检索结果-内蒙古大学图书馆

Revolutionizing wildlife protection: a novel approach combining deep learning and night-time surveillance

Multimedia Tools and Applications 2024年 1-35页

作者： Madhasu, Nithya Pande, Sagar Dhanraj VIT-AP University Andhra Pradesh India Department of Computer Science and Engineering School of Engineering and Technology Pimpri Chinchwad University Maharashtra Pune India

The increasing instances of animals encroaching on human settlements, as well as the illicit trafficking of wildlife, have prompted immediate actions to protect the natural heritage. In addition to this, the difficulties of night-time animal surveillance are also being faced. This paper highlights the urgent necessity for comprehensive animal welfare monitoring and effective anti-illegal trafficking prevention. The expensive cost of installing night vision cameras heightens the necessity of locating an affordable and effective solution. To overcome these issues, a unique strategy, combining colorization utilizing Customised Conditional GAN (Generative Adversarial Net) for night-time applications and YOLO-CNAS (You Only Look Once-Customised Neural Architecture Search) classification for intelligent wildlife detection is proposed. Colorization during the night enables the discovery of critical nocturnal behaviors, encouraging a greater knowledge and relationship with nature. Using these powerful deep learning algorithms helps to recognize the wildlife throughout both daylight and night-time hours, as well as smugglers trespassing into the forest. The suggested method obtains an amazing testing accuracy rate that has improved from 55.73% to 72.54% and then finally to 94.67%, demonstrating the revolutionary approach's potential for animal protection. The extensive dataset used for training and assessment was meticulously sourced from various websites including iNaturalist, Unsplash, and Pexels. These platforms provided a rich array of diverse images. During the pressing need to protect the nation's irreplaceable heritage, the intelligent model provides a ray of hope. Conservationists and policymakers may work together to safeguard the natural heritage by enabling effective wildlife surveillance and maintaining a happy coexistence between humans and animals for future generations. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of S

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

EAMR-Net: A multiscale effective spatial and cross-channel attention network for retinal vessel segmentation

引用

Mathematical Biosciences and engineering 2024年第3期21卷 4742-4761页

作者： Prethija, G. Katiravan, Jeevaa School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Department of Information Technology Velammal Engineering College Chennai600066 India

Delineation of retinal vessels in fundus images is essential for detecting a range of eye disorders. An automated technique for vessel segmentation can assist clinicians and enhance the efficiency of the diagnostic process. Traditional methods fail to extract multiscale information, discard unnecessary information, and delineate thin vessels. In this paper, a novel residual U-Net architecture that incorporates multi-scale feature learning and effective attention is proposed to delineate the retinal vessels precisely. Since drop block regularization performs better than drop out in preventing overfitting, drop block was used in this study. A multi-scale feature learning module was added instead of a skip connection to learn multi-scale features. A novel effective attention block was proposed and integrated with the decoder block to obtain precise spatial and channel information. Experimental findings indicated that the proposed model exhibited outstanding performance in retinal vessel delineation. The sensitivities achieved for DRIVE, STARE, and CHASE_DB datasets were 0.8293, 0.8151 and 0.8084, respectively. © 2024the Author(s).

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Enhanced Neural Differential Distinguisher for Speck32/64 Using Attention Mechanisms and Multi Ciphertext Inputs

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第19期49卷 197-210页

作者： Jiang, Xue Li, Min Kaiyrbek, Makulov Lakhno, Valerii Andrii, Sahun School of Computer and Information Engineering Bengbu University Bengbu233030 China Department of Computer Systems Networks and Cybersecurity National University of Life and Environmental Sciences of Ukraine Kyiv03041 Ukraine Department of Computer Science Caspian University of Technology and Engineering Almaty050151 Kazakhstan

In recent years, neural network-based differential distinguishers have demonstrated significant advantages in accuracy and effi-ciency over traditional differential distinguishers in symmetric cipher differential analysis. However, when dealing with ciphers involving a higher number of encryption rounds, neural network differential distinguishers still struggle to accurately identify ci-phertext pairs. To address this issue, this study proposes a neural network differential distinguisher model based on attention mechanisms and optimized ciphertext input structures. Specifically, the model first innovates the residual structure within the attention mechanism to maximize the weight of highly discriminative features, enhancing the feature extraction capability of the improved model. Secondly, a multi-scale convolution method is employed, integrating the network structure ideas of RegNet, with the addition of convolutional branches and optimization of activation functions, which further enhances the model's feature ex-traction capability. Finally, a multi-ciphertext input pattern is introduced to improve the input data information, and random key encryption is applied to the input ciphertext structure to construct multi-feature information representations of the ciphertext and encryption functions. The results from 5-8 rounds of experiments on Speck 32/64 indicate that the proposed new neural distinguisher can significantly improve discrimination accuracy to a maximum of 1.65%. On this basis, we carried out an optimization study on the construction method of the multi-ciphertext-pair dataset. The new dataset can increase the accuracy of the distinguisher by 49.16% compared to that of the single-ciphertext-pair case, and can extend the number of attack rounds from 7 to 8. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Graph Neural Network Based Learning Model for Urban Metro Flow Prediction 22

A Graph Neural Network Based Learning Model for Urban Metro ...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Drosouli, Ifigenia Voulodimos, Athanasios Mastorocostas, Paris Miaoulis, Georgios Ghazanfarpour, Djamchid Engineering University of West Attica Department of Informatics & Computer Athens Greece School of Electrical & Computer Engineering National Technical Univ. of Athens Athens Greece University of Limoges Department of Informatics Limoges France

ISBN: (纸本)9798350345346

- Abstract-Transport data with dynamic spatial-temporal dependencies elevates transportation flow forecasting to a significant issue for operational planning, managing passenger flow, and arranging for individual travel in a smart city. The task is challenging due to the composite spatial dependency on transportation networks and the non-linear temporal dynamics with mobility conditions changing over time. To address these challenges, we propose a Spatial- Temporal Graph Convolutional Recurrent Network that learns from both the spatial stations network data and time-series of historical mobility changes so as to predict urban metro flow at a future time. The model is based on Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) in order to further improve the estimation accuracy. Extensive experiments on a real-world dataset of Hangzhou metro system prove the effectiveness of the proposed model. © 2023 IEEE.

关键词： Graph Convolutional Networks spatial-temporal dependencies urban metro flow prediction

来源：评论

学校读者我要写书评

暂无评论

Absorb and Repel: Pseudo-Label Refinement for Intra-Camera Supervised Person Re-Identification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2884-2896页

作者： Li, Wei Chen, Chuyi Huang, Kaizhu Southeast University School of Instrument Science and Engineering Nanjing210096 China Duke Kunshan University Department of Electrical and Computer Engineering Kunshan215316 China

Person re-identification (ReID) aims to identify pedestrian images with the same identity across non-overlapping camera views. Intra-camera supervised person re-identification (ICS-ReID) is a new paradigm that trains a model using only intra-camera labels, thus reducing the cost of inter-camera identity association. Pseudo-label-based clustering algorithms perform well in the unsupervised ReID task, whereas they inevitably generate noisy pseudo labels through clustering, especially in the early training stage. Given this, we propose an unsupervised pseudo-labeling method to help in the semi-supervised ICS-ReID task. This method improves the clustering results by reassigning pseudo labels for the training data and consists of two modules, Absorb and Repel. The Absorb module aims to group all data with the same intra-camera identity into one cluster. The Repel module ensures that images under the same camera view but with different identities do not appear in the same cluster. Both modules are independent yet complementary to reduce the error rate of pseudo labels generated in each epoch. To our knowledge, this is the first attempt to refine pseudo labels for ICS-ReID. Our method is a simple, nonparametric, and effective strategy that can be easily integrated into existing clustering-based unsupervised ReID tasks. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art ICS-ReID approaches on three large-scale benchmark person ReID datasets. © 2020 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Document Classification and Data Extraction 3

Document Classification and Data Extraction

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Khurana, Madhav Chaturvedi, Ravi Prakash Mishra, Annu Gupta, Devika Negi, Ishika Mishra, Ambuj Sharma, Hirdesh Jemtec Department of Computer Science & Engineering Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Applications Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350384598

T- Data classification and extraction are fundamental tasks in the field of computer vision and data analysis. This abstract presents an overview of these concepts along with the utilization of Python and OpenCV, a popular computer vision library, in building data extraction tools. Data classification involves organizing data into categories or classes based on certain characteristics or features. It enables efficient data management and analysis by grouping similar data together. In the context of computer vision, data classification often involves categorizing images or videos based on their content, such as identifying objects, scenes, or patterns within them. Data extraction, on the other hand, involves retrieving specific information or features from a dataset. This process is crucial for tasks like data mining, information retrieval, and automated document processing. In computer vision applications, data extraction often entails locating and extracting relevant information from images or videos, such as text, objects, or numerical data. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Optimal Bidding Strategies of Microgrid with Demand Side Management for Economic Emission Dispatch Incorporating Uncertainty and Outage of Renewable Energy Sources

引用

Energy engineering 2024年第4期121卷 849-867页

作者： Mousumi Basu Chitralekha Jena Baseem Khan Ahmed Ali Department of Power Engineering Jadavpur UniversityJadavpurIndia School of Electrical Engineering KIIT UniversityBhubaneswarIndia Department of Electrical and Computer Engineering Hawassa UniversityHawassaEthiopia Department of Electrical and Electronic Engineering Technology Faculty of Engineering and the Built EnvironmentUniversity of JohannesburgJohannesburgSouth Africa

In the restructured electricity market,microgrid(MG),with the incorporation of smart grid technologies,distributed energy resources(DERs),a pumped-storage-hydraulic(PSH)unit,and a demand response program(DRP),is a smarter and more reliable electricity *** consists of gas turbines and renewable energy sources such as photovoltaic systems and wind *** bidding strategies,prepared by MG operators,decrease the electricity cost and emissions from upstream grid and conventional and renewable energy sources(RES).But it is inefficient due to the very high sporadic characteristics of RES and the very high outage *** solve these issues,this study suggests non-dominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ)for an optimal bidding strategy considering pumped hydroelectric energy storage and DRP based on outage conditions and uncertainties of renewable energy *** uncertainty related to solar and wind units is modeled using lognormal and Weibull probability ***-based DRP is used,especially considering the time of outages along with the time of peak loads and prices,to enhance the reliability of MG and reduce costs and emissions.

关键词： Micro-grid distributed energy resources demand response program uncertainty outage

来源：评论

学校读者我要写书评

暂无评论

Extending Online 4D Situational Awareness in Connected and Automated Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第8期9卷 1-19页

作者： Piperigkos, Nikos Anagnostopoulos, Christos Lalos, Aris S. Berberidis, Kostas Computer Engineering and Informatics Department University of Patras Greece Industrial Systems Institute ATHENA Research Center Patras Greece

Empowering each vehicle with four dimensional (4D) situational awareness, i.e., accurate knowledge of neighboring vehicles' 3D locations over time in a cooperative manner (instead of focusing only on self-localization), is fundamental for improving autonomous driving performance in diverse traffic conditions. For this task, identification, localization and tracking of nearby road users is critical for enhancing safety, motion planning and energy consumption of automated vehicles. Advanced perception sensors as well as communication abilities, enable the close collaboration of moving vehicles and other road users, and significantly increase the positioning accuracy via multi-modal sensor fusion. The challenge here is to actually match the extracted measurements from perception sensors with the correct vehicle ID, through data association. In this paper, two novel and distributed Cooperative Localization or Awareness algorithms are formulated, based on linear least-squares minimization and the celebrated Kalman Filter. They both aim to improve ego vehicle's 4D situational awareness, so as to be fully location aware of its surrounding and not just its own position. For that purpose, ego vehicle forms a star like topology with its neighbors, and fuses four types of multi-modal inter-vehicular measurements (position, distance, azimuth and inclination angle) via the linear Graph Laplacian operator and geometry capturing differential coordinates. Moreover, a data association strategy has been integrated to the algorithms as part of the identification process, which is shown to be much more beneficial than traditional Hungarian algorithm. An extensive experimental study has been conducted in CARLA, SUMO and Artery simulators, highlighting the benefits of the proposed methods in a variety of experimental scenarios, and verifying increased situational awareness ability. The proposed distributed approaches offer high positioning accuracy, outperforming other state-of-the-art c

关键词： Laplace equation

来源：评论

学校读者我要写书评

暂无评论

Federated learning-based hybrid convolutional recurrent neural network for multi-class intrusion detection in IoT networks

引用

Discover Internet of Things 2025年第1期5卷 1-22页

作者： Selvam, Prabu Karthikeyan, P. Manochitra, S. Sujith, A.V.L.N. Ganesan, T. Ayyasamy, Rajaram Shuaib, Mohammed Alam, Shadab Rajendran, A. School of Computing SRM Institute of Science and Technology Tiruchirappalli621105 India Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Tamil Nadu Madurai625009 India Department of Computer Science Engineering St Joseph’s College of Engineering Tamil Nadu Chennai600119 India School of Engineering Malla Reddy University Telangana Hyderabad500043 India Department of Computer Science Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Electronics and Communication Engineering E.G.S Pillay Engineering College Tamil Nadu Nagapattinam611002 India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of ECE Karpagam College of Engineering Tamil Nadu Othakkal Mandapam India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

As Internet of Things (IoT) devices leads an significant challenges in securing the systems from cyber-attacks in large-scale IoT networks. Traditional methods faces struggle to precisely detecting the complex intrusion patterns due to the heterogeneity and distributed IoT devices. There is a pressing need for scalable, real-time, and privacy-preserving solutions to secure IoT and IIoT systems. For multi-class intrusion detection in IoT networks, this study proposed an novel hybrid convolutional recurrent neural network (CRNN) model based on federated learning. By integrating federated learning, the proposed approach ensures privacy by enabling decentralized model training among IoT devices without exchanging sensitive data. The hybrid CRNN model improves detection accuracy for a variety of attack types in IoT networks by combining Recurrent Neural Networks for sequential pattern recognition and Convolutional Neural Networks for feature extraction from raw data. The proposed model classifies incoming network traffic into different attack classes. The experimental results conducted on the Edge-IIoT dataset reveal that the proposed model has attained the detection accuracy of 98.93% with balanced precision and recall for all the attack types and low-support classes such as SQL Injection and Man-in-the-Middle. This balance improves model’s ability to reduce both false negatives and false positives compared with conventional approaches. Together with real-time detection, our approach excels in a privacy-preserving manner, providing a practical, scalable solution for securing complex IoT networks, and addressing critical gaps in current IDS frameworks. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Framework For Bankruptcy Prediction In Corporate Finances Using Explainable AI Techniques

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第15期49卷 15-26页

作者： Maktum, Tabassum Pulgam, Namita Chandgadkar, Vaishnavi Pathak, Prachi Solanki, Aditya Department of Computer Engineering School of Engineering & Technology Anjuman I Islam’s Kalsekar Technical Campus Maharashtra New Panvel India D J Sanghvi College of Engineering Maharashtra Mumbai India Department of Computer Engineering Ramrao Adik Institute of Technology D Y Patil Deemed to be University Maharashtra Navi Mumbai India

Forecasting bankruptcy within corporate finances is an indispensable endeavor crucial for sustaining business growth and fostering stability. The paper presents a methodology to redefine the conventional approach to bankruptcy prediction within corporate finance. Through the adept utilization of advanced machine learning techniques, notably classification models, a dynamic and adaptable framework is established, enabling the systematic categorization of companies based on their bankruptcy risk profiles. Moreover, the methodology addresses the inherent challenge of data bias by integrating oversampling techniques like the Synthetic Minority Over-sampling Technique (SMOTE), thereby ensuring a more equitable representation of minority class samples and bolstering the model’s predictive accuracy. The resulting model delivers timely and precise forecasts of bankruptcy risk, fortified by crucial recommendations such as the Altman Z-Score for vulnerability assessment, Debt-to-Equity Ratio for insights into leverage, Quick Ratio for assessing liquidity, and Explainable AI Techniques like SHapley Additive exPlanations (SHAP) analysis for transparent interpretations. This comprehensive approach equips stakeholders with tailored recommendations, empowering them to proactively safeguard their organizations’ financial well-being and avert the perils of bankruptcy. The comparative analysis presented in paper demonstrates that the proposed method assesses the bankruptcy risk more accurately. The integration of Explainable AI techniques and key financial metrics helps the stakeholders to take vital decisions about corporate finances. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Risk assessment

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：