检索结果-内蒙古大学图书馆

IEEE Region 10 International Conference TENCON

作者： Babita Deepak Ranjan Nayak Dept. of Computer Science and Engineering Malaviya National Institute of Technology Jaipur India

ISBN: (数字)9798350350821

ISBN: (纸本)9798350350838

Classification of multiclass breast cancer through histopathological images is indispensable and poses daunting challenges due to color inconsistencies, high appearance variations, and large inter-class similarities. Regardless of the success of traditional convolutional neural networks (CNNs) and vision transformers (ViTs), they often fail to capture intricate patterns and local contextual information, respectively, while demanding high computational resources and data requirements. To mitigate these issues, this paper proposes a lightweight convo-lutional transformer network named LiCT-Net for multiclass breast cancer classification. The LiCT-Net introduces a local-global spatially-aware transformer layer and integrates it with a pre-trained FastViT model to effectively capture global and local contextual features, thereby facilitating learning fine-grained and intricate lesion patterns from histopathological images. The LiCT-Net is validated on a benchmark dataset and the experimental results and comparative analysis demonstrate its effectiveness. In specific, it achieves a higher accuracy of 96.16 %, 95.62 %, 95.25 %, and 94.21 % on $40\times, 100\times, 200\times$ , and $400\times$ magniflcations respectively,

关键词： Training Image color analysis Computational modeling Benchmark testing Transformers Breast cancer Lesions Convolutional neural networks Kernel Context modeling

来源：评论

学校读者我要写书评

暂无评论

A Study on Predicting Ratings System through Sentiment Analysis and Clustering of Coupang Product Reviews

A Study on Predicting Ratings System through Sentiment Analy...

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Si-Yoon Sung Jin-Woo Jung Dept. of Computer Science and Engineering Dongguk Univ. Seoul South Korea

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

With the expansion of e-commerce platforms, online reviews have become increasingly important. Users often decide on purchases based on reviews and ratings. This study notes that reviews with identical ratings can differ in emotional content and hypothesizes that overall satisfaction can be inferred from these emotions. The aim is to develop a system to quantify satisfaction based on review content, especially when ratings are absent. This approach addresses situations where reviews lack ratings or users struggle to rate products despite providing feedback. We crawled product reviews from Coupang and performed sentiment analysis using a BERT model tailored for Korean. The sentiment analysis results were clustered using six different algorithms, and the outcomes were evaluated. The study explored the best methodology among 30 combinations of clustering algorithms and hyper-parameters. For evaluation, ‘accuracy’ and ‘mean absolute error’ were used as external metrics to compare with actual ratings, while the ‘silhouette coefficient’ was used as an internal metric to assess cluster clarity. Agglomerative Clustering showed the highest performance in external metrics but lower internal metric performance. Spectral Clustering demonstrated well-balanced and excellent performance across all metrics.

关键词： Measurement Sentiment analysis Analytical models Reviews Clustering algorithms Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Automating Document Classification in the Financial Markets: A Comparative Study of Simple Models Versus Complex Models

Automating Document Classification in the Financial Markets:...

引用

International Conference on Advanced Systems and Electric Technologies (IC_ASET)

作者： Houda Atmani Mohamed Tarik Moutacalli dept. of Mathematics Computer Science and Engineering University of Quebec at Rimouski Quebec Canada

ISBN: (数字)9798350384895

ISBN: (纸本)9798350384901

As the volume of textual data continues to surge, the demand for automated techniques to classify and analyze large text datasets intensifies. This article addresses the critical task of text classification, particularly in the context of financial market regulation, where efficient document analysis is paramount. Our study conducts a comparative analysis employing both simple learning models and complex language models to automate and enhance document classification. By leveraging a diverse dataset from a prominent online platform, meticulous preprocessing techniques, and rigorous Out of Sample testing, we aim to evaluate the generalizability of our models across various contexts and datasets, including the complexities and biases inherent in real so-cial media data. Results indicate that the Random Forest emerges as a standout performer among simple models, achieving a low error rate of 3.755% and a notable False Negative Rate (PI0) of 3.154 %. Conversely, among complex models, the Bidirectional Encoder Representations from Transformers (BERT) is identified as the preferred choice, displaying a superior balance of a low error rate of 2.843% and a minimal PI0 of 2% at a threshold of 0.9. This research not only provides insights into effective resource prioritization for businesses but also acknowledges the challenges of working with real social media data, emphasizing the importance of capturing and addressing the intricacies and biases present in such datasets. Future avenues of exploration may include advanced data balancing methods, sophisticated preprocessing techniques, and alternative classification models to further enrich document classification research in dynamic social media contexts and beyond.

关键词： Analytical models Error analysis Social networking (online) Text categorization Data models Regulation Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Segmentation of Weed Images in crop fields using U-Net

Deep Learning Based Segmentation of Weed Images in crop fiel...

引用

Advancement in Technology (ICONAT), International Conference for

作者： K. Jairam Naik Dept. of Computer Science & Engineering National Institute of Technology Raipur Raipur India

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

Weeds are problems for crop yields because they exert harmful effects on the yields by competing with cultivated crops for necessary resources like nutrients, sunlight, and soil. As a result, continual attempts are being made to create safer and more effective herbicide formulations. For precision weeding and to reduce pesticide pollution, segmenting weeds in photos is extremely important. However, weeds and crops are comparable in the field setting, making it challenging to precisely segregate weed from intricate field photos. A deep learning-based system for segmenting weeds from photos was proposed in this paper. This algorithm can distinguish between weeds and crops and soil in photos. Utilizing a condensed U-net, this semantic segmentation method was created. An image augmentation strategy was suggested because image tagging for the semantic segmentation of weeds is challenging. The classification algorithms used in the modified U-Net are Support Vector Machine (SVM), Random Forrest (RF) and Decision Tree (DT). These were also used for predicting the weed part in a sample image before their segmentation. The threshold accuracy for segmenting the image using to be around 51.85% with a segmentation time of approximately 01.02 ms whereas our modified U-Netis obtained 91.03% accuracy and the segmentation time of 50.35ms. The results showed the modified U-Net successfully differentiated weeds from images with numerous other plants. This study seeks to demonstrate that the weed-associated image segmentation technique is effectively identifying and separating weeds in intricate field conditions.

关键词： Training Support vector machines Radio frequency Image segmentation Accuracy Pollution Semantic segmentation Training data Soil Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Pre Shoplifting Suspicious Behavior Using Deep Learning 16

Detection of Pre Shoplifting Suspicious Behavior Using Deep ...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Shrestha, Sujan Taniguchi, Yoji Tanaka, Tetsuo Graduate school of Engineering Kanagawa Institute of Tehnology Course of Information and computer sciences Atsugi Japan Daiichi Institute of Technology Artificial Intelligence and Data Science Department of Information Tokyo Japan Kanagawa Institute of Technology Faculty of Information Technology Dept. of Information and Computer Sciences Atsugi Japan

ISBN: (纸本)9798350377903

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence;however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Social Media Mining: Twitter Sentiments Comparison

SSRN

引用

SSRN 2024年

作者： Sharma, Riya Junaid Rasool, Mir Arora, Komal Dept. of Computer Science and Engineering Lovely Professional University Punjab Phagwara India

Numerous social media platforms have evolved in the information era and absorbed themselves into our daily lives. These social networking sites generate large volumes of user data, which offer useful information to corporations and governments. However, efficiently going through the data to uncover meaningful information has grown more difficult due to the overwhelming amount of information available. Social media mining uses automated sentiment, feeling, and opinion analysis to identify insightful information in order to overcome this problem. Social media mining identifies patterns, trends, and insights that can guide decision-making and produce superior results across a wide range of disciplines by collecting, analyzing, and interpreting data from diverse platforms including Twitter, Instagram, and Facebook. An overview of the newly emerging discipline of social media mining, which entails the analysis of sizable datasets produced by social media platforms, is given in this review paper. In the paper, different social media mining methodologies and techniques are highlighted, such as sentiment analysis, text mining, and opinion analysis along with examining the challenges associated with social media mining. In addition, the paper explores the diverse applications of social media mining in areas such as marketing, public opinion analysis, and crisis management. © 2024, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Software Framework Based on JUnit for Automated Software Testing in computer science Courses

A Software Framework Based on JUnit for Automated Software T...

引用

Frontiers in Education (FIE) Conference

作者： Michael A. Zmuda Dept. of Computer Science and Software Engineering Miami University Oxford OH USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice full paper describes a new software framework based on JU nit to test student work. Automated testing is an important capability when teaching software development at the college level. Ideally, a testing system will allow the instructor to efficiently create a thorough set of tests. Also, the software should facilitate grading tasks and produce informative reports that can be distributed to the students in a timely fashion. For Java development, the well-known JUnit framework enables a test suite to be applied to a student's submission. The mutools library presented here extends the JUnit framework in novel ways to accelerate the instructor's task of creating test suites. This new framework allows the instructor to augment tests with directives to control scoring and reporting. The four main capabilities of the software include: 1) An assert statement that does not terminate the test when it has failed. Instead, statistics are maintained regarding the success or failure of each assert statement. 2) Tests that can be configured to award partial credit. This can be useful in situations where the instructor deems it appropriate to award students some credit even in the presence of incorrect asserts. 3) Tests that can be grouped into categories that match a particular rubric item. Java annotations are placed on the test suite to define these categories. For example, @TestCategory(name= “remove”, points=10.0) specifies that 10 points will be awarded for successful implementation of all tests related to removing an item from the collection class. 4) Testing reports that contain varying levels of information. With minimal details, the testing report shows each testing category with the following information: assert statistics, whether the test timed out or had abnormal termination. This software has been used for many semesters and has been found to increase the speed at which the instructor can develop test suites for grading. The framework is av

关键词： Software testing computer science Java Annotations Education Life estimation Software Libraries Software development management

来源：评论

学校读者我要写书评

暂无评论

CAPLC: Cellular Automata-Powered Lightweight Cipher-Unveiling Secure Communication in Resource-Constrained Environments Using Cellular Automata and Henon Map

CAPLC: Cellular Automata-Powered Lightweight Cipher-Unveilin...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Biswarup Yogi Satyabrata Roy Umashankar Rawat Shweta Redkar Utsav Upadhyay Dept. of Computational Sciences Brainware University Kolkata West Bengal India Dept. of Computer Science and Engineering Manipal University Jaipur Rajasthan India Dept. of Data Science and Engineering Manipal University Jaipur Rajasthan India Dept. of Computer Science & Engineering Sir Padampat Singhania University Udaipur Rajasthan India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

In today's interconnected world, ensuring secure communication in resource-constrained contexts is still challenging. This study offers CAPLC, a novel technique for lightweight encryption that uses Cellular Automata (CA) and Henon maps. Its goal is to improve security in such situations. The method uses 1D Cellular Automata for initial data transformation and incorporates the Henon map to improve encryption strength. We used conventional metrics to evaluate CAPLC's effectiveness on image encryption, and the findings were promising: NPCR of 99.6154%, UACI of 33.88235, and PSNR of 9.1924. These numbers show the method's capacity to dramatically change image while maintaining quality and anonymity. The implications of CAPLC go beyond image encryption, providing a scalable solution for secure communication in circumstances with limited computational resources. Future studies ought to explore CAPLC's real-time application and performance across various kinds of datasets, with a focus on the potential of merging CA with Henon maps to create efficient encryption methods for improving secure communications technology.

关键词： Measurement Merging Automata Medical services Information processing Parallel processing Real-time systems Encryption Resilience Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Autonomous Drone Landing on a Moving Naval Base using Vision-Based Robot Control

Autonomous Drone Landing on a Moving Naval Base using Vision...

引用

2023 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Subamanian, Senthil Pon Vignesh Subramanian, Suvetha Meenaa Muthiah, Padmapriya Shajahan, Jalaluddin Mohd Ansari Saveetha University Simats School of Engineering Dept. of Elec. and Comm. Engg. Chennai India City University of New York City College of New York Dept. of Computer Science New York United States Monroe College King Graduate School Dept. of Computer Science New York United States City University of New York City College of New York Dept. of Electrical Engineering New York United States

ISBN: (纸本)9798350322972

This paper proposes a novel technique of an Autonomous Drone landing on top of a moving Naval Vessel Base using Vision-Based Robot Control. To achieve an effective landing a camera is fixed under the drone which captures the images and detects the movement of the landing base. The landing base on top of the vessel is specially designed with a nested tag which is scanned by the fixed camera on the drone from a high altitude. This nested tag is a fiducial marker that is used by the imaging system of the drone as a point of reference in the Naval Vessel Base for precise landing. The controller is designed in the image coordinate frame captured by the imaging system on the drone with the help of the Jacobian Matrix. Whether the vessel remains stationary or moving, it always trembles, especially, when a vessel experiences bad weather at sea, it will be quite challenging for the drone to land on the trembling Naval Vessel Base. These unexpected movements cause the landing tag to disorient from the horizontal view of the captured frames, which makes it difficult to obtain the expected mid-point of the tag. To overcome this complication the translational and rotational motions of the drone are decoupled from the camera using the Virtual Camera Method where the mid-point of the tag is set as the feature point which helps to obtain the expected position during the horizontal plane disorientation of the tag image captured by the camera from the drone. Additionally, Kalman Filter is employed in the imaging system to reduce the observation noise so that precise estimation of the feature point can be achieved. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An optimal energy-throughput efficient cross-layer solution using naked mole rat algorithm for wireless underground sensor networks 2

An optimal energy-throughput efficient cross-layer solution ...

引用

2nd Symposium on Synthesis, Characterization and Processing of Inorganic, Bio and Nano Materials, SCPINM 2021

作者： Singh, Pratap Singh, Rishi Pal Singh, Yudhvir Dept. of Computer Science and Engineering GJUSandT Hisar125001 India Dept. of Computer Science and Engineering MDU Rohtak124001 India

Wireless Underground Sensor Networks (WUSNs) have emerged as prominent solution for variety of applications such as monitoring of underground pipelines, maintenance of power grids, smart and precision agriculture, sports fields maintenance, keeping check on underground oil leakage and many more. Whereas traditional electromagnetic wave communication mechanism doesn't work good for such sensor networks, the magnetic induction (MI) technique offers stable communication channel conditions and therefore, is considered better option by researchers. As well as communication protocols are concerned in light of tough underground conditions, cross-layered approach has proven to be better in comparison to conventional layered protocol approach. In this article, a distributed cross-layer solution for MI-operated WUSNs will be proposed, which is based on a novel optimization approach - Naked Mole Rat algorithm (NMRA). This Distributed Energy-Throughput Efficient Cross-Layer solution using NMRA approach, also called as DECN, has been developed for Direct MI communication as well as MI waveguide communication (using relay coils) using the interaction of various layer features to fulfill Quality of Service (QoS) parameters and attain an optimal saving in energy consumption and at the same time, gain in throughput. The simulation results have indicated that significant energy saving, high performance efficiency and reliable channel communication are achieved with the proposed cross-layered approach for WUSNs. © 2021 Elsevier Ltd. All rights reserved.

关键词： Rats

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：