检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Anand, Deva Gowr, P. Sheela Logesh, S. Anand, S.M. Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350338607

Alzheimer's disease is a pressing healthcare concern worldwide, highlighting the importance of early and accurate detection. Deep learning models, particularly those utilizing transfer learning, have shown promise for AD classification. This research study explores the effectiveness of transfer learning in training models based on deep learning for the classification of Alzheimer's condition. We trained several transfer models using DenseNet121, InceptionV3, Xception, and ResNet101. Based on performance evaluation, InceptionV3 was selected as the base model, outperforming in comparison to the accuracy of the other models. To enhance the accuracy of the InceptionV3 base model, we added capacity, tuned hyperparameters using Keras tuner, and utilized data augmentation techniques. The final model was trained on the Kaggle Alzheimer's Dataset, consisting of 4 classes of images, and achieving an AUC value of 87%. Our research demonstrates that transfer learning and other data augmentation approaches are useful in improving the accuracy of deep learning models for the categorization of Alzheimer's condition. This research has practical implications for improving public health outcomes, facilitating timely intervention and effective treatment. It contributes to the development of more accurate diagnostic tools for AD and can help address the challenges associated with this disease. © 2023 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models 3

Hyperspectral Images for Crop Prediction using Machine and D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Technique Based Automated Feature Analysis of Gene Expression Data

Reinforcement Learning Technique Based Automated Feature Ana...

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Jayakrishnan, R. Meera, S. Vels Institute of Science Technology and Advanced Studies Computer Science & Engineering Tamil Nadu Chennai India Vels Institute of Science Technology and Advanced Studies Department of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350333244

Immunohistochemistry and reverse transcription polymerase chain reaction, it is feasible to find molecular markers that are specific to cancer;nevertheless, there are no pathognomonic molecular markers available for the vast majority of solid tumors at this time. In this paper, we develop a Reinforcement learning Technique based automated feature analysis of gene expression data. This provides support for the idea that, on average, all the validation findings and training data from each epoch were utilized. This proposed method helps to acquiring knowledge at a more leisurely pace is, in the end, what makes episodic deep RL possible as a potential choice for students to pursue. To put it another way, the slow but steady accumulation of knowledge paves the path for the rapid extension of one existing body of information. The proposed methods provide 98 percent of the accuracy result than existing ANN and DNN. The proposed framework outperformed existing methods in terms of increase accuracy rate and reduced execution time than other methods © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Approach to Online Planning 41

A Bayesian Approach to Online Planning

引用

41st International Conference on Machine Learning, ICML 2024

作者： Greshler, Nir Eli, David Ben Rabinovitz, Carmel Guetta, Gabi Gispan, Liran Zohar, Guy Tamar, Aviv General Motors Advanced Technical Center Israel Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel

The combination of Monte Carlo tree search and neural networks has revolutionized online planning. As neural network approximations are often imperfect, we ask whether uncertainty estimates about the network outputs could be used to improve planning. We develop a Bayesian planning approach that facilitates such uncertainty quantification, inspired by classical ideas from the meta-reasoning literature. We propose a Thompson sampling based algorithm for searching the tree of possible actions, for which we prove the first (to our knowledge) finite time Bayesian regret bound, and propose an efficient implementation for a restricted family of posterior distributions. In addition we propose a variant of the Bayes-UCB method applied to trees. Empirically, we demonstrate that on the ProcGen Maze and Leaper environments, when the uncertainty estimates are accurate but the neural network output is inaccurate, our Bayesian approach searches the tree much more effectively. In addition, we investigate whether popular uncertainty estimation methods are accurate enough to yield significant gains in planning. Our code is available at: https://***/nirgreshler/bayesian-online-planning. Copyright 2024 by the author(s)

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Application of Text Mining in Cybersecurity

引用

Recent Advances in computer Science and Communications 2023年第3期16卷 80-93页

作者： Barik, Kousik Misra, Sanjay Konar, Karabi Kaushik, Manju Ahuja, Ravin Department of Computer Science JIS Institute of Advanced Studies & Research JIS University Kolkata India Department of Computer Science and Communication Ostfold University Halden Norway Department of Computer Engineering Amity University Jaipur India Center of ICT/ICE Research CUCRID Covenant University Ota Nigeria

Aims: This paper aims to conduct a Systematic Literature Review (SLR) of the relative applications of text mining in cybersecurity. Objectives: The amount of data generated worldwide has been attributed to a change in different activities associated with cyber security, and demands a high automation level. Methods: In the cyber security domain, text mining is an alternative for improving the usefulness of various activities that entail unstructured data. This study searched databases of 516 papers from 2015 to 2021. Out of which, 75 papers are selected for analysis. A detailed evaluation of the selected studies employs sources, techniques, and information extraction on cyber security applications. Results: This study extends gaps for future studies, such as text processing, availability of datasets, innovative methods, and intelligent text mining. Conclusion: This study concludes with interesting findings of employing text mining in cybersecurity applications;the researchers need to exploit all related techniques and algorithms in text mining to detect and protect the organization from Cybersecurity applications. © 2023 Bentham Science Publishers.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of DBST, a lightweight block cipher

引用

Frontiers of computer Science 2024年第4期18卷 219-221页

作者： Sadegh SADEGHI Nasour BAGHERI Department of Mathematics Institute for Advanced Studies in Basic Sciences(IASBS)Zanjan 45137-66731Iran Research Center for Basic Sciences and Modern Technologies(RBST) Institute for Advanced Studies in Basic Sciences(IASBS)Zanjan 45137-66731Iran Electrical Engineering Department Shahid Rajaee Teacher Training UniversityTehran 16788-15811Iran School of Computer Science(SCS) Institute for Research in Fundamental Sciences(IPM)Tehran 19395-5531Iran

1 Introduction Conventional cryptographic primitives are not suitable for resource-constrained ***,numerous lightweight primitives have been proposed over the past decade,specifically tailored for such ***,such ciphers would not be used in a real-world application unless they were thoroughly tested for security against existing *** this direction,DBST[1]cipher has been recently proposed by Yan et *** balance security,cost,and efficiency,DBST has implemented a novel 4-branch generalized Feistel variant *** this structure,a 2-branch XOR operation has been incorporated in the middle section,establishing interconnections between all *** the other hand,by leveraging the bit-slice technique and subkeys,the algorithm introduces an innovative approach to constructing a dynamic S-box *** designers of DBST cipher have extensively investigated its resistance to known attacks such as linear and differential cryptanalysis,as well as impossible differential cryptanalysis,among *** them,the objective of differential cryptanalysis[2]is to identify high-probability characteristics in the plaintext that are transmitted to the ciphertext,known as distinguishers.

关键词： structure. primitive branch

来源：评论

学校读者我要写书评

暂无评论

Low-Power Convolutional Neural Network Accelerator on FPGA 5

Low-Power Convolutional Neural Network Accelerator on FPGA

引用

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Khalil, Kasem Kumar, Ashok Bayoumi, Magdy University of Mississippi Department of Electrical and Computer Engineering Mississippi United States Assiut University Department of Electrical Engineering Egypt University of Louisiana at Lafayette The Center for Advanced Computer Studies LA United States University of Louisiana at Lafayette Department of Electrical and Computer Engineering LA United States

ISBN: (纸本)9798350332674

Convolutional Neural Network (CNN) accelerator is highly beneficial for mobile and resource-constrained devices. One of the research challenges is to design a power-economic accelerator. This paper proposes a CNN accelerator with low power consumption and acceptable performance. The proposed method uses pipelining between the used kernels for the convolution process and a shared multiplication and accumulation block. The available kernels work consequently while each one performs a different operation in sequence. The proposed method utilizes a series of operations between the kernels and memory weights to speed up the convolution process. The proposed accelerator is implemented using VHDL and FPGA Altera Arria 10 GX. The results show that the proposed method achieves 26.37 GOPS/W of energy consumption, which is lower than the existing method, with acceptable resource usage and performance. The proposed method is ideally suited for small and constrained devices. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Skin Lesion Image Using FCM with Color Transformation Saliency 1

Segmentation of Skin Lesion Image Using FCM with Color Trans...

引用

1st IEEE International Conference on Computing and Data Science, ICCDS 2024

作者： Bavya, S. Saravana Kumar, V. Kavitha, M. Anantha SivaPrakasam, S. Vels Institute of Science Technology & Advanced Studies Department of Computer Science & Engineering Chennai India Sreenidhi Institute of Science and Technology Department of Information Technology Hyderabad India S A Engineering College Department of Computer Science & Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science & Technology Chennai India

ISBN: (数字)9798350365337

ISBN: (纸本)9798350365337

In the majority of Western nations including America, Australia and Europe, skin cancer is badly-behaved. Skin concealing, inadequacy of Sun-lights, climate, age, and inherited are major risk factors. Early identification of skin cancer and proceed the treatment can avoid death. The abnormal skin region determines where the skin diseases had been found. Various sorts of skin ailments be existent currently. Melanoma is the sort of skin threat which has grows the greater part of mortality rate. The timely identification and intercession of melanoma include myriad changes of fix. Melanoma has been recognized by shape, size, concealing and outward of the skin injury. This paper demonstration about the traditional clustering technique in particular Fuzzy Clustering technique is acted in these skin lesion pictures. This strategy is segmenting this melanoma from these dermoscopic images effectively. The presentation of this strategy is assessed as far as pixel grouped and time complexity. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence in computer Science to Manage Stress and Anxiety: Applications and Innovations 2

Leveraging Artificial Intelligence in Computer Science to Ma...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Mittal, Ketan Shikha Sharma, Ronak Attri, Jeevesh Kumar Taneja, Kritika Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Faridabad India Department of electrical and electronics engineering Manav Rachna International Institute of Research and Studies Faridabad India

ISBN: (纸本)9798331541217

This study explores the effectiveness, ethical considerations, and demographic influences of AI-based interventions in managing stress and anxiety. AI technologies, including Machine Learning, Natural Language Processing (NLP), and Biometric Monitoring, have shown promising results in reducing stress and anxiety across diverse populations. Machine Learning algorithms excel in predictive analytics, enabling early detection and intervention, while NLP tools offer real-time cognitive-behavioural therapy (CBT) and emotional support through AI-powered chatbots. Biometric Monitoring provides objective physiological data, further enhancing the precision of stress management strategies. However, the effectiveness of these interventions is influenced by demographic variables such as age, gender, socio-economic status, and cultural background, with younger, tech-savvy users and those of higher socio-economic status showing greater engagement and benefit. Also, the mobile application named "sahayya" has been discussed along with its merits. Discussing how technology can be put to better use. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Ultra-low-defect homoepitaxial micro-LEDs with enhanced efficiency and monochromaticity for high-PPI AR/MR displays

引用

PhotoniX 2024年第1期5卷 335-356页

作者： Yibo Liu Guobin Wang Feng Feng Mengyuan Zhanghu Zhengnan Yuan Zichun Li Ke Xu Hoi Sing Kwok Zhaojun Liu Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong Kong SARChina Department of Electrical and Electronic Engineering Southern University of Science and TechnologyShenzhenChina Suzhou Institute of Nano-Tech and Nano-Bionics Chinese Academy of SciencesJiangsu Institute of Advanced SemiconductorsSuzhouChina

The issue of brightness in strong ambient light conditions is one of the critical obstacles restricting the application of augmented reality(AR)and mixed reality(MR).Gallium nitride(GaN)-based micro-LEDs,renowned for their exceptional brightness and stability,are considered the foremost contenders for AR ***,conventional heteroepitaxial growth micro-LED devices confront formidable challenges,including substantial wavelength shifts and efficiency *** this paper,we firstly demonstrated the high-quality homoepitaxial GaN-on-GaN micro-LEDs microdisplay,and thoroughly analyzed the possible benefits for free-standing GaN substrate from the material-level characterization to device optoelectronic properties and microdisplay application compared with sapphire *** GaN-on-GaN structure exhibits a superior crystal quality with ultra-low threading dislocation densities(TDDs)of~105 cm^(-2),which is three orders of magnitude lower than that of *** an in-depth size-dependent optoelectronic analysis of blue/green emission GaN-on-GaN/Sapphire micro-LEDs from 100×100 shrink to 3×3μm^2),real that a lower forward voltage and series resistance,a consistent emission wavelength(1.21 nm for blue and 4.79 nm for green@500 A/cm2),coupled with a notable reduction in efficiency droop ratios(15.6%for blue and 28.5%for green@500 A/cm^(2))and expanded color gamut(103.57%over Rec.2020)within GaN-on-GaN 10μm *** but not least,the GaN-on-GaN micro-display with 3000 pixels per inch(PPI)showcased enhanced display uniformity and higher luminance in comparison to its GaN-on-Sapphire counterpart,demonstrating significant potentials for high-brightness AR/MR applications under strong ambient light.

关键词： optoelectronic ambient epitaxial

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：