检索结果-内蒙古大学图书馆

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Tyagi, Anshuman Singh, Pawan Dev, Harsh Department of Computer Science and Engineering Amity School of Engineering and Technology Lucknow Amity University Uttar Pradesh Lucknow India Department of Computer Science and Engineering Pranveer Singh Institute of Technology Uttar Pradesh Kanpur India

ISBN: (纸本)9789819778614

Human Activity Recognition (HAR) is an AI-based technique aimed at identifying and labeling human activities. It gathers activity data from sources like wearable sensors and smart devices. Essentially, it categorizes human activities based on interactions, movements, and actions. Currently, it finds widespread application across various domains, leading to continuous research efforts for practical improvements. The present study revolves around HAR, a hybrid DM-CNN model, where the activities of humans are recognized by four phases including preprocessing, segmentation, feature extraction, and recognition. Here, the hybrid DM-CNN model uses a specific set of extracted features for enhanced training and they are MTH, IGBP and hierarchy of skeleton. Most importantly, the hybrid DM-CNN model provides excellent results on human activity recognition through the development of the Modified Osprey Optimization (MOO) algorithm for fine-tuning the DM and CNN models. The specificity of the proposed model is 95%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Human form models

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

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

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

Code Optimization for Python using Large Pre-Trained Model 5

Code Optimization for Python using Large Pre-Trained Model

引用

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

Infield disease detection in citrus plants: integrating semantic segmentation and dynamic deep learning object detection model for enhanced agricultural yield

引用

Neural Computing and Applications 2024年第35期36卷 22485-22510页

作者： Rani, N. Shobha Krishna, Arun Sri Sunag, M. Sangamesha, M.A. Pushpa, B.R. University Bengaluru India Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru India Department of Chemistry The National Institute of Engineering Mysuru India

Simultaneous and dynamic detection of diseases from infield images of citrus plants is the primary objective of this investigation. Refraining from discarding the disease-related issues would reduce agricultural yield and production, resulting in significant crop loss and economic instability. computer Vision offers an inexpensive and efficient solution for detecting and predicting multiple diseases from infield images of citrus plants in various stages of plant growth. This study aims to perform simultaneous detection and prediction of cankers, mites, and nutritional deficiencies from infield images of citrus plants. For this purpose, over 4914 samples are annotated that are obtained from 441 image samples collected from orchards of citrus plants. Initially, the input image is subject to preprocessing followed by segmentation of prominent leaf regions and disease prediction. Contributions investigated in this work are two-fold: a deep semantic segmentation model named Dynamic U-Net is employed to extract prominent regions of interest, and a dynamic, lightweight object detection deep learning model for predicting diseases. From experimental outcomes, the segmentation efficiency is found to be 89.07% foreground accuracy, 0.7881 of IoU, and 0.9188 of the Dice coefficient. The object detection performance is quantified using the mapped metric, resulting in 0.85, 0.71, 0.64, and 0.27 efficiency concerning plant diseases, cankers, mites, and nutritional deficiency. As per the findings, the proposed approach is an effective solution to perform automated detection and prediction from infield images of citrus plants. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Automatic Assessment of Quadratic Equation Solutions Using MathBERT and RoBERTa Embeddings 15

Automatic Assessment of Quadratic Equation Solutions Using M...

引用

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

作者： Rao, Subhiksha Suresh Mishra, Sahil Akhilesh, S. Balakrishnan, Roshni M. Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350370249

This project aims to create a machine learning classification system that classifies solutions to quadratic equations into three different groups: 'Incorrect,' 'Partially Correct,' and 'Correct.' MathBERT and RoBERTa embeddings are utilized in this system. A multi-class classification technique is used by the system, with an emphasis on feature engineering, data preparation, and model selection. To improve model performance, methods like Principal Component Analysis (PCA), LIME (Local Interpretable Model-Agnostic Explanations), and ensemble meta models with Boosting, Voting, and Stacking are used. The efficacy of many classification models in correctly classifying quadratic solutions is examined in this work. To evaluate the performance of the model, evaluation measures including F1-score, accuracy, precision, and recall are used. The results show that MathBERT embeddings outperform RoBERTa embeddings. Ensemble models, especially those that include SVM and MLP classifiers, achieve the best performance, with the stacking approach yielding an accuracy of approximately 65%. This model accurately classifies solutions into the correct categories, demonstrating the potential for practical applications in mathematics education. © 2024 IEEE.

关键词： Automated Evaluation Classification Educational Technology Machine Learning MathBERT Quadratic Equations RoBERTa Solution Accuracy

来源：评论

学校读者我要写书评

暂无评论

Securing Neural Network-Based Personalized Medicine for Advanced Liver Cancer Detection in Healthcare

Securing Neural Network-Based Personalized Medicine for Adva...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Kasturi, Salvadi Singh, Jagendra Agarwal, Mohit Kumar, Ashwini Mishra, Komal Sharma, Yogita Cvr College of Engineering Department of Computer Science Engineering Vastunagar India School of Computer Science Engineering & Technology Bennett University Greater Noida India Compucom Institute of Technology & Management Department of Computer Science Engineering Jaipur India Chandigarh University Department of University Institute of Computing Chandigarh India School of Management and Commerce Manav Rachna University Faridabad India

ISBN: (纸本)9798350382693

This research is aimed at discussing the critical meeting point of healthcare and artificial intelligence, including the need to protect the required treatment solution. Investigation into the utility of various deep learning techniques such as VGG 16, VGG 19, Convolutional Neural Networks (CNN), and Recurrent Neural Network (RNN) for the prediction of liver cancer stages and their respective treatments has been completed. The generation of 2340 of medical images from multiple sources, including the internet and records of hospitals, as a dataset was performed in a secure cloud. The security measures have allowed only authorized personnel to access the data and ensured the privacy and secrecy of data. The created dataset was then separated into two parts: training, which consisted of training the model on 70% of images, and testing, which implied that 30% of images were used to test the generated model. For each of the run models, performance evaluation measurements such as accuracy, precision, recall, and F1 score were calculated. The results have shown the highest efficiency of VGG 19 model, which resulted in 98.44% of accuracy. For the generated model, a fictitious ROC curve and specificity rate were also provided to showcase the discrimination abilities of each of the submitted models. The results show that the utility of neural network-based personalized medicine is beneficial for the further progression of the early prediction stage of liver cancer and its treatment. The result showed that the proposed models has successfully contributed to the field of healthcare informatics and further opportunities for artificial intelligence application to increase patient outcomes in the form of personalized medicine that may be performed. © 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

News Topic Categorization on Telugu Dataset Using Deep Learning Models 15

News Topic Categorization on Telugu Dataset Using Deep Learn...

引用

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

作者： Deepika, M. Sree Subramanyam, N. Sri Lekhya Pranav, P. Shiva Reddy, Pulaputhuru Subramanyam Venugopalan, Manju Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

The digital age has ushered in an unprecedented era of data proliferation across various domains, with the news sector being no exception, accumulating vast amounts of information, often measured in petabytes. Manual classification of such voluminous data is impractical, particularly considering the complexity of languages like Telugu, belonging to the Dravidian family, renowned for its intricate morphological characteristics. Natural Language Processing (NLP) offers a promising avenue for tackling textual data, leveraging diverse word embedding techniques to enrich model representations. Notably, prior research in this domain has predominantly relied on count-based algorithms for word embeddings. However, in this investigation, we explore alternative approaches, specifically custom-built Deep Learning models integrated with word embeddings, to optimize the classification of newspaper articles. Through a series of methodical experiments, we endeavor to identify the most effective model architecture for this task, aiming to enhance the accuracy and efficiency of article categorization in Telugu. The proposed model has experimented with word embeddings such as FastText and GloVE with deep learning models like LSTM, Bi-LSTM, CNN. Among the models experimented, FastText in combination with CNN have reported the highest F1-Score of 0.93. © 2024 IEEE.

关键词： Categorization Deep Learning News data Word Embedding

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

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：