检索结果-内蒙古大学图书馆

Chatbots: Understanding Their World, Classification, and Their Current State 2nd

Chatbots: Understanding Their World, Classification, and The...

Emergent Converging Technologies and Biomedical systems Select Proceedings of the 2nd International Conference, ETBS 2022

作者： Singh, Amit Sharma, K.K. Kumar, Parveen Vats, Sandeep Kumar Computer Science and Engineering Department Sanskriti University Mathura UP Chatta India Centre for Railways Information System Chanakyapuri Delhi India

ISBN: (纸本)9789819922703

An extraordinary growth is being witnessed for mobile devices and their ever-growing computational powers. Also, the chip demand is very high. This demand is not only coming from the software industry, but almost all the other sectors also contribute to this enormous growth. With the recent innovations in chip manufacturing, complemented with very high demands, compute power costs are getting reduced at a significant rate. The computation power of chips fuels the artificial intelligence (AI) technologies to harness them. AI is a very computation resource demanding technology, and, in many cases, it requires specialized computational resources. Due to deep mobile penetration in the society, AI technologies such as Data science and NLP are taking great pace. On the other hand, chatbots are gaining momentum beyond customer care and typical use cases. This paper analyzes the history, growth, and new trends of chatbots. Especially the impact of AI on bot technologies and the road ahead. This paper will take a look at the chatbot journey. It also examines where chatbots are making an impact on human lives. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Massive Fabrication of Carbon Nanotube Transistors by Surface Tension-Driven Inkjet-Printing Method 5

Massive Fabrication of Carbon Nanotube Transistors by Surfac...

引用

5th IEEE International Conference on Flexible and Printable Sensors and systems, FLEPS 2023

作者： Park, Soohyun Shin, Minhye Kang, Hongki Lee, Yoonhee Division of Electronics and Information System Daegu42988 Korea Republic of Department of Electrical Engineering and Computer Science Daegu42988 Korea Republic of

ISBN: (纸本)9781665457330

Carbon nanotube field-effect transistors (CNTFETs) have been ideal nanoelectronics in semiconductor technologies with exceptional electrical properties. Scaling the CNT -FET fabrication enables the expansion of the application fields. However, placing nanotubes with uniform alignment and controlled density to the electrode contacts has been the maj or challenge in massive manufacturing. Here, we introduce the in-place inkjet-printing method for fabricating CNTFETs with controlled numbers of connected CNTs at a single CNT level. A picoliter (pL) drop of CNT ink is printed to the pre-patterned electrode arrays in parallel over a four-inch silicon wafer, allowing adaptive manufacturing without additional lithographic processes. Drops form thin films on the metal electrode patterns driven by the surface tension flow, diluting the surface density of CNT on the one-micrometer channel gap and avoiding bundled coffee ring edges. Finally, single CNTs are correctly bridged to the electrodes with high statistical yield. This process enables reproducible and high-throughput single CNT deposition, integrating into the FET manufacturing process, and can be used for versatile nanoelectronics applications, such as biosensors. © 2023 IEEE.

关键词： Carbon nanotubes

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: Fooling Segment Anything Model to Segment Nothing 38

DarkSAM: Fooling Segment Anything Model to Segment Nothing

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM. © 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

DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems 41

DPN: Decoupling Partition and Navigation for Neural Solvers ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zheng, Zhi Yao, Shunyu Wang, Zhenkun Tong, Xialiang Yuan, Mingxuan Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China China Huawei Noah's Ark Lab Shenzhen China

The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest ***, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency and ***, these methods fail to exploit the problem-specific properties in learning representations, resulting in less effective features for decoding optimal *** paper considers the sequential planning process of min-max VRPs as two coupled optimization tasks: customer partition for different routes and customer navigation in each route (i.e., partition and navigation).To effectively process min-max VRP instances, we present a novel attention-based Partition-and-Navigation encoder (P&N Encoder) that learns distinct embeddings for partition and ***, we utilize an inherent symmetry in decoding routes and develop an effective agent-permutation-symmetric (APS) loss *** results demonstrate that the proposed Decoupling-Partition-Navigation (DPN) method significantly surpasses existing learning-based methods in both single-depot and multi-depot minmax *** code is available at. Copyright 2024 by the author(s)

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Multi - Task Learning with Convolutional Neural Network for Packet Format Detection and Modulation Classification of Wireless LAN 13

Multi - Task Learning with Convolutional Neural Network for ...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Putra, Dody Ichwana Pratama, M. Harry Bintang Nagao, Yuhei Kurosaki, Masayuki Ochi, Hiroshi Graduate School of Computer Science and System Engineering Kyushu Institute of Technology Iizuka Japan

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

In this paper, we propose multi-task learning (MTL) using a convolutional neural network (CNN) to simultaneously perform packet format detection and modulation classification of wireless LAN (WLAN) signals. Compared to single-task learning, the main advantage of this method is the high classification accuracy and rapid learning with a lightweight neural network model. These are achieved because of learning shared knowledge (i.e., model weight or gradients) between related tasks. This shared representation model increases data efficiency and reduces overfitting. The WLAN signals generated by the Matlab wave generator are used to validate and test the model. The results show that even with different time offsets, the proposed method has an accuracy of 98% for packet format detection and 86% for modulation classification. © 2022 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Polarization-induced photocurrent switching effect in heterojunction photodiodes

引用

Nano Research 2023年第4期16卷 5503-5510页

作者： Dingbo Chen Yu-Chang Chen Guang Zeng Yu-Chun Li Xiao-Xi Li Dong Li Chao Shen Nan Chi Boon S.Ooi David Wei Zhang Hong-Liang Lu State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics&SystemsSchool of MicroelectronicsFudan UniversityShanghai 200433China Key Laboratory for Information Science of Electromagnetic Waves Department of Communication Science and EngineeringFudan UniversityShanghai 200433China Photonics Laboratory Division of ComputerElectricaland Mathematical Sciences and EngineeringKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia

The unipolar photocurrent in conventional photodiodes(PDs)based on photovoltaic effect limits the output modes and potential versatility of these devices in *** photodiodes with photocurrent switching are emerging as a promising solution for obtaining photoelectric devices with unique and attractive functions,such as optical logic ***,we design an all-solid-state chip-scale ultraviolet(UV)PD based on a hybrid GaN heterojunction with engineered bipolar polarized electric *** introducing the polarization-induced photocurrent switching effect,the photocurrent direction can be switched in response to the wavelength of incident light at 0 V *** particular,the photocurrent direction exhibits negative when the irradiation wavelength is less than 315 nm,but positive when the wavelength is longer than 315 *** device shows a responsivity of up to−6.7 mA/W at 300 nm and 5.3 mA/W at 340 nm,*** particular,three special logic gates in response to different dual UV light inputs are demonstrated via a single bipolar PD,which may be beneficial for future multifunctional UV photonic integrated devices and systems.

关键词： GaN heterostructure ultraviolet(UV)photodiodes bipolar photocurrent optical logic device

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multi-Agent system Swarm Performance Through Explainable AI 11

Optimizing Multi-Agent System Swarm Performance Through Expl...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Mahmud, Shekhar Kutlu, Mustafa Alan, Alper Turan Military Technological College System Engineering Department Muscat Oman Sakarya University of Applied Sciences Mechatronics Engineering Department Sakarya Turkey International University of Kuwait Computer Science & Cybersecurity Department Kuwait City Kuwait

ISBN: (纸本)9798331509293

Advancements in multi-agent systems (MAS) have enabled swarm-based systems to perform decentralized decision-making and autonomous tasks. However, optimizing their performance while ensuring transparency and interpretability remains a challenge. This paper introduces a framework that combines Bayesian optimization with Explainable Artificial Intelligence (XAI) techniques to enhance both the efficiency and transparency of MAS swarms. The Bayesian optimization framework fine-tunes agent parameters to improve swarm metrics such as energy efficiency, task completion time, and coordination success. The experimental results show significant improvements: a 25% increase in the coordination success rate, a 15% increase in energy efficiency, and a 20 % reduction in task completion time. XAI techniques, including SHAP values, provide interpretable explanations for optimization decisions, improving user trust and understanding. This study demonstrates the efficacy of integrating Bayesian optimization with XAI to create transparent, efficient, and reliable MAS swarms. Future work should address scalability and implications in dynamic environments. © 2025 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Text to Image Generation Using Attentional Generative Adversarial Network 1

引用

1st International Conference on Advanced Computing, Machine Learning, Robotics and Internet Technologies, AMRIT 2023

作者： Rao, Supriya B. Shetty, Shailesh S. Singh, Chandra M, Srinivas P. Bekal, Anush Department of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bangalore Karnataka Mangaluru India Department of Computer Science and Business System Srinivas Institute of Technology Karnataka Mangaluru India Department of Electronics & Communication Engineering Sahyadri College of Engineering & Management Karnataka Mangaluru India Department of Computer Science Engineering Sahyadri College of Engineering & Management Karnataka Mangaluru India

ISBN: (数字)9783031472213

ISBN: (纸本)9783031472206

AttnGan – Attentional Generative Adversarial Network (GAN) is a type of GANs that is used for text to image generation. Unlike other art models, it focuses on fine-grained word level information and once the model is trained by mapping the images and the corresponding text in the dataset, the model will generate image part-by-part using the image description given by the user as an input to the model. Current paper, focuses on the conversion of text into images based on the description provided by the user. This enables them to translate their ideas in the form of text into images of their required choices. The model is initially trained by the description of the text and images and when the user provides the text as an input to the system, it is used as a testing data. By analyzing the text word-by-word, the respective images pertaining to the text is generated part-by-part by considering the text description into account. This can heavily help the users in a applications such as in editing aids, documental archives, etc. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction 37

ES-Mask: Evolutionary Strip Mask for Explaining Time Series ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Sun, Yifei Song, Cheng Lu, Feng Li, Wei Jin, Hai Zomaya, Albert Y. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Computer Science University of Sydney Australia

ISBN: (纸本)9781577358800

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Automatic skin lesion classification using a novel densely connected convolutional network integrated with an attention module

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 8943-8956页

作者： Shan, Pufang Chen, Jialei Fu, Chong Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science The University of Auckland Auckland New Zealand

Automated skin lesion classification in dermoscopy images remains challenging due to the existence of artefacts and intrinsic cutaneous features, diversity of lesion morphology, insufficiency of training data, and class imbalance problem. To address these challenges, we propose a new densely connected convolutional network termed AttDenseNet-121, which is obtained by integrating the convolutional block attention module (CBAM) into DenseNet-121. CBAM is a simple yet efficient attention module, which is further improved by adding a novel pooling layer (multiscale-pooling) to effectively enhance its attention capability. The optimized CBAM strengthens the representation power of DenseNet-121 by emphasizing meaningful features and suppressing unnecessary ones, thus significantly enhancing the classification performance. Besides, to handle the imbalanced dataset, we employ an improved focal loss function rather than the traditional cross-entropy loss function to train AttDenseNet-121. The improved focal loss is calculated from a different perspective compared with the original focal loss. It makes the distribution of positive samples and negative samples in each batch the same as that in the original data, successfully mitigating the negative influence of class imbalance on this multi-class classification task. We conduct extensive experiments on the public benchmark dataset (HAM10000) and the results indicate that our proposed method achieves superior performance compared with that of the baselines and state-of-the-art algorithms. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

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：