检索结果-内蒙古大学图书馆

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Adithya Gokulan, S. Reddy, Mahati Varshith, M. Belwal, Meena Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376685

Optimizing Python code is essential for enhancing performance and efficiency. This project investigates the use of large pre-trained language models, specifically GPT (Generative Pre-trained Transformer), for Python code optimization. By leveraging the advanced capabilities of these models, we aim to improve traditional optimization techniques. Our approach involves preprocessing Python code, feeding it into the pre-trained model, and generating optimized code sequences. Experimental results show significant improvements in code efficiency and execution time, validating the effectiveness of our method. Additionally, we explore the practical implications, challenges, and future directions of incorporating large pre-trained models into code optimization, aiming to bridge the gap between standard optimization techniques and Python programming for a more intelligent and efficient software development practice. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Path Execution with Uncertainty 17th

Multi-Agent Path Execution with Uncertainty

引用

17th International Symposium on Combinatorial Search, SoCS 2024

作者： Liu, Yihao Tang, Xueyan Cai, Wentong Li, Jingning School of Computer Science and Engineering Nanyang Technological University Singapore NCS Pte Ltd Singapore

ISBN: (纸本)9781577358916

In real-world multi-agent applications, unexpected conditions can break the assumptions made in path planning and degrade the effectiveness of path execution. This paper studies robust and effective execution of multi-agent path plans under uncertainty. To guarantee conflict-freeness and deadlock-freeness, we define a feasibility problem to check whether the remaining portion of a path plan can be successfully executed. We prove that the problem is NP-complete and propose a feasibility test algorithm. We further develop algorithms to coordinate the agents online and have as many of them as possible moving concurrently to maximize the effectiveness of execution. We experimentally demonstrate the path execution effectiveness and computational efficiency of our algorithms. © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Crop Recommendation and Yield prediction Using Machine Learning based Approaches 5

Crop Recommendation and Yield prediction Using Machine Learn...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Padmavathi, A. Gupta, Arnab Prakash, Koppadi Bhanu Sai Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa VidyaPeetham Chennai India

ISBN: (纸本)9798350351378

India is an agricultural country, supporting a significant portion of the population. Agriculture is a source of income for millions of Indians. But due to lack of knowledge and the state's diverse climate and soil conditions often leave farmers grappling with the critical decisions of which crops to cultivate and what yields to expect. This in turn makes the farmers suffering from losses as they cultivate a crop hoping they will get a good harvest but in reality, they don't get the expected amount of production. To address these challenges prior researchers have used soil and climatic conditions data to recommend crops for a particular soil and predict its expected yield using various types of machine learning and deep learning algorithms. This paper presents a survey of previous works where deep learning and machine learning techniques are used and performs a comparative examination of some bagging and boosting machine learning techniques including random forest, gradient boost, XG boost, Ada boost, light bgm and cat boost for effective recommendation of crop and prediction of its expected yield. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

An Integrated Mobile Applications for Enhancing Women's Safety - A Comprehensive Approach 2

An Integrated Mobile Applications for Enhancing Women's Safe...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Ashwini, K. Perla, Sree Neha Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383287

Women's safety is a critical concern in today's society, necessitating innovative solutions that leverage technological advancements. This Proposed paper proposes two different applications, namely Womenify for the user especially women and Wopo for police which is combined with computer-aided dispatch (CAD) software to enhance women's safety and improve police response time. This research paper lays the groundwork for a comprehensive technical solution and presents valuable insights for creating safer communities for women. The proposed Womenify application will enable users to scan their surroundings using GPS tracking, access crime data in required areas to know whether the place is safe or not, and can also trigger emergency alerts. On the police side, the Wopo application provides patrolling schedules and real-time notifications. Further, the developed app can also be integrated with CAD software, using real-time data, ensuring easy accessibility for illiterate or unemployed women, expanding features, incorporating advanced technologies like predictive policing, and collaborating with law enforcement agencies. The effectiveness and functionality of the proposed application are evaluated through a feedback-based evaluation process which yielded positive results, indicating their effectiveness in enhancing women's safety. © 2024 IEEE.

关键词： Law enforcement

来源：评论

学校读者我要写书评

暂无评论

Adaptive Malware Detection in Android: An Active Learning and XGBoost Approach 5

Adaptive Malware Detection in Android: An Active Learning an...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Prattipati, Anshitha Saravanan, S. Veluchamy, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350376685

The growing dependence on mobile devices like smartphones has caught the consideration of cybercriminals. It creates numerous chances for intruders to infiltrate and compromise them. This current continuing challenge demands the need for more efficient and effective methods to shield Android users by recognizing various malwares. Though researchers and companies strive for a steady and consistent approach to increase the classification algorithms accuracy to categorize malicious Android applications, the search for the ultimate answer continues. Hence, we introduce an active learning-based classifier to advance the accuracy of classification in Android mal-ware. In our proposed system, we find the prediction probability of each test instance. If this probability falls below a certain threshold, we generate a similar test instance, incorporate it into the original dataset and retrain the model to get better accuracy of the classification. We evaluated the proposed system on CIC-Maldroid2020 dataset which comprises of 17,341 instances with five various android application categories consisting of Adware, Banking, SMS, Riskware, and Benign. This experiment results imply that the XGBoost (eXtreme Gradient Boosting) algorithm outperforms the various other five machine learning algorithms. Further, the active learning component of our proposed system improves accuracy from 95.34% to 98.5%. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Approximated Triple Modular Redundancy of Convolutional Neural Networks Based on Residual Quantization 17

Approximated Triple Modular Redundancy of Convolutional Neur...

引用

17th IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip, MCSoC 2024

作者： Saikawa, Yamato Tomioka, Yoichi The University of Aizu Graduate School of Computer Science and Engineering Fukushima Aizu-Wakamatsu City Japan

ISBN: (纸本)9798331530471

Triple modular redundancy (TMR) is a fault-tolerant system that detects faults and allows processing to continue by employing three identical modules. However, TMR introduces challenges such as tripled circuit area and increased power consumption. In this paper, we propose an approximated TMR (ATMR), which consists of the original module and two smaller modules achieved through quantization, specifically tailored for convolutional neural networks (CNNs). For evaluation, we conduct experiments using ResNet-20 to simulate fault recovery through linear and residual quantization when the original module fails. The results demonstrate that ATMR maintains high inference accuracy across many layers, even when employing low-bit linear or residual quantization for recovery. © 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

XAI - Empowered Ensemble Deep Learning for Deepfake Detection 15

XAI - Empowered Ensemble Deep Learning for Deepfake Detectio...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kumar, Amidela Anil Dheepthi Priyangha, S.J. Meghana, P. Dheeraj, Muppalla Aarthi, R. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

Recent technologies have evolved rapidly, allowing the creation of fake videos/images that are realistic. These artificial media pieces have provoked grave worries about the possibilities of their misuse in different areas like politics, journalism, and communication. Consequently, the demand for deepfake detection methods is increasing. In response to this growing threat, there is an increasing demand for robust deepfake detection methods. This paper proposes an ensemble-based approach for deepfake detection, leveraging deep learning techniques. Specifically, we employ a combination of CNN models, including VGG, Xception, RegularizedConvNet, and RegularizedConvDenseNet, designed for image classification. Our approach integrates predictions from multiple models to enhance detection accuracy and reliability. Specifically, the base is formed by the ensemble of RegularizedConvNet and RegularizedConvDenseNet, which cooperate to prevent the spread of deepfakes and protect digital integrity. Experimental results show that our Ensemble method achieve better detection values with accuracy of 94.5% and AUC of 0.98. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A High-Throughput and Energy-Efficient SHA-256 Design using Approximate Arithmetic

引用

IEIE Transactions on Smart Processing and Computing 2022年第5期11卷 385-391页

作者： Baik, Junhyuk Kim, Yongtae School of Computer Science and Engineering Kyungpook National University Daegu Korea Republic of

This paper presents a novel high-throughput SHA-256 design exploiting approximate computing. The 32-bit addition of the SHA-256 architecture consumes a lot of hardware resources, hence we suggest a split k-bit adder-based SHA-256 design to significantly reduce hardware resources while ensuring acceptable hash functionality. The proposed designs enhance the area, delay, and energy when employed with 28-nm CMOS technology by 8.9%, 45.7%, and 9.3% in the 2-bit configuration and 15%, 52.9%, and 11.3% in the 1-bit configuration, respectively, compared to the conventional SHA-256 design. Additionally, the proposed designs improve the area-delay product (ADP), energy-delay product (EDP), and throughput performances by at least 19.1%, 20.2%, and 18.6% with a maximum of 149.8%, 139.3%, and 112.1%, respectively, compared to the traditional design. Additionally, all of the proposed designs obtain a higher average of Avalanche effect than the traditional ones, and all the message digests generated by the proposed SHA-256 are randomly distributed. © 2022 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Age Estimation using Diverse Facial Datasets 15

Convolutional Neural Network Based Age Estimation using Dive...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chandana, Sidda Siri Vithyatharshana, N. Ghnana Prasoona, Y. Thrinayani, Yedhoti Jyotsna, C. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Determining an individual's age accurately is important in many contexts, including forensic investigations, medical diagnostics, and security applications. Traditional age estimation techniques rely on manual evaluation, which can be laborious and error prone. Convolutional neural networks (CNN) have been utilized more and more for image-based age estimation since the development of deep learning. The Objective is to create a CNN-based age estimation algorithm that can precisely estimate a person's age from facial photos. The proposed study used the UTKFace dataset and Facial Image dataset, which included 30,000+ facial images of people from various ethnic backgrounds, aged 0 to 116 and Facial pictures, a public dataset, which is a compilation of digital portraits of people. Five convolutional layers, five pooling layers, and two fully linked layers make up the deep CNN model that has been developed and trained in this project. The study's findings show how well CNN-based deep learning models may be used to determine an individual's age from face photos. For the model's training, the UTKFace dataset and Facial Images dataset supplied a wide-ranging and sizable combined dataset. The model performed better than more established age estimation techniques. © 2024 IEEE.

关键词： Age detection Convolutional Neural Networks Deep Learning Facial Images Image Analysis UTKFace

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Patterns With Deep Learning For Classification For Indian Pines 15

Hyperspectral Patterns With Deep Learning For Classification...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vishwanath, Vaishnav Sreekanth, K. Prakash, Jishnu Rajendran, Adithya Gopakumar, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350370249

The Indian Pines test site, located primarily in north-western Indiana, is renowned for its Airborne Visible InfraRed Imaging Spectrometer (AVIRIS) scene, which has been extensively studied over the years. The hyperspectral nature of this image introduces challenges related to pixel mixture complexity, creating difficulties for supervised subpixel detection and mixed-pixel classification. Despite the prevalent use of supervised approaches for this scene due to the complexity of forming an appropriate sample pool for supervised classification, there is limited research on supervised classification for this image. The study leverages cutting-edge deep learning models and transfer learning techniques, including ResNet50 (99.68% accuracy), InceptionV3 (99.55% accuracy), DenseNet121 (99.10% accuracy), and MobileNetV3 (99.94% accuracy). These models are employed for predictive analysis, highlighting their effectiveness in handling the complexities of the Indian Pines scene and showcasing their high accuracy rates in supervised image classification. This research contributes valuable insights into the application of deep learning and transfer learning methodologies, offering a promising approach to addressing the challenges presented by complex hyperspectral imagery. © 2024 IEEE.

关键词： Self-supervised learning

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：