检索结果-内蒙古大学图书馆

Enhancing multiple document summarisation with DNETCNN and BCHOA techniques

International Journal of Business Intelligence and Data Mining 2025年第3-4期26卷 257-281页

作者： Mandava, Mamatha Vinta, Surendra Reddy School of Computer Science and Engineering VIT-AP University Amaravathi India

Multi-document summarising (MDS) is a helpful method for information aggregation that creates a clear and informative summary from a collection of papers linked to the same subject. Due to the significant number of information available online, it might be challenging to extract the needed information from an internet source these days. To generate the summary, we propose the binary chimp optimisation algorithm (BChOA) in this research. Several preprocessing techniques utilised to remove unwanted terms from the content. Then, for word embedding, FastText is used. The semantic and synthetic features are extracted using the DarkNet-53 and ConvNeXt methods. Using a darknet convolutional neural network (DNetCNN), the features derived from the syntactic and semantic features are concatenated. The Movie review dataset contains 2000 review files, and the BBC news dataset has 50 unique documents. Finally, the outcome demonstrates that our model compares to cutting-edge solutions in terms of semantics and syntactic structure. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CyberGrid: an IEC61850 protocol-based substation automation virtual cyber range for cybersecurity research in the smart grid

引用

Cyber-Physical Systems 2025年第1期11卷 47-66页

作者： Efiong, John E. Akinwale, Abiodun Akinyemi, B.O. Olajubu, Emmanuel Aderounmu, Sola Computer Science and Engineering Obafemi Awolowo University Ile-Ife Nigeria

A cyber range provides a controlled environment for simulating mission-critical systems for cybersecurity research following the high risks involved in conducting experiments in real-life systems. Existing cyber ranges do not provide close emulation of Cyber-Physical Systems (CPS) in the Smart Grid Networks (SGNs), with emphasis on industry-based proprietary and IED protocols. This paper presents CyberGrid Testbed–a virtual Cyber-Range developed by the CyberSCADA Research Laboratory at Obafemi Awolowo University, Ile-Ife, Nigeria, which emulates Substation Automation processes with IEC61850 and Modbus/TCP protocols and support for MMS, and IED. This was built on OpenPLC6185, simulating Twelve attack patterns, and four attack types. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Metamorphic testing of deep neural network-based autonomous driving systems using behavioural domain adequacy

引用

Neural Computing and Applications 2025年第9期37卷 6677-6724页

作者： Kalaee, Akram Parsa, Saeed School of Computer Engineering Iran University of Science and Technology Tehran Iran

Deep neural networks (DNNs) are crucial in autonomous driving systems (ADSs) for tasks like steering control, but model inaccuracies, biased training data, and incorrect runtime parameters can compromise their reliability. Metamorphic testing (MT) enhances reliability by generating follow-up tests from mutated DNN source inputs, identifying inconsistencies as defects. Various MT techniques for ADSs include generative/transfer models, neuron-based coverage maximization, and adaptive test selection. Despite these efforts, significant challenges remain, including the ambiguity of neuron coverage’s correlation with misbehaviour detection, a lack of focus on DNN critical pathways, inadequate use of search-based methods, and the absence of an integrated method that effectively selects sources and generates follow-ups. This paper addresses such challenges by introducing DeepDomain, a grey-box multi-objective test generation approach for DNN models. It involves adaptively selecting diverse source inputs and generating domain-oriented follow-up tests. Such follow-ups explore critical pathways, extracted by neuron contribution, with broader coverage compared to their source tests (inter-behavioural domain) and attaining high neural boundary coverage of the misbehaviour regions detected in previous follow-ups (intra-behavioural domain). An empirical evaluation of the proposed approach on three DNN models used in the Udacity self-driving car challenge, and 18 different MRs demonstrates that relying on behavioural domain adequacy is a more reliable indicator than coverage criteria for effectively guiding the testing of DNNs. Additionally, DeepDomain significantly outperforms selected baselines in misbehaviour detection by up to 94 times, fault-revealing capability by up to 79%, output diversity by 71%, corner-case detection by up to 187 times, identification of robustness subdomains of MRs by up to 33 percentage points, and naturalness by two times. The results confirm that stat

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Enhanced Offline Writer Recognition System Employing Blended Multi-Input CNN and Bi-LSTM Model on Diverse Handwritten Texts

International Journal of Mathematical, Engineering and Manag...

引用

International Journal of Mathematical, engineering and Management sciences 2025年第4期10卷 1032-1054页

作者： Purohit, Naresh Panwar, Subhash Department of Computer Science & Engineering Government Engineering College Bikaner Rajasthan Bikaner India

Since author’s writing styles are often ambiguous, writer recognition is an appealing research problem for handwritten manuscript investigation. Pattern identification allows for recognizing the author of a handwritten work. Due to the variety of text visuals, especially handwriting images, author recognition is challenging. Convolution Neural Network (CNN) excels in many fields. This paper presents a complete framework that emphasizes feature engineering and uses a simple, efficient deep neural network. Writer recognition begins with data collection. Programming a technique to generate several database texts enhances the data. To capture and categorize feature information, a multi-path CNN with a Bidirectional Long Short Term Memory (Bi-LSTM) module is developed. By integrating CNN and Bi-LSTMs, the proposed model combines spatial and temporal information, offering a comprehensive representation of handwriting. This synergy makes it particularly effective in handling the variability and complexity of offline writer recognition. Languages are occasionally blended when writing in multilingual regions. The system performed well on two publicly accessible handwritten English language benchmark databases, CVL and IAM, in addition to an in-house bilingual database comprising English and Hindi scripts. This study is unconventional since it addressed offline writer recognition using monolingual and bilingual handwritten text corpora. Analytically, our findings are encouraging compared to previous studies. The model achieves accuracies of 98.78% on the IAM dataset, 98.55% on the CVL dataset, and 99% on an in-house bilingual dataset. These results demonstrate a significant improvement over other state-of-the-art methodologies in offline writer recognition. Copyright © Ram Arti Publishers.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of image compression methods: from prediction models to advanced techniques

引用

Multimedia Tools and Applications 2025年 1-39页

作者： Devadason, Joshua Rajah D, Aju School of Computer Science and Engineering Vellore Institute of Technology Vellore India

Images are used widely nowadays. Images are used in many fields such as medicine to terrain mapping. There is a need to compress the images and represent them in shorter form for effective transmission. Several techniques are reviewed in this paper. The first group of techniques is the data compression technique. The data compression methods are Huffman encoding, Lempel–Ziv Welch (LZW), arithmetic encoding, run length encoding, and Shannon-Fano encoding. The second group of methods is prediction, here the neighboring pixels are utilized in the prediction of the present pixel and the error is encoded using an entropy encoder. In wavelet-based techniques, the source image is transformed from the spatial domain to the wavelet domain, and the coefficients are encoded. In learning-based techniques, a neural network is used to model the image data for compression. Fractal encoding is a compression method that searches for similar blocks in an image and compresses the difference between the blocks. With an average bitrate of 4.87 bpp (bits per pixel) on the first 10 photos of the Digital Imaging and Communications in Medicine (DICOM) image collection, the results indicate that LZW is the top performing data compression technique among the data compression techniques. In prediction-based techniques, Context Adaptive Lossless Image Codec (CALIC) is the best performing with 3.5 bpp. The modern neural method, compressive autoencoder outperforms established methods such as Joint Photographic Experts Group (JPEG), by achieving a PSNR of 35 on the Kodak dataset compared with 32 PSNR on the same dataset at 1.0 bpp. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

3D brain image based tumor classification using ensemble of reinforcement transfer-based belief neural networks

引用

Multimedia Tools and Applications 2025年第14期84卷 14001-14028页

作者： Arora, Shraddha Lamba, Monika Department of Computer Science and Engineering The NorthCap University Haryana Gurugram India

The procedure of segmenting a brain tumour is an essential step in the field of medical image processing. In order to improve the efficacy of disease treatment choices and the likelihood of patient survival, the timely detection of a brain tumour is not only highly essential but a vital factor. For the purpose of cancer diagnosis, manually segmenting brain tumours from the large number of MRI images that are generated in clinical practice is a hard and time-consuming process. Automatic brain tumour image segmentation is a technique that absolutely has to exist. Using deep learning and machine learning architectures for segmentation and feature extraction, this research proposes a novel approach to the detection of brain tumours. In this case, the input consists of a collection of 3-D brain slice pictures that have been smoothed and with noise eliminated. After that, the picture that has been processed is segmented by using a convolutional radial function architecture that centres on contours. The segmented image features retrieval has been accomplished by the use of an ensemble of reinforcement transfer-based belief neural networks. The results of the experimental study have been completed with regard to precision, recall, accuracy, F-1 score, area under the curve, dice coefficient, and root mean square error. The strategy that was recommended was successful in achieving 97.57% accuracy, 97.15% precision, 89.37% recall, 83.56% F-1 score, 69.59% area under the curve, 63.83% dice coefficient, and 55.56% root mean square error. The sagittal, coronal, and axial planes of the pictures were shown in order to acquire the specific position of the tumour as well as its characteristics, which included its height, breadth, and depth. When it comes to the prediction of tumours, the findings of the assessment of semantic segmentation based on deep learning networks are highly positive. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Spri

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Smart traffic control: machine learning for dynamic road traffic management in urban environments

引用

Multimedia Tools and Applications 2025年第12期84卷 10321-10345页

作者： Khan, Hameed Thakur, Jitendra Singh Deptt of Computer Science & Engineering Jabalpur Engineering College Madhya Pradesh Jabalpur India

Roadside and outside environmental elements contribute to the road traffic setting's highly dynamic and turbulent nature. The human factor, primarily disregarded in the present research, is an essential element that contributes to the traffic context in addition to infrastructure-related elements like traffic signals, road infrastructure, and other road networks. Timing the green light and tracing the object that makes the incorrect turn using real-time visual information for traffic monitoring are still challenging tasks for the conventional traffic control system. We describe a self-adaptive real-time algorithm based on real-time traffic flow and monitoring. Combining image processing with AI-powered, self-adaptive machine learning for controlling traffic clearance at intersections is a forward-thinking approach with great potential. The suggested system uses the You Only Look Once v3 (YOLOv3) model and single image processing using a neural network to determine traffic clearance at the signal. YOLOv3 method to recognize objects from video frames. Subsequently, the centroid object tracking technique is used to monitor the movement of each vehicle within a proposed framework. We implemented algorithms to identify vehicles traveling in the incorrect direction based on their trajectories. This integrated approach enhances accurate object recognition, real-time vehicle tracking, and the detection of traffic violations, enhancing overall road safety measures. The experimental findings are quite promising, achieving an exclusive comparison between expected and actual vehicle numbers is crucial for any traffic monitoring system. The average object detection accuracy of 88.43% is impressive, and the exceptional 90.45% accuracy in tracking vehicles engaging in wrong turns or reckless driving behaviors is particularly noteworthy—it provides the system's ability to address safety concerns effectively. Integrating a Convolutional Neural Network (CNN) into the algorithm to all

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving intrusion detection with federated learning: enhancing privacy and efficiency in IoT networks

引用

International Journal of Machine Learning and Cybernetics 2025年 1-19页

作者： Sharma, Hemant Yadav, Gyan Singh Department of Computer Science and Engineering IIIT Kota Rajasthan Kota India

Intrusion detection systems (IDS) are crucial in the identification of unauthorized activities on a digital network, enabling cybersecurity measures to initiate prevention protocols to protect the security of their networks and data. With Internet of Things (IoT) as a ubiquitous phenomenon, IDS has become increasingly important owing to the massive growth of connected devices. Machine learning algorithms can detect anomalies in large datasets, but centralized methods pose security risks by gathering all data in one place. Federated learning (FL) offers a safer alternative, allowing multiple clients to collaborate on a model without sharing data, reducing the risk of data leaks and enhancing privacy. In this paper, we propose a FL-based IDS. Herein, we have applied the FL approach to a number of clients that are grouped in sets where the number of clients in a set varies from 2 to 10. After that, we applied feature ranking via a random forest approach, wherein the features are ranked based on their importance to find the optimal and reduced dataset for reducing the inference time. Further, three models for each of the clients were trained using the refined dataset obtained. Next, the central server aggregates the data from the clients using three methods. We have updated the dataset with two types of scenarios, one with two classes (Benign and Attacks) and the second with a multi-class (Benign, Dodag, Flooding, Rank, Blackhole) for identifying the attack. The experimental results establish that the proposed methodology achieves superior performance as compared to similar existing methodologies. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

SERLogic: A Logic-Integrated Framework for Enhancing Sequential Recommendations

引用

IEEE Access 2025年 13卷 72221-72234页

作者： Fan, Lihang Beihang University School of Computer Science and Engineering Beijing100191 China

Sequential recommendation models are used to predict users’ next top-K preferred items based on their historical interactions. However, these models often struggle in "fuzzy areas" where recommendation scores are near decision thresholds, leading to false positives and false negatives. To overcome this limitation, we propose SERLogic, an innovative framework that incorporates logic rules, termed TIE+s, into existing sequential recommendation models to enhance their accuracy without the need for training a new machine learning model. TIE+s represent a novel class of graph prediction rules characterized by a dual graph pattern (Formula presented) and a dependency X → (x, likes, y) , where (Formula presented) exhibits a dual star structure, and X extends ML sequential recommendation models and 1-WL test as predicates. With SERLogic , we show 1) validation problem for TIE+s is in polynomial time (PTIME), enabling efficient verification of whether a graph satisfies a set of TIE+s;2) creator-critic algorithm that iteratively learns high-quality TIE+s;3) parallel algorithm that applies the discovered TIE+s to generate recommendations efficiently. Empirical evaluation on real-world datasets reveals that SERLogic significantly enhances the performance of sequential recommendation models in terms of Recall@K and NDCG@K, while also achieving superior computational efficiency. © 2013 IEEE.

关键词： Learning algorithms

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：