检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Malik, Kush Pandey, Manas Khan, Asma Srivastav, Manvesh Gera, Anju Chauhan, Sansar Singh G L Bajaj Institute of Technology and Management Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

Preventing crime is important for justice and safety in cities. Using computers to predict crime trends can help make cities safer. Reliable real-time crime prediction is necessary for public safety, but there are still difficulties facing science. Crime rates are influenced by numerous intricate factors. Crime is low in comparison to many predictable events. For computer systems, determining the criminal activity rate, kinds, and hotspots based on historical patterns is both a challenge and an opportunity. The accuracy of machine learning using SVM stacking, KNN, Naïve Bayes, Random Forest, and deep learning using LSTM are compared in this study. This paper presents a comprehensive review of the literature on deep learning and machine learning approaches to crime prediction. It's an important tool for scholars studying the subject because it provides information that law enforcement organizations can use to improve how they prevent and deal with criminal activity. Moreover, the system outlined in the paper offers predictions about potential future crimes, allowing for proactive measures to be taken to prevent them. © 2024 IEEE.

关键词： Crime prediction deep learning KNN LSTM machine learning Naïve Bayes Random Forest SVM stacking

来源：评论

学校读者我要写书评

暂无评论

Layoffs Analysis and Prediction Using Machine Learning Algorithms 6th

Layoffs Analysis and Prediction Using Machine Learning Algor...

引用

6th International Conference on Communications and Cyber-Physical engineering, ICCCE 2023

作者： Prakash, P. Sakthivel, V. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India

ISBN: (纸本)9789819971367

This research aims to develop a model that can predict layoffs within a company using a combination of financial performance, industry trends, and company demographics as input variables. A machine learning algorithm was trained and tested using a dataset of historical data to identify patterns and correlations between these factors and layoffs. The model was then evaluated using a separate dataset to determine its accuracy in predicting future layoffs. The results showed that the model performed well, with high degree of accuracy in predicting layoffs. The research provides valuable insights for companies to better prepare for potential workforce reductions and for employees to anticipate potential job loss. The ability to predict layoffs can also help companies make better decisions on how to manage their workforce and minimize the impact on their employees. This research provides a valuable tool for companies to better plan for future workforce reductions, and for employees to be more aware of potential job loss. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fast face detection using a unified architecture for unconstrained and infrared face images

引用

Cognitive Systems Research 2022年 74卷 18-38页

作者： Dash, Priyabrata Ranjan Kisku, Dakshina Gupta, Phalguni Kanta Sing, Jamuna Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur721302 India Department of Computer Science and Engineering National Institute of Technology Durgapur West Bengal Durgapur713209 India Department of Computer Science and Engineering Institute of Engineering & Technology GLA University Uttar Pradesh Mathura281406 India Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata700032 India

Human face detection along with its localization is a difficult task when the face is presented in the cluttered scene in an unconstrained scenario that might be with arbitrary pose variations, occlusions, random backgrounds and infrared (IR) environment. This paper proposes a novel face detection method which can address some of these issues and challenges quite successfully during face detection in unconstrained as well as infrared environments. It makes use of Fast Successive Mean Quantization Transform (FastSMQT) features for image enhancement and feature representation to deal with illumination and sensor insensitiveness. A split up Sparse Network of Winnows (SNoW) with Winnow updating rule is then exploited to speed up the original SNoW classifier. Finally, the features and classifiers are combined together with skin detection algorithm for face detection in crowd image and head orientation correction of near infrared faces. The proposed face detector is robust in handling pose, occlusion, illumination, blur and low image resolution. The experiment is performed on six challenging and publicly available databases, viz. BIOID, LFW, FDDB, UFI, WIDER FACE and IIT Delhi near infrared. The experimental results depict that the proposed method outperforms traditional as well as some advanced methods in detecting unconstrained and infrared faces under challenging situations. © 2022 Elsevier B.V.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

HOLOAID: Revolutionizing Disaster Relief with Digital Holography 5

HOLOAID: Revolutionizing Disaster Relief with Digital Hologr...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Menaga, D. Vignesh, V. Vijay, S. St. Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

This research proposes a Virtual Reality Sensing System (VRSS) integrated with activity network technology to enhance emergency response coordination. By combining VR with real-time data from Wireless Sensor Networks (WSNs), the VRSS provides responders with an immersive and realistic simulation of disaster scenarios, including dynamic environmental conditions and obstacles. This immersive experience enables responders to practice critical decision-making, resource allocation, and coordinated response activities in a safe and controlled environment. Through iterative improvements and rigorous testing, the VRSS aims to enhance emergency preparedness, improve resource management, and ultimately improve the effectiveness of disaster response efforts. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Advancing Image Forgery Detection: A CNN-Based Approach 8

Advancing Image Forgery Detection: A CNN-Based Approach

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Nalini, N. Rakshitha, Sai Nithyashree, H.V. Rakshitha, S.L. Shravan, Motamarri Sai Uttej, K Sai Nitte Meenakshi Institute of Technology Dept. of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798331505462

In the digital age, image forgery is a significant concern due to advanced editing tools. This study addresses the need for reliable forgery detection, focusing on copy-move, splicing, and retouching techniques. Using Convolutional Neural Networks (CNNs) known for learning hierarchical image features, the research developed a robust detection system. The CNN model, trained on a diverse dataset which has over 10,000+ images and it is split into test and train data for better classification results, detected subtle inconsistencies indicative of manipulation, achieving a peak accuracy of 94% over 50 training epochs. Test cases showed the system effectively detected forged images and identified forgery types, though it had shortcomings with invalid inputs. The CNN architecture employed convolutional and max-pooling layers with specific hyperparameters to enhance feature extraction. This paper offers a valuable tool for digital forensics experts, law enforcement, and journalists to ensure the authenticity of visual content. © 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

Exploring Few-Shot Learning to Enhance NLP's Cross-Domain Capabilities

Exploring Few-Shot Learning to Enhance NLP's Cross-Domain Ca...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Balakrishnan, T. Suresh Gururama Senthilvel, P. Ebenezar, U. Samson Karthikeyan, L. Kishan, B.S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Saveetha University Department of Computer Science and Engineering Chennai India Bms Institute of Technology and Management Department of Mechanical Engineering Bangalore India

ISBN: (纸本)9798331538538

Here, few shot learning (FSL) has been identified as a valuable method for improving the flexibility of NLP when dealing with new and different datasets with small amounts of training data. Most of the traditional NLP models are affected by shift since they are based on a big data set of a different domain. To overcome this challenge, FSL facilitates training of models to extrapolate from a few examples and not necessarily from numerous samples that may be present in LMMs. In this paper, I delve into meta-learning, prompt-based learning, and transfer learning as some of the methods that can be applied to boost NLP's cross-domain performance. We explain how these methods contribute to enhance performance in the use of fewer resources and evaluate the efficiency of those techniques on textual classification, sentiment analysis, and machine translation. Also, the pretrained GPT and BERT are beneficial to few-shot learning as it takes place through contextual learning. Based on our results, the conclusion is made that the application of FSL techniques in NLP pipelines enhances generalization and reduces the time and expenses on data annotation. Yet, some of the challenges that are associated with text analytics are data bias, sensibility of the prompts and computational problems. Finally, we propose some future works for FSL such as: the proposal of a new FSL model that combines traditional supervised and unsupervised learning;the presentation of a new FSL model based on a reinforcement learning theory. Hence, with the use of FSL, NLP models can perform well in different domains of application with little to no labeled data hence transferring knowledge to different domains to increase efficiency and scale in knowledge. © 2025 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Taming Breast Cancer Diagnosis Through Transfer Learning: A Binary Classification Framework for Enhanced Disease Detection 4

Taming Breast Cancer Diagnosis Through Transfer Learning: A ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Shandilya, Gunjan Anand, Vatsala Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science Punjab India

ISBN: (纸本)9798350387490

Among the deadliest types of disease is cancer. It is also the most prevalent cancer in women, and if it is not correctly identified, it can even be fatal. Although medical technology has advanced significantly over the years, breast cancer detection remains a challenge that can only be solved through biopsy. By examining histological pictures seen under a microscope, pathologists can identify cancer. Visual inspection is an important part of cancer inspection;it takes time, competence, and a great deal of attention to detail. A quicker and more effective method of identifying breast cancer is therefore required. Numerous studies are being conducted to develop an effective partially or computer-monitored diagnostic system due to developments in deep learning and image analysis. To differentiate between benign and malignant forms of breast cancer, this study uses histopathological scans and convolutional neural networks in combination with transfer learning, a sophisticated kind of image-based machine learning. A large-scale multi-cancer dataset is used in the study's analysis. A refined VGG16 model that has been pre-trained for the categorization of breast cell images is presented in the article, exhibiting outstanding outcomes with an overall accuracy of 97.89 %, precision of 97 % and recall of 98 %. The incorporation of this model into healthcare systems has the potential to enable timely and precise diagnosis of breast cancer. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Tackling E-Waste Management Using Decentralized Marketplace Leveraging Ethereum Blockchain

Tackling E-Waste Management Using Decentralized Marketplace ...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Allu, Himasri Bharti, Anjali Satapathy, Shashank Mouli School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9798331540685

This study explores the implementation of a decen-tralized marketplace using blockchain technology for e-waste management. Through stakeholder-driven validation using the proof of stake and on-chain attestation, the platform ensures transparency and accountability in the e-waste supply chain. Integrating the Meta Mask wallet facilitates secure transactions, enhancing user experience and adoption. Results demonstrate a 95% reduction in transaction confirmation time and a 25% cost reduction in Ethereum transactions compared to SWIFT transfers, enhancing economic viability and user engagement. Leveraging blockchain for e-waste management presents a promising avenue for addressing complex supply chain challenges and advancing toward a more sustainable future. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Data Analysis on Determining False Movie Ratings

Data Analysis on Determining False Movie Ratings

引用

Congress on Control, Robotics, and Mechatronics, CRM 2023

作者： Sahni, Ridhika Arockiasamy, Karmel School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India

ISBN: (纸本)9789819955206

Online movie ratings have evolved into a serious business. Hollywood generates around $10 billion in box office revenue in the United States each year, and online ratings aggregators may have an increasing influence over where that money goes. A single film critic can no longer make or break a film, but perhaps thousands of critics, both professional and amateur, can how well can these platforms be trusted especially if they are showing the ratings and making money by selling the tickets? Do they have a bias by rating movies higher than it should be? The objective of the analysis is to provide brief research of one such online movie-ticket selling company, Fandango. The data collected from Fandango are analyzed and compared with the data collected from sites like Rotten Tomatoes, IMDB, and Metacritic. With the help of visualization, fraud and risk can be reduced offered by such online sites. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Wild-Animal Detection near Roads using IoT Sensor and Optimization

Machine Learning based Wild-Animal Detection near Roads usin...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Simonthomas, S. Rohith, K. Shalini, K.Shantha Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Chennai India Aarupadai Veedu Institute of Technology Department of Intelligence and Data Science Chennai India

ISBN: (纸本)9798331539948

The increasing incidence of vehicle-animal collisions poses significant risks to both human and wildlife safety. To address this challenge, the implementation of IoT (Internet of Things) sensor networks for wild-animal detection near roads offers a promising solution. This paper explores the design and deployment of an IoT-based system aimed at detecting the presence of wild animals near roadways, thereby enhancing road safety and wildlife conservation. The proposed system utilizes a network of infrared (IR) sensors, motion detectors, and cameras strategically placed along road sections prone to wildlife crossings. These sensors continuously monitor the area, and upon detecting an animal, they transmit real-time data to a central processing unit via wireless communication protocols. The system then processes this data to generate immediate alerts for drivers through connected road signs or mobile applications, warning them of potential hazards ahead. Additionally, the collected data is stored and analyzed to understand animal movement patterns, which aids in making informed decisions about further preventive measures and the placement of wildlife crossings. The incorporation of machine learning algorithms improves the system's precision in distinguishing between different types of animals and minimizing false alarms. This IoT sensor network not only mitigates the risk of accidents but also contributes to the conservation of wildlife by preventing unnecessary fatalities. This project explores the use of Genetic Algorithms (GA) to optimize a detection system that can identify wild animals near roadsides. The paper summarize with a discussion on the effectiveness of the system, potential challenges in implementation, and outlines future pathways for research and innovation in this domain. © 2024 IEEE.

关键词： Traffic signs

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：