检索结果-内蒙古大学图书馆

Key-based data augmentation with curriculum learning for few-shot code search

Neural Computing and applications 2025年第3期37卷 1475-1490页

作者： Zhang, Fan Peng, Manman Wu, Qiang Shen, Yuanyuan College of Computer Science and Electronic Engineering Hunan University Lushan South Road Hunan Province Changsha410082 China Hunan Provincial Key Laboratory of Blockchain Infrastructure and Application Hunan University Lushan South Road Hunan Province Changsha410082 China

Given a natural language query, code search aims to find matching code snippets from a codebase. Recent works are mainly designed for mainstream programming languages with large amounts of training data. However, code search is also needed for domain-specific programming languages, which have fewer training data, and it is a heavy burden to label a large amount of training data for each domain-specific language. To this end, we propose DAFCS, a data augmentation framework with curriculum learning for few-shot code search tasks. Specifically, we first collect unlabeled codes in the same programming language as the original codes, which can provide additional semantic signals to the original codes. Second, we employ an occlusion-based method to identify key statements in code fragments. Third, we design a set of new key-based augmentation operations for the original codes. Finally, we use curriculum learning to reasonably schedule augmented samples for training well-performing models. We conduct retrieval experiments on a public dataset and find that DAFCS surpasses state-of-the-art methods by 5.42% and 5.05% in the Solidity and SQL domain-specific languages, respectively. Our study shows that DAFCS, which adopts data augmentation and curriculum learning strategies, can achieve promising performance in few-shot code search tasks. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Code search Curriculum learning Data augmentation Few shot learning

来源：评论

学校读者我要写书评

暂无评论

Research on central arterial pressure estimation algorithm based on clustering 2022

Research on central arterial pressure estimation algorithm b...

引用

2nd International Conference on Bioinformatics and Intelligent Computing, BIC 2022

作者： Zhang, Jiahao Ge, Hui Computer Application China Aerospace Academy of Systems Science and Engineering Beijing China

ISBN: (纸本)9781450395755

Central arterial pressure (CAP) plays an important role in the detection and diagnosis of cardiovascular diseases. Although the traditional universal transfer function method has good accuracy in measuring central arterial pressure, it does not take into account the characteristic information contained in pulse wave shape, and the accuracy needs to be further ***, a clustering based estimation algorithm for central arterial pressure is proposed. First of all, 5 layer Symlets wavelet and hard-soft compromised threshold was used to remove high-frequency noise of the data set. Secondly, in order to extract the characteristics of pulse waves themselves, k-means++ clustering was carried out for pulse waves in the training set. In order to reduce the over-fitting phenomenon, the initial number of cluster centers is selected as 1000. Finally, in each cluster, discrete Fourier transform is performed on pulse wave and central artery wave to obtain amplitude and phase data and train the transfer function. The test set was used for verification. Firstly, the corresponding clustering category of pulse wave was calculated, and then CAP was calculated by transfer function. The results showed that the absolute errors of systolic blood pressure (SBP), diastolic blood pressure (DBP) and pulse pressure (PP) were 2.50±2.22mmHg, 4.47±2.72mmHg and 4.60±3.73mmHg respectively. Compared with other algorithms, our method has better accuracy. © 2022 ACM.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

A novel Approach for optimizing the crop yield by considering climatic and soil features through fusion of Machine Learning and Deep Learning algorithms 15

A novel Approach for optimizing the crop yield by considerin...

引用

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

作者： Suganthavalli, K. Meenakshi, C. Parvathy, K. Department of Computer Science Chennai Tamil Nadu Pallavaram India Department of Computer Application Chennai Tamil Nadu Pallavaram India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore India

ISBN: (纸本)9798350370249

The agricultural sector is the scientific and artistic cultivation of plants and animals. Agriculture has an important role in India's economy, which covers a significant 60.45% of the country's land and stands as the world's second-largest agricultural sector, driving economic growth through its diverse produce and associated industries. Soil composition really matters for growing stuff. Elements like Nitrogen, Phosphorous, & Potassium play a big role. The way you rotate crops, soil moisture, and even temperature all affect how well things grow. Rainfall is important too. Research has shown that using machine learning can help figure out the best crops to grow. They utilize methods that include Random Forest (RF), Decision Tree (DT), and Artificial Neural Network (ANN) for this. The study also looks into deep learning methods to make the model even better. In addition to predicting crop yields, it also provides detailed information on the required amounts of soil elements and their associated costs. The new model offers superior precision compared to the current one. The system examines the provided data and assists farmers in forecasting a crop, which subsequently aids in achieving financial gains. The prediction of a suitable yield takes into account the meteorological and soil parameters of the area. This Python-based system utilizes advanced algorithms to optimize decision-making, forecasting the most lucrative outcomes in various situations while streamlining costs and boosting productivity. The study employs Support Vector Machines (SVM) as an example of Machine Learning (ML) method, while Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) are used as Deep Learning (DL) techniques. © 2024 IEEE.

关键词： Agriculture crop Prediction DL LSTM and RNN ML SVM

来源：评论

学校读者我要写书评

暂无评论

Cross-Guided Attention and Combined Loss for Optimizing Gastrointestinal Visual Question Answering

Cross-Guided Attention and Combined Loss for Optimizing Gast...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yang, Qian Liu, Lijun Yang, Xiaobing Liu, Li Peng, Wei Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming650500 China

ISBN: (纸本)9798350386226

Medical Visual Question Answering (Med-VQA) aims at answering clinical questions related to medical imaging, providing important reference for medical imaging diagnosis. Gastrointestinal visual question answering can deeply understand and analyze gastrointestinal medical images, provides supporting information to answer questions about the diagnostic process, and improves diagnostic accuracy and efficiency. However, most existing Med-VQA can only handle simple and general questions, struggling to tackle visual question answering related to complex diseases. Therefore, this paper proposes a Med-VQA model called CACL, which uses cross-guidance and improved combined loss. The model focuses on gastrointestinal image analysis and achieves efficient and accurate feature extraction for gastrointestinal images. A cross-guided attention module is also designed to enhance the model's reasoning ability when dealing with complex cross-modal tasks. In addition, a multi-task composite loss function is designed to balance the loss of segmentation task and classification task, and improve the overall performance. Experimental results show that the proposed method can effectively improve the accuracy of gastrointestinal visual question answering. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Lis...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Shen, Kailai Yan, Diqun Dong, Li Ren, Ying Wu, Xiaoxun Hu, Jing Ningbo University Faculty of Electrical Engineering and Computer Science China Zhejiang Key Laboratory of Mobile Network Application Technology China

ISBN: (纸本)9798350306897

In this paper, we propose the speech quality assessment transformer utilizing listener dependent modeling (SQAT-LD) mean opinion score (MOS) prediction system, which was submitted to the 2023 VoiceMOS Challenge. The system is based on a combination of self-supervised learning (SSL) models and listener-dependent modeling. Due to this challenge's emphasis on real-world and challenging zero-shot out-of-domain MOS prediction in three different voice evaluation scenarios, we specifically designed a two-branch module to predict scores and weights for each frame, aiming to achieve better generalization. In the challenge, our system achieved fourth place in Track 1a, second place in Track 1b and first place in Track 2. Additionally, we conducted an ablation study to investigate the effectiveness of our proposed method. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Oddity Based Botnet Recognition Utilizing AI Model in the Internet of Things Framework 4

Oddity Based Botnet Recognition Utilizing AI Model in the In...

引用

4th International Conference on Computation, Automation and Knowledge Management, ICCAKM 2023

作者： Rani, Rupa Chakraborty, Sudeshna Singh, Pooja Varshney, Neha Abes Institute of Technology Computer Science & Engineering U.P Ghaziabad India Banasthali Vidyapith Department of Computer Science & Engineering Rajasthan India School of Computer Application and Technology Galgotias University UP India Abes Institute of Technology Department of Computer Science & Engineering U.P Ghaziabad India

ISBN: (纸本)9798350393248

Advanced hooligans are grabbing the opportunity to mull over related contraptions with their IoT adware. The majority of digital attacks target these devices due to the rapid evolution of IoT advancements. With the diversity of modern advancements such as Industry 4.0, IoT, and Modern IoT, the linked gadgets are gradually expanding. The malware is zeroing in on frail devices. In this particular circumstance, we suggested an abnormality-based simulated intelligence model that can capably recognize the threatening practices in the association using change hyper-limit Light GBM computation. The proposed framework can be reached to identify new sorts of impending assaults and also, accomplish a lightweight nature. With the most recent Bot-IoT dataset, our model is prepared. Furthermore, by utilizing the Destroyed technique, the model similarly monitored the dataset's lopsidedness condition. With only one helping cycle, our suggested model demonstrates 99.99% accuracy with © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Predicting the Spread of Covid-19 Using Machine as a Service (MaaS) Through Modified Apriori Algorithm

Predicting the Spread of Covid-19 Using Machine as a Service...

引用

International Conference on Smart Systems and Wireless Communication, SSWC 2024

作者： Sett, Samir Kumar Sett, Aishik Ghosh, Anupam Department of Computer Application Techno India Kolkata India ITC Infotech Kolkata India Department of Computer Science and Engineering and Department of Artificial Intelligence & Machine Learning Netaji Subhash Engineering College Kolkata India

ISBN: (纸本)9789819613472

The cloud computing and machine learning is one of growing technology in the field of computer science. In recent years, the word "Cloud" is like a cup of tea in our daily lives. Every day, a significant volume of data is produced by different IT sectors, banking sectors, e-commerce websites like flipkart. It provides the organization with consistency, scalability, and strong enumerating power. It also delivers eminence service by generating proper outcomes in a brief amount of time. The objective of this paper is to predict the growth of Covid-19 virus in near future using Machine as a Service (MaaS) through modified Apriori algorithm. In this paper, we will obtain the working graph of the algorithm. The result is also analyzed by obtaining the graphs for confidence against lift, support against confidence. At last, a running time comparative graph for modified apriori and apriori is shown for a certain duration of time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Apriori Cloud computing Confidence Covid-19 MaaS Support

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploit Reversible Gates to Implement Fast Quantum Sorting Algorithm 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Bhattacharjee, Subhasree Das, Kunal Sadhu, Arindam Sarkar, Soumyadip Sarkar, Bikramjit Department of Computer Application Narula Institute of Technology West Bengal Kolkata India Department of Computer Science Acharya Prafulla Chandra College West Bengal Kolkata India Department of Electronics and Communication Engineering Greater Kolkata College of Engineering and Management West Bengal Kolkata India Department of Computer Science and Engineering JIS College of Engineering West Bengal Kalyani India

ISBN: (数字)9789819997046

ISBN: (纸本)9789819997039

This paper proposes an algorithm of divide-compare-swap-based (DCS) sorting that reduces time complexity by utilizing quantum parallelism. A new cost optimized comparator circuit has been designed and simulated using qiskit for comparing two quantum numbers. The sorting process consists of divide, compare-swap and merge. The set of n quantum numbers are divided equally into two sub arrays followed by comparing-swapping of two middle elements. This process continues in two sub arrays till array with single element is found. The sorting circuit performs well in qiskit with time complexity n, which has a significant improvement over existing quantum sorting technique. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Unmasking the Reality: A Comprehensive Study of Deepfake Identification Techniques and Their Expanding Terrain 2

Unmasking the Reality: A Comprehensive Study of Deepfake Ide...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Sharma, Shubh Pathak, Disha Mohini Jain, Dhyanendra Srivastava, Somya Vats, Prashant Upadhyay, Govind Murari Department of Computer Science ABES Engineering College U.P. Ghaziabad India Department of Computer Science Engineering-AIML ABES Engineering College U.P. Ghaziabad India Dept. of CSE School of CSE Manipal University Jaipur Rajasthan Jaipur India Dept. of Computer Application Manipal University Jaipur Rajasthan Jaipur India

ISBN: (纸本)9798331530389

The swift progression of deepfake-generating technologies has elicited much apprehension about their potential misuse in digital media, necessitating the development of efficient detection methods. This research aims to improve the precision of deepfake detection by the application of spatial-temporal feature engineering methods. A comparative comparison of advanced preprocessing techniques is performed to enhance the extraction of spatial and temporal indicators essential for detecting deepfake abnormalities. The study investigates the amalgamation of sophisticated machine learning and deep learning models with designed characteristics to get enhanced detection efficacy. Experimental assessments are conducted on benchmark datasets to verify the effectiveness of the suggested methodologies. The findings highlight the importance of effective preprocessing strategies in enhancing model generalizability and dependability, hence supporting the overarching goal of preserving digital authenticity. © 2025 IEEE.

关键词： Contrastive 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：