检索结果-内蒙古大学图书馆

4th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2023

作者： Han, Yue Fu, Zhenyong Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350306323

Automatic Check-Out (ACO) aims to accurately forecast the presence and counts of each product in any given product combination. This paper concentrates on the ACO problem within generalized zero-shot Learning (GZSL) setting. Many recent GZSL studies have adopted a feature generation approach. However, these methods treat each class synthesis process independently, ignoring the rich dependency structure of different classes and their compositions. We propose a generative model that captures the common structure between classes and a classifier which optimizes classification boundaries by imposing a multi-class Deep SVDD constraint on seen classes. The evaluations are performed on the large-scale RPC dataset during the experiments. © 2023 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Smart Classroom Using Cisco Packet Tracer 1

Design and Implementation of Smart Classroom Using Cisco Pac...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Duvvuri, Kavya Kanisettypalli, Harshitha Kunisetty, Jaswanth Khanna, Manju Amrita School of Engineering Dept. of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798350348057

schools and colleges play a very crucial role in everyone's life. It is very important to impart good morals and safe education to future generations. As days go by, the necessity for faster job completion and smarter devices is increasing. The safety of students becomes important as the number of students enrolling in schools is gradually increasing. Discipline and time management skills must be imparted to students from a tender age in the school environment. Both safety and discipline can be ensured by making use of devices that are smarter and remotely controllable. Through this work, we have introduced the design of a smart classroom using a network simulation called Cisco Packet Tracer. The work is based on the concept of the Internet of Things. It has multiple subsystems that together make the class a wonderful place for students to build their future. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

On the Adversarial Robustness of Hierarchical Classification

On the Adversarial Robustness of Hierarchical Classification

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Ran Zeng, Simeng Wu, Wenhui Jia, Yuheng Ng, Wing W. Y. Wang, Xizhao School of Mathematical Sciences Shenzhen University Shenzhen518060 China College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China School of Computer Science and Engineering Southeast University Nanjing211189 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9781665410205

Deep neural networks (DNNs) have demonstrated remarkable success on various learning problems, but they face a formidable challenge in the form of adversarial attacks. Especially, when dealing with complex classification tasks for numerous classes with a hierarchical structure, the adversarial robustness of a DNN model may drop seriously. In this paper, we investigate the adversarial robustness of DNN models on such complex classification tasks. In response, we propose a two-stage hierarchical classification framework, which is composed of a coarse-grained classifier and a series of fine-grained classifiers. A data correction sampling module is designed between the two stages, in order to mitigate the influence of misclassification caused by the coarse-grained classifier;and a discriminative filter learning module is employed in the fine-grained classification, in order to gain better distinguish abilities among fine-grained categories. Experiments on the well-known dataset CIFAR-100 and a newly-constructed hierarchical dataset mini-ImageNet76 demonstrate that employing a hierarchical framework can effectively improve the model robustness on such complex classification tasks. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning and the K-Nearest Neighbour Classification Method to Assess Autism Risk 4

Using Machine Learning and the K-Nearest Neighbour Classific...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Singla, Muskan Gill, Kanwarpartap Singh Aggarwal, Priyanshi Rawat, Ramesh Singh Chanti, Yerrolla Chitkara University Institute of Engineering and Technology Punjab India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350307757

The K-Nearest Neighbour (KNN) classification approach, one of the machine learning algorithms examined in this work, is used to determine a person's likelihood of developing autism spectrum disorder (ASD). The study use a dataset that encompasses a wide range of elements and practical training, such as behavioural characteristics, demographic data, and clinical markers linked to Autism Spectrum Disorder (ASD). The K-nearest neighbours (KNN) technique, renowned for its simplicity and efficacy in classification tasks, is used to examine patterns within the dataset and provide predictions pertaining to the probability of autism. The research starts with the first stage of data preparation, which access the processes of feature selection and normalisation. These steps are undertaken to optimise the performance of the model. Following this, a thorough assessment of the K-Nearest Neighbours (KNN) method is undertaken, taking into account various hyperparameter configurations and evaluating its efficacy in properly categorising and accessing people into Autism Spectrum Disorder (ASD) and non-ASD groups. The results demonstrate the effectiveness of the algorithm in identifying subtle patterns within the dataset, so enhancing our comprehensive comprehension of the elements that influence the risk of autism. The study findings have broader significance outside the field of diagnostics, as the model's precision that was established has the capacity to support clinicians and researchers in identifying and intervening early with people who are at risk of Autism Spectrum Disorder (ASD). This work makes a valuable contribution to the continuing endeavours aimed at improving the accuracy and effectiveness of autism risk assessment via the integration of machine learning approaches. Ultimately, this research aims to provide timely and targeted therapies, leading to enhanced results. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Contour Refinement for Box Based Interactive Object Segmentation

Contour Refinement for Box Based Interactive Object Segmenta...

引用

2023 International Conference on Communications, Computing and Artificial Intelligence, CCCAI 2023

作者： Ma, Jing Shi, Ran Shen, Xiaobo Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350311297

As the development of interactive object segmentation, the optimization of the segmented contour draws much attention. Inspired by current interactive object segmentation and contour-based methods, this paper proposes an end-to-end framework for contour refinement for box based interactive object segmentation. Compared with traditional interactive object segmentation approaches, our method not only constrains the scope of segmentation in terms of region, but also controls and optimizes the deformational results of the contour, which achieves the goal of refined interactive object segmentation. We build a complete system including a contour extraction model and a contour deformation model. The initial contour extracted from the result of segmentation by the contour extraction model is fed to the contour deformation model for vertices offset and contour deformation. Meanwhile, we perform dynamic dilation for the initial contour before contour refinement to improve the feature information provided by the contour extraction model. In addition, we put the compactness of each contour as a reference factor into the point set sampled on the contour to solve the problem of over-sharp boundary. Experiments show that the proposed method achieves advanced performance for interactive object segmentation. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A comparative review on machine learning based medical diagnostic systems for Chikungunya and Zika virus 4th

A comparative review on machine learning based medical diagn...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Gupta, Nisha Singh, Harjeet Singla, Jimmy Chitkara Institute of Engineering and Technology Chitkara University India School of Computer Science and Engineering Lovely Professional University India

ISBN: (纸本)9781032911571

The Chikungunya arbovirus and zika virus have recently experienced widespread outbreaks, which have allowed the virus to spread rapidly worldwide. These illnesses initially manifest as an acute stage of fever and severe joint inflammation. However, this stage gradually turns into a chronic stage, and during this time, a person experiences debilitating articular pain that is persistent and long-lasting. Additionally, the traditional methodologies used to identify it are not very effective and time-consuming. However, in the current years, the advancement in technology assists in monitoring, diagnosing, and treating individuals suffering from this virus remotely. For healthcare systems, Machine Learning (ML) is a godsend since it helps experts identify, diagnose, treat, and control dangerous diseases. In order to detect Zika and Chikungunya virus, this review study evaluates and compares the performance parameters of various ML approaches utilized in existing studies. This paper discusses the top techniques for diagnosing the selected viruses and offers a thorough evaluation of medical expert systems. © 2025 the Author(s).

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Framework for Face recognition and Scene Description using Deep Learning for Visually Challenged people 1

Framework for Face recognition and Scene Description using D...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Sharon, Felicia Sellamuthu, Suseela Nachiyappan, S. Akila, V. Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Gokaraju Rangaraju Institute of Engineering and Technology School of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350359756

In today's world, independent living becomes increasingly crucial for those who are visually impaired, as they encounter numerous challenges. Visually impaired people are at a disadvantage since they need manual help to compel information about their surroundings. Since many tasks require visual information, visually impaired persons find it difficult to complete many of life's essential chores, such as going for a stroll, eating, and conversing with a group of people. As technology has advanced, helping the blind is now possible. This project offers an advanced solution to assist visually challenged individuals, taking advantage of recent advancements in Artificial Intelligence (AI) Technologies and Deep Learning frameworks. This project proposes a sophisticated system to help visually challenged people. The system uses a novel strategy of combining Deep Learning Faster R-CNN ResNet-50 FPN for object detection, CNN ResNet-50 for Face recognition, and CNN ResNet-50 and LSTM for Image Captioning and adding some more objects to the existing dataset to customize it for visually impaired people. Then a voice message is generated to assist the Visually Impaired person. Furthermore, each of the models used in the system is compared with two other models to determine the most effective model. Of all the three models used for Face recognition, Image Captioning, and Object detection, the proposed system performs the best with 80.6%, 0.493(BLEU-1), and 92.7% respectively. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Interpretable Fake News Detection on Social Media 23

Interpretable Fake News Detection on Social Media

引用

6th International Conference on Software engineering and Information Management, ICSIM 2023

作者： Xu, Xiwei Qin, Ke School of Computer Science and Engineering University of Electronic Science and Technology of China China

ISBN: (纸本)9781450398237

With the development of information technology, public opinion can quickly spread to all over the world, permeate every corner of social life, and have a great impact on human's lives. Extracted from large-scale and multi-mode social media, user-generated information is anonymous and noisy. It is found that users' social interaction helps to detect fake news. At present, most methods focus on effectively detecting fake news with potential characteristics, but most models are lack of interpretability. Therefore, this paper studies the interpretable detection of fake information in public social media platform, and proposes a model based on in-depth sentence-comment interactive reasoning network. The model uses fake information content and user comments to capture the most worth checking information sentences from user comments, in order to detect fake information and provide some explanation. This paper solves the following challenges: (1) how to detect fake news while improving the detection performance and interpretability;(2) how to extract the correlation between false content and user comments in the social media platform. © 2023 ACM.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Practical Teaching Methods of Oral English Under the Background of Big Data and Artificial Intelligence

引用

computer-Aided Design and Applications 2023年第S9期20卷 256-265页

作者： Yang, Yifang Chen, Aimin School of Humanities Hunan City University Yiyang413000 China School of Computer and Engineering Hunan University of Science and Technology Xiangtan411100 China

As an integral part of education, the goal of oral English is to enable students to master the basic knowledge and skills of the language, and to lay a good foundation for the sustainable development of students. The purpose of oral English teaching is to stimulate and cultivate students' interest in learning and to improve their oral English level. With the rapid application of data science and AI algorithms in various industries, all industries are developing in the direction of intelligence, and major changes are also taking place in the education industry. In the context of big data and artificial intelligence, teaching methods are no longer limited to traditional task-based teaching or other oral language teaching modes, but to intelligently recommend teaching based on the actual situation of students. © 2023 CAD Solutions, LLC.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Optimizing University Time Table Schedules for Smart Space Utilization 5

Optimizing University Time Table Schedules for Smart Space U...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Dasari, Chetan Aditya Kumar, Solasa Manikanta Arpitalaxmi, Arpitalaxmi Thushara, M.G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Applications Amritapuri India

ISBN: (纸本)9798350376685

Manual university course timetable scheduling is a time-consuming and error-prone process, often resulting in conflicts and inefficiencies. An optimized timetable is crucial for smooth academic operations, ensuring efficient use of resources and fostering a positive learning environment for students and faculty. We address the challenge of university course scheduling by proposing an optimized time-table scheduling algorithm. This paper will identify suitable approaches to automate timetable generation, considering factors like lecturer availability, student groups, room capacity, and course requirements. Keeping track of all the different factors that affect things like course requirements, teacher availability, room capacity, and fair task distribution is hard. By working on slot-based scheduling methods, we hope to find ways to make the schedule work best for both students and teachers, which will make everyone happier and help them learn more. © 2024 IEEE.

关键词： Students

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：