检索结果-内蒙古大学图书馆

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Darani Rajasekhar Mahammad Rafi D Shanker Chandre Vandana Kate Jhakeshwar Prasad Anandbabu Gopatoti Department of Electronics and Communication Engineering G.Pulla Reddy Engineering College(Autonomous) Kurnool Andhra Pradesh India Department of CSE GITAM University Hyderabad Telangana India Department of Computer Science & Artificial Intelligence SR University Warangal Telangana India Department of Computer Science and Information Technology Acropolis Institute of Technology and Research Indore Madhya Pradesh India Shri Shankaracharya College of Pharmaceutical Sciences Bhilai Chhattisgarh India Department of Electronics and Communication Engineering Hindusthan College of Engineering and Technology Coimbatore Tamil Nadu India

New statistics show that about 950,000 individuals a year lose their lives to breast carcinoma, making it the deadliest form of cancer worldwide. Early detection and accurate diagnosis of an illness can increase the likelihood of a favorable result, decreasing the mortality rate. Premature victims can be spared if the disease is detected early. Investigators who study cancer face various challenges, including the difficulty of differentiating benign and malignant tumors and the difficulty of classifying mild and metastatic breast cancer. Here, the pattern-recognition algorithms are used to accurately identify every tumor. However, they are all based on the idea of "binary grouping" (malignant and benign). This research made use of different pre-trained networks to speed up the training process. While evaluating the efficacy of the models, many measures were used. By using the images captured during the modeling process, both breasts can be shown together, without having to split them to show the right and left sides. After the data preparation phases, the Ensemble learning model showed the highest classification performance with an accuracy value of 100% when compared to the other pre-trained network models. In this research, thermographic images of breast cancer were used to classify the disease, and the results were combined with experimental data to form a computer-aided diagnosis method. Clinical data is used to validate the models' predictions. After constructing and evaluating two models with distinct designs, the model using the same design performed best, suggesting that the clinical data decisions were essential in improving the model's performance.

关键词： Deep learning Training Renewable energy sources Ultrasonic imaging Computational modeling Neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

DMINet: A lightweight dual-mixed channel-independent network for cataract recognition

DMINet: A lightweight dual-mixed channel-independent network...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiao Wu Yu Chen Qiuyang Yan Yuhang Zhao Jilu Zhao Xiaoqing Zhang Risa Higashita Jiang Liu Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Tomey Corporation Nagoya Japan Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Cataracts are the leading cause of visual impairment and blindness globally attracting abroad attention from society. Over the years researchers have developed many state-of-the-art convolutional neural networks (CNNs) to recognize cataract severity levels based on different ophthalmic images. However most current works focus on improving cataract recognition performance by designing complex CNNs often ignoring resource-constrained medical device limitations. To this problem this paper proposes a novel dual-mixed channel-independent convolution (DMIConv) method which takes advantage of the multiscale convolution kernels by combining a depthwise convolution with a depthwise dilated convolution sequentially. Moreover we build a lightweight dual-mixed channel-independent network (DMINet) to recognize cataracts. To verify the effectiveness and efficiency of DMINet we conduct extensive experiments on a clinical anterior segment optical coherence tomography (AS-OCT) dataset of nuclear cataract (NC) and a publicly available OCT dataset. The results show that our proposed DMINet keeps a better tradeoff between the model complexity and the classification performance than efficient CNNs e.g DMINet outperforms MixNet by 3.34% of accuracy by using 4.58 % fewer parameters

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity in Internet of Things Networks using Deep Learning Models

Cybersecurity in Internet of Things Networks using Deep Lear...

引用

Sustainable Computing and Data Communication Systems (ICSCDS), International Conference on

作者： V Anitha C.G. Naveen Kumar Ramu Kuchipudi Khushboo Sharma J Muralidharan R. Rajagopal Department of Computer Science and Engineering Imayam College of Engineering Kannanur Thuraiyur Trichy Tamil Nadu India Department of Studies and Research in Computer Science Karnataka State Open University Mysuru-06 Karnataka India Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering JECRC University Jaipur Rajasthan Department of ECE KPR Institute of Engineering and technology Coimbatore Tamil Nadu India Department of Computer Science & Engineering Alliance College of Engineering & Design Alliance University Bangalore Karnataka India

The Internet of Things and global grid that connects millions of sensors and devices have made distributed software and services ubiquitous. IoT’s vast reach and economic value make it a natural target for hackers, making security the industry’s top worry. Privacy has always been studied, but IoT design and new intimidations make most standard safeguards ineffective. Deep learning’s data, odd case technique, and ability to detect unexpected threats may help detect IoT intrusions. The “Internet of Things” includes computers, sensors, network infrastructure, software, networks, users, gateways, and services (IoT). Due to the increasing importance of Internet of Things (IoT) innovations, growth and management are huge. Data protection and privacy have recently caught users’ attention. As social media grows, more people connect. As connections grow, more safe spaces are needed. This article discusses data protection, including deep learning models, Machine Learning (ML) concepts, safety and security, and cybersecurity management. To illustrate IoT network vulnerability, convolutional neural networks (CNN), Long Short-Term Memory (LS TM), and CNN combinations have been studied and compared. We can detect IoT cyberattacks with over 99% accuracy using Modbus network traffic data.

关键词： Deep learning Biological system modeling Data protection Telecommunication traffic Software Data models Sensors

来源：评论

学校读者我要写书评

暂无评论

Understanding the Strengths and Limitations of AI for Data Access Optimization

Understanding the Strengths and Limitations of AI for Data A...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Manpreet Singh Preeti Naval Nagaraj Patil Mohit Tiwari V. Ashok Shilpa M. Katikar Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Mechanical Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Ramnagar District Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Artificial Intelligence (AI) has emerge as an increasing number of famous in recent years due to its potential to learn from facts, make predictions, and automate decision-making techniques. Within the realm of facts get right of entry to optimization, AI algorithms are getting used to enhance the overall performance and performance of information storage, retrieval, and analysis. but, like every other generation, AI has its personal strengths and boundaries that need to be understood on the way to effectively utilize it for information get entry to *** of the key strengths of AI is its capability to technique and examine massive amounts of facts speedy and as it should be. This is important in records get entry to optimization, wherein the speed and accuracy of records retrieval and evaluation is critical for choice-making. By the use of AI, companies can save time and sources that would in any other case be spent on manual records processing and evaluation. Additionally, AI has the potential to identify hidden patterns and correlations in facts that may not be obvious to humans. This may lead to extra efficient and powerful information get entry to strategies, as AI can find insights and traits which can were omitted through human analysts. This is particularly useful in complicated facts environments with high volumes of statistics.

关键词： Accuracy Correlation Decision making Manuals Companies Prediction algorithms Human in the loop Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Unsupervised optical flow estimation with dynamic timing representation for spike camera 23

Unsupervised optical flow estimation with dynamic timing rep...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Lujie Xia Ziluo Ding Rui Zhao Jiyuan Zhang Lei Ma Zhaofei Yu Tiejun Huang Ruiqin Xiong School of Computer Science Peking University and National Engineering Research Center of Visual Technology (NERCVT) National Engineering Research Center of Visual Technology (NERCVT) and Beijing Academy of Artificial Intelligence National Biomedical Imaging Center College of Future Technology Peking University School of Computer Science Peking University and National Engineering Research Center of Visual Technology (NERCVT) and Institute for Artificial Intelligence Peking University

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers architecture, it applies dilated convolutions on temporal dimension to extract features on multi-temporal scales with few parameters. And we design layer attention to dynamically fuse these features. Moreover, we propose an unsupervised learning method for optical flow estimation in a spike-based manner to break the dependence on labeled data. In addition, to verify the robustness, we also build a spike-based synthetic validation dataset for extreme scenarios in autonomous driving, denoted as SSES dataset. It consists of various corner cases. Experiments show that our method can predict optical flow from spike streams in different high-speed scenes, including real scenes. For instance, our method achieves 15% and 19% error reduction on PHM dataset compared to the best spike-based work, SCFlow, in Δt = 10 and Δt = 20 respectively, using the same settings as in previous works. The source code and dataset are available at https://***/Bosserhead/USFlow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Multicast Protocols over ATM Networks

An Investigation of Multicast Protocols over ATM Networks

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Diptonil Banerjee Kambam Vedantan Priyanka More S. Hemelatha Amit Kumar T. Vanaja College of Engineering Teerthanker Mahaveer University Moradabad Uttar Pradesh India School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka India Computer Engineering Vishwakarma Institute of InformationTechnology Pune India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore India Centre for Interdisciplinary Research for Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The paper investigates the impact of the multicast method used over an asynchronous transfer mode (ATM) network in comparison to factor-to-factor solutions. The paper investigated mechanisms, multicast, and point-to-point (P2P) and in comparison their overall performance in phrases of throughput, total delay, and packet loss charge when beneath various community conditions. It turned into located that multicast had benefits in terms of total throughput and postpone while compared to P2P in phrases of cost of bandwidth for larger variety of receivers. Further, the multicast method had a lower packet loss charge than P2P in all situations. This paper concluded that no matter the complexity related multicast, because of its inherent blessings, is taken into consideration a better answer for multimedia programs that require a large number of receivers. Average, its miles counseled that multicast is the era of desire over ATM networks when the number of receivers growth.

关键词： Multicast algorithms Unicast Packet loss Receivers Throughput Multicast protocols Routing Delays Reliability Asynchronous transfer mode

来源：评论

学校读者我要写书评

暂无评论

Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation

arXiv

引用

arXiv 2023年

作者： Xue, Ye Lau, Vincent Shenzhen Research Institute of Big Data Shenzhen China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Low-rank model compression is a widely used technique for reducing the computational load when training machine learning models. However, existing methods often rely on relaxing the low-rank constraint of the model weights using a regularized nuclear norm penalty, which requires an appropriate hyperparameter that can be difficult to determine in practice. Furthermore, existing compression techniques are not directly applicable to efficient over-the-air (OTA) aggregation in federated learning (FL) systems for distributed Internet-of-Things (IoT) scenarios. In this paper, we propose a novel manifold optimization formulation for low-rank model compression in FL that does not relax the low-rank constraint. Our optimization is conducted directly over the low-rank manifold, guaranteeing that the model is exactly low-rank. We also introduce a consensus penalty in the optimization formulation to support OTA aggregation. Based on our optimization formulation, we propose an alternating Riemannian optimization algorithm with a precoder that enables efficient OTA aggregation of low-rank local models without sacrificing training performance. Additionally, we provide convergence analysis in terms of key system parameters and conduct extensive experiments with real-world datasets to demonstrate the effectiveness of our proposed Riemannian low-rank model compression scheme compared to various state-of-the-art baselines. © 2023, CC BY-NC-ND.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Deep-sea Nodule Mineral Image Segmentation Algorithm Based on Pix2PixHD

引用

computers, Materials & Continua 2022年第10期73卷 1449-1462页

作者： Wei Song Haolin Wang Xinping Zhang Jianxin Xia Tongmu Liu Yuxi Shi School of Information and Engineering Minzu University of ChinaBeijing100081China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourceGuangzhou510300China National Language Resource Monitoring&Research Center of Minority Languages Beijing100081China School of Ocean Science China University of GeosciencesBeijing100191China Department of Buoy Engineering South China Sea Marine Survey and Technology CenterGuangzhou510300China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNew Jersey07102USA

Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and *** application of artificial intelligence technology to deep-sea mining projects can effectively improve the quality and efficiency of *** existing deep learning-based underwater image segmentation algorithms have problems such as the accuracy rate is not high enough and the running time is slightly *** order to improve the segmentation performance of underwater mineral images,this paper uses the Pix2PixHD(Pixel to Pixel High Definition)algorithm based on Conditional Generative Adversarial Network(CGAN)to segment deep-sea mineral *** model uses a coarse-to-fine generator composed of a global generation network and two local enhancement networks,and multiple multi-scale discriminators with same network structures but different input pictures to generate highquality *** test results on the deep-sea mineral datasets show that the Pix2PixHD algorithm can identify more target minerals under certain other *** evaluation index shows that the Pix2PixHD algorithm effectively improves the accuracy rate and the recall rate of deep-sea mineral image segmentation compared with the CGAN algorithm and the U-Net *** is important for expanding the application of deep learning techniques in the field of deep-sea exploration and mining.

关键词： Deep-sea mineral image segmentation generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Botanic Alchemy: Cultivating Insight through Extensive Plant Disease Dataset and Reweighted Visual Analysis

Botanic Alchemy: Cultivating Insight through Extensive Plant...

引用

computer, Communication and Control (IC4), International Conference on

作者： S.M. Mustafa Nawaz K. Maharajan J. Vijay Anand G. Malathi Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and education Tamil Nadu Department of Electronics and Communication Engineering J.N.N Institutes of Engineeriung Tamil Nadu Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai. Kanchipuram Tamil Nadu

Diagnosing plant diseases research tackles the vital challenge of identifying plant diseases in agriculture by focusing on the intricate complexities found in images displaying diverse symptoms, scattered lesions, and complex backgrounds. To aid this endeavor, a substantial dataset of 220,592 images is assembled. The proposed method uses a reweighting strategy that targets both visual regions and loss. Initially, weights for segmented patches are calculated based on their discriminative potential obtained from cluster distributions. These weights are then seamlessly integrated into the training process, assigning them to individual patch-label pairs during weakly-supervised training, aiding in recognizing disease-specific regions. Features extracted from this trained network create a comprehensive feature representation. This integration incorporates the GRU algorithm to encode the sequence of weighted patch features. Thorough evaluations on the newly curated dataset and a public dataset demonstrate the effectiveness and superiority of this methodology. This research significantly advances the field of plant disease recognition in image processing, opening doors for further innovative exploration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Pesticide Spraying Robots in Agricultural Practices

A Review on the Applications of Pesticide Spraying Robots in...

引用

engineering and technology (PICET), Parul International Conference on

作者： Mohan K. Warbhe Rajendra M. Rewatkar Prateek Verma Yash S. Pachghare Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Sawangi Wardha Maharashtra India Department of Biomedical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Sawangi Wardha Maharashtra India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

India is an agriculture based economy and it is one of the most significant sector in India. In traditional agriculture methods, there are various challenges such as reliance on manual labor and limited access to modern farming techniquies due to lack of advanced infrastructure. The spraying of pesticides pose a serious risk to human health as spraying contains potentially hazardous chemicals. This study provides a review on the various techniques being used for spraying pesticides in the agricultural fields. Robots can automate task like planting, weeding and harvesting with better performance in less time. Equipped with sensors and Artificial Intelligence (AI), they can collect the information to make the accurate decisions about soil, crop, health and weather in real time, thereby reducing costs and environmental impact while enhancing productivity. The robotic spraying provides the advantage over traditional methods as it has the ability to maintain its maximum capacity with best efficiency while the pesticide spraying system evenly cover the plants with spray in the appropriate quantities. This connectivity to smart agriculture systems emphasizes the technology's role as a pillar in the shift to efficient and sustainable farming methods. The deployment of these agricultural robots leads to reduction in risk of the potential hazards linked to human contact with dangerous substances and also supports sustainable agriculture.

关键词： Accuracy Reviews Spraying Crops Pesticides Robot sensing systems Agriculture Robots Water resources Farming

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：