检索结果-内蒙古大学图书馆

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： Yatendra Sahu Arpita Bhargava Ghanshyam Singh Thakur Rishi Jain Department of Computer Science and Engineering IIIT Bhopal India Department of Computer Application MANIT Bhopal India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391572

The apple industry faces significant economic losses due to diseases and pests, contributing to low productivity levels. Detecting apple diseases promptly is essential for controlling their spread and improving overall productivity. However, early identification and diagnosis of these diseases are challenging due to various factors. In this work, we evaluated the performance of three distinct models: a custom CNN, Xception, and Resnet152V2. These models were tested on an expert-annotated dataset of apple diseases, comprising approximately 1821 high-quality RGB images across different categories of following types: C1: scab affected apple, C2: cedar apple affected by rust, C3: diseases of complex nature, and C4 samples of healthy apples. The custom CNN based proposed model trained for 50 epochs could yield an approximate accuracy of around 95%.

关键词： Productivity Industries Accuracy Biological system modeling Computational modeling Hardware Time factors

来源：评论

学校读者我要写书评

暂无评论

Melanoma Skin Cancer Detection Using Deep Learning Techniques 7

Melanoma Skin Cancer Detection Using Deep Learning Technique...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Kashikar, Arya Maurya, Sudhanshu Pant, Himanshu Gupta, Parbhat Asudani, Deepak Suresh Yadav, Ajay Kumar Symbiosis Institute of Technology Nagpur Campus Pune India Graphic Era Hill University Bhimtal Campus Uttarakhand India Srm Institute of Science and Technology Department of Computer Science and Engineering Delhi NCR Campus Ghaziabad India United Institute of Management Department of Computer Application Prayagraj India

ISBN: (纸本)9798350350067

Skin cancer, known as melanoma, is very dangerous in case of when it is not diagnosed at an early stage and has a positive prognosis when it is treated within the time frame. This work goes deep into the field of deep learning techniques to enhance the automation of melanoma detection. Using a dataset including 735 dermatoscopic pictures and two profound deep learning models were put to the test: A CNN model with ResNet-50 as the backbone and a Faster R-CNN model with MobileNet v3 as the backbone. The ResNet-50-powered CNN brought a precision rate of 85.06%, which proves that it is viable for accurately differentiating melanoma sores. To take identification accuracy to a higher level, the Faster R-CNN model was introduced, combining sore characterization with bounding inside the pictures. Finally, this integrated approach produced a quite impressive accuracy of 90 percent. This is good for clinical applications, as indicated by its 03% rating. From the disclosures made in the review, it is possible to infer that deep learning models, particularly those that have been augmented with district-based methods, hold the potential for early identification of melanoma. These mechanical headways can enhance patient results by integrating with adequate diagnosis and treatment, potentially saving lives and enhancing the quality of patient care in dermatology and oncology practices. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Side-channel analysis attacks based on deep learning network

引用

Frontiers of computer science 2022年第2期16卷 35-45页

作者： Yu OU Lang LI Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China

There has been a growing interest in the sidechannel analysis(SCA)field based on deep learning(DL)*** DL network or model has been developed to improve the efficiency of ***,few studies have investigated the impact of the different models on attack results and the exact relationship between power consumption traces and intermediate *** on the convolutional neural network and the autoencoder,this paper proposes a Template Analysis Pre-trained DL Classification model named TAPDC which contains three *** TAPDC model detects the periodicity of power trace,relating power to the intermediate values and mining the deeper features by the multi-layer convolutional *** implement the TAPDC model and compare it with two classical models in a fair *** evaluative results show that the TAPDC model with autoencoder and deep convolution feature extraction structure in SCA can more effectively extract information from power consumption ***,Using the classifier layer,this model links power information to the probability of intermediate *** completes the conversion from power trace to intermediate values and greatly improves the efficiency of the power attack.

关键词： side-channel analysis template attack machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Design of Deep Learning Models for the Identification of Harmful Attack Activities in the Industrial Internet of Things (IIOT) 10

Design of Deep Learning Models for the Identification of Har...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Rajesh, M. Vincent, Rajiv Kathuria, Sakshi Jamalpur, Bhavana Durgam, Thirupathi Jaiswal, Tarun School of Computer Science and Engineering Vellore Institute of Technology Chennai India K. R. Mangalam University University Computer Science and Engineering Haryana Gurugram India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India Ece India National Institute of Technology Department. of Computer Application C.G. Raipur India

ISBN: (纸本)9798350382471

Traditional industrial processes benefit greatly from the Industrial Internet of Things (IIoT), which increases efficiency as well as productivity. However, as IIoT becomes more connected, critical infrastructure is exposed to a variety of cyber risks. In order to accurately identify dangerous attack behaviors within IIoT systems, the present research focuses on the development and execution of deep learning models, combining recurrent neural networks (RNNs) including artificial neural networks (ANNs). The approach uses Python-based visualization techniques, model creation, and data pretreatment. By proactively identifying and mitigating cyber risks, our research seeks to strengthen IIoT security and ensure the resilience and honesty of industrial operations in a world that is becoming more linked. © 2023 IEEE.

关键词： Artificial Neural Networks (ANNs) Attack Identification Cyber Threat Detection Deep Learning Models IIoT Security Industrial Cyber security Recurrent Neural Networks (RNNs)

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Internet of Things in Wireless Sensor Networks for Industry 4.0 applications 1

Exploring the Role of Internet of Things in Wireless Sensor ...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Palarimath, Suresh Maran, Pyingkodi N.r, Wilfred Blessing Sujatha, T. Renuga, S. R.s, Chithra College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman Kongu Engineering College Department of Computer Application Erode India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India Ponjesly College of Engineering Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350365016

Recent developments in computer networking have made it possible to access information from a faraway location via either wireless or wired networks. The recent advancements in wireless infrastructure are directly responsible for the advent of wireless sensor networks, often known as WSNs. These networks make it easier to keep track of environmental happenings and activities, as well as document them and manage them. In WSNs, data relaying is accomplished through the use of a variety of routing strategies. Industry 4.0, also known as the fourth industrial revolution, is characterized by the incorporation of highly developed physical automation systems. These systems are made up of several pieces of machinery and gadgets that are linked together by sensors and are operated by software. The goal of the fourth industrial revolution is to improve the effectiveness and dependability of business processes. The Internet of Things (IoT) can be leveraged in manufacturing, which gives a means of linking engines, power grids, and sensors to the cloud in an industrial context. This is accomplished through the use of Industrial IoT. The purpose of this paper is to gain an understanding of how the Internet of Things functions in wireless sensor networks and its possible applications in a variety of settings. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Antenna Optimization Method Based on Preferred Parameter Spaces

A Multi-objective Antenna Optimization Method Based on Prefe...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Dou, Jiangling Lin, Siyu Song, Jian Wang, Qingwang Shen, Tao Kunming University of Science and Technology School of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Graduate School Kunming650500 China

ISBN: (纸本)9798350375909

Machine learning has been successfully used in the field of multi-objective antenna design, enabling the enhancement of antenna performance and optimizing efficiency. However, the prediction within an exceptionally vast parameter space imposes significant demands on machine learning algorithms. Moreover, minor adjustments in dimensions can bring about significant alterations in antenna performance, which renders simultaneous optimization for all objectives exceedingly challenging. To solve the multi-objective antenna optimization problem, a multi-objective antenna optimization method based on a preferred parameter space is proposed. Specifically, this method utilizes the KNN algorithm to preliminarily optimize the antenna and acquire a high-quality dataset. Subsequently, the sensitivity of ten selected parameters based on the electromagnetic (EM) simulation results is calculated by the XGBoost algorithm. The value of the parameter sensitivity is acquired by averaging ten calculations. The top four ranked parameters are designated as variables while the rest are fixed as constants. This approach reduces the number of parameters for subsequent optimization, thus greatly improving the subsequent prediction accuracy while ensuring the antenna performance. Finally, the variables derived from XGBoost are input into the fruit-fly optimization algorithm (FOA) to find the near-optimal solution. Hence, the task of parameter optimization under the multi-objectives of the impedance bandwidth and circular polarization characteristics can be effectively accomplished. To further validate its performance, the proposed algorithm is applied to optimize the S-band miniaturized broadband circularly polarized antenna. Compared to the results obtained by electromagnetic simulation only, the optimized results exhibit a 17.95% improvement of impedance bandwidth and a 42.86% enhancement of axial ratio bandwidth. Numerical outcomes validate that the proposed method achieves multi-objective o

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

An Efficient Antenna Optimization Method Based on a Parameter Dimensionality Reduction Approach

An Efficient Antenna Optimization Method Based on a Paramete...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Dou, Jiangling Zhao, Chenyang Song, Jian Wang, Qingwang Shen, Tao Kunming University of Science and Technology School of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Graduate School Kunming650500 China

ISBN: (纸本)9798350375909

As antenna structure grow in complexity, the problem of time-consuming in electromagnetic (EM) simulation have become more common. This problem undoubtedly brings a series of the challenges in raising the effectiveness of antenna optimization. In order to overcome the existing difficulties, an antenna optimization method based on RF-GWO method is proposed. This approach consists of three major components. Firstly, an artificial neural network (ANN) is used to build the dataset. Compared with the traditional sampling method, the data filtered by the artificial neural network (ANN) are closer to the optimization objective. Consequently, it can better responsive to the relationship between the antenna parameters and the optimization objective. Then, the Random Forest method (RF) is utilized to analyze the impact of the ten selected parameters based on the electromagnetic (EM) simulation results on the antenna performance. Random Forest Algorithm (RF) has strong interpretability, allowing for the assessment of the contribution of different parameters to the optimization objective, which can effectively reduce the number of design variables. Finally, the antenna optimization is performed utilizing the Grey Wolf Optimization (GWO) algorithm. Combined with the sensitivity analysis results, the Gray Wolf Algorithm (GWO) can effectively search for improved results in a faster manner. In order to evaluate the algorithm's performance, the proposed method is employed to optimize a multiband miniaturized microstrip antenna. The result demonstrates that substantial improvement in impedance bandwidth is achieved by the proposed method, with an approximate 29% increase compared to conventional manual optimization methods. This outcome has proved potential and effectiveness of the proposed method in practical implications of antenna optimization. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Review on Predicting the Landslide Susceptibility using Machine Learning Techniques

Review on Predicting the Landslide Susceptibility using Mach...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Abhishek Sinha Shivam Kumar Giri Himanshu Yadav Sanjeev Kumar Prasad Priya Mishra School of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Application ABES Engineering College Ghaziabad India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

This Landslide susceptibility prediction is a critical task for Alleviating the risks associated with landslide hazards, which have significant socio-economic and environmental impacts. Existing techniques face challenges related to data quality, model coherence, and generalizability across diverse geographical and climatic regions. Additionally, while advanced machine learning (ML) and deep learning (DL) models offer high accuracy, they often require significant computational resources, which limits their practical application in real-time scenarios. In this review, we aim to highlight the strengths, limitations, and potential improvements of machine learning techniques in predicting landslide susceptibility, providing a comprehensive reference for researchers and practitioners in this domain. Furthermore, the role of Explainable AI is examined to address the critical need for interpretable and transparent models in real-world applications. Hybrid ML-DL models outperform traditional methods in handling complex spatial-temporal data, with dynamic factors improving accuracy and reliability. Explainable AI enhances interpretability, while advancements and collaborations address data and generalizability challenges.

关键词： Deep learning Accuracy Reviews Explainable AI Computational modeling Predictive models Terrain factors Data models Real-time systems Reliability

来源：评论

学校读者我要写书评

暂无评论

Research on Rice Disease Identification Based on Improved ShuffleNet V2 Network 4

Research on Rice Disease Identification Based on Improved Sh...

引用

4th International Symposium on computer Technology and Information science, ISCTIS 2024

作者： Chen, Zhihuan Gu, Shenming Yu, Minghui Huang, Zhaoquan Zhejiang Ocean University Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhoushan310622 China Ningbo University School of Faculty of Electrical Engineering and Computer Science Ningbo315000 China Zhejiang Normal University College of Mathematics and Computer Science Jinhua321000 China

ISBN: (纸本)9798350354560

How to efficiently and accurately identify rice diseases plays a crucial role in rice planting and production. Deploying large convolutional neural networks in practical applications is challenging due to their complex model parameters, while lightweight networks often compromise accuracy to reduce model size. In this study, we introduce a lightweight and precise network called GM-ShuffleNet for rice disease recognition. Building upon the ShuffleNet V2 network, we integrated the Ghost module and MCA attention mechanism, adjusted the network structure and number of channels, and replaced the ReLU activation function with Mish. Through comparative experiments, the accuracy of GM-ShuffleNet algorithm proposed in this paper reaches 96.20%, which is superior to ShuffleNet V2 and other excellent lightweight networks. In addition, in terms of model complexity comparison, the number of model parameters and FLOPs decreased by 82.54% and 77.44% respectively compared with the original network. © 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

SCENERY:a lightweight block cipher based on Feistel structure

引用

Frontiers of computer science 2022年第3期16卷 193-202页

作者： Jingya FENG Lang LI Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China

In this paper,we propose a new lightweight block cipher called *** main purpose of SCENERY design applies to hardware and software *** is a 64-bit block cipher supporting 80-bit keys,and its data processing consists of 28 *** round function of SCENERY consists of 84×4 S-boxes in parallel and a 32× 32 binary matrix,and we can implement SCENERY with some basic logic *** hardware implementation of SCENERY only requires 1438 GE based on 0.18 um CMOS technology,and the software implementation of encrypting or decrypting a block takes approximately 1516 clock cycles 0118-bit microcontrollers and 364 clock cycles on 64-bit *** with other encryption algorithms,the performance of SCENERY is well balanced for both hardware and *** the security analyses,SCENERY can achieve enough security margin against known attacks,such as differential cryptanalysis,linear cryptanalysis,impossible differential cryptanalysis and related-key attacks.

关键词： lightweight block cipher feistel structure cryptanalysis 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：