检索结果-内蒙古大学图书馆

Software effort estimation using convolutional neural network and fuzzy clustering

Neural Computing and Applications 2024年第23期36卷 14449-14464页

作者： Azzeh, Mohammad Alkhateeb, Abedalrhman Bou Nassif, Ali Department of Data Science Princess Sumaya University for Technology Amman Jordan Department of Computer Science Lakehead University Thunder Bay Canada Department of Computer Engineering University of Sharjah Sharjah United Arab Emirates

Adopting an efficient software process model is critical for building high-quality software applications. An important factor impacting the software development process is an accurate estimate of human effort required to complete the software project. While machine learning methods were historically used to develop estimation models, there has been little investigation into the potential of deep convolutional neural networks (DCNNs) for improving software effort estimation. One of the biggest obstacles in using DCNN for this purpose is the common nature of software datasets, which often consist of vectorized samples rather than matrices. To defeat this obstacle and reduce vagueness in software attribute measurement, this study uses Fuzzy theory to generate an appropriate two-dimensional datapoint representation. The fuzzy clustering is commonly used to split dataset samples into separate clusters, which can help to generate Fuzzy membership functions. This approach makes it easier to generate a two-dimensional array representation for each data sample based on the membership values, allowing it to be used as input to the DCNN model. The efficiency of the proposed model was thoroughly evaluated using PROMISE benchmark datasets. The findings based on mean absolute errors and standardized accuracy show that our proposed model produced very good performance with low error rates and outperformed several current state-of-the-art effort estimation models. Nonetheless, further research is needed to determine the impact of different cluster numbers and features on the performance of our model. In conclusion, this study emphasizes the possibility for incorporating DCNN into software effort estimates and highlights the viability of utilizing fuzzy modeling and clustering techniques to enhance the data representation of software datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

AI Enhanced Yoga Pose Detection And Alignment Using Deep Learning 3

AI Enhanced Yoga Pose Detection And Alignment Using Deep Lea...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Lavanya, V. Kalila, C.N.A. Premkumar, K. Rohith, R. Velammal College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India Velammal College of Engineering and Technology Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798350381931

Yoga practice offers numerous health benefits, but incorrect poses can lead to injuries and hinder progress. This project leverages the power of deep learning, specifically Convolutional Neural Networks (CNNs) and TensorFlow Movenet, to address this challenge. We introduce an AI-enhanced system that performs real-time yoga pose detection and alignment. Users can choose from a variety of yoga poses, access step-by-step instructions, and activate the system. When the correct pose is achieved, 17 key body points turn green, activating a timer with an alarm-like sound. If the pose becomes incorrect, the timer and sound cease, providing immediate feedback. This project aims to enhance yoga practice safety, provide real-time guidance, and track progress, fostering a more effective and enjoyable yoga experience. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Monocular Quasi-Dense 3D Object Tracking

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第2期45卷 1992-2008页

作者： Hu, Hou-Ning Yang, Yung-Hsu Fischer, Tobias Darrell, Trevor Yu, Fisher Sun, Min National Tsing Hua University Department of Electrical Engineering Hsinchu300 Taiwan Eth Zurich Department of Information Technology and Electrical Engineering Zürich8092 Switzerland Uc Berkeley Department of Electrical Engineering and Computer Science BerkeleyCA94720-1770 United States

A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform. The object association leverages quasi-dense similarity learning to identify objects in various poses and viewpoints with appearance cues only. After initial 2D association, we further utilize 3D bounding boxes depth-ordering heuristics for robust instance association and motion-based 3D trajectory prediction for re-identification of occluded vehicles. In the end, an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation. Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios. On the Waymo Open benchmark, we establish the first camera-only baseline in the 3D tracking and 3D detection challenges. Our quasi-dense 3D tracking pipeline achieves impressive improvements on the nuScenes 3D tracking benchmark with near five times tracking accuracy of the best vision-only submission among all published methods. © 1979-2012 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Unmasking Toxicity: A Comprehensive Analysis of Hate Speech Detection in Banglish 6

Unmasking Toxicity: A Comprehensive Analysis of Hate Speech ...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Islam, Md. Hasibul Farzana, Kaniz Khalil, Ibrahim Ara, Shaneen Shazid, Md.Ruhul Amin Kabir Mehedi, Md Humaion Bangladesh University of Business and Technology Department of Computer Science and Engineering Dhaka Bangladesh Brac University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

As the digital landscape expands, the rise of online hate speech presents a pressing challenge, necessitating sophis-ticated tools for effective detection and mitigation. This project focuses on the intricate linguistic landscape of Banglish a hybrid language amalgamating Bengali and English striving to develop robust models tailored to its unique characteristics. The dataset, comprising 5000 Banglish comments categorized into various hate speech types, serves as the foundation for model exploration. Our approach spans a wide variety of models, including traditional machine learning (SVM, Logistic Regression,random forest), advanced deep learning architectures and innovative hybrid models (CNN+BiLSTM). Approaches for feature extraction such word embedding, TF-IDF, and Bag-of-Words and sentiment analysis scores are adapted to the nuances of Banglish. Ethical considerations guide our development, addressing algorithmic bias and user rights. The experimental results provide a nuanced understanding of model performance, in- cluding accuracy (90%), precision, recall, and F1 score. Insights derived from these analyses contribute to the ongoing refinement of hate speech detection methodologies, advancing the field of computational linguistics and ethical artificial intelligence. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A deep convolutional neural network for COVID-19 detection using chest X-rays

引用

Research on Biomedical engineering 2022年第1期38卷 139-148页

作者： Bassi, Pedro R. A. S. Attux, Romis Department of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Campinas Brazil

Purpose: We present image classifiers based on Dense Convolutional Networks and transfer learning to classify chest X-ray images according to three labels: COVID-19, pneumonia, and normal. Methods: We fine-tuned neural networks pretrained on ImageNet and applied a twice transfer learning approach, using NIH ChestX-ray14 dataset as an intermediate step. We also suggested a novelty called output neuron keeping, which changes the twice transfer learning technique. In order to clarify the modus operandi of the models, we used Layer-wise Relevance Propagation (LRP) to generate heatmaps. Results: We were able to reach test accuracy of 100% on our test dataset. Twice transfer learning and output neuron keeping showed promising results improving performances, mainly in the beginning of the training process. Although LRP revealed that words on the X-rays can influence the networks’ predictions, we discovered this had only a very small effect on accuracy. Conclusion: Although clinical studies and larger datasets are still needed to further ensure good generalization, the state-of-the-art performances we achieved show that, with the help of artificial intelligence, chest X-rays can become a cheap and accurate auxiliary method for COVID-19 diagnosis. Heatmaps generated by LRP improve the interpretability of the deep neural networks and indicate an analytical path for future research on diagnosis. Twice transfer learning with output neuron keeping improved DNN performance. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Security Threats to xApps Access Control and E2 Interface in O-RAN

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2024年 5卷 1197-1203页

作者： Hung, Cheng-Feng Chen, You-Run Tseng, Chi-Heng Cheng, Shin-Ming National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106335 Taiwan

Open Radio Access Networks (O-RANs) represent a novel wireless access network architecture that decomposes traditional RAN functions and makes them openly accessible. O-RANs enable real-time coordination, RAN performance optimization, and management through RAN Intelligent Controllers (RICs) and their related xApps. Due to the openness of O-RAN, developers have the flexibility to download various pre-developed xApps from the Internet for deployment. They can even develop their xApps to enhance the flexibility and innovation of the RAN. The current O-RAN official WG11 has defined numerous specifications for secure implementations. However, not only is accurately detecting malicious xApps a significant challenge, but the existing H-Release also does not fully adhere to the specifications in its implementation. This could potentially introduce security risks and threats. In this paper, we implement an experimental O-RAN H-Release environment and discover significant threats from the absence of specified access control permissions for xApps. Malicious attackers can illegally access APIs to utilize other services or launch attacks on legitimate xApps and E2 nodes through the E2 interface, potentially causing a complete RAN disruption. We used the identified vulnerabilities to design three attacks, providing detailed explanations and a comprehensive analysis of their impact on the system. Finally, we also submit the discovered threats to CVEs (CVE-2023-42358 and CVE-2023-41628), providing a reference for O-RAN officials to improve security in the future. © 2020 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Chaos Theory Based Gravitational Search Algorithm For Medical Image Segmentation 27th

Chaos Theory Based Gravitational Search Algorithm For Medica...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Rather, Sajad Ahmad Roy, Partha Pratim Das, Sujit Department of Computer Science and Engineering Indian Institute of Technology Roorkee247667 India Department of Computer Science and Engineering National Institute of Technology Telangana506004 India

ISBN: (纸本)9783031781032

Multilevel thresholding plays a crucial role in image processing, with extensive applications in object detection, machine vision, medical imaging, and traffic control systems. It entails the partitioning of an image into distinct regions based on optimal pixel values. However, as the number of threshold levels increases, so does the computational cost for segmentation. To address this challenge, a novel method is proposed namely Chaos theory based Gravitational Search Algorithm (CGSA) for multilevel thresholding. CGSA combines the standard Gravitational Search Algorithm (GSA) for exploration with chaotic maps for exploitation of the complex pixel problem space. In this study, Kapur’s entropy method is utilized to segment sample images into various partitions based on optimal pixel values. The effectiveness of CGSA in real-world scenarios is evaluated using COVID-19 chest CT scan imaging datasets from Kaggle database. The quality, symmetry, and consistency of the segmented output are assessed using metrics like Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Feature Similarity Index Measure (FSIM). Qualitative analysis includes convergence curves, segmented graphs, colormap images, and box plots. Statistical validation is conducted using the signed Wilcoxon rank sum test. Additionally, a comparison is made between CGSA’s performance and that of eight state-of-the-art heuristic algorithms. The findings demonstrate the superior performance of CGSA, evidenced by its reduced computational time and enhanced image quality metrics values. Specifically, CGSA achieved SSIM of 0.81, FSIM of 0.82, and PSNR of 24.27, surpassing the performance of other competitive algorithms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Faulty Sensors Detection in Planar Array Antenna Using Fish School Search Algorithm 5

Faulty Sensors Detection in Planar Array Antenna Using Fish ...

引用

5th International Conference on electrical, Communication and computer engineering, ICECCE 2024

作者： Nasir, Ammar Iqbal, Shahid Khan, Shafqat Ullah Zaman, Fawad Waseem, Athar University of Gujrat Department of Electrical Engineering Gujrat Pakistan University of Buner Department of Electronics Buner Pakistan COMSATS University Department of Electrical & Computer Engineering Islamabad Pakistan International Islamic University Department of Electrical & Computer Engineering Pakistan

ISBN: (纸本)9798331529437

Antenna arrays are integral to high-performance systems such as radar, wireless communications, satellite communications, radio astronomy, and medical imaging. However, sensor failure within PAA can severely affect the radiation pattern, which may cause signal gain reduction and compromised directionality, especially when central elements are not working. This paper presents a new approach in antenna arrays for detecting faulty sensors using the Fish School Search Algorithm (FSSA). The detection problem is framed as an optimization of the Mean Square Error (MSE) between the expected and actual radiation patterns for single and multiple elements faults, enabling early identification of these faults. Simulations on both 3x3 and 9x9 planar arrays are performed to evaluate the method's accuracy, considering different fault scenarios, including central and edge element failures. Simulation results show that FSSA accurately detects faulty sensors, with central element failures having a significant impact on system performance. The proposed method enhances system reliability by detecting faults promptly and minimizing performance downtime in critical applications. © 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

Analysis of Reciprocity Based Downlink Channel Estimation with Uneven Uplink Channel 1st

Analysis of Reciprocity Based Downlink Channel Estimation wi...

引用

1st International Symposium on Intelligent Computing and Networking, ISICN 2024

作者： Kumar, Venkataramani Ye, Feng Department of Electrical and Computer Engineering University of Dayton DaytonOH United States Department of Electrical and Computer Engineering University of Wisconsin-Madison MadisonWI United States

ISBN: (纸本)9783031674464

Multiple input multiple output (MIMO) plays an important role in realizing the present fifth-generation (5G) as well as the next-generation wireless networks. The channel estimation process in the majority of the existing works in MIMO focuses on equal uplink and downlink channels. However, certain applications such as satellite internet utilize narrow uplink to estimate wider downlink channels. In this work, we intend to analyze the performance of channel estimations in systems with unequal uplink and downlink channels using some of the existing approaches in the literature that focus on channel reciprocity. The proposed idea is validated on an open-source dataset comprising uplink In-phase and Quadrature (I/Q) components collected at 2.4 GHz. The preliminary evaluation results are discussed within the scope of this work. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Sentiment Classification for Depression Detection: Integrating Capsule Networks with CNNs on Review Data

Sentiment Classification for Depression Detection: Integrati...

引用

2025 International Conference on Emerging Technologies for Intelligent Systems, ETIS 2025

作者： Sagili, Sreenivas Reddy Shibi, B. Rvs, Praveen Anjana, P. Rochester Institute of Technology Department of Computer Science United States Sona College of Technology Computer Science and Engineering Tamil Nadu Salem India LTI Mindtree Digital Engineering India Awh Engineering College Computer Science and Engineering Kerala India

ISBN: (纸本)9798331507541

This research is focused on the analysis of how Capsule Networks should be combined with Convolutional Neural Networks (CNNs) for improving the sentiment classification with the target of depression detection based on the data offered by the reviews. Other methodologies of analysing the sentiment of a phrase may encounter disability in the process of analysing texts in natural language following depression since they do not analyse the text deeply enough to consider the context. The proposed method intends to enhance accuracy and resistance when compared to state-of-the-art techniques by combining the attributes of Capsule Networks, that effectively maintain the spatial hierarchy and the connections within the data, with CNNs' feature extraction ability. The proposed hybrid model helps overcome disadvantages of the plain sentiment analysis because it identifies intricate patterns and dependencies in the review data and enhances the depressive sentiments' detection. This paper assesses the propriety of the integrated Capsule-CNN through an evaluation on review datasets in relation to its ability in the successful differentiate between depressive and non-depressive sentiments. The findings reveal a considerable increase in method accuracy and present a leap of progress in the field of automatic depression detection, which in turn helps to develop more accurate and efficient tools for monitoring patients' mental status. © 2025 IEEE.

关键词： Emotion Recognition

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：