检索结果-内蒙古大学图书馆

5th International Conference on Advancements in Computing, ICAC 2023

作者： Jayakody, E.R.T. Rabel, W.T.T. Estrop, R.D.V. Herath, K.G.L.P. Harshanath, S.M.B. Abeygunawardhana, Pradeep K. W. Sri Lanka Institute Information Technology Dept. of Computer Systems Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Software Engineering Colombo Sri Lanka

ISBN: (纸本)9798350358131

The automation of processes in greenhouses provides a significant advantage to the agricultural sector. Due to the rapid growth of the population, increasing demand for food and labor shortage make the autonomous monitoring and management of agricultural work more important. Capsicum is a largely consumed vegetable in South Asia, which can be efficiently grown in greenhouses. Although there are many capsicum farms, they lack quality and efficient production to match the increasing demand. This paper proposes a robotic system for use in capsicum greenhouses that can navigate and monitor the plants to identify diseases, track the yield, and take remediation actions. The robot navigates to each plant in the greenhouse autonomously by using the SLAM approach with the use of laser range sensor data. The 4 DoF robotic arm of the robot has a camera and a sprayer attached to its end to investigate plants and spray remedies to diseased plants. The robotic arm moves around the plant to capture the images to detect deceases and count the pods to estimate the yield. The sprayer of the robot sprays remedies precisely to targeted plants to control pests and diseases. The system was successfully implemented and tested with the proposed functions. © 2023 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Lightweight and Roubust Key Agreement for Securing IIoT-Driven Flexible Manufacturing systems

引用

IEEE Internet of Things Journal 2025年第11期12卷 17197-17209页

作者： Hammad, Muhammad Badshah, Akhtar Almeer, Mohammed A. Waqas, Muhammad Song, Houbing Chen, Sheng Han, Zhu GIK Institute of Engineering Sciences and Technology Faculty of Mechanical Engineering Topi23640 Pakistan University of Malakand Department of Software Engineering Dir Lower18800 Pakistan University of Bahrain Computer Engineering Department College of Information Technology 32038 Bahrain University of Greenwich Faculty of Engineering and Science Centre for Sustainable Cybersecurity United Kingdom Edith Cowan University School of Engineering PerthWA6027 Australia Department of Information Systems BaltimoreMD United States University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

The ever-evolving Internet of Things (IoT) has ushered in a new era of intelligent manufacturing across multiple industries. However, the security and privacy of real-time data transmitted over the public channel of the industrial IoT (IIoT) remain formidable challenges. Existing lightweight protocols often omit one or more critical security features, such as anonymity and untraceability, and are susceptible to threats like desynchronization attacks. Additionally, they struggle to achieve an optimal balance between robust security and performance efficiency. To bridge these gaps, we introduce a new lightweight key agreement security scheme that guarantees secure access to the IIoT-enabled flexible manufacturing system (FMS). The strength of our scheme lies in its utilization of the authenticated encryption with associative data (AEAD) primitive, AEGIS, along with hash functions and physical unclonable functions, which secure the IIoT ecosystem. Additionally, our scheme offers flexibility in the form of the addition of new machines, password updates, and revocation in cases of theft or loss. A comprehensive security analysis demonstrates the efficacy of the proposed scheme in thwarting various attacks. The formal analysis, based on the Real-Or-Random (RoR) model, ensures session key indistinguishability, while the informal analysis highlights its resilience against known attacks. The comparative assessment demonstrate that the proposed scheme consistently outperforms the benchmark schemes across multiple dimensions, including security and functionality features, computational and communication overheads, and runtime efficiency. Specifically, the proposed scheme achieves peak performance enhancements of 77.55%, 44.73%, and 69.6% in computational overhead, runtime overhead, and communication overhead, respectively, underscoring its substantial performance advantages. © 2025 IEEE.

关键词： Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

Toward actionable testing of deep learning models

引用

Science China(information Sciences) 2023年第7期66卷 300-302页

作者： Yingfei XIONG Yongqiang TIAN Yepang LIU Shing-Chi CHEUNG Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of Education School of Computer Science Peking University Department of Computer Science and Engineering The Hong Kong University of Science and Technology School of Computer Science University of Waterloo Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Computer Science and Engineering Southern University of Science and Technology

Deep learning has become an important computational paradigm in our daily lives with a wide range of applications,from authentication using facial recognition to autonomous driving in smart vehicles. The quality of the deep learning models, i.e., neural architectures with parameters trained over a dataset, is crucial to our daily living and economy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph-in-Graph Convolutional Network for Hyperspectral Image Classification

引用

IEEE Transactions on Neural Networks and Learning systems 2024年第1期35卷 1157-1171页

作者： Jia, Sen Jiang, Shuguo Zhang, Shuyu Xu, Meng Jia, Xiuping College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Key Laboratory for Geo-Environmental Monitoring of Coastal Zone Shenzhen University Ministry of Natural Resources Shenzhen518060 China School of Engineering and Information Technology University of New South Wales CanberraACT 2612 Australia

With the development of hyperspectral sensors, accessible hyperspectral images (HSIs) are increasing, and pixel-oriented classification has attracted much attention. Recently, graph convolutional networks (GCNs) have been proposed to process graph-structured data in non-Euclidean domains and have been employed in HSI classification. But most methods based on GCN are hard to sufficiently exploit information of ground objects due to feature aggregation. To solve this issue, in this article, we proposed a graph-in-graph (GiG) model and a related GiG convolutional network (GiGCN) for HSI classification from a superpixel viewpoint. The GiG representation covers information inside and outside superpixels, respectively, corresponding to the local and global characteristics of ground objects. Concretely, after segmenting HSI into disjoint superpixels, each one is converted to an internal graph. Meanwhile, an external graph is constructed according to the spatial adjacent relationships among superpixels. Significantly, each node in the external graph embeds a corresponding internal graph, forming the so-called GiG structure. Then, GiGCN composed of internal and External graph convolution (EGC) is designed to extract hierarchical features and integrate them into multiple scales, improving the discriminability of GiGCN. Ensemble learning is incorporated to further boost the robustness of GiGCN. It is worth noting that we are the first to propose the GiG framework from the superpixel point and the GiGCN scheme for HSI classification. Experiment results on four benchmark datasets demonstrate that our proposed method is effective and feasible for HSI classification with limited labeled samples. For study replication, the code developed for this study is available at https://***/ShuGuoJ/***. © 2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Toward Drought Modeling in South Asia: Machine Learning Approaches, Challenges, and Opportunities

引用

IEEE Access 2025年 13卷 87654-87671页

作者： Mana Saleh Al Reshan Muhammad Owais Raza Naeem Ahmed Mahoto Adel Rajab Asadullah Shaikh Mohamed A. Elmagzoub Khairan D. Rajab Department of Information Systems College of Computer Science and Information Systems Najran University Najran Saudi Arabia Emerging Technologies Research Laboratory (ETRL) College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Computer Engineering Istanbul Sabahattin Zaim University İstanbul Türkiye Department of Software Engineering Mehran University of Engineering and Technology Jamshoro Sindh Pakistan Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Network and Communication Engineering College of Computer Science and Information Systems Najran University Najran Saudi Arabia

Drought is an environmental and economic problem. Sustainable ecosystems, water resources, food security, and ecosystem sustainability. Machine all are severely affected by drought. Due to the increasing frequency and severity of droughts caused by climate change. Effective drought modeling is crucial for early warning systems and risk mitigation. Recent advances in machine learning (ML) and deep learning (DL) techniques have been developed as potential drought modeling tools, which offer accurate and reliable drought detection. This review paper summarizes the drought modeling(Drought Prediction, Drought Detection and Drought Forecasting) approaches. This paper focuses on three main aspect. 1) The selection of the region for this study, for this study South Asia(SA) is selected as region of interest (ROI) that offer accurate drought modeling, providing policymakers and decision-makers with insightful information. The geographical scope of this study is the region of South Asia. This region is selected because of its heavy reliance on agriculture. 2) This paper focuses on the current and future trends, challenges, and advances of and vulnerability to droughts. The review offers a thorough grasp of how drought conditions are evaluated by gathering and analyzing the most important drought indicators and metrics specific to South Asia. The paper explores the current state-of-the-art in ML and DL for drought modeling. 3) This review encapsulates the indicator and metrics (Complex Machine learning and deep learning models) for drought modeling which are most relevant to the SA region. This study sum up as most common challenges in drought modeling are, highlighting current challenges such as incomplete and inconsistent datasets, lack of explainable and interpretable models, and unavailability of data for model uncertainty analysis. This study proposes that these problems can be solved with modern machine learning techniques such as explainable machine learning and federa

关键词： Droughts Machine learning Asia Deep learning Indexes Water resources Remote sensing Predictive models computer science Climate change Environmental monitoring Economics

来源：评论

学校读者我要写书评

暂无评论

Research and development of an information system for speech recognition based on neural network algorithms metrics 4

Research and development of an information system for speech...

引用

4th IEEE International Conference on Smart information systems and Technologies, SIST 2024

作者： Kanashev, Maksat Mukasheva, Assel Yedilkhan, Didar Rakhmetulaeva, Sabina Gnatyuk, Sergiy Nazym, Mirambayeva Almaty University of Power Engineering and Telecommunications Almaty Kazakhstan The School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan The Department of Computer Engineering Astana IT University Astana Kazakhstan The Department of Information Systems International University of Information Technologies Almaty Kazakhstan The Faculty of Cybersecurity Computer and Software Engineering National Aviation University National Aviation University Kyiv Ukraine

ISBN: (纸本)9798350374865

This article examines the parameters of speech recognition in audio recordings containing a variety of phrases uttered by different people with different accents and intonations. The aim of the study is to evaluate the recognition speed, the accuracy of audio-to-text conversion and resource consumption when using SpeechRecognition and Levenshtein libraries. During the analysis, the above libraries were used to record and recognize audio files, as well as to calculate the distance between two lines and determine the recognition accuracy. The findings of this study can be useful for improving speech recognition systems and creating more adaptive and efficient solutions for audio data processing. The results of comparing the accuracy of speech recognition models are recorded in JSON format, after which, using the matplotlib library, they are visualized as graphs, comparing the speed and accuracy of recognition. Visualization of data in this way contributes to their improvement and more effective integration into educational systems. In conclusion, the authors emphasize the prospects for further development of speech recognition technologies in different fields. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

SUCP Analysis for Region-Centric UAV-Assisted MEC Networks 20th

SUCP Analysis for Region-Centric UAV-Assisted MEC Networks

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： Li, Yan Yi, Zhaozhi Long, Qingmin Luo, Lailong Guo, Deke School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410004 China National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789819628636

With the increase of computing-intensive and delay-sensitive applications, mobile edge computing (MEC) technology has sprung up. It effectively satisfies the needs of user equipment (UE) for real-time computing resources by placing servers at the edge of the network. However, traditional MEC infrastructures are constrained by their fixed locations and emergency mobility needs. Unmanned aerial vehicles (UAVs) offer an effective solution with low cost, high mobility, and flexible deployment capabilities. In this paper, we propose a region-centric UAV-assisted MEC model, where the whole network space is divided into a set of hexagonal cells of equal area, and all UAVs in the same cell jointly process UE offloading data. Assume all UAVs are assumed to be equipped with independent MEC servers, and both UAVs and terrestrial UE follow independent homogeneous Poisson point process (PPP) distributions. Using the stochastic geometry analysis framework, we derive the successful uplink communication probability (SUCP) of uplink transmission for users. Finally, we compare the simulation results with the theoretical values to verify the model’s accuracy and evaluate the influence of key performance parameters on the network performance. © IFIP International Federation for information Processing 2025.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition 41

Learning Label Shift Correction for Test-Agnostic Long-Taile...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wei, Tong Mao, Zhen Zhou, Zi-Hao Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between long-tailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing long-tail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction. Copyright 2024 by the author(s)

关键词： Black-box testing

来源：评论

学校读者我要写书评

暂无评论

An Effective Detection of Brain Tumor Detection Using ResNet-50 Model

An Effective Detection of Brain Tumor Detection Using ResNet...

引用

2024 International Conference on Advancement in Renewable Energy and Intelligent systems, AREIS 2024

作者： Raji, V. Maheswari, S. Dharinya, S. Sree Chinniah, P. Kavin, K.S. Raja, Kiruba Thangam S.K.P. Engineering College Dept. of Information Technology Tiruvannamalai India Tamilnadu Erode India School of Computer Science Engineering and Information Systems Vit University Dept. of Software and Systems Engineering Vellore India ST. Joseph College of Engineering Dept. of Ece Tamilnadu Sriperumbudur India Government College of Engineering Dept. of Eee Tamil Nadu Tirunelveli India Vit University Dept. of Software and Systems Engineering Vellore India

ISBN: (纸本)9798350387230

Rapid proliferation of aberrant neurons in brain tumors significantly damages organ function or causes death, endangering adult health. These tumors vary widely in terms of their locations, sizes, and textures. Finding malignant tumors requires the use of Magnetic Resonance Imaging (MRI). However, physically diagnosing brain tumors is a timeconsuming and potentially unpredictable technique. Cropping and resizing to fixed dimensions ensures consistency before submitting brain MRI images for analysis using deep learning models such as modified ResNet-50. This study uses the modified ResNet-50 model, a deep Convolutional Neural Network (CNN) renowned for its accuracy and resilience in image recognition tasks, to provide an efficient method for brain tumor diagnosis. Initially trained on Image Net, the modified ResNet-50 model further improved using transfer learning on many annotated brain MRI scan datasets. By adding variation to the dataset, data augmentation makes the model more robust and helps it to generalize. Deeper networks are trained without sacrificing performance to the model's architecture, which addresses the vanishing gradient problem. This work classification model implemented using Python software, which facilitated the development, training, and evaluation processes, allowing for an analysis of their performance. The optimized model outperformed conventional Machine Learning (ML) techniques, demonstrating over 94% accuracy in tumor identification and classification tests. With the potential to enhance patient outcomes and diagnostic efficiency, the integration of modified ResNet-50 in brain tumor identification offers a significant development towards accurate and dependable automated diagnostic systems. The accuracy of the modified Resnet-50 is 94%, and the specificity comparison of the modified ResNet-50 is 93.5%, respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Yolo Based License Plate Detection of Triple Riders and Violators

Yolo Based License Plate Detection of Triple Riders and Viol...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Nandhakumar, R.G. Devi, K. Nirmala Krishnamoorthy, N. Shanthi, S. Pranesh, V.R. Nikhalyaa, S. Kongu Enginering College Perundurai Department of Computer Science and Engineering Tamilnadu Erode India Vellore Institutte of Technology School of Information and Engineering Department of Software Systems and Engineering Vellore India

ISBN: (纸本)9798350348217

Road safety is of prime importance as road accidents are among the biggest causes of deaths in the country. Road Accidents are majorly due to violators and lawbreakers of road safety rules like not wearing helmets, triple riding etc. Even though there are many smart systems to monitor these violations, it is complicated to keep a track of the data and view it efficiently anywhere. Also monitoring the permit details of other state vehicles is hard. A method was proposed to address this issue. based on Deep learning and Optical Character Recognition (OCR). Here we detect the riders not wearing helmet and triple riders using object detection by comparing YOLOv2 and YOLOv3. This simplifies the task of traffic police who can't continuously and efficiently monitor all the violators. We gathered our data from three different sources. Kaggle was used to collect the data set. A number of items can be recognized by the real-time object recognition system YOLO in a single frame. It recognizes object more precisely and faster than other recognition systems. It can predict up to 9000 classes and even unseen classes. It divides the image into m∗m matrix and each grid detects objects within itself. The trained model is tested using a test dataset set after training in order to measure the performance. For Number plate detection we use OCR based character recognition. The recognized license plate images of violators are captured and stored in a database which is then sent to the concerned department. The stored data can be easily accessed using the developed mobile app. Metrics considered for evaluation is Accuracy. The average is utilized to assess object detection models like R-CNN and YOLO. The average calculates a score by comparing the detected box to the ground-truth bounding box. The better the score, the more precise the model's detections are. When compared to YOLOv2, YOLOv3 exhibits strong performance in terms of accuracy with 95.5%. © 2023 IEEE.

关键词： Object detection

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：