检索结果-内蒙古大学图书馆

Smart question answering system using vectorization approach and statistical scoring method

Materials Today: Proceedings 2023年 80卷 3719-3725页

作者： Manjunath, T.N. Yogish, Deepa Mahalakshmi, S. Yogish, H.K. Information Science & Engineering B M S Institute of Technology &Management Karnataka Bangalore560064 India K S School of Engineering & Management Computer Science & Engineering Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of Master of Computer Applications M S Ramaiah Institute of Technology Karnataka Bangalore560054 India

In this digital era, internet users are increasing day by day to extract information related to various fields such as health, economic, educational, politics and daily needs from information Retrieval Systems (IRS) such as Google, Ask, Yahoo etc. information Retrieval (IR) is a conventional method which depends on metadata searching method that is searching of adocuments for information within documents and information about documents. Lot of research in the IR area improves accessing the quality of information. Most of the search engines such as Google, Yahoo, Ask Jeeves depends on keyword based query processing mechanism internally which can't handle natural language questions which results in returning long list of documents for a query. The task of users is to manually explore each document to retrieve correct answer which is a time consuming process. To overcome the problems of conventional search engines, smart question answering system comes to play. The objective of Smart Automated Answering system is to impart accurate and valid answers to user question in natural language rather than set of full documents. The Smart Question answering system which accepts user question in Natural language in specific domain and provide short and precise answer using Natural language processing technique, used for pre-processing, normalized term weighting-TF-IDF with cosine similarity approach for document retrieval and enhanced BM25 ranking function to extract answer. The main focus is on decreasing the response time, designing ranking function and giving the pertinent responses to the users’ intent. The system achieved an overall Precision of 93.2%, Recall of 84.3% and F-measure of 88.5% with 80% of Accuracy. © 2021

关键词： information retrieval

来源：评论

学校读者我要写书评

暂无评论

A novel transfer deep learning method for detection and classification of plant leaf disease

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12407-12424页

作者： Kaur, Prabhjot Harnal, Shilpi Gautam, Vinay Singh, Mukund Pratap Singh, Santar Pal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science and Engineering Rashtrakavi Ramdhari Singh Dinkar College of Engineering Begusarai India

The major cause of plant mortality and devastation, particularly among trees is plant diseases. This problem, however, may be handled and treated effectively through early detection. Crop/plant diseases must be identified and prevented as soon as possible to improve yield. Plant disease classification and identification by plant protection professionals through eye observation is a time-consuming and error-prone process. Previously, many researchers used hand-crafted techniques for the detection and classification of diseases. Also, due to a lack of knowledge experts and improper laboratory facilities, classification at an early stage is not possible. In terms of precision agriculture applications, developing effective, rapid, and highly successful computer-aided disease detection systems have become a necessity. A deep learning-based convolutional neural network (CNN) technique is used successfully in numerous computer vision tasks such as picture classification, object detection, segmentation, and image analysis for finding the best results. The existing models had been worked on a mixed crop approach and single class dataset with average accuracy. In this paper, the Modified InceptionResNet-V2 (MIR-V2) which is a form of the CNN model is used in conjunction with a transfer learning approach to recognize illnesses in images of tomato leaves. The proposed model is trained on a public dataset and self-collected dataset that includes seven different tomato leaf disease classifications with one healthy leaf. For the evaluation of model performance, different parameters such as dropout, learning rate, batch size, count of epochs, and accuracy are used. The disease classification accuracy rate for the applied models is 98.92% and the F1 score is 97.94%. The experimental results support the suggested approach’s validity and find it effective in detecting tomato leaf disease. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Dynamic domain testing with multi-agent Markov chain Monte Carlo method

引用

Soft Computing 2024年第13-14期28卷 8293-8317页

作者： Golmohammadi, Roshan Parsa, Saeed Zakeri-Nasrabadi, Morteza School of Computer Engineering Iran University of Science and Technology Hengam St. Resalat Sq. Tehran16846-13114 Iran

Path testing is one of the most efficient approaches for covering a program during the test. However, executing a path with a single or limited number of test data does not guarantee that the path is fault-free, specifically in the fault-prone paths. A common solution in these cases is to extract the corresponding domain of the path constraint that covers the path and select the arbitrary numbers of test data from the extracted domain. Many approaches have been proposed to extract and partition the program input domain statically without executing the program under test. However, extracting domain based on the path constraints is inaccurate and time-consuming, specifically in high dimensional inputs. This paper presents a dynamic approach for extracting the input domain of a given path based on the modified Markov chain Monte Carlo method, multi-agent Metropolis algorithm. The algorithm uses sampling and randomly walks around symmetric proposal distribution to find a finite number of points that approximate the target domain. Our approach chooses the highest fault-prone path from the minimum-cost test paths for domain extraction to maximize the fault detection capabilities. Our experiments with ten Python programs reveal a 14% improvement in the accuracy of the extracted domains compared to the state-of-the-art domain extraction approaches. In addition, the mutation score of automatically generated test cases has improved by an average of 17.95% compared to branch and prime-path testing approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Deciphering Plant Seedlings: Enhancing Classification and Interpretability with Vision Transformers 5

Deciphering Plant Seedlings: Enhancing Classification and In...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Feng, Jinke Xu, Xintao Donghua University College of Computer Science and Technology Shanghai China Lanzhou Jiaotong University School of Electronic and Information Engineering Lanzhou China

ISBN: (纸本)9798350373820

The application of deep learning in agriculture for tasks such as plant seedling classification holds the potential to revolutionize crop management and yield optimization. With the popularity of transformer in computer vision, leveraging this architecture for classification tasks has obtained a great attention in both academic and industurial fields. This paper explores the utilization of a Vision Transformer (ViT), a model architecture that has shown superior performance in various image classification tasks, extending its application to the agricultural domain. By fine-tuning a pre-trained ViT model to distinguish among 12 plant species, we achieve high classification accuracy, reaching a specificity of 95.1%, which demonstrates the model's potential in smart agriculture. Moreover, we enhance model interpretability through Explainable Artificial Intelligence (XAI) techniques, employing attention heatmaps to reveal the model's focus and decision-making process. Our results showcase the viability of using ViTs for domain-specific challenges and contribute to the advancement of transparent and reliable AI tools in sustainable farming practices. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Gene association analysis for Bayesian network integrated classification

Gene association analysis for Bayesian network integrated cl...

引用

2024 International Conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Liao, Sha Liao, Xuhong Li, Zhijie School of Information Science and Engineering Hunan Institute of Science and Technology Hunan Yueyang414006 China

ISBN: (纸本)9781510685437

This paper proposes a gene association analysis algorithm that effectively identifies causal relationships between genes through gene association entropy, and uses heuristic search strategies to construct gene association Bayesian tree (GABT) and gene association Bayesian forest (GABF). Unlike ordinary gene Bayesian networks that describe the dependency relationship between gene expression levels, GABT and GABF are a type of gene sequence Bayesian network. The object of gene association analysis is the sequence formed by sorting the gene expression values of biological tissue samples and replacing them with gene column subscripts. The experimental results on multiple tumor or non tumor gene expression datasets show that the Bayesian network classification algorithm based on gene association analysis can better fit gene expression data than other similar algorithms, with significantly improved accuracy or reduced analysis time. © 2024 SPIE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Partitioning-based Active Trust Mechanism in Cloud-Edge-Device Collaborative Data Collection 21

Partitioning-based Active Trust Mechanism in Cloud-Edge-Devi...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Xia, Zhuoqun Wang, Ziyu Liu, Xiao Changsha University of Science and Technology School of Computer and Communication Engineering Changsha China Guangxi University School of Computer Electronics and Information Nanning China

ISBN: (纸本)9798350329223

Since the open character of the Internet of Things (IoT), IoT devices are vulnerable to various attacks. Compromised devices may maliciously provide unreliable data to the cloud. Furthermore, existing trust evaluation models struggle to balance data security needs across different regions. To address this issue, the paper proposes a partition-based active trust mechanism (PATM). This PATM scheme mainly includes the following parts: First, the region is divided into subregions, and evaluations are conducted for the indicators of each subregion. Mechanism modeling and fuzzy analytic hierarchy process are used to analyze the impact of each indicator on the sensitivity of subregions. Second, the direct estimation method is utilized to estimate the demand for active detection routing based on the sensitivity of subregions. Then, the number of operations of malicious nodes is increased through the high-frequency transmission of detection routes required by each subregion. Additionally, a trust calculation method based on node operations is proposed to evaluate the reliability of the device. The experimental results show that the PATM scheme proposed in this article can quickly identify the trust degree of nodes while balancing the needs of different regions, ensuring the credibility of data collection. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Improvisation in Water Quality Prediction using H20 ViML: A comparative study

Improvisation in Water Quality Prediction using H20 ViML: A ...

引用

2024 OPJU International technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Mallika Singh, Nanhay Lathar, Pankaj Netaji Subhas University of Technology Department of Computer Science & Engineering East Campus Delhi India Delhi Skill & Entrepreneurship University School of Information Technology & Information Technology Enabled Services Delhi India

ISBN: (纸本)9798350373783

Water is the source of life. The concern however rounds about to availability of safe and healthy drinking water to beings. With increasing industrialization and urbanization pollution levels are increasing. Relying on age old long calculative methods for water quality prediction is simply wastage of our resources. Nowadays collected data is also a resource. If we use Machine Learning models, dependency on manual calculation and identification of degraded parameter can pave way to enhancement. This can be a breakthrough in global concern of water management. Currently Water Quality Indexing is used which is a lengthy, data dependent and trouble some process. Machine Learning models for regression to increase accuracy can be used. Comparison can be drawn between Random forest, XG Boost, Decision tree and other regression focused algorithm, Further using ensemble models using H2O ML stacked ensemble automation accuracy can be increased. Further proper identification of parameters can be achieved by using genetic algorithms such as PSO, sparrow searching. The main objective is to improve accuracy and broaden the spectrum of parameter consideration using Machine Learning algorithms. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalization Bounds via Conditional f-information 38

Generalization Bounds via Conditional f-Information

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wang, Ziqiao Mao, Yongyi School of Computer Science and Technology Tongji University Shanghai China School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

In this work, we introduce novel information-theoretic generalization bounds using the conditional f-information framework, an extension of the traditional conditional mutual information (MI) framework. We provide a generic approach to derive generalization bounds via f-information in the supersample setting, applicable to both bounded and unbounded loss functions. Unlike previous MI-based bounds, our proof strategy does not rely on upper bounding the cumulant-generating function (CGF) in the variational formula of MI. Instead, we set the CGF or its upper bound to zero by carefully selecting the measurable function invoked in the variational formula. Although some of our techniques are partially inspired by recent advances in the coin-betting framework (e.g., Jang et al. (2023)), our results are independent of any previous findings from regret guarantees of online gambling algorithms. Additionally, our newly derived MI-based bound recovers many previous results and improves our understanding of their potential limitations. Finally, we empirically compare various f-information measures for generalization, demonstrating the improvement of our new bounds over the previous bounds. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation Design of High Precision Sigma-Delta ADC Modulator System for Electronic Audio Equipment 2

Simulation Design of High Precision Sigma-Delta ADC Modulato...

引用

2nd IEEE International Conference on Electrical, Automation and computer engineering, ICEACE 2024

作者： Wang, Shaodong Harbin Institute of Technology School of Information Science and Engineering Weihai264209 China

ISBN: (纸本)9798350368208

With the diversified development of electronic audio devices, analog-to-digital converters (ADCs) used in high-quality audio chips have received significant attention and extensive research. This paper utilizes computer simulation technology to propose the design and simulation of a second-order 1-bit high-precision Sigma-Delta ADC modulator system. First, based on the design requirements of audio signal bandwidth and a signal-to-noise ratio greater than 98 dB, the modulator structure was determined through theoretical analysis and in-depth research, specifying a 256-fold oversampling, second-order, and 1-bit quantization. Then, in the MATLAB Simulink simulation environment, the ideal structure model of the modulator is determined, and the coefficient of its topology is improved, and the simulation design of the modulator under ideal conditions is completed. Finally, the non-ideal factors that significantly impact the performance of the modulator in actual circuits were analyzed, and a system simulation of the modulator was completed. The simulation results show that its signal-to-noise distortion ratio is 106.8 dB, meeting the design specifications. © 2024 IEEE.

关键词： Delta sigma modulation

来源：评论

学校读者我要写书评

暂无评论

Relationship extraction of red character resources based on attention mechanism deep neural networks 9

Relationship extraction of red character resources based on ...

引用

9th International Symposium on Advances in Electrical, Electronics, and computer engineering, ISAEECE 2024

作者： Wang, Fengying Wu, Jing Du, Liming School of Computer Science and Engineering Shenyang Jianzhu University 110168 China School of Information Engineering Suqian University 223800 China

ISBN: (纸本)9781510683303

In this study, historical resources about the red historical figure Zhu Rui were collected through field surveys, online research, and expert interviews. To create a domain ontology suitable for Zhu Rui, the figure's characteristics and resource types were taken into consideration. Through semantic annotation and classification of the ontology, entity categories related to red historical figures' resources were identified. To improve accuracy, relationship extraction was performed using a convolutional neural network model with an attention mechanism. This study provides a foundation for a semantic understanding of resources related to red historical figures, which is essential for digitalizing and providing knowledge services. However, limitations exist due to the diverse types of resources and subjective views. Future work will focus on optimizing entity extraction to further improve relationship extraction accuracy. © 2024 SPIE.

关键词： Convolutional neural networks

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：