检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hu, Xinyi Lee, Jasper C.H. Lee, Jimmy H.M. Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Sciences Institute for Foundations of Data Science University of Wisconsin–Madison WI United States

Consider the setting of constrained optimization, with some parameters unknown at solving time and requiring prediction from relevant features. Predict+Optimize is a recent framework for end-to-end training supervised learning models for such predictions, incorporating information about the optimization problem in the training process in order to yield better predictions in terms of the quality of the predicted solution under the true parameters. Almost all prior works have focused on the special case where the unknowns appear only in the optimization objective and not the constraints. Hu et al. proposed the first adaptation of Predict+Optimize to handle unknowns appearing in constraints, but the framework has somewhat ad-hoc elements, and they provided a training algorithm only for covering and packing linear programs. In this work, we give a new simpler and more powerful framework called Two-Stage Predict+Optimize, which we believe should be the canonical framework for the Predict+Optimize setting. We also give a training algorithm usable for all mixed integer linear programs, vastly generalizing the applicability of the framework. Experimental results demonstrate the superior prediction performance of our training framework over all classical and state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Video Frame Prediction Using Convolutional LSTM Encoder and Decoder

Video Frame Prediction Using Convolutional LSTM Encoder and ...

引用

data, Computation and Communication (ICDCC), International Conference on

作者： G. Revathy Pavithra Jagadeesan R. Vajubunnisa Begum Vijay Anand P H. Jasmin S. Gayathri Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Computer Science and Engineering Karpaga vinayaga college of engineering and technology Chennai India Department of Electronics and Communication Science Justice Basheer Ahmed Sayeed College for Women Affiliated by University of Madras Teynampet Chennai Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering K. Ramakrishnan College of Technology Trichy Tamilnadu India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

With rapid growth of audiovisual content now spreading through social networking sites, chances of exposure towards violent and mature content by the youth are growing. This project addresses the risk of detection of such content using advanced video frame prediction techniques. We present here an encoder-decoder model of Convolutional LSTMs in the film for violent and obscene sequence detection. The spatiotemporal nature of video data encourages our algorithm to exploit accurate predictions of future frames from past content, which can be used in real time for dangerous material detection. The study relies on recent literature that highlights the psychological implications arising from the viewing of violent content by teenagers, thus making the need for efficient automated detection mechanisms ever more pertinent. Furthermore, we present a complete definition of “violence” for the standardized detection mechanisms and to cross-compare various studies. Using Violent Scene Detection, our results indicate high improvements in the detection accuracy and therefore become effective in this context for parental control and content moderation. Such results help safeguard children in the increasingly digital environment: traditional as well as currently ever-increasing.

关键词： Accuracy Social networking (online) Psychology Machine learning Streaming media Prediction algorithms Real-time systems Spatiotemporal phenomena Decoding Long short term memory

来源：评论

学校读者我要写书评

暂无评论

data-Driven Design for Anomaly Detection in Network Access Control Systems

Data-Driven Design for Anomaly Detection in Network Access C...

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Musa Abubakar Muhammad Fabio Caraffini Adebamigbe Fasanmade Olabayo Ishola Kabiru Mohammed Jarrad Morden School of Computing Mathematics and Data Science Coventry University Coventry UK Department of Computer Science Swansea University Swansea UK School of Computer Science and Informatics De Montfort University Leicester UK

Current network access control systems can contain unpredictable interactions between multiple device models, multiple network protocol layers (e.g. TCP, UDP and ICMP), hardware, and clock-skew-specific influences, and cannot detect or identify abnormal behaviours based on the type of device. To complicate things further, the ‘bring your own device’ policy is increasing security threats, vulnerabilities, and risks to enterprise network environments, making intrusion detection and prevention systems unable to detect illegal and unauthorised access to devices in the enterprise network. The consequences can be disastrous. In this light, this work propose a simple but effective clustering approach capable of separating normal and abnormal network traffic patterns to detect such challenges (anomalies). The work in this paper applies this approach to single devices and aggregations of data per device type. Additionally, this work propose plotting the notched box for each cluster to acquire a better understanding of their data distributions and measuring the clusters’ performance using the Adjusted Rand Index. The results show that the proposed method is valid, can be used in several contexts, and features a 95% confidence that most single device and device type distributions overlap, which makes them equivalently usable for anomaly detection purposes.

关键词： Performance evaluation Access control Protocols Clustering algorithms Telecommunication traffic Partitioning algorithms Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Determining Variables Associated with Annual Oil Palm Yield: An Explainable Gradient Boosting Approach

引用

Procedia computer science 2023年 227卷 262-271页

作者： Gregorius Natanael Elwirehardja Teddy Suparyanto Miftakhurrokhmat Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia 55282 Faculty of Industrial Technology Universitas Islam Indonesia Yogyakarta Indonesia 55584 Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

With the growing demands for Precision Agriculture (PA) in Indonesia, researchers have evaluated the utilization of Machine Learning for predicting oil palm yields and determining variables affecting them. Previous studies showed that meteorological variables, including rainfalls and wind speed, are associated with oil palm yields. In this research, the Extreme Gradient Boosting (XGBoost) model and the Shapley Additive exPlanations (SHAP) were deployed for analyzing the importance of 15 agrometeorological variables in predicting oil palm yield. The best model attained 1.911 RMSE and 0.855 R2. By analyzing the weights and gains of the XGBoost model along with the SHAP values, it was found that the yield in the previous year, the age and number of plants, the area of peat lands, and meteorological parameters such as rainfall rates and the number of rainy days in the previous three years were considered important. The previous year's yield in particular possesses the greatest weight and gain values according to the model, and the highest SHAP value among all input variables. However, the meteorological data used in this research are only limited to rainfall rates and the number of rainy days. In the future, more diverse variables can be analyzed.

关键词： Oil Palm Yield Machine Learning XGBoost XAI SHAP

来源：评论

学校读者我要写书评

暂无评论

Character Classification and Actor Recognition in Yakshagana Images Using Machine Learning Techniques and Facial Makeup Pattern Analysis

Character Classification and Actor Recognition in Yakshagana...

引用

IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)

作者： Anantha Murthy Prathwini Sanjeev Kulkarni Savitha G Department of Master of Computer Applications NMAM Institute of Technology NITTE (Deemed to be University) Nitte Karkala and and Research Scholar Institute of Computer Science and Information Science” Srinivas University India Department of Master of Computer Applications NMAM Institute of Technology NITTE (Deemed to be University) Nitte Karkala India Department of Computer Science and Engineering Srinivas University Institute of Engineering and Technology Mangalore India Department of Data Science and Computer Applications Manipal Academy of higher Education Manipal Institute of Technology Manipal

ISBN: (数字)9798350350593

ISBN: (纸本)9798350350609

Yakshagana, a traditional theater form from Karnataka, India, features a unique combination of vibrant costumes, dynamic dance movements, and elaborate facial makeup, making character and actor identification a challenging task for automated systems. This research work presents a novel approach to classify Yakshagana characters into two primary categories, Vaishnava and Shaiva, and to identify the actors performing these characters using advanced machine learning techniques. Our research employs a Cyclic Gated Recurrent Neural Network (Cyclic GRNN) for classification and identification tasks. For character category classification, we integrate YOLOv3 and Faster R-CNN models, achieving an accuracy of 92.85% with YOLOv3 and 88.285% with Faster R-CNN. The categorization is specifically focused on distinguishing between Vaishnava and Shaiva characters. Additionally, for actor name identification, we utilize a RESNET-50 model, attaining a high accuracy of 95.60%. The results demonstrate the efficacy of Cyclic GRNN combined with state-of-the-art object detection and image classification models in accurately recognizing and categorizing Yakshagana characters and actors. This research contributes to the preservation and digital documentation of Yakshagana by providing robust tools for automated identification, thereby facilitating cultural heritage studies and enhancing audience engagement with this traditional art form.

关键词： YOLO Accuracy Image recognition Recurrent neural networks Machine learning Documentation Logic gates Character recognition Cultural differences Image classification

来源：评论

学校读者我要写书评

暂无评论

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Guotong Wu Yang Nan Ke Shang Hisao Ishibuchi Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC.

关键词： Training Accuracy Machine learning Approximation algorithms Graph neural networks Approximation methods Cybernetics Testing

来源：评论

学校读者我要写书评

暂无评论

NLP Model for Postgraduate Research Examiner Recommendation Based on Scholarly Activity

NLP Model for Postgraduate Research Examiner Recommendation ...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Sadura Priscilla Akinrinwa Samuel Tolulope Ogunjo Kehinde Dennis Akinrinwa Department of Data Science Federal University of Technology Akure Akure Nigeria Department of Physics Federal University of Technology Akure Akure Nigeria Department of Computer Science Federal University of Technology Akure Akure Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Fairness and equity is important in postgraduate research assessment to deter malpractice, mitigate victimization of students, and protect the integrity of the process. Most universities in Africa rely on a human based system to appoint internal and external assessors for postgraduate students’ thesis. This approach is fraught with nepotism and devoid of fairness. In this study, a natural language processing model is proposed for the appointment of internal assessors for postgraduate thesis using the Federal University of Technology Akure, Nigeria as a case study. Our approach utilizes the cosine similarity function to compare students’ abstract with published abstracts of qualified examiners in SCOPUS database. Results obtained in this study showed marked difference between existing approach and the proposed method. Difference in cosine similarity scores was found to be in the range 0.0961 and 0.3345. Specifically, the algorithm showed examiners with better similarity to the students’ work. The approach proposed in this work can significantly improve the assignment of assessors for postgraduate students using a transparent, less bias, and more reliable method.

关键词： Text mining Humanities Machine learning algorithms databases Reviews Ecosystems Natural language processing Recycling Reliability Recommender systems

来源：评论

学校读者我要写书评

暂无评论

SoMeLVLM: A Large Vision Language Model for Social Media Processing

arXiv

引用

arXiv 2024年

作者： Zhang, Xinnong Kuang, Haoyu Mou, Xinyi Lyu, Hanjia Wu, Kun Chen, Siming Luo, Jiebo Huang, Xuanjing Wei, Zhongyu Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China School of Data Science Fudan University China Department of Computer Science University of Rochester United States School of Computer Science Fudan University China Research Institute of Intelligent Complex Systems Fudan University China

The growth of social media, characterized by its multimodal nature, has led to the emergence of diverse phenomena and challenges, which calls for an effective approach to uniformly solve automated tasks. The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks. In this paper, we introduce a Large Vision Language Model for Social Media Processing (SoMeLVLM), which is a cognitive framework equipped with five key capabilities including knowledge & comprehension, application, analysis, evaluation, and creation. SoMeLVLM is designed to understand and generate realistic social media behavior. We have developed a 654k multimodal social media instruction-tuning dataset to support our cognitive framework and fine-tune our model. Our experiments demonstrate that SoMeLVLM achieves state-of-the-art performance in multiple social media tasks. Further analysis shows its significant advantages over baselines in terms of cognitive abilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Implementation of Indexing Techniques to Prevent data Leakage and Duplication in Internet

Implementation of Indexing Techniques to Prevent Data Leakag...

引用

2022 IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2022

作者： Nalini, M.K. Dhinakaran, K. Elantamilan, D. Gnanavel, R. Vinod, D. BMS College of Engineering Department of ISE Bangalore India Dhanalakshmi College of Engineering Department of Artificial Intelligence and Data Science Chennai India VallalP. T. LeeChengalvarayaNaicker Arts and Science College Department of Computer Science Chennai India R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Dept of CSE Chennai India

ISBN: (纸本)9781665495295

Research in this area aims to create a new and efficient method for detecting near-duplicates in online content. Web pages that a search engine has scoured are first parsed to remove HTML elements and java scripts. After this phase, remove common keywords or stop words from the crawled pages. The affixes (prefix and suffix) from crawled pages are drawn by extracting keywords from the text. Finally, the collected keywords generate the similarity score between two papers. This research has proved that the suggested algorithms outperform earlier ones by conducting an extensive experimental investigation on several actual datasets. New algorithms outperform those already in use, according to the test findings. Since there are so many documents on the internet, web search engines have had difficulty finding relevant results for their customers. Overhead costs for search engines have risen dramatically due to an overabundance of almost similar or identical documents somehow. The web crawling community has long been aware of duplicate and near-identical online pages. Users want search engines to return relevant results for their searches on the first page, free of duplicates and redundancies. This is an important criterion. An essential enabler in the health industry is record or data linking, as connected data is an economic resource that may aid enhance research into health policy, detecting bad medication responses, and cutting expenses while uncovering health system fraud. Recent years have seen significant progress in several record linking approaches, mostly due to breakthroughs in data mining and machine learning. Most of these novel technologies have not yet been incorporated in current record linking systems or are disguised in commercial software as 'black boxes.' When it comes to learning about new record linking strategies and comparing old methods with new ones, this makes it difficult for users to do so. Innovative record-linking systems must be tested and im

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy

arXiv

引用

arXiv 2023年

作者： Wang, Chendi Su, Buxin Ye, Jiayuan Shokri, Reza Su, Weijie J. Wharton Statistics and Data Science Department University of Pennsylvania Shenzhen Research Institute of Big data China Department of Mathematics University of Pennsylvania United States Department of Computer Science National University of Singapore Singapore

Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling. However, such randomness is difficult to take into account when proving differential privacy bounds because it induces mixture distributions for the algorithm’s output that are difficult to analyze. This paper focuses on improving privacy bounds for shuffling models and one-iteration differentially private gradient descent (DP-GD) with random initializations using f-DP. We derive a closed-form expression of the trade-off function for shuffling models that outperforms the most up-to-date results based on (ϵ, δ)-DP. Moreover, we investigate the effects of random initialization on the privacy of one-iteration DP-GD. Our numerical computations of the trade-off function indicate that random initialization can enhance the privacy of DP-GD. Our analysis of f-DP guarantees for these mixture mechanisms relies on an inequality for trade-off functions introduced in this paper. This inequality implies the joint convexity of F-divergences. Finally, we study an f-DP analog of the advanced joint convexity of the hockey-stick divergence related to (ϵ, δ)-DP and apply it to analyze the privacy of mixture mechanisms. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：