检索结果-内蒙古大学图书馆

13th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2022

作者： Chaitra, P.C. Saravanakumar, R. Dayananda Sagar Academy of Technology and Management/Computer Science and Engineering Bangalore India

ISBN: (纸本)9781713857938

Cancer is most dangerous disease and most of the deaths are because of this deadly disease. Microarray cancer analysis is currently one of the most popular study topics in machine learning, computational biology. In the case of binary classes, classification and analysis of cancer data play a critical role in diagnosis, distinguishing negative and positive cases and treatment. The curse of dimensionality and a lack of sufficient sample data are the key challenges with microarray cancer datasets. In this paper presents, problems associated with micro array and handling of problems and make datasets ready for analysis. Different classification algorithms explained with pros and cons of each algorithm in detail. © Grenze Scientific Society, 2022.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Multimodal Depression Recognition Based on Self-Supervised Learning 4

Multimodal Depression Recognition Based on Self-Supervised L...

引用

4th International Conference on computer science, Electronic Information engineering and Intelligent Control technology, CEI 2024

作者： Wang, Guangkai Wang, Rui Yang, Qin Wu, Yong School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China Ordnance NCO Academy Army Engineering University PLA Wuhan China

ISBN: (纸本)9798350378542

Depression is a widespread and severe mental health disorder, characterized by a significant prevalence and a high incidence rate, which presents numerous challenges in diagnosis and treatment. We introduce an innovative multimodal approach for depression recognition utilizing self-supervised learning. The method analyzes audio and video data through three steps: extracting image features, extracting audio features, and performing multimodal temporal fusion, enabling an assessment of depression severity. Extensive experiments conducted on the AVEC2014 dataset demonstrate that the proposed model achieves a Mean Absolute Error (MAE) of 7.013 and a Root Mean Square Error (RMSE) of 8.616 in depression prediction tasks, showcasing strong performance. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Explainable Framework to Predict Child Sexual Abuse Awareness in People Using Supervised Machine Learning Models

引用

Journal of technology in Behavioral science 2024年第2期9卷 346-362页

作者： Chadaga, Krishnaraj Prabhu, Srikanth Sampathila, Niranjana Chadaga, Rajagopala Bairy, Muralidhar S, Swathi K. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Biomedical Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Mechanical and Industrial Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India Prasanna School of Public Health Manipal Academy of Higher Education Karnataka Manipal 576104 India

Child sexual abuse (CSA) is a type of abuse in which an individual exploits a kid/adolescent sexually. CSA can happen in several places, such as schools, households, hostels, and other public spaces. However, a large number of people, including parents, do not have an awareness of this sensitive issue. Artificial intelligence (AI) and machine learning (ML) are being used in various disciplines in the modern era. Hence, supervised machine learning models have been used to predict child sexual abuse awareness in this study. The dataset contains answers provided by 3002 people regarding CSA. A questionnaire dataset obtained though crowdsourcing has been used to predict a person’s knowledge level regarding sexual abuse in children. Heterogenous ML and deep learning models have been used to make accurate predictions. To demystify the decisions made by the models, explainable artificial intelligence (XAI) techniques have also been utilized. XAI helps in making the models more interpretable, decipherable, and transparent. Four XAI techniques: Shapley additive values (SHAP), Eli5, QLattice, and local interpretable model-agnostic explanations (LIME), have been utilized to demystify the models. Among all the classifiers, the final stacked model obtained the best results with an accuracy of 94% for the test dataset. The excellent results demonstrated by the classifiers point to the use of artificial intelligence in preventing child sexual abuse by making people aware of it. The models can be used real time in facilities such as schools, hospitals, and other places to increase awareness among people regarding sexual abuse in children. © 2023, The Author(s).

关键词： Artificial intelligence Child sexual abuse Child sexual abuse awareness Explainable artificial intelligence Local interpretable model-agnostic explanations (LIME) Shapley additive values (SHAP) Supervised machine learning

来源：评论

学校读者我要写书评

暂无评论

DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 364-373页

作者： Ni, Shiwen Li, Jiawen Yang, Min Kao, Hung-Yu Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518000 China Guangdong Ocean University Maritime College Zhanjiang524000 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan

Adversarial training has been proven to be a powerful regularization technique to improve language models. In this work, we propose a novel random dropped weight attack adversarial training method (DropAttack) for natural language understanding. Our DropAttack improves the generalization of models by minimizing the internal adversarial risk caused by a multitude of attack combinations. Specifically, DropAttack enhances the adversarial attack space by intentionally adding worst-case adversarial perturbations to the weight parameters and randomly dropping the specific proportion of attack perturbations. To extensively validate the effectiveness of DropAttack, 12 public English natural language understanding datasets were used. Experiments on the GLUE benchmark show that when DropAttack is applied only to the finetuning stage, it is able to improve the overall test scores of the BERT-base pre-trained model from 78.3 to 79.7 and RoBERTa-large pre-trained model from 88.1 to 88.8. Further, DropAttack also significantly improves models trained from scratch. Theoretical analysis reveals that DropAttack performs potential gradient regularization on the input and weight parameters of the model. Moreover, visualization experiments show that DropAttack can push the minimum risk of the neural network to a lower and flatter loss landscape. © 2014 IEEE.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid-Logic Scheme for High-Performance and Low-Power Decoders in 7nm Process 17

A Hybrid-Logic Scheme for High-Performance and Low-Power Dec...

引用

17th IEEE International Conference on Solid-State and Integrated Circuit technology, ICSICT 2024

作者： Xia, Donghao Zhang, Yuejun Xu, Mengfan Wen, Liang Guo, Yiting Ningbo University Faculty of Electrical Engineering and Computer Science Zhejiang315211 China China Coast Guard Academy Department of Electronic Technology Ningbo315211 China

ISBN: (纸本)9798350361834

Advancing memory circuitry has heightened the performance criteria for memory in diverse chip applications. Decoders, serving as peripheral circuits to memory devices, have be a prominent area of academic interest. The new NAND/NOR gate circuits are proposed using pass-transistor logic (PTL) and transmission gate logic (TGL). The two hybrid-logic design schemes of high-performance and low-power (HPLP) and HPLP inverting (HPLPI) utilizing PTL and TGL gate in combination with static CMOS logic for decoders are proposed, while achieving fewer transistors, faster speed, lower power dissipation as compared to conventional circuits. Experiments are conducted in TSMC 7nm FinFET process for hybrid-logic decoders. The simulation results indicate that, in comparison to conventional decoders, the proposed hybrid-logic 3-8 decoder demonstrates improvements, with the HPLP design reducing delay by over 19% and power by over 71%, and the HPLPI design reducing delay by over 17% and power by over 48%. © 2024 IEEE.

关键词： NAND circuits

来源：评论

学校读者我要写书评

暂无评论

Adaptive Frequency Regulation Approach for Wind Turbines Contained Microgrids Using Balloon Effect Tequnique

Adaptive Frequency Regulation Approach for Wind Turbines Con...

引用

2024 Advances in science and engineering technology International Conferences, ASET 2024

作者： Hassan, Ahmed Tawfik Hassan, Ammar M Qudaih, Yaser Rashwan, Asmaa Fawzy Mosa, Mohamed Roshdi Mohamed, Tarek Hassan Aswan University Electrical Engineering Department Aswan Egypt Arab Academy of Science South Valley Department of Computer Science Aswan Egypt Higher Coleges of Technology Electrical Engineering Department Dubai United Arab Emirates

ISBN: (纸本)9798350344134

This paper proposes an adaptive control approach supported by Balloon Effect identifier, based on sine cosine optimization method (SCO). System has been evaluated using the suggested adaptive control approach in the presence of a fluctuating load, uncertainties in the system characteristics are also considered. The effect of presence wind turbine unit has been studied. A digital test environment is created using the Simulink/MATLAB program. The suggested adaptive controller with participation of wind turbine is successful in regulating both of the power and frequency of an islanded power system area (μGs) that depends on a diesel generator, as per the simulation findings. to gauge how effective the suggested control strategy is. Other control strategies (adaptive controller with only SCO, adaptive controller with only Jaya, and classical integral controller) are compared. The outcomes of the simulation demonstrated that, when it comes for stabilization of frequency in case of random load variations and parameter changes, the recommended control strategy utilizing (SCO + BE + wind turbine) clearly outperforms alternative control strategies. © 2024 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction

Prompt Based Tri-Channel Graph Convolution Neural Network fo...

引用

2024 SIAM International Conference on Data Mining, SDM 2024

作者： Peng, Kun Jiang, Lei Peng, Hao Liu, Rui Yu, Zhengtao Ren, Jiaqian Hao, Zhifeng Philip, S.Yu. Institute of Information Engineering Chinese Academy of Sciences China School of Cyberspace Security University of Chinese Academy of Sciences China School of Cyber Science and Technology Beihang University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China College of Science University of Shantou China University of Illinois at Chicago Department of Computer Science United States

ISBN: (纸本)9781611978032

Aspect Sentiment Triplet Extraction (ASTE) is an emerging task to extract a given sentence's triplets, which consist of aspects, opinions, and sentiments. Recent studies tend to address this task with a table-filling paradigm, wherein word relations are encoded in a two-dimensional table, and the process involves clarifying all the individual cells to extract triples. However, these studies ignore the deep interaction between neighbor cells, which we find quite helpful for accurate extraction. To this end, we propose a novel model for the ASTE task, called Prompt-based Tri-Channel Graph Convolution Neural Network (PT-GCN), which converts the relation table into a graph to explore more comprehensive relational information. Specifically, we treat the original table cells as nodes and utilize a prompt attention score computation module to determine the edges' weights. This enables us to construct a target-aware grid-like graph to enhance the overall extraction process. After that, a triple-channel convolution module is conducted to extract precise sentiment knowledge. Extensive experiments on the benchmark datasets show that our model achieves state-of-the-art performance. The code is available at https://***/KunPunCN/PT-GCN. Copyright © 2024 by SIAM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Novel Collision Detection Protocol for Wireless Full-duplex Networks 20

A Novel Collision Detection Protocol for Wireless Full-duple...

引用

20th IEEE International Conference on Networking, Sensing and Control, ICNSC 2023

作者： Zhao, Qinglin Feng, Li Zhou, MengChu Yu, Haisheng Sun, Yi Macau University of Science and Technology School of Computer Science and Engineering China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark United States Macau University of Science and Technology International Institute of Next Generation Internet China Chinese Academy of Sciences Institute of Computing Technology Beijing China

ISBN: (纸本)9798350369502

Conventional wireless networks are half-duplex and most of them use contention-based protocols. These protocols usually adopt a principle of contention with collision avoidance and infer a collision occurrence very late from the absence of an acknowledgement after data transmission, thus causing low network performance. Wireless full-duplex enables simultaneous transmission (TX) and reception (RX) on the same channel. By exploiting this functionality, this work proposes a novel design that enables contention with collision detection (CCD) to improve the network performance. With this design, in contention, a node exploits its TX antenna to transmit a signal for channel contention, while exploiting its RX antenna to sense if other nodes are transmitting too. By checking the status of TX and RX antennas, the node can detect the contention collision before data transmission and hence obtains an opportunity to avoid data collision effectively. This work then develops a theoretical model to analyze the collision probability of this design. Extensive simulation results verify the effectiveness of our proposed design in improving wireless network performance. © 2023 IEEE.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Advanced Source Privacy: DQ-NN and Phantom Routing in IoT-Integrated Multiple-Source and Destination Wireless Sensor Networks 15

Advanced Source Privacy: DQ-NN and Phantom Routing in IoT-In...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Arpitha, T. Chouhan, Dharamendra Shreyas, J. University Visvesvaraya College of Engineering Bangalore University Department of Computer Science and Engineering Bengaluru560001 India Manipal Institute of Technology Department of Information Technology Bangalore India Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9798350370249

Internet of Things (IoT) and Wireless Sensor Networks (WSNs) have brought about revolutionary opportunities for many areas, they have also raised serious security issues, especially with relation to source node location privacy in IoT-enabled WSNs. In response, we put out a brand-new hybrid Deep Q-learning Neural Network (DQ-NN) strategy designed specifically for Source Location Privacy (SLP) in Internet of Things (IoT)-enabled WSNs that use phantom routing. Through the strategic selection of phantom nodes, our method establishes various routing paths from source to sink nodes via these phantoms, taking into account factors such as neighbour lists, energy levels, distances, and trust heterogeneity. The use of DQ-NN, a combination of Deep Q-learning Network (DQN) and Deep Neural Network (DNN), is essential to our approach since it guarantees source node location privacy protection in addition to effective and reliable data transfer through IoT-enabled WSNs, strengthening the privacy and security environment of IoT networks and facilitating easy integration with everyday life. The suggested DQ-NN performs better than other current methods. © 2024 IEEE.

关键词： deep q learning neural network deep q neural networks Internet of things phantom routing source location privacy

来源：评论

学校读者我要写书评

暂无评论

U-Net lesion segmentation network combining attention and pyramid fusion 6

U-Net lesion segmentation network combining attention and py...

引用

6th International Conference on Machine Learning and Machine Intelligence, MLMI 2023

作者： Guo, Min Bai, Bingyang Li, Yang College of Computer Science and Engineering Changchun University of Technology China Academy for Advanced Interdisciplinary Studies Northeast Normal University China

ISBN: (纸本)9798400709456

In order to solve the problems of limited feature expression ability and low segmentation accuracy of the lesion segmentation network, CGM-UNet based on Coordinate Attention (CA), Multi-Head Self-Attention (MHSA) and Global Pyramid Guidance (GPG) was proposed. The model uses CA in the encoder to enhance the representation of the region of interest, replaces the convolutional pooling operation with MHSA at the highest stage of the encoder, and exploits the global interaction between encoder features to explicitly model complete contextual information and reduces the model parameter quantity, two kinds of attention are combined to capture long-distance dependencies in images. Use GPG to reconstruct skip connections to provide different levels of global context information. In order to verify the effectiveness of the proposed method, experiments were conducted on the stroke segmentation dataset of the cooperative hospital, the ISIC 2018 dataset and the Kvasir-SEG dataset and compared with advanced algorithms. Experimental results show that CGM-UNet has advantages in multiple segmentation evaluation indicators, can effectively segment multiple types of lesions, and can provide a reliable basis for clinical diagnosis and quantification. © 2023 ACM.

关键词： Image segmentation

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：