检索结果-内蒙古大学图书馆

Social and Sustainable Innovations in Technology and engineering (SASI-ITE), International Conference on

作者： N Devakirubai Anitha Velu D Sumathi A Prasanth Department of Artificial Intelligence and Data Science R P Sarathy Institute of Technology Salem Tamilnadu India Department of Electronics and Communication Engineering Sri Sairam College of Engineering Bengaluru India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798350360790

ISBN: (纸本)9798350360806

In the continually evolving field of vehicular communications, the efficient allocation of time slots for Vehicle-to-Vehicle (V2V) communication is of utmost importance. This work introduces a novel approach that employs a K-Nearest Neighbors (KNN) algorithm to allocate time slots in NR V2X sidelink communications. The allocation is specifically tailored to dynamically adjust to the current density of traffic in real-time. The efficacy of the KNN-based time slot allocation system is assessed through simulating the V2X environment, encompassing a fleet of vehicles. The efficacy of the suggested methodology is assessed in relation to a random allocation technique and it is observed that the suggested strategy notably enhances allocation efficiency, slot utilization, contention window, and communication time. The findings illustrate the capacity of a KNN-based dynamic allocation system to adapt to different levels of traffic congestion, leading to the efficient utilization of network resources and the mitigation of communication latency. Furthermore, the examination of the implementation of priority queues in the allocation process is explored, resulting in enhanced efficiency of the system in scenarios involving a substantial amount of traffic.

关键词： Technological innovation Vehicular ad hoc networks Sidelink Nearest neighbor methods Dynamic scheduling Real-time systems Resource management

来源：评论

学校读者我要写书评

暂无评论

Overcoming data Inequality across Domains with Semi-Supervised Domain Generalization

arXiv

引用

arXiv 2024年

作者： Park, Jinha Cho, Wonguk Kim, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of Graduate School of Data Science Seoul National University Korea Republic of

While there have been considerable advancements in machine learning driven by extensive datasets, a significant disparity still persists in the availability of data across various sources and populations. This inequality across domains poses challenges in modeling for those with limited data, which can lead to profound practical and ethical concerns. In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled. We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes along with progressive generalization via uncertainty-adaptive mixing of labeled and unlabeled domains. Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD, outperforming all baseline models including single domain generalization and semi-supervised learning. Source code will be released upon acceptance of the paper. Copyright © 2024, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Model Splitting and Device Task Assignment for Private Multi-hop Split Learning

Joint Optimization of Model Splitting and Device Task Assign...

引用

Annual Conference on Information sciences and Systems (CISS)

作者： Dongyu Wei Qianqian Zhang Yuchen Liu Mingzhe Chen Department of Electrical and Computer Engineering University of Miami Coral Gables FL USA Department of Electrical and Computer Engineering Rowan University Glassboro NJ USA Department of Computer Science NC State University Raleigh NC USA Frost Institute for Data Science and Computing University of Miami Coral Gables FL USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

In this paper, a deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdropper from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the eavesdropped information while meeting the model training energy consumption and delay constraints. To solve this problem, we propose an actor-critic deep reinforcement learning (AC-DRL) framework that enables a centralized agent to dynamically determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device while considering network topology and device properties (e.g., energy and privacy constraints). The proposed AC-DRL framework integrates an actor network to generate optimal actions and a critic network to stabilize the learning process by evaluating the cumulative rewards. Simulation results demonstrate that the proposed method improves the convergence rate by 3× and the accumulated reward by up to 40% compared with the proximal policy optimization (PPO) algorithm.

关键词： Training Performance evaluation Privacy Network topology Simulation Heuristic algorithms data models Delays Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Multimodal Supported Chatbot Framework for People with Aphasia

Multimodal Supported Chatbot Framework for People with Aphas...

引用

Moratuwa engineering Research Conference (MERCon)

作者： R.L.A. Sanduni Ayesha L.B. Hasini M. Vijayarathna N.P.A. Vithanage Uthayasanker Thayasivam Damminda Alahakoon Achini Adikari Nuwan Pallewela Department of Computer Science and Engineering University of Moratuwa Katubedda Sri Lanka Research Centre for Data Analytics and Cognition La Trobe University Australia

ISBN: (数字)9798331529048

ISBN: (纸本)9798331529055

Chatbots have become a trending topic with emerging platforms like ChatGPT, Gemini, and Copilot, for conversation assistance. Current chatbots mainly focus on the general public assuming a natural flow of conversation. However, there is a need for a chatbot that supports people with various communication disabilities. This research fills this gap by offering a novel technique for a chatbot that assists people with Aphasia, a condition characterised by difficulties with language. We propose a multi-modal chatbot that is customised and designed to assist users with communication disabilities in navigating a website. Unlike typical chatbots, which rely on one form of communication, our architecture combines multiple modalities to improve comprehension and promote effective communication for people with Aphasia. We focus on gathering multimodal inputs by recognising and combining user intents from diverse sources. The use of Txtai, an all-in-one embeddings database for semantic search improves our chatbot’s capacity to process various inputs efficiently. We leverage specialised models like Whisper for audio transcription and MediaPipe Gesture Recognizer for gesture detection to enhance user interactions. Additionally, Rasa Core integration improves conversational experiences for users. We propose that this new approach will make communication more accessible and inclusive for individuals with Aphasia.

关键词： Navigation Semantic search Intent recognition Diversity reception Oral communication Gesture recognition Machine learning Aphasia Chatbots User experience

来源：评论

学校读者我要写书评

暂无评论

A Fresh Look at Sanity Checks for Saliency Maps

arXiv

引用

arXiv 2024年

作者： Hedström, Anna Weber, Leander Lapuschkin, Sebastian Höhne, Marina Department of Electrical Engineering and Computer Science TU Berlin Germany Department of Artificial Intelligence Fraunhofer HHI Berlin Germany Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany Department of Computer Science University of Potsdam Germany

The Model Parameter Randomisation Test (MPRT) is highly recognised in the eXplainable Artificial Intelligence (XAI) community due to its fundamental evaluative criterion: explanations should be sensitive to the parameters of the model they seek to explain. However, recent studies have raised several methodological concerns for the empirical interpretation of MPRT. In response, we propose two modifications to the original test: Smooth MPRT and Efficient MPRT. The former reduces the impact of noise on evaluation outcomes via sampling, while the latter avoids the need for biased similarity measurements by re-interpreting the test through the increase in explanation complexity after full model randomisation. Our experiments show that these modifications enhance the metric reliability, facilitating a more trustworthy deployment of explanation methods. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Why AI still doesn't have consciousness?

引用

CAAI Transactions on Intelligence Technology 2021年第2期6卷 175-179页

作者： Deyi Li Wen He Yike Guo Department of Computer Science and Technology Tsinghua UniversityBeijingChina Instltute of Systems Engineering Academy of Military SciencesPLABeijingChina Data Science Institute Imperial College LondonUK Hongkong Baptist University Hong KongChina

Consciousness is one of the unique features of creatures,and is also the root of biological *** to now,all machines and robots havenJt had ***,will the artificial intelligence(AI)be conscious?Will robots have real intelligence without consciousness?The most primitive consciousness is the perception and expression of *** order to perceive the existence of the concept of‘Ij,a creature must first have a perceivable boundary such as skin to separate‘I’from‘non-1’.For robots,to have the self-awareness,they also need to be wrapped by a similar sensory ***,as intelligent tools,AI systems should also be regarded as the external extension of human *** tools are *** development of AI shows that intelligence can exist without *** human beings enter into the era of life intelligence from AI,it is not the AI became conscious,but that conscious lives will have strong ***,it becomes more necessary to be careful on applying AI to living creatures,even to those lower-level animals with only *** subversive revolution of such application may produce more careful thinking.

关键词： intelligence consciousness conscious

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Pneumonia Prediction Approach Using Deep Learning

An Analysis of Pneumonia Prediction Approach Using Deep Lear...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Ayushi Pandey Tushar Mehrotra Ravin Kumar Sandeep Saxena Department of Data Science NIET Greater Noida Department of Computer Science & Engineering Sharda School of Engineering and Technology Sharda University Greater Noida GNIOT Gr.Noida

A bacterial infection in the lungs' alveoli frequently results in pneumonia, an infectious disease. Pus occurs in infected lung tissue as it gets irritated. To ascertain whether a patient has pneumonia, experts perform physical examinations and diagnose their patients using a chest X-ray, ultrasound, or lung biopsy. A patient's mortality may result from a misdiagnosis, ineffective treatment, or disregard for the disease. The development of deep learning aids specialists in their decision-making when it comes to diagnosing pneumonia patients. The study uses six CNN models to predict and identify a patient with and without the condition using an X-ray image of their chest. It combines versatile and affordable deep learning approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Domain Adaptation with Transformer-Based Feature Generation for Subject-Independent EEG-Based Emotion Recognition

Multi-Source Domain Adaptation with Transformer-Based Featur...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shadi Sartipi Mujdat Cetin Department of Electrical and Computer Engineering University of Rochester Rochester NY USA Goergen Institute for Data Science University of Rochester Rochester NY USA

Although deep learning-based algorithms have demonstrated excellent performance in automated emotion recognition via electroencephalogram (EEG) signals, variations across brain signal patterns of individuals can diminish the model’s effectiveness when applied across different subjects. While transfer learning techniques have exhibited promising outcomes, they still encounter challenges related to inadequate feature representations and may overlook the fact that source subjects themselves can possess distinct characteristics. In this work, we propose a multi-source domain adaptation approach with a transformer-based feature generator (MSDA-TF) designed to leverage information from multiple sources. The proposed feature generator retains convolutional layers to capture shallow spatial, temporal, and spectral EEG data representations, while self-attention mechanisms extract global dependencies within these features. During the adaptation process, we group the source subjects based on correlation values and aim to align the moments of the target subject with each source as well as within the sources. MSDA-TF is validated on the SEED dataset and is shown to yield promising results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Elite Archive-Assisted Multi-Objective Evolutionary Algorithm for mRNA Design

An Elite Archive-Assisted Multi-Objective Evolutionary Algor...

引用

Congress on Evolutionary Computation

作者： Wenjing Hong Cheng Chen Zexuan Zhu Ke Tang National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Messenger RNA (mRNA) vaccines have emerged as highly effective strategies in the prophylaxis and treatment of diseases. mRNA design, a key to the success of mRNA vaccines, in-volves finding optimal codons and increasing secondary structure stability to lengthen mRNA half-life, ultimately enhancing protein expression. Despite receiving widespread attention, most methods primarily rely on manual design, which is time-consuming and labor-intensive. While optimization approaches can alleviate this issue, existing methods still exhibit critical limitations caused by conflicts between codon usage and mRNA structural stability, compounded by the vast design space of mRNA resulting from the presence of synonymous codons. In this paper, a novel multi-objective evolutionary optimization-based mRNA design method is proposed. We first formulate the mRNA design problem as a multi-objective optimization problem and then develop an Elite Archive-Assisted Multi-Objective Evolutionary algorithm for mRNA Design, namely EAA-MOED, by incorporating a novel elite archive-assisted method into a weighted optimization framework to improve search efficiency. Experimental studies, involving two state-of-the-art mRNA design methods and five well-known MOEAs, show the competitiveness of the proposed EAA-MOED in mRNA design.

关键词： Measurement Design methodology Evolutionary computation Search problems Linear programming Stability analysis Vaccines

来源：评论

学校读者我要写书评

暂无评论

DCSim: Computing and Networking Integration based Container Scheduling Simulator for data Centers

arXiv

引用

arXiv 2024年

作者： Hu, Jinlong Rao, Zhizhe Liu, Xingchen Deng, Lihao Dong, Shoubin Guangdong Key Lab of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou China

The increasing prevalence of cloud-native technologies, particularly containers, has led to the widespread adoption of containerized deployments in data centers. The advancement of deep neural network models has increased the demand for container-based distributed model training and inference, where frequent data transmission among nodes has emerged as a significant performance bottleneck. However, traditional container scheduling simulators often overlook the influence of network modeling on the efficiency of container scheduling, primarily concentrating on modeling computational resources. In this paper, we focus on a container scheduling simulator based on collaboration between computing and networking within data centers. We propose a new container scheduling simulator for data centers, named DCSim. The simulator consists of several modules: a data center module, a network simulation module, a container scheduling module, a discrete event-driven module, and a data collection and analysis module. Together, these modules provide heterogeneous computing power modeling and dynamic network simulation capabilities. We design a discrete event model using SimPy to represent various aspects of container processing, including container requests, scheduling, execution, pauses, communication, migration, and termination within data centers. Among these, lightweight virtualization technology based on Mininet is employed to construct a software-defined network. An experimental environment for container scheduling simulation was established, and functional and performance tests were conducted on the simulator to validate its scheduling simulation capabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Software testing

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：