检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ohayon, Guy Elad, Michael Michaeli, Tomer Faculty of Computer Science Technion-Israel Institute of Technology Israel Faculty of Electrical and Computer Engineering Technion-Israel Institute of Technology Israel

Fairness in image restoration tasks is the desire to treat different sub-groups of images equally well. Existing definitions of fairness in image restoration are highly restrictive. They consider a reconstruction to be a correct outcome for a group (e.g., women) only if it falls within the group's set of ground truth images (e.g., natural images of women);otherwise, it is considered entirely incorrect. Consequently, such definitions are prone to controversy, as errors in image restoration can manifest in various ways. In this work we offer an alternative approach towards fairness in image restoration, by considering the Group Perceptual Index (GPI), which we define as the statistical distance between the distribution of the group's ground truth images and the distribution of their reconstructions. We assess the fairness of an algorithm by comparing the GPI of different groups, and say that it achieves perfect Perceptual Fairness (PF) if the GPIs of all groups are identical. We motivate and theoretically study our new notion of fairness, draw its connection to previous ones, and demonstrate its utility on state-of-the-art face image restoration algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clickbait Detection in Indonesia Headline News Using BERT Ensemble Models 6

Clickbait Detection in Indonesia Headline News Using BERT En...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Syahputra, Muhammad Edo Kemala, Ade Putera Tjan, Farrel Alexander Susanto, Rudy School of Computer Science Computer Science Binus University Jakarta Indonesia Binus Universitty Faculty of Engineering Computer Engineering Jakarta Indonesia

ISBN: (纸本)9798350358346

This study explores the effectiveness of combining BERT (Bidirectional Encoder Representations from Transformers) with convolutional neural networks (CNN) and multilayer perceptrons (MLP) for a specific task. The results showcase promising performance of the BERT + CNN model, with precision, recall, and F1-score values of 0.91, 0.86, and 0.89, respectively. The BERT + MLP model exhibits consistent performance with an F1-score of 0.875. A comparative analysis against a previous study utilizing IndoBERT highlights the competitive edge of our BERT + CNN model, particularly in terms of recall and F1-score. Additionally, our proposed model demonstrates competitive performance against other state-of-the- art models such as RoBERTa and xlmRoBERTa. This study contributes valuable insights into the optimization of BERT -based models for specific tasks, emphasizing the efficacy of the BERT + CNN architecture. © 2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Edge Computing for Dual Hop Communication in Satellite Assisted UAVs enabled VANETs

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2024年第3期5卷 108-127页

作者： Hamdi, Mustafa Maad Rashid, Sami Abduljabbar Nafea, Ahmed Adil Department of Computer Science College of Computer Science and IT University of Anbar Ramadi Iraq Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Parit Raja Johor Batu Pahat86400 Malaysia Department of Artificial Intelligence College of Computer Science and IT University of Anbar Ramadi Iraq

VANETs are highly attractive and is used in maximum of the applications of cross-regional communication. To increase the coverage of the vehicular network, Unmanned Arial Vehicles (UAVs) are introduced, and they get connected with the satellite networks to perform heterogeneous communication. With the help of this connectivity, the communication quality of ground level to air medium is increased. Currently the vehicle usage is highly increased and as a results of communication link failure, improper resource allocation are arises whither abruptly assumes a stability about a network with that increases an energy consumption and communication delay in the heterogeneous networks. In these conditions, thus study is idea of Resource Allocation and Edge Computing for Dual Hop Communication (RAEDH) in introduced in satellite assisted UAVs enabled VANETs. The major sections of the approach are UAV assisted mobile computing, resource allocation among the vehicles and the UAVs, and dual communication among the vehicles and the *** these methods the input resources are properly allocated and that reduces the power utility and communication delay. Initially, the vehicular network is established, incorporating trusted components like TA, RSU, and CRS. Subsequently, mobile edge computing reduces energy consumption through computation offloading and optimized UAV trajectory selection. Resource allocation, facilitated by whale optimization, ensures effective utilization across vehicles. The implementation of this method is done in NS3, and the scenario is analyzed using two parameters like number of vehicles and its speed. The output parameters that remain thought-out over a performance examination stay throughput, end-to-end delay, energy efficiency, packet loss, packet delivery ratio, and routing overhead, and as well those results are compared with the earlier methods. Finally, dual-hop transmission between vehicles and UAVs enhances delivery ratio and throughput. From

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Detection of Agricultural Crops Using CNN 14

A Novel Approach for Detection of Agricultural Crops Using C...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Mahesh, T.R. Singh Chandel, Aman Gupta, Harshitha Jain, Rakshit Garg, Sadhvi Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335095

Crop classification is an important aspect of farming because it improves crop management and increases crop yield. This study proposes a CNN-based crop classification technique using high-resolution images. To use this method, we created a database of 30 crops, including jute, maize, almonds, rice, sugarcane, banana, wheat, and others. The Convolutional Neural Network (CNN) is an Artificial Intelligence-based algorithm that learns similar features from images and is capable of performing a variety of tasks such as image classification, object detection, and segmentation. In this system, CNN or ConvNet is used to learn the features provided in the input images by sequentially entering several layers such as Convolution, Activation function (RELU), Pooling, and Flattening. Finally, with only a few explanations in the training set, this providing outstanding classifies new images. The proposed method has two major components: preprocessing and categorization. The experimental results show that the proposed tactic worked extremely well, with a ground truth of 0.9264. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Smart CIoT with Secure Healthcare Framework Using Optimized Deep Recuperator Neural Network Long Short-Term Memory

引用

IEEE Internet of Things Journal 2024年第6期11卷 10551-10562页

作者： Narmatha, C. Manimurugan, S. Karthikeyan, P. University of Tabuk Faculty of Computers and Information Technology Tabuk71491 Saudi Arabia Oakland University Department of Electrical and Computer Engineering RochesterMI112345 United States National Chung Cheng University Department of Computer Science and Information Engineering Chiayi62102 Taiwan RV University School of Computer Science and Engineering Bengaluru560059 India

The healthcare system currently relies on the facility to store and process large amounts of health data, supported by efficient management. The Internet of Things (IoT) has driven the growth of Adroit Healthcare, which has vast data processing capabilities and extensive data collection. The consumer IoT (CIoT), also known as the IoT in the context of individual use cases, is dominated by personal healthcare applications. The remarkable expansion of the CIoT can be attributed to the extensive embrace of wearable technology, facilitating everyday monitoring of vital health indicators like blood pressure, heart rate, and respiration rate. However, the CIoT raises concerns about data security, confidentiality, and customer trust. This study proposes an integrating blockchain and deep learning (DL) approach to promote responsible use of CIoT. The study develops an Intelligent IoT (IIoT) and healthcare diagnostic model, named BT-PWO-DRNN-LSTM, using blockchain technology and Prairie Wolf optimization-based deep recuperator neural network (DRNN) and long short-term memory (LSTM). The BT-PWO-DRNN-LSTM approach includes three key processes: 1) encrypted transactions;2) cryptographic hash feature;and 3) medical diagnosis. The PWO technique is used for secure communication of medical images, the neighborhood catalogue disposition (NCD) technique is used in the cryptographic hash feature operation (CHFO), and the DL approach is employed as a classification algorithm for diagnosing disorders. The use of PWO methodology for secure healthcare communication and optimal parameter fine-tuning highlights the originality of the study. The BT-PWO-DRNN-LSTM prototype showed positive results with high sensitivity, specificity, and accuracy during the diagnostic process. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Study on optimization of multi-UAV nucleic acid sample delivery paths in large cities under the influence of epidemic environment

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7593-7620页

作者： Han, Yuhang Xiang, Hongyu Cao, Jianing Yang, Xiaohua Pan, Nan Huang, Linhai Mechanical Engineering Faculty of Civil Aviation and Aeronautics Kunming University of Science and Technology Yunnan China Computer Science and Technology Metrology Center Yunnan Power Grid Co. Ltd. Yunnan China Computer Science and Technology Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan China

In the context of global novel coronavirus infection, we studied the distribution problem of nucleic acid samples, which are medical supplies with high urgency. A multi-UAV delivery model of nucleic acid samples with time windows and a UAV (Unmanned Aerial Vehicle) dynamics model for multiple distribution centers is established by considering UAVs’ impact cost and trajectory cost. The Golden Eagle optimization algorithm (SGDCV-GEO) based on gradient optimization and Corsi variation is proposed to solve the model by introducing gradient optimization and Corsi variation strategy in the Golden Eagle optimization algorithm. Performance evaluation by optimizing test functions, Friedman and Nemenyi test compared with Golden Jackal Optimization (GJO), Hunter-Prey Optimization (HPO), Pelican Optimization Algorithm (POA), Reptile Search Algorithm (RSA) and Golden Eagle Optimization (GEO), the convergence performance of SGDCV-GEO algorithm was demonstrated. Further, the improved RRT (Rapidly-exploring Random Trees) algorithm is used in the UAV path planning, and the pruning process and logistic chaotic mapping strategy are introduced in the path generation method. Finally, simulation experiments are conducted based on 8 hospitals and 50 randomly selected communities in the Pudong district of Shanghai, southern China. The experimental results show that the developed algorithm can effectively reduce the delivery cost and total delivery time compared with simulated annealing algorithm (SA), crow search algorithm (CSA), particle swarm algorithm (PSO), and taboo search algorithm (TS), and the developed algorithm has good uniformity, robustness, and high convergence accuracy, which can be effectively applied to the multi-UAV nucleic acid sample delivery path optimization in large cities under the influence of an epidemic environment. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep Learning and Machine Learning Methods for Breast Cancer Detection 1

Analysis of Deep Learning and Machine Learning Methods for B...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Latha, D.U. Mahesh, T.R. Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350341737

Breast cancer is the disease with the greatest incidence rate and the fastest global spread. Compared to men, women are diagnosed with breast cancer far more frequently. If detected early enough, breast cancer can be successfully treated. One of the leading causes of death internationally, breast cancer accounted for 22.6% of all cancer-related deaths worldwide in 2013. This indicates that more than one crore cancer-related deaths were brought on by breast cancer. 14.7% of all cancer cases in India are caused by breast cancer. Early breast cancer recognition has been the subject of extensive investigation since it can help with treatment start-up and reduce overall mortality rates. Many instances can be managed and the overall death rate can be lowered with an early diagnosis. Breast cancer has been the subject of numerous research studies. Machine learning is the method being applied in research. Older machine learning-based research that excelled in their respective fields include those that used decision trees, KNN, SVM, and naive bays techniques. Better algorithms have been created as a result of these investigations. On the other hand, deep learning, a recently created technique, is currently being utilised to categorize breast cancer. Data science commonly makes use of convolutional neural networks, recurrent neural networks, and other deep learning-based techniques. Deep learning algorithms outperform machine learning algorithms in terms of performance. The most captivating portions of the photographs have been removed. Many academics utilize CNN to categorize the images. In a nutshell, CNN is the technique that is most frequently used to categorize images. This piece of work compares and contrasts the employment of machine learning and deep learning techniques in numerous journals. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Innovation Development of Neuro Controller for Condition Monitoring and Smart Industrial Instrumentation 2

An Innovation Development of Neuro Controller for Condition ...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Vanitha, K. Raja Praveen, K.N. Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

The Neuro Controller is an innovative piece of industrial instrumentation designed to monitor conditions in smart industrial settings. It is a powerful and versatile controller that can be used to monitor, control, and manage industrial processes. The Neuro Controller is equipped with advanced sensors and actuators, enabling it to accurately measure and control a variety of conditions. The Neuro Controller is able to monitor and control temperature, pressure, humidity, flow, and other parameters in an industrial setting. It is also capable of detecting changes in these parameters, allowing it to respond to changes quickly and accurately. The Neuro Controller uses advanced algorithms to analyze data and make decisions, allowing it to optimize and control processes efficiently. Additionally, the controller is able to integrate data from numerous sources, providing a comprehensive view of a process. In this paper, a smart Neuro Controller for Condition Monitoring and smart industrial instrumentation. The Neuro Controller is designed to provide enhanced safety and efficiency in industrial settings. It is capable of detecting potentially hazardous conditions and alerting personnel to take action. Additionally, the controller can be used to automate processes, reducing the risk of accidents and improving process efficiency. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Image Classifications Methods Analysis with Differen Methods to for Identifying best Image Layout with High Resolution

Image Classifications Methods Analysis with Differen Methods...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Mahesh, T.R. Vivek, V. Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350322309

This researcher investigated effective much eye opening and pattern detection algorithms. Finally, this article used two frameworks to argue that geospatial investigation systems for patterns are necessary. One of most popular method for analyzing photographs using image processing and analysis math is probably visual configuration methods. Imagery description is also necessary for the evaluation of remote sensing tools used for thorough land investigation. The three main image configuration techniques that are often used for far detection are opinion piece visual analysis, controlled groupings, and solos visual categorization. The approach used in these image layout techniques is combined in the present study. The present study also briefly summarizes each approach's use in exploring distant sensing info while also outlining the steps for each way using stream outlines and frameworks. Generally speaking, a quick overview of image layout techniques is included in the test. © 2023 IEEE.

关键词： Image classification

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：