检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Afroj, Maharin Jahan, Israt Islam, Md Polash Saifur Rahman, Md. Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Stockholm University Dept. of Computer and Systems Sciences Stockholm Sweden

ISBN: (纸本)9798331529765

The crucial field of fruit classification in computer vision and deep learning brings about breakthroughs that have broad applications in the retail and agricultural industries. By automating the identification and sorting of various fruit types, these technologies enhance efficiency, accuracy, and scalability, benefiting processes from farm production to market distribution. The integration of sophisticated algorithms and neural networks not only improves the speed and reliability of fruit classification but also offers the potential for real-time quality control and inventory management, revolutionizing traditional methods and paving the way for more innovative, data-driven approaches in these sectors. This study introduces LightNN, a novel and effective paradigm with a lightweight architecture that tackles the complex problems related to computational efficiency. Combining a small classifier with a simplified feature extractor, LightNN achieves the ideal balance between simplicity and accuracy. The feature extractor is capable of extracting hierarchical features from RGB images by using convolutional layers with ReLU activations and max-pooling procedures. The flattened output is then processed by the classifier, which consists of fully connected layers with ReLU activations and dropout regularisation. Remarkably, LightNN, with just 298,835 parameters, manages to get a respectable 96.37% test accuracy in fruit categorization tasks. The results highlight LightNN's promise as an effective and efficient fruit classifying method, particularly in situations with constrained computational resources. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Unveiling Insights: Vision-Based Data Mining Analysis of Webpages in Transition from HTML 3 to HTML 5 5

Unveiling Insights: Vision-Based Data Mining Analysis of Web...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Chaudhary, Meena Pooja Chandwani, Gunjan Manav Rachna University Dept. of Computer Science and Technology Faridabad India Galgotias University Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350383522

Deep web material is accessed with web database requests, and returned information is packaged into dynamically generated web pages known as deep Web pages. Due to their intricate structure, it is tedious task to retrieve organized data from deep web pages. A great many approaches to address this problem are yet to be proposed, but all of them have inherent drawbacks because they are based on the website and the programming language. The contents of Sites are always shown for users to search daily, like the common two-dimensional media. This motivates us to search for an alternative way to extract deep Web information, by using some interesting popular visual features from deep Webpages, to address the limitations of past works. A novel blog vision approach is proposed in this paper to overcome these issues. This technique uses visual features in deep web pages specifically to conduct deep web data extraction. This paper also recommends a new appraisal measure to capture the required human activity to make maximum mining. The proposed methodology is highly efficient in the deep network data extraction, according to our studies with a large set of web-based data bases. © 2024 IEEE.

关键词： Data mining HTML 3 HTML5 Vision based technique Web Content Mining

来源：评论

学校读者我要写书评

暂无评论

The Impact of Compiler Warnings on Code Quality in C++ Projects 32

The Impact of Compiler Warnings on Code Quality in C++ Proje...

引用

32nd IEEE/ACM International Conference on Program Comprehension, ICPC 2024

作者： Johansson, Albin Holmberg, Carl Neto, Francisco G. De Oliveira Leitner, Philipp Chalmers University of Technology Dept. of Computer Science and Engineering Gothenburg Sweden Chalmers - University of Gothenburg Dept. of Computer Science and Engineering Gothenburg Sweden

ISBN: (纸本)9798400705861

Modern compilers often offer a variety of warning flags, which developers can enable to get feedback on code that, while syntactically correct, may be problematic. In the case of C++, one example of such 'correct but problematic' code is code that leads to undefined behavior (UB). The usage of compiler warnings has long been suspected as a way to decrease bugs and increase code quality. However, empirical evidence that supports this hypothesis is rare. In this study, we present evidence from a study of 127 open source C++ projects. We categorize their usage of compiler warnings into five groups based on which warning flags are being used, and analyse the relationship between compiler warnings and five quality metrics (bugs, critical issues, vulnerabilities, code smells, and technical debt) using Bayesian analysis. We conclude that, in general, compiler warnings indeed correlate with, and potentially cause, higher code quality, with the clearest impact being on the number of critical issues in a project. Using stricter warning flags expectantly correlates with higher code quality in our study objects. However, there are substantial differences between projects, which we attribute to the project's individual development culture. That is, while warnings matter, other factors such as quality culture, are likely to be even more important to source code quality. © 2024 ACM.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

COMPARING WSN PERFORMANCE: TRADITIONAL VS. SDN APPROACH

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer Science 2024年第4期86卷 81-94页

作者： Hamad, Diyar Jamal Yalda, Khirota Gorgees Okumus, Ibrahim Taner Tapus, Nicolae Faculty of Automatic Control and Computer Science University of Science and Technology POLITEHNICA Bucharest Soran Technical college Erbil Polytechnic University Erbil Iraq Computer Engineering Kahramanmaras Sutcu Imam University Kahramanmaras Turkey Dept. of Computer Science University of Science and Technology POLITEHNICA Bucharest Romania

The proliferation of Wireless Sensor Networks (WSN) in various applications has necessitated the exploration of network architectures that can ensure efficient, scalable, and reliable communication. This study presents a comparative performance evaluation of traditional networking paradigms and Software-Defined Networking (SDN)-based architectures within WSN. Utilizing the Floodlight SDN controller and Mininet-WiFi emulator, we conducted a series of experiments across three different network topologies, varying the number of hosts and access points. The performance metrics focused on are average latency, packet loss percentage, and throughput. The results demonstrate a considerable improvement in all measured parameters under the SDN-based environment compared to the traditional setup. Specifically, SDN environments consistently showcased lower latency, minimal packet loss, and higher throughput, with the most notable difference observed in smaller network configurations. The findings suggest that SDN, with its centralized control plane, can significantly enhance the performance of WSNs, particularly in scenarios demanding rapid scalability and dynamic traffic management. This study underscores the potential of SDN architectures in optimizing WSN operations and lays the groundwork for future research in this domain. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Floodlighting

来源：评论

学校读者我要写书评

暂无评论

EfficientNet Convolutional Neural Network for Automated Cervical Spine Fracture Identification 6

EfficientNet Convolutional Neural Network for Automated Cerv...

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Sidpara, Pragati Agarwal, Anshul Swain, Debabrata Gupta, Rajeev Kumar Bhilare, Amol Upkare, Makarand Pandit Deendayal Energy University Dept. of Computer Science and Engineering Gandhinagar India Vishwakarma Institute of Technology Vishwakarma Institute of Technology Dept. of Computer Engineering Pune India

ISBN: (纸本)9798331516796

The aim of this study is to develop an automatic system that uses deep learning techniques to detect cervical spine fractures from medical images. Using a DICOM (Digital imaging and communications in medicine) images of cervical spine, the system can identify a fracture and specify which vertebrae has a fracture. This process involves first processing provided DICOM images, then applying data augmentation techniques including metadata information, finally designing neural network architecture for feature extraction. We use a method called transfer learning, utilizing a pre-trained model like EfficientNet, which is used for feature extraction, while optimizing network parameters using AdanW optimizer and CosineAnnealingWarmup learning rate scheduler. The results demonstrate the successful training of neural network models to identify fracture and that fractured vertebrae, with commendable performance and accuracy level noted during evaluation on validation data. This study has important implications for medical imaging and healthcare industries, since automated fracture detection can increase diagnostic efficiency and accuracy. Moreover, such a system would provide good support to healthcare professionals, specifically radiologists, to identify cervical spine fracture easily. © 2024 IEEE.

关键词： Digital Imaging and Communications in Medicine (DICOM)

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Predicting Ovarian Cancer in its Early Stages Using Biomarkers 6

Machine Learning Techniques for Predicting Ovarian Cancer in...

引用

6th International Conference on Electrical Engineering and Information and Communication technology, ICEEICT 2024

作者： Alam, Mir Jafikul Anawar, Jannat-E Mohi Uddin, Khandaker Mohammad Rahman, Md. Hasibur Rahman, Md. Mahbubur Dhaka International University Dept. of Computer Science and Engineering Dhaka Bangladesh Southeast University Dept. of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

The deadliest gynecological cancer affecting women is ovarian cancer, currently incurable with no effective medication treatments. The key focus of this research is to assess insights for early diagnosis using statistical analysis and machine learning techniques on data from clinical trials obtained from 349 patients. Several techniques, including Random Forest, Decision Tree, Gaussian NB, AdaBoost, and Logistic regression, were applied to find the most reliable factor for ovarian cancer prediction. A clinically evaluated raw dataset of benign samples and malignant ovarian tumor patient data set is used to develop early-stage ovarian cancer predictions, and the effectiveness of ML models was examined utilizing metrics including F1-score, Accuracy, Precision, and Recall. The proposed study shows better outcomes, with the Random Forest classifier exhibiting the highest accuracy for validation at 99% based on the test data of ovarian cancer predictions. Even though early-stage ovarian cancer detection is generally unavailable, cancer diagnosis may be greatly aided by machine learning. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

TARG: A Reference-Free, Lossless, Customized General-Purpose Encoder for Genome Sequence in Raw, FASTA, or Multi-FASTA Formats 4

TARG: A Reference-Free, Lossless, Customized General-Purpose...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Roy, Subhankar Ghosh, Partha Mukhopadhyay, Anirban Academy of Technology Dept. of Computer Science and Engg. Hooghly India University of Kalyani Dept. of Computer Science and Engg. Nadia India

ISBN: (纸本)9798350389128

The ability to efficiently encode and store vast amounts of genome sequence data is paramount for various analytical and computational tasks. General-purpose compressors fail to efficiently compress genome sequences, primarily due to the highly repetitive nature of genomic data, the complexity and variability of genomes across organisms, the large size of genome sequences, the limitations of standard compression algorithms, and the absence of optimization for genomic data patterns. This article addresses this challenge through the development of a reference-free, lossless, customized general-purpose encoder for genome sequences in raw, FASTA (FAST-ALL), or multi-FASTA formats. The proposed encoder offers a versatile solution that can handle diverse genome datasets without relying on preexisting reference sequences, ensuring compatibility with emerging genome sequencing technologies. We tested and evaluated the encoder thoroughly to show that it works well and is reliable. We looked at compression ratios, compression and decompression speeds, memory, and how well it recreated the original genome sequences. This encoder not only addresses the pressing need for efficient data storage and transmission in genomics but also paves the way for further advancements in genome analysis and interpretation. Unlike other algorithms, the proposed method, TARG (Two-bit coding encoded using ASCII with Run length encoding followed by General-purpose encoding), does not depend on time-consuming parameter settings. Based on experiments, the average compression ratio of TARG on 10 benchmark genome datasets is 4.33, while the current state-of-the-art general-purpose algorithms gzip, bzip2, zstd, and bsc have respective averages of 3.26, 3.51, 4.21, and 4.28. © 2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

A comprehensive step of XAI for Bengali and English text detection and recognition from natural scene images 2

A comprehensive step of XAI for Bengali and English text det...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Dutta, Mithun Das, Utpol Kanti Das, Jugal Krishna Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350367461

A critical first step in many applications, including augmented reality, document analysis, and scene comprehension, is text detection from images. Even though text identification for the English language has advanced significantly, there are particular difficulties when applying these methods to languages such as Bengali because of variations in script, morphology, and typographic characteristics. This article offers a wonderful method for leveraging the Faster R-CNN framework to identify and categorize text from images that contain Bengali and English sentences. The study utilizes a dataset named "Bengali and English text image dataset (BETID)"that consists of images with text in both Bengali and English scripts, taken from a variety of sources such as books, documents, natural scenes, internet images, and landscapes. Pre-processing methods are used to improve the resilience and generalization of the model, including image scaling, normalization, and augmentation. The Faster R-CNN architecture is tuned and trained to identify text regions in images and categorize Bengali or English text. The performance of the text Classification model is evaluated using evaluation measures such as accuracy on the BETID dataset. The proposed Faster R-CNN model achieved an average of 97.90% accuracy, which is better than other deep learning models. Empirical findings showcase the capacity of transfer learning to alleviate data scarcity concerns and enhance text detection precision for low-resource languages such as Bengali.) © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A review on 3D image reconstruction on specific and generic objects

引用

Materials Today: Proceedings 2023年 80卷 2400-2405页

作者： Shalma, H. Selvaraj, P. Dept. of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Dept. of Information Technology SRM Institute of Science and Technology Kattankulathur Chennai India

With the emergence of various techniques involved in deep learning the researchers of computer vision tends to focus on the strategies such as object recognition and segmentation of image. This has inclined to accomplish the deep learning techniques in 3D reconstruction of both specific and generic objects. As the space for reconstruction of 3D images either in single or multi view has envisioned the researchers to concentrate on the available technologies used for reconstruction. With the available built in methods and technologies in deep learning, the performance of the proposed methods were reviewed and analyzed using several parameters. As the remaking of 2D images is still in the beginning stage, it is important to study the 3D shape representations, various network architecture, methodologies and approaches behind 3D reconstruction. In this work a review of deep learning methods for single or multiple RGB images of specific and generic object 3D reconstruction was done. Several methods and their importance were also discussed along with the challenges encountered and with further research directions. This paper critically analyzes the various 3D Shaped Representations, 3D Data Network Architectures, dept. Estimation methods, Multi View Representations and the Data Representation Techniques. © 2021

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Monitoring through Drone Images via Yolov5 and Kalman Filter 5

Smart Traffic Monitoring through Drone Images via Yolov5 and...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Hanzla, Muhammad Ali, Shuja Jalal, Ahmad Air University Dept. of Computer Sciences Islamabad Pakistan Air University Dept. of Creative Technology Islamabad Pakistan Air University Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350394764

Monitoring traffic is of vital relevance in our modern scenario. Over the years, standard ways of capturing data, such as induction loops and camcorders, were applied for this aim. Nevertheless, the introduction of unmanned aerial vehicles (UAVs) has opened new possibilities in this subject, leading to extensive study in computer vision. However, there are still issues in object detection and tracking because of the complexities that come from a high number of objects, shifting heights of unmanned aerial vehicles (UAVs), and variable lighting conditions. Our study provides a new approach that combines centroid tracking with the YOLOv5 algorithm to successfully monitor and identify vehicles. To acquire an accurate analysis, we began our method by aligning and referencing aerial images. These basic measurements assisted the advancement to next phases covering feature extraction, segmentation of the region of interest, and tasks connected to detection and tracking. The effectiveness of our technique was tested by applying it to the VAID dataset, resulting in amazing levels of accuracy demonstrated by our recommended solution. Our system exhibited an unparalleled accuracy of 98.5% for object detection and a reasonable 90.9% for tracking tests. The validation indicates the robustness and efficacy of our designed system in solving the obstacles given by sophisticated aerial surveillance conditions. © 2024 IEEE.

关键词： Object 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

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

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：