检索结果-内蒙古大学图书馆

4th International Symposium on Intelligent Robotics and Systems, ISoIRS 2024

作者： Wu, Zewei Peng, Chengbin Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798350364798

Defect classification in the aviation industry plays a crucial role in manufacturing. However, in non-standardized captured scenes, the object to be inspected and the background are often complex and variable, e.g., lighting, angle, occlusion, etc., which can affect the core features of the image data. Therefore, achieving accurate classification using a limited number of defect samples from products photographed in non-standardized environments has emerged as a challenging yet promising research focus. To address this issue, this study proposes a learning approach that can be trained using standardized industrial defect datasets to detect defects in few-shot, non-standardized industrial defect production. Specifically, this approach initially utilizes the knowledge acquired from a standardized pre-training dataset to crop the data within the query set. Subsequently, an embedding extraction is employed to obtain feature embedding and classification results. Our practice demonstrates a performance improvement of roughly 5% on non-standard datasets compared to few-shot classification methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Adaptive Discontinuous Reception Method for Cognitive Radios 16

Deep Reinforcement Learning based Adaptive Discontinuous Rec...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Sun, Weijie Jin, Ming Jiang, Tao Li, Zhaoteng Chen, Guo Li, Wenjuan Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China

ISBN: (纸本)9798331506322

Discontinuous reception (DRX) is one of the important power-saving mechanisms for 5G/B5G cognitive radio systems. Conventional DRX methods improve the power-saving performance at the cost of data transmission delay. To address this issue, a deep reinforcement learning based DRX method is proposed. An adaptive time-slot DRX structure is propsed and the DRX mechanism is modeled as a Markov decision process. The state set, action space and reward expressions are jointly designed for the DRX mechanism. A DRX decision strategy is obtained by deep reinforcement learning, which adaptively adjusts the window length of wake-up period. Simulation results are provided to demonstrate that the proposed DRX method improves the power-saving performance while the average transmission delay of data packages closes to the lower bound. © 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

Closed form Solution of Moving Source Localization Using TDOA and FDOA Measurements Under Sensor Location Errors 16

Closed form Solution of Moving Source Localization Using TDO...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Sheng, Menglei Li, Youming Zhou, Yapeng Cai, Wanyuan Qi, Qinke Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798331506322

The moving source localization is very sensitive to the knowledge of sensor locations. In this paper, we propose a two-stage closed-form method for locating a moving source by using Time Difference of Arrival (TDOA) and Frequency Difference of Arrival (FDOA) measurements in the presence of random errors in sensor locations. In the first stage, we establish a series of pseudo-linear equations by introducing the auxiliary variables and obtain an initial location estimation based on the bias reduced criteria and the Lagrange multiplier theory. In the second stage,we propose a modified weighted least squares method to obtain the final estimation by exploring the relationship between the auxiliary variables and the moving source location and velocity. The proposed method is in closed form and therefore computationally efficient as well as free from the divergence problem unlike iterative techniques. Simulations show the better performance of the proposed method. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Optimizing Diabetes Prediction using Machine Learning with Data Deviation 6

Optimizing Diabetes Prediction using Machine Learning with D...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Triandi, Budi Tanti, Lili Puspasari, Ratih Elhiyas, Mas Ayoe Marwan Faculty of Engineering and Computer Science Universitas Potensi Utama Medan Indonesia

ISBN: (纸本)9798331539603

Diabetes mellitus is a chronic disease that affects global health with an increasing prevalence rate. Early prediction can provide opportunities for earlier intervention and better management of health conditions. This study explores various classification techniques to analyze data sets that include potential risk factors such as family history, body mass index (BMI), blood pressure, and blood sugar levels. This approach uses several machine learning algorithms such as Decision Trees, Gradient Boosting, support vector machines (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB) and Random Forest (RF) to identify patterns related to the development of diabetes. In this study, we have carried out a comparison of several machine learning (ML) algorithms, aiming to classify the "No Diabetes" or "Diabetes" class by considering several parameters such as, Age, gender, polyuria, polydipsia, sudden_weight_reduction, weakness, polyphagia, genital_thrush., visual_blurry, itching, irritability, delayed_healing, partial_paresis, muscle_stiffness, alopecia, obesity and classes collected in one dataset. The ML model is optimized by normalizing standard deviation data and 20-fold cross validation to get the best model and to determine the log loss or accuracy matrix and its performance. The results show that the model built using Gradient Boosting and SVM gave the best accuracy results on the entire test set, the Decision Trees, Random Forest and k-NN models also gave good results, while Naïve Bayes proved to be the least good in terms of accuracy results. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Closed-Form Method For Underwater Source Localization With Isogradient Sound Speed Profile 16

An Efficient Closed-Form Method For Underwater Source Locali...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Chen, Guanxu Wang, Gang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798331506322

In this paper, we address the underwater localization problem with isogradient sound speed profile (SSP) using time-of-arrival (TOA) measurements. The sound speed is related to the unknown source depth in the isogradient SSP model, which is highly nonlinear. Owing to this nature of the isogradient SSP model, the maximum likelihood (ML) problem for estimating the source position is non-convex such that local convergence may occur without sufficiently good initialization. To address this difficulty, we first approximate the isogradient SSP model, and then propose a closed-form two-step weighted least squares (TSWLS) method for estimating the source position based on the approximate model. The solution method is accurate since the approximate model takes the source depth into consideration, and can be used to solve the ML problem as an initialization. Moreover, the proposed TSWLS solution is simple and computationally attractive since it is in closed form. Simulation results show that the proposed TSWLS solution is sufficiently accurate and can be used as the initial estimate for solving the non-convex ML problem, such that the mean square error (MSE) of the ML solution can reach the Cramér-Rao lower bound (CRLB). Index Terms-Underwater localization, time-of-arrival, isogradient sound speed profile, two-step weighted least squares. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Overview of Emerging Biological Computational Framework for Olfactory Studies Utilizing Contextual Technobiomedical engineering 2

Overview of Emerging Biological Computational Framework for ...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Chaudhri, Shiv Nath Faculty of Engineering & Technology Department of Computer Science and Design Wardha India

ISBN: (纸本)9798331528713

Organoid intelligence (OI), the next paradigm of intelligence, draws inspiration from the biological learning of organs. On the other hand, artificial intelligence (AI) draws its inspiration only from the cognitive processes of the brain. While taking ethical and technological limitations into account, biological learning helps to conceptualize, accept, and apply them. Just as AI helped to make supercomputers possible, OI may help create biocomputers. Even though AI has increased the capabilities of technology to unimaginable heights, it still appears immature and is steadily moving toward cognitive computing to push the envelope even farther. In contrast to AI, OI is a new multidisciplinary computer area that attempts to be more approachable. OI has the ability to produce novel biocomputers, such as organoids, that use parts derived from live organisms to perform computational tasks. Organoids, such as human nasal organoids, are microscopic tissue cultures made from stem cells that mimic some of the functions of real organs. Although they have been used for many different purposes, including drug discovery and illness modeling, scientists are only now beginning to explore their potential for biological information processing. © 2024 IEEE.

关键词： Artificial Intelligence (AI) Biological Information Processing Biological Learning Olfactory Organoids Organoid Intelligence (OI)

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm for optimizing meteorological sensors placement using airborne LiDAR data 24

Genetic algorithm for optimizing meteorological sensors plac...

引用

24th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2024

作者： Lukač, Niko Kavran, Domen Ovčjak, Monika Ferk Bizjak, Marko Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia

ISBN: (纸本)9798350353433

This paper presents a novel method for optimizing meteorological sensor placement over large geographic areas, leveraging genetic algorithm (GA) and classified Light Detection And Ranging (LiDAR) data. The airborne LiDAR data provides detailed surface information necessary for finding the optimal locations for sensor placement. By considering semantic segmentation of surface, relative Sky View Factor (SVF), and surface slope, the method significantly reduces the search space to find suitable locations for sensors placement. The considered GA then uniformly and optimally positions a user-specified number of sensors, guided by optimization constraints within the fitness function. This approach enhances dense meteorological data collection efficiency, ensuring better data quality and coverage in areas such as weather forecasting, climate studies, and pollution monitoring. It reduces redundancy and deployment costs while maximizing sensors exposure to environmental physical processes such as solar radiation and wind. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Fabrication Classifiation in Visual Tweets by Using Machine Learning with Deep Features

Fabrication Classifiation in Visual Tweets by Using Machine ...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Deshmukh, Vaishnavi J Ambhaikar, Asha Kalinga University Department of Computer Science & Engineering Chattisgarh Raipur India Kalinga University Faculty of Engineering Department of Computer Science and Engineering Chattisgarh Raipur India

ISBN: (纸本)9798350348460

In the context of online news outlets like Twitter, our work gives a summary of the situation as of rumor identification utilizing visual content. The majority of studies in the literature use visual content to illustrate several solutions to the issue. As opposed to combining them, we suggested an approach for Twitter rumours. The majority of our research work focuses on the use of supervised techniques, particularly deep learning models by utilising the deduced feature sets from the Twitter MediaEval dataset, which included 3000 images in total, a VGG-19 deep neural network was trained and evaluated. The VGG-19 achieves a highest sensitivity and an accuracy of using features taken from images during training and testing, which struggle to function in situations other than those in which they were trained. The simulation findings show that compared to other state-of-the-art architecture, the suggested design is more accurate and sensitive. © 2024 IEEE.

关键词： deep learning machine learning Twitter VGG-19

来源：评论

学校读者我要写书评

暂无评论

UNRAVELING THE EFFECTIVENESS OF THE K-NN ALGORITHM FOR IMBALANCED DATA IN RESEARCH TOPIC RECOMMENDATIONS

引用

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2024年第1期59卷 271-282页

作者： Muludi, Kurnia Aisyah, Nonik Nama, Gigih Forda Lumbanraja, Favorisen R. Informatics & Business Institute Darmajaya Bandar Lampung35142 Indonesia Computer Science Department Faculty of Science The University of Lampung Bandar Lampung Indonesia Informatics Engineering Department Faculty of Science The University of Lampung Bandar Lampung Indonesia

This study addresses the challenge of selecting research topics for undergraduate students, focusing on computer science, by evaluating a recommendation model based on the k-Nearest Neighbor algorithm (kNN). The objective is to enhance the accuracy of research topic recommendations in the presence of imbalanced data. The methodology involves data cleaning, transformation, and correlation-based feature selection, with a particular focus on addressing missing values and optimizing the feature set. The Synthetic Minority Over-Sampling Technique (SMOTE) is employed to balance the dataset. The model development includes a comprehensive analysis of various k values, leading to the identification of k=3 with Manhattan distance as the optimal configuration, achieving an accuracy of 82%. The experiment explores different training data proportions, revealing that a 90:10 ratio yields the highest accuracy. This study incorporates a Grid Search technique for hyperparameter tuning, highlighting the importance of selecting appropriate distance metrics and nearest neighbor values. The system implementation is presented with user and administrator interfaces. Findings indicate varying model performance across research categories, emphasizing the need for category-specific evaluation metrics. The study concludes with a discussion on the significance of the results, which contribute to the improvement of research topic recommendation systems for students through the integration of advanced machine learning techniques. © 2024 by the authors.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Technical Means for Teaching 'computer Modelling and Information Technology' at Lower Secondary Education 23

Technical Means for Teaching 'Computer Modelling and Informa...

引用

23rd International Symposium on Electrical Apparatus and Technologies, SIELA 2024

作者： Minchev, Dimitar Pisarova, Ivanka Burgas Free University Faculty of Computer Science and Engineering Burgas Bulgaria

ISBN: (纸本)9798350382365

This scientific article examines the importance of technological tools in teaching computer Modeling and Information Technology in lower secondary education. The focus is on integrating popular platforms such as micro:bit, Arduino, and Raspberry Pi into the learning process. The article presents pedagogical approaches and methods that use these technologies to enrich the learning environment and support the development of computer modeling and information technologies in students at lower secondary education. © 2024 IEEE.

关键词： Digital elevation model

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：