检索结果-内蒙古大学图书馆

11th International Conference on Soft Computing and Machine Intelligence, ISCMI 2024

作者： Ala'anzy, Mohammed Alaa Mazhit, Zhanar Ala'anzy, Alaa Fadhil Algarni, Abdulmohsen Akhmedov, Ramis Bauyrzhan, Abdiyev SDU University Department of Computer Science Almaty Kazakhstan Al-Hikma University College Department of Business Administration Baghdad Iraq King Khalid University Department of Computer Science Abha61421 Saudi Arabia Eurasian National University Department of Computer and Software Engineering Astana Kazakhstan

ISBN: (纸本)9798331518127

In the realm of computer science, sorting algorithms play a pivotal role in optimising data organisation and retrieval processes across various applications. This paper presents a comprehensive examination and comparative analysis of the most commonly used sorting algorithms, focusing on their time, space complexity, and efficiency. By scrutinising both traditional methods like bubble sort, selection sort, and insertion sort, and advanced techniques such as merge sort, quick sort, heap sort, and radix sort, this study sheds light on the performance metrics of each algorithm. Through meticulous implementation and evaluation across datasets of varying magnitudes, ranging from 100 to 100,000 integers, the research provides valuable insights into the strengths and weaknesses of these sorting techniques. The outcomes of this study offer practical guidance for professionals in data engineering and software development, aiding in the informed selection of sorting algorithms tailored to specific application needs. Utilising a rigorous experimental setup with the pseudocode, the study meticulously measures the time complexity of each algorithm, recording CPU time in seconds. The analysis reveals significant performance differentials among the algorithms, showcasing the efficiency of quick sort, shell sort, and heap sort on small datasets, while highlighting the scalability of merge sort, radix sort, and quick sort as dataset sizes increase. This research contributes to the advancement of algorithmic knowledge and provides a valuable resource for practitioners seeking to optimise sorting processes in their computational tasks. © 2024 IEEE.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

DBT-UNETR: Double Branch Transformer with Cross Fusion for 3D Medical Image Segmentation

DBT-UNETR: Double Branch Transformer with Cross Fusion for 3...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Tao, Haojie Mao, Keming Zhao, Yuhai Northeastern University College of Software Shenyang China Northeastern University College of Computer Science and Engineering Shenyang China

ISBN: (纸本)9781665468190

Medical image segmentation is significant for diagnosis and prognosis. Inspired by the success of Transformer for Natural Language Processing, this paper presents DBT-UNETR, a novel double branch Transformer architecture with cross fusion for multi-scale feature representation, which enhances the model performance of 3D medical image segmentation. The DBT-UNETR consists of a single scale Transformer and a multiple scale Transformer to capture informative feature. These two branch features are cross fused and then they are combined together. Finally, these feature representations are sent to decoders via skip connection for final segmentation. Moreover, in order to further improve the model performance, an Early Fusion module is designed. Comprehensive experiments are conducted on public available dataset, Multi-Atlas Labeling Beyond The Cranial Vault (BTCV), and it demonstrates the proposed model outperforms the comparative baseline methods. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

LLaMA-LoRA Neural Prompt engineering:A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains

引用

Data Intelligence 2024年第2期6卷 375-408页

作者： Songlin Chen Weicheng Wang Xiaoliang Chen Peng lu Zaiyan Yang Yajun Du School of Computer and Software Engineering Xihua Universitychengdu 610039P.R.china Department of Computer Science and Operations Research University of MontrealMontrealQC H3C3J7Canada College of Artificial intelligence Beijing University of Posts and TelecommunicationsBeijing100876China

The exption of Chinese natural language processing(NLP)has stimulated research in the broader NLP ***,existing large language models have limitations in comprehending and reasoning in *** paper addresses these limitations by enhancing Chinese language models comprehension and reasoning capabilities while minimizing resource *** propose LLaMA-LoRA,a neural prompt engineering framework that builds upon the LLaMA-13B model and incorporates the Low-Rank Adaptation(LoRA)of Large Language Models technique for ***-of-Thought(CoT)are crucial for generating intermediate reasoning chains in language models,but their effectiveness can be limited by isolated language *** reasoning resulting from conventional prompts negatively impacts model *** prompts are introduced to encourage reasoning chain generation and accurate answer *** the model with an extensive corpus of Chinese CoT data enhances its comprehension and reasoning *** LLaMA-LoRA model demonstrates exceptional performance across numerous Chinese language tasks,surpassing benchmark performance achieved by related language models such as GPT-3.5,Chat-GLM,and OpenAssistant,delivering accurate,comprehensive,and professional *** availability of our open-source model code facilitates further research in the field of Chinese text logical reasoning thinking chains.

关键词： Chinese natural language processing Neural prompt engineering Large language models Low-Rank adaptation Chain-of-thought

来源：评论

学校读者我要写书评

暂无评论

Currency Portfolio using Combination of Assets and Cryptocurrency based on LSTM-TLS 2022

Currency Portfolio using Combination of Assets and Cryptocur...

引用

13th International Conference on E-Business, Management and Economics, ICEME 2022

作者： Guo, Liangyuan Deng, Hewen He, Wenyue College of Mathematics and Statistics Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9781450396394

Virtual currency has been greeted with an avalanche of attention these days. In this case, allocate investments into traditional assets and virtual currency properly seems very important. In this paper, we select gold and bitcoin as our research objects, and select a series of representative indicators in the financial field. After data preprocessing, XGBoost algorithm is used to sort the importance of indicators, thus eliminating some unimportant indicators. Next, LSTM is used to predict the price of gold and bitcoin respectively. Therefore, the portfolio can be built based on it. In reality, trades often come with transaction costs. So we improve the Mean-Variance model considering the transaction costs, so as to get the initial portfolio strategy. On this basis, taking investment potential into account, we propose Traffic Light Signal(TLS) model, and successfully increasing the gross profit rate from 11.582% to 13.614%. Finally, we prove our portfolio model earns the highest returns by comparing it to other traditional portfolio models in terms of metrics Cumulative Yield, Annual Yield, and Max Drawdown Ratio. © 2022 ACM.

关键词： Bitcoin

来源：评论

学校读者我要写书评

暂无评论

An Improved Bi-LSTM EEG Emotion Recognition Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第3期7卷 623-639页

作者： Ma, Shuai Cui, Jianfeng Chen, Chin-Ling Xiao, Weidong Liu, Lijuan School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China College of Software Engineering Xiamen University of Technology Xiamen361024 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

EEG emotion signal feature extraction is computationally intensive and the classification accuracy of the model is not high. Therefore, it can seriously affect the overall performance of classification algorithms. In order to better apply deep learning methods to EEG emotion recognition classification. To address the above problems, this paper uses the Fast Fourier Transformation algorithm to extract richer and more complete multi-channel feature information in feature extraction. At the same time, for the problem of low classification accuracy, an improved Bi-LSTM classification model is proposed. Finally, the model proposed in this paper is verified by 32-channel EEG signal data. The experimental results show that the classification method proposed improves the accuracy of Arousal to 93.35% and Valence to 93.09%. Compared with other models, the improved Bi-LSTM model has an excellent performance in EEG emotion recognition. Meanwhile, this paper explores the brain emotion mechanism by the accuracy of the improved model for different brain region channels, showing that the brain regions with the highest emotional relevance are the parietal and frontal lobes in the brain. © 2022 Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Intelligent Detection and Classification of Rice Plant Diseases Based on Leaf Image Dataset

引用

computer Systems science & engineering 2023年第11期47卷 1385-1413页

作者： Fawad Ali Shah Habib Akbar Abid Ali Parveen Amna Maha Aljohani Eman A.Aldhahri Harun Jamil Department of IT The University of HaripurHaripur22620Pakistan Department of Computer Science University of Engineering and TechnologyTaxila47080Pakistan Department of Computer Science GANK(S)DC KTS HaripurHaripur22620Pakistan College of Pharmacy Gachon University Medical CampusNo.191HambakmoeroYeonsu-guIncheon21936Korea Software Engineering Department College of Computer Science and EngineeringUniversity of JeddahJeddah23218Saudi Arabia College of Computer Sciences and Engineering Department of Computer Science and Artificial IntelligenceUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering Jeju National UniversityJejusi63243Korea

The detection of rice leaf disease is significant because,as an agricultural and rice exporter country,Pakistan needs to advance in production and lower the risk of *** this rapid globalization era,information technology has increased.A sensing system is mandatory to detect rice diseases using Artificial Intelligence(AI).It is being adopted in all medical and plant sciences fields to access and measure the accuracy of results and detection while lowering the risk of *** Neural Network(DNN)is a novel technique that will help detect disease present on a rice leave because DNN is also considered a state-of-the-art solution in image detection using sensing *** in this paper,the adoption of the mixed-method approach Deep Convolutional Neural Network(Deep CNN)has assisted the research in increasing the effectiveness of the proposed *** CNN is used for image recognition and is a class of deep-learning neural *** is popular and mostly used in the field of image recognition.A dataset of images with three main leaf diseases is selected for training and testing the proposed *** the image acquisition and preprocessing process,the Deep CNN model was trained to detect and classify three rice diseases(Brown spot,bacterial blight,and blast disease).The proposed model achieved 98.3%accuracy in comparison with similar state-of-the-art techniques.

关键词： Rice plant disease detection convolution neural network image classification biological classification

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Sequential Transfer Optimization: Benchmark Problems and Preliminary Results 13

Multiobjective Sequential Transfer Optimization: Benchmark P...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Xue, Xiaoming Feng, Liang Yang, Cuie Liu, Songbai Song, Linqi Tan, Kay Chen City University of Hong Kong Department of Computer Science Hong Kong College of Computer Science Chongqing University Chongqing China Northeastern University State Key Lab of Synthetic Automation for Process Industries Shenyang China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350308365

In cases of frequent problem-solving of multiobjective optimization tasks from a domain due to changing conditions or problem features, a growing number of individual tasks will be solved and stored in a database, providing an opportunity for a target task at hand to achieve better optimization performance through knowledge transfer from the previously-solved tasks, which is also known as sequential transfer optimization. Despite a variety of transfer algorithms that have been developed over the years, the research on the design of benchmark problems for evaluating such algorithms received far less attention. Oftentimes, the source and target tasks in existing test problems are manually assembled or extended from specific practical problems, limiting their ability to represent the diverse yet complex source-target similarity relationships in real-world problems. In light of this, we propose design methods to generate multiobjective sequential transfer optimization problems (MSTOPs) systematically in this work, wherein the Pareto manifolds of individual tasks and the manifold-based similarity between the tasks can be customized with ease, enabling a broad spectrum of representation of the diverse similarity relationships between the source-target Pareto manifolds of MSTOPs. Lastly, a benchmark suite with 12 test problems is developed using the proposed methods, which would serve as an arena for electing superior multiobjective sequential transfer optimization algorithms. The source code is available at https://***/XmingHsueh/MSTOP. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Brain Tumor Detection Using Transfer Learning with Fine-Tuned Efficientnet-B3 Blocks and Graph-Based Spatial Attention Capsule Networks 21

Enhanced Brain Tumor Detection Using Transfer Learning with ...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Aggrey, Esther Stacy E.B Zhen, Qin Kodjiku, Seth Larweh Fiasem, Delali Linda Sey, Collins Ejiyi, Chukwuebuka Joseph Ntia, Nsikakabasi Williamson School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Technology Zhejiang Gongshang University Hangzhou China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (纸本)9798331519254

Brain tumors are critical medical conditions that require timely and accurate diagnosis to improve survival outcomes. This research proposes a cutting-edge framework for brain tumor classification, combining fine-tuned EfficientNet-B3 blocks with graph-based spatial attention capsule networks. By addressing challenges such as limited data availability, overfitting, and the complex nature of tumor structures, the framework employs partial transfer learning, advanced feature extraction, and attention mechanisms to effectively model spatial relationships in MRI images. Evaluated on a dataset of 3,064 contrast-enhanced brain MRI images, the model demonstrated exceptional performance, achieving 99.85% classification accuracy and notable improvements in precision, recall, and F1 scores for glioma, meningioma, and pituitary tumours. The use of advanced data augmentation techniques significantly improved the model's ability to generalize, while its computational efficiency makes it well-suited for clinical diagnostic applications. © 2024 IEEE.

关键词： Dynamic contrast enhanced MRI

来源：评论

学校读者我要写书评

暂无评论

Slice-Level Label Attention with Global-Guided Attention Regularization for Multi-Label Classification in Knee MRI Sequences

Slice-Level Label Attention with Global-Guided Attention Reg...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Yang, Jingzhi Shen, Hua Liu, Ziyu Wu, Weilong Wu, Ji Ni, Ming Yuan, Huishu Fu, Xiangling Li, Miao National Pilot Software Engineering School Bupt School of Computer Science Beijing China Tsinghua University College of Ai Department of Electronic Engineering Beijing China Peking University Third Hospital Beijing China

ISBN: (纸本)9798350362480

Magnetic Resonance Imaging (MRI) is crucial for diagnosing various knee-related diseases, and developing automatic diagnostic models based on knee MRI data is highly valuable. However, this task presents significant challenges due to the need to manage MRI data with multiple sequences and numerous images, where different diseases are often associated with specific images within certain sequences. To address these challenges, we propose a multi-label classification framework designed to effectively process MRI data and handle a large-scale label space encompassing hundreds of disease categories. Our approach introduces a Slice-Level Label Attention mechanism, which enables the model to learn the alignment between labels and images within sequences, thereby enhancing both performance and interpretability. Additionally, we present a Global-Guided Attention Regularization mechanism that further improves the consistency and robustness of the Slice-Level Label Attention results. We validate our framework on a large-scale MRI dataset involving multi-label classification across hundreds of fine-grained disease categories. Experimental results demonstrate that our method not only achieves superior performance but also provides more robust and consistent interpretability. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Integrity Estimation of Twitter Based Event Recognition Using Scrutiny of Analyzed Data 2

Integrity Estimation of Twitter Based Event Recognition Usin...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Siva Rama Lingham, N. Parameswari, M. Karthick, P. Priya, T. Subha Rathi Rajesh, G. Jagannathan, J. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering Chennai India School of Engineering and Technology Jeppiaar University Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Software and Systems Engineering Vellore Katpadi632014 India

ISBN: (纸本)9798350328202

Twitter has been observed to be one of the essential data resources for dependable event accreditation. In any case, Twitter-based event affirmation structures can't guarantee assessment concerning their attestation results. Talk statement has been locked in starting late to enable liberal event Recognition. This problem is not yet evident in light of the assumption that most people tend to think that they have a specific limit to the data on Twitter that have frames based on events based on Twitter. Current appraisals see new pieces by seeing and looking at the significant psychological aspects of hitting the details on Twitter. No matter, the scale of the visual cues can be well established, with the intention that it is essential to design an integrated Twitter experiment with another set of extensible data resources to rectify this problem. The problem is the processes by which you should wholeheartedly investigate all converted data because it has different data structures, transfer times, etc. This issue of address, the paper proposes a framework for evaluating the use of Twitter-based events and examines two types of data resources for the reliability of impact testing. Our framework uses the resultant of the request obtaining by various events and relevant to the articles on it. This paper has improved the cleaning test with the proposed process how the integrity estimation of twitter based event can be recognized with the help of group of analyzed data. The evaluation indicates that the proposed system provides visible high-level testing events and a variety of low-level testing events. © 2024 IEEE.

关键词： Impact testing

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：