Department of Informatics and Systems University of Management and Technology Lahore Pakistan Department of Computer Science Government College University Lahore Lahore Pakistan Department of Communication & Network Engineering Prince Sultan University Riyadh Saudi Arabia Department of Computer Science Bahria University Islamabad Islamabad Pakistan

Online examination evaluation methods are used as an alternative to the traditional examination’s way of evaluation methods. They offer a number of advantages while addressing issues associated with outdated conventional approaches. Online evaluation methods are mainly used for objective and short answers based exams but may not suitable for assessing the depth knowledge in candidates. So, candidate’s descriptive examinations are conducted to assess their depth of knowledge. Descriptive evaluation methods have been put into practice for quite some time but they greatly rely on keyword-matching techniques between the questions and answers. Due to this limitation, the semantic meanings of these answers are ignored. In current research, the deficiencies in prevalent systems have been addressed by calculating the semantic and syntactic similarity between answers. Moreover, the repetitive words and similarity between counteractive answers has also been considered. We have used SQuAD 1 dataset in current research. Our model has achieved a value of 0.88 in terms of accuracy for while computing similarity among listed items.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients

arXiv

引用

arXiv 2025年

作者： Leng, Jiaqi Ju, Yakun Duan, Yuanxu Zhang, Jiangnan Lv, Qingxuan Wu, Zuxuan Fan, Hao Haide College Ocean University of China China Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China School of Computing and Mathematic Sciences University of Leicester United Kingdom Department of Computer Engineering Qingdao City University China College of Computer Science and Technology Ocean University of China China

Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy and handling high-resolution inputs, particularly facing the complex nature of discontinuities and the inefficiencies associated with large-scale linear solvers. Although recent advances in deep learning, such as photometric stereo, have enhanced normal estimation accuracy, they do not fully address the intricacies of gradient-based surface reconstruction. To overcome these limitations, we propose a Fourier neural operator-based Numerical Integration Network (FNIN) within a two-stage optimization framework. In the first stage, our approach employs an iterative architecture for numerical integration, harnessing an advanced Fourier neural operator to approximate the solution operator in Fourier space. Additionally, a self-learning attention mechanism is incorporated to effectively detect and handle discontinuities. In the second stage, we refine the surface reconstruction by formulating a weighted least squares problem, addressing the identified discontinuities rationally. Extensive experiments demonstrate that our method achieves significant improvements in both accuracy and efficiency compared to current state-of-the-art solvers. This is particularly evident in handling high-resolution images with complex data, achieving errors of fewer than 0.1 mm on tested objects. Copyright © 2025, The Authors. All rights reserved.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Agriculture through Cyber Physical Systems: The Role of Robotics in Smart Farming

Revolutionizing Agriculture through Cyber Physical Systems: ...

引用

Electrical Electronics and computing Technologies (ICEECT), International Conference on

作者： T. Chithrakumar Sandeep Kumar Mathivanan M. Thangamani Rajasekhara Babu L Balamurugan Balusamy Shilpa Gite Nilkanth Deshpande Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh India School of Computing Science and Engineering Galgotias Greater Noida India Department of Computer Science and Engineering Muthayammal Engineering College Namakkal TamilNadu India Delhi-National Capital Region (NCR) Shiv Nadar University India Department of AIML Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Department of AIML Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Increased production in agriculture is anticipated with localized management that is founded on several analyses of the crops and soil. The following issues arise with this method: it takes a long time because there are a lot of measurement locations, different sensors are needed for different measures and the sun and wind might cause inaccurate data to be produced. Our proposed method benefits from multiple measurements made possible by swappable sensor units, constant measurements made possible by shielding the crop from wind and sunlight, and precise measurements made possible by a robot. The system experimented to track the crops and soil in a cabbage field simultaneously as a pilot test for the device. With a battery life of more than 4 hours, the robot could be mobile in the field and scan crops in 100 different areas. It could also detect electrical conductivity in the soil. Whether the sensor unit’s measuring circumstances remained steady during the trial was also assessed. The illumination became 280 times more constant (standard deviation = 0.4 lx) compared to the uncovered condition, and wind-induced crop shaking reduced by 20 times (root mean square inaccuracy of the image pixels = 0.5%). High repeatability owing to the shared sensor unit and the anticipation of fresh encounters through the use of accurate internal sensors are some possible repercussions of this.

关键词： Accuracy Soil measurements Crops Soil Robot sensing systems Sensor systems Battery charge measurement Sensors Robots Fertilizers

来源：评论

学校读者我要写书评

暂无评论

Inflammation Segmentation Module using Convolution Neural Network for Alzheimer's Disease Detection using Magnetic Resonance Imaging Inputs

Inflammation Segmentation Module using Convolution Neural Ne...

引用

International Conference on Science Technology engineering and Management (ICONSTEM)

作者： Sahana Shetty Ramesh S R Nithya P. Thangaraj Antony Vijay J Sangamithrai K Department of CSE-AIML and Cyber Security School of CSE FET - Jain Bangalore India Department of Computing Technologies College of Engineering & Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of CSE Bannari Amman Institute of Technology Erode Tamilnadu India Department of CSE Builders Engineering College Tirupur Dt Tamilnadu India Department of CSE Karpagam College of Engineering Coimbatore Tamilnadu India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Magnetic Resonance Imaging (MRI) inputs have been most commonly used in diagnosing Alzheimer's Disease (AD) in recent years. The patterns of brain functions are deliberately observed in the MRI inputs for efficient AD detection. This article introduces an Inflammation Segmentation Module (ISM) using a convolution neural network (CNN) to augment better AD detection. This segmentation module identifies the textural differences in inflammation regions through training input cross-correlation. The cross-correlation process is reliable in identifying similar and differential textural features to improve the detection accuracy. The CNN is trained using an external dataset and correlated outputs for high precision. This proposed module is reliable in detecting inflammation textures with high precision and less analysis time.

关键词： Training Image segmentation Accuracy Convolution Magnetic resonance imaging Feature extraction Reliability

来源：评论

学校读者我要写书评

暂无评论

Learning to Solve Tasks with Exploring Prior Behaviours

arXiv

引用

arXiv 2023年

作者： Zhu, Ruiqi Li, Siyuan Dai, Tianhong Zhang, Chongjie Celiktutan, Oya The Department of Engineering King’s College London United Kingdom The School of Computer Science and Technology Harbin Institute of Technology China The Department of Computing Science University of Aberdeen United Kingdom Tsinghua University China

Demonstrations are widely used in Deep Reinforcement Learning (DRL) for facilitating solving tasks with sparse rewards. However, the tasks in real-world scenarios can often have varied initial conditions from the demonstration, which would require additional prior behaviours. For example, consider we are given the demonstration for the task of picking up an object from an open drawer, but the drawer is closed in the training. Without acquiring the prior behaviours of opening the drawer, the robot is unlikely to solve the task. To address this, in this paper we propose an Intrinsic Rewards Driven Example-based Control (IRDEC). Our method can endow agents with the ability to explore and acquire the required prior behaviours and then connect to the task-specific behaviours in the demonstration to solve sparse-reward tasks without requiring additional demonstration of the prior behaviours. The performance of our method outperforms other baselines on three navigation tasks and one robotic manipulation task with sparse rewards. Codes are available at https://***/Ricky-Zhu/IRDEC. Copyright © 2023, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Optimised with Secure Approach in Detecting and Isolation of Malicious Nodes in MANET

引用

Wireless Personal Communications 2021年第1期119卷 21-35页

作者： Thiagarajan, R. Ganesan, R. Anbarasu, V. Baskar, M. Arthi, K. Ramkumar, J. Department of Computer Science and Engineering Prathyusha Engineering College Chennai India Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chengalpattu Chennai India

To keep the process of routing and data transmission operations, it’s needed for a proper layer of security to keep it safe from malicious attacks. So in this paper, we proposed a framework that helps in detecting the malicious nodes at each of the destinations. After the detection process, it is isolated and discarded in while path establishment through various techniques. The development of an algorithm that supports Multipath Reliable Routing helps in determining paths for a set of disjoint nodes. Based on the index of reliability the paths are reordered. Now the process of information in form of data are been dispersed from source to destination. The main primary path is set to transfer the information. The final destination in case of mismatch of information transferred from a source when received at destination then feedback is given in negative manner stating that there is a mismatch of data along with the information related to the transmission and its path. Hence due to this, the destination will be able to recover since the information is checked each time for reliability. The final results show that the proposed approach results and have a greater impact when compared to the existing methods. Further, it reduces delay in packet transmission and overhead parallel it increases the delivery of packets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAINER: A Robust Ensemble Learning Grid Search-Tuned Framework for Rainfall Patterns Prediction

arXiv

引用

arXiv 2025年

作者： Li, Zhenqi Zhong, Junhao Wang, Hewei Xu, Jinfeng Li, Yijie You, Jinjiang Zhang, Jiayi Wu, Runzhi Dev, Soumyabrata The Fu Foundation School of Engineering and Applied Science Columbia University United States Biomedical Engineering Department Pratt School of Engineering Duke University United States School of Computer Science University College Dublin Ireland Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Robotics Institute School of Computer Science Carnegie Mellon University United States Faculty of Science and Engineering University of Nottingham Ningbo China China College of Intelligence and Computing Tianjin University China The ADAPT SFI Research Centre

Rainfall prediction remains a persistent challenge due to the highly nonlinear and complex nature of meteorological data. Existing approaches lack systematic utilization of grid search for optimal hyperparameter tuning, relying instead on heuristic or manual selection, frequently resulting in sub-optimal results. Additionally, these methods rarely incorporate newly constructed meteorological features such as differences between temperature and humidity, to capture critical weather dynamics. Furthermore, there is a lack of systematic evaluation of ensemble learning techniques and limited exploration of diverse advanced models introduced in the past one or two years. To address these limitations, we propose a Robust ensemble LeArning grId search-tuNed framEwoRk (RAINER) for rainfall prediction. RAINER incorporates a comprehensive feature engineering pipeline, including outlier removal, imputation of missing values, feature reconstruction, and dimensionality reduction via Principal Component Analysis (PCA). The framework integrates novel meteorological features to capture dynamic weather patterns and systematically evaluates non-learning mathematical-based methods and a variety of machine learning models, from weak classifiers (e.g., KNN, LASSO, and Random Forest) to advanced neural networks such as Kolmogorov-Arnold Networks (KAN). By leveraging grid search for hyperparameter tuning and ensemble voting techniques, RAINER achieves state-of-the-art results within real-world dataset. Extensive experiments demonstrate the framework’s superior performance across diverse metrics, such as Accuracy, Precision, Recall, F1-score, and AUC, highlighting the pivotal role of feature engineering, grid search, and ensemble learning in rainfall prediction tasks. © 2025, CC BY.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Optimizing AIGC Services Using Learning-based Stackelberg Game in Vehicular Metaverses

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Lai, Bingkun Luo, Xiaofeng Kang, Jiawen Gao, Xiaozheng Yang, Zuyuan Niyato, Dusit Mao, Shiwen Guangdong University of Technology School of Automation Guangzhou510006 China Beijing Institute of Technology School of Information and Electronics Beijing10081 China Nanyang Technological University College of Computing and Data Science Singapore Auburn University Department of Electrical and Computer Engineering AuburnAL United States

The emerging vehicular metaverse embodies the next-generation vehicular networking paradigm. In the vehicular metaverses, Artificial Intelligence-Generated Content (AIGC) technology as a powerful content generation tool, is capable of providing an immersive experience for Vehicular Metaverse Users (VMUs). Due to limited computational resources within vehicles, VMUs rely on AIGC Service Providers (ASPs) to execute resource-intensive AIGC tasks within vehicular metaverses. However, large-scale AIGC service requests can lead to resource scarcity within the ASP, ultimately leading to declining service quality for VMUs. To tackle this challenge, we introduce a novel Stackelberg game framework utilizing the Generative Diffusion Model (GDM) for AIGC services, in which we experimentally reveal a relationship between image quality and diffusion steps. A Transformer-based Deep Reinforcement Learning (TDRL) algorithm is employed to find the optimal Stackelberg equilibrium under incomplete information. Numerical results indicate that our method converges to equilibrium efficiently, with superior utilities compared to baseline approaches. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MADP-IIME: malware attack detection protocol in IoT-enabled industrial multimedia environment using machine learning approach

MADP-IIME: malware attack detection protocol in IoT-enabled ...

引用

作者： Pundir, Sumit Obaidat, Mohammad S. Wazid, Mohammad Das, Ashok Kumar Singh, Devesh Pratap Rodrigues, Joel J. P. C. Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun 248 002 India College of Computing and Informatics University of Sharjah UAE with King Abdullah II School of Information Technology The University of Jordan Amman 11942 Jordan University of Science and Technology Beijing Beijing 100083 China Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad 500 032 India Federal University of Piauí (UFPI) PI Teresina 64049-550 Brazil Instituto de Telecomunicações Covilhã 6201-001 Portugal

Internet of Things (IoT) is one of the fastest-growing technologies. With the deployment of massive and faster mobile networks, almost every daily-use item is connected to the Internet. IoT-enabled industrial multimedia environment is used for the collection and analysis of different types of multimedia data (i.e., images, videos, audios, etc.). This multimedia data is generated by various types of smart devices like drones, robots, smart controller, smart surveillance system which are deployed for the industrial monitoring and control. The multimedia data is generated in the enormous amount which can be considered as the big data. This data is further utilized in various types of business needs for example, chances of fire accidents in the industrial plant, overall machine health, etc., which can be predicted through the application of big data analytics. Therefore, IoT-enabled industrial multimedia environment is very helpful to the concerned authorities as they come to know the important information in advance. However, all the smart devices are connected and controlled through the Internet. It further causes severe threats to the communication happens in an IoT-enabled industrial multimedia environment. It is vulnerable to various types of attacks such as replay, man-in-the-middle, impersonation, secret information leakage, sensitive information modification, and malware injection (i.e., mirai). Therefore, it is important to prevent the communication of such an environment against the different types of possible attacks. These days, the attacks performed by botnets (i.e., malware attacks such as mirai and reaper) have drawn attention to the researchers. Under the influence of such attacks, the communication of IoT-enabled industrial multimedia environment is disrupted. Moreover, the attackers may also control the smart devices remotely and can change their functionalities. Hence, we need some robust mechanism to detect the presence of the malware attacks in such

关键词： Internet of things

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：