检索结果-内蒙古大学图书馆

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： Priyanga P S. Sridevi Ashwini K Deepa S R Department of Artificial Intelligence and Machine Learning RNS Institute of Technology Bangalore Karnataka India Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamil Nadu India Department of Computer Science and Design K.S. Institute of Technology Bangalore Karnataka India

The smart factory of the future would not be possible without the development of AI and ML technologies, which have ushered in a new era of production. Traditional industrial processes are being revolutionized by AI and ML due to their capacity to evaluate large quantities of data and make autonomous choices, which is leading to greater efficiency, productivity, and profitability. Predictive maintenance is one area where AI and ML are making important contributions. These systems may prevent unexpected and expensive failures by constantly monitoring equipment performance and analyzing real-time data. Taking preventative measures like these results in less downtime, lower maintenance expenses, and more efficient machinery. Synergies between AI and ML are improving factory quality assurance. These technologies can identify even the smallest flaws or deviations from product standards using sophisticated vision systems and pattern recognition algorithms. Manufacturing companies may reduce waste and customer complaints by maintaining a constant quality standard via the use of automated inspection methods. Optimization of production planning and scheduling is another important use of AI and ML in manufacturing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental multi-feature tensor subspace learning based smart traffic control system and traffic density calculation using image processing 2

Incremental multi-feature tensor subspace learning based sma...

引用

2nd International Conference on Computation, Automation and Knowledge Management, ICCAKM 2021

作者： Suseendran, G. Akila, D. Balaganesh, D. Elangovan, V.R. Vijayalakshmi, V. Vels Institute of Science Technology Advanced Studies Department of Information Technology Chennai India Computer Science and Multimedia Lincoln University College Malaysia Agurchand Manmull Jain College Department of Computer Science Chennai India SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9781728194912

In times, urban centers are growing at a high rate. Growing with them is a road traffic jam. Traffic jams, especially at peak hours, became routine. As a result, traffic management is one of the foremost pressing issues in today's towns. Several alternatives are being sought to affect the matter. These include expanding road networks, regulating the number of vehicles on the roads, and deployment of Intelligent Transportation Systems (ITSs). Aside from the ITSs, the opposite alternatives (however significant) have many practical challenges in their implementation. ITSs have supported a good range of technologies like loop sensors and video surveillance systems. Vision-based ITSs have proved advantageous over the standard methods supported loop sensors. In these modern systems, video surveillance cameras are installed along the roads and road intersections where they're wont to collect traffic data. The info is then analyzed to get traffic parameters like road traffic density. This paper presents a comfortable and stylish approach for estimating the road traffic density during daytime using image processing and computer vision algorithms. The video data collected is first weakened into frames, which are then preprocessed during a series of steps. Finally, the vehicles are detected and extracted from the pictures and Density estimated. The traffic density is then obtained because of the number of vehicles per unit area of the road section. The proposed approach was implemented in MATLAB R2013a and average vehicle detection accuracy of 96.0% and 82.1% were achieved for fast-paced and slow-moving traffic scenes. © 2021 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF SELF-SUPERVISED SPEECH MODELS ON CHILDREN’S SPEECH AND INFANT VOCALIZATIONS

arXiv

引用

arXiv 2024年

作者： Li, Jialu Hasegawa-Johnson, Mark McElwain, Nancy L. Department of Electrical and Computer Engineering University of Illinois United States Beckman Institute for Advanced Science and Technology University of Illinois United States Department of Human Development and Family Studies University of Illinois United States

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer representations in adult speech. Limited work has investigated how pre-training and fine-tuning affect SSL models encoding children’s speech and vocalizations. In this study, we aim to bridge this gap by probing SSL models on two relevant downstream tasks: (1) phoneme recognition (PR) on the speech of adults, older children (8-10 years old), and younger children (1-4 years old), and (2) vocalization classification (VC) distinguishing cry, fuss, and babble for infants under 14 months old. For younger children’s PR, the superiority of fine-tuned SSL models is largely due to their ability to learn features that represent older children’s speech and then adapt those features to the speech of younger children. For infant VC, SSL models pre-trained on large-scale home recordings learn to leverage phonetic representations at middle layers, and thereby enhance the performance of this task. © 2024, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Noises Over Quantum Key Distribution Protocol 7th

Comparative Study of Noises Over Quantum Key Distribution ...

引用

7th International Conference on Data Management, Analytics and Innovation, ICDMAI 2023

作者： Bhattacharyya, Sawan Das, Ajanta Banerjee, Anindita Chakrabarti, Amlan Department of Computer Science Ramakrishna Mission Vivekananda Centenary College West Bengal Kolkata India Amity Institute of Information Technology Amity University Kolkata Kolkata India Corporate Research and Development Centre for Development of Advanced Computing Pune India A. K. Choudhury School of Information Technology University of Calcutta West Bengal Kolkata India

ISBN: (纸本)9789819914135

The security of modern cryptographic systems mostly depends on mathematical hardness to solve a particular problem manually. The most popular and widely used classical cryptosystem, RSA (Rivest, Shamir, Alderman) is based on the mathematical hardness of prime factorization of the product of two large prime by any of the present classical processors. But the advancement in technology particularly in quantum information provides a threat to the present communication protocols. It motivates the researchers to move to new technologies that are fundamentally more secure through the principle of quantum mechanics. Such protocols rely upon quantum bits or qubits for data transmissions securely. The application of qubits instead of bits in cryptography using quantum key distribution protocols makes encryption robust. But the quantum communication protocols are prone to noise due to environmental factors, fragile and traverse’ a long fiber optical path. Hence, the states of qubits are easily tampered with by external factors. Noise alters the information;eventually, the message may not be meaningful to receivers. Except for bit flip and phase flip noises, depolarization, amplitude damping, decoherence, thermal relaxation, and phase damping are obstacles to achieving long-distance communication. The objective of this paper is to present a comparative study of quantum communication protocols in a noisy environment with different classes of noise. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Quantum-Informed Recursive Optimization Algorithms

引用

PRX Quantum 2024年第2期5卷 020327-020327页

作者： Jernej Rudi Finžgar Aron Kerschbaumer Martin J.A. Schuetz Christian B. Mendl Helmut G. Katzgraber BMW AG Munich Germany Department of Computer Science Technical University Munich School of CIT Garching Germany Amazon Quantum Solutions Lab Seattle Washington USA AWS Center for Quantum Computing Pasadena California USA Technical University of Munich Institute for Advanced Study Garching Germany

We propose and implement a family of quantum-informed recursive optimization (QIRO) algorithms for combinatorial optimization problems. Our approach leverages quantum resources to obtain information that is used in problem-specific classical reduction steps that recursively simplify the problem. These reduction steps address the limitations of the quantum component (e.g., locality) and ensure solution feasibility in constrained optimization problems. Additionally, we use backtracking techniques to further improve the performance of the algorithm without increasing the requirements on the quantum hardware. We showcase the capabilities of our approach by informing QIRO with correlations from classical simulations of shallow circuits of the quantum approximate optimization algorithm, solving instances of maximum independent set and maximum satisfiability problems with hundreds of variables. We also demonstrate how QIRO can be deployed on a neutral atom quantum processor to find large independent sets of graphs. In summary, our scheme achieves results comparable to classical heuristics even with relatively weak quantum resources. Furthermore, enhancing the quality of these quantum resources improves the performance of the algorithms. Notably, the modular nature of QIRO offers various avenues for modifications, positioning our work as a template for a broader class of hybrid quantum-classical algorithms for combinatorial optimization.

关键词： Adiabatic quantum optimization Optimization problems Quantum algorithms Quantum information with atoms & light

来源：评论

学校读者我要写书评

暂无评论

Conformal Graph-level Out-of-distribution Detection with Adaptive Data Augmentation 25

Conformal Graph-level Out-of-distribution Detection with Ada...

引用

34th ACM Web Conference, WWW 2025

作者： Lin, Xixun Cao, Yanan Sun, Nan Zou, Lixin Zhou, Chuan Zhang, Peng Zhang, Shuai Zhang, Ge Wu, Jia Institute of Information Engineering Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Cyber Science and Engineering Wuhan University Wuhan China Academy of Mathematics and Systems Science CAS School of Cyber Security University of Chinese Academy of Sciences Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Academy of Mathematics and Systems Science CAS Beijing China School of Computer Science and Technology Donghua University Shanghai China Department of Computing Macquarie University Sydney Australia

ISBN: (纸本)9798400712746

Graph-level out-of-distribution (OOD) detection, which attempts to identify OOD graphs originated from an unknown distribution, is a vital building block for safety-critical applications in Web and society. Current approaches concentrate on how to learn better graph representations, but fail to provide any statistically guarantee on detection results, therefore impeding their deployments in the scenario where detection errors would result in serious consequences. To overcome this critical issue, we propose the Conformal Graph-level Out-of-distribution Detection (CGOD), extending the theory of conformal prediction to graph-level OOD detection with a rigorous control over the false positive rate. In CGOD, we develop a new aggregated non-conformity score function based on the proposed adaptive data augmentation. Through the guidance from two designed metrics, i.e., score consistency and representation diversity, our augmentation strategy can generate multiple non-conformity scores, and aggregating these generated non-conformity scores together is robust to the misleading information. Meanwhile, our score function can perceive the subsequent process of conformal inference, enabling the aggregated non-conformity score to be adaptive to different input graphs and deriving a more accurate score estimation. We conduct experiments on multiple real-world datasets with different empirical settings. Extensive results and model analyses demonstrate the superior performance of our approach over several competitive baselines. © 2025 Copyright held by the owner/author(s).

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Evaluating Conditional Handover for 5g Networks with Dynamic Obstacles

SSRN

引用

SSRN 2024年

作者： Deb, Souvik Rathod, Megh Balamurugan, Rishi Singh, Rajeev Kumar Sanyal, Samriddha Ghosh, Shankar K. Advanced Computing & Microelectronics Unit Indian Statistical Institute West Bengal Kolkata700108 India Department of Computer Science and Engineering Shiv Nadar Institution of Eminence Delhi201314 India School of Computing and Data Science FLAME University Maharashtra Pune412115 India Shiv Nadar University India

To enhance seamless connectivity in millimetre wave New radio networks, Conditional handover has evolved as a promising solution. Unlike A3 handover where handover execution is certain after receiving handover command from the serving access network, in conditional handover, handover execution is conditional on the Reference signal received power measurements from both current and target access networks, as well as on mobility parameters such as preparation and execution offsets. Presence of dynamic obstacles may block the signal from serving and (or) target access networks, which results in violation of the conditions for the handover preparation/execution. Moreover, signal blockage by dynamic obstacles may cause radio link failure, which may cause handover failure as well. Analytic evaluations of conditional handover performance in the presence of dynamic obstacles are quite limited in the preceding literature. In this work, handover performance of conditional handover has been carried out in terms of handover latency, handover packet loss and handover failure probability. A Markov model accounting the effect of dynamic obstacles, different mobility parameters (e.g., execution offset, preparation offset, time-to-preparation and time-to-execution), user velocity and channel fading characteristics has been proposed to characterize handover failure. Results obtained from the analytic model has been validated against extensive simulation results. Our study reveal that optimal configuration of the mobility parameters is actually conditional on the presence of dynamic obstacles, user velocity and fading characteristics. This study will be helpful for the mobile operators to configure the mobility parameters for New radio systems where dynamic obstacles are present. © 2024, The Authors. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Explainable physics-based constraints on reinforcement learning for accelerator controls

arXiv

引用

arXiv 2025年

作者： Colen, Jonathan Schram, Malachi Rajput, Kishansingh Kasparian, Armen Joint Institute on Advanced Computing for Environmental Studies Old Dominion University NorfolkVA23539 United States Hampton Roads Biomedical Research Consortium PortsmouthVA23703 United States Data Science Department Thomas Jefferson National Accelerator Facility Newport NewsVA23606 United States Computer Science Department Old Dominion University NorfolkVA23539 United States Department of Computer Science University of Houston HoustonTX77204 United States

We present a reinforcement learning (RL) framework for controlling particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator controls environments designed to emulate the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment. In addition, we find that the introduction of a physics-based surrogate enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dependent randomized rounding for clustering and partition systems with knapsack constraints

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 3494-3534页

作者： David G. Harris Thomas Pensyl Aravind Srinivasan Khoa Trinh Department of Computer Science University of Maryland College Park MD Bandwidth Inc. Raleigh NC Department of Computer Science and Institute for Advanced Computer Studies University of Maryland College Park MD Google Mountain View CA

Clustering problems are fundamental to unsupervised learning. There is an increased emphasis on fairness in machine learning and AI; one representative notion of fairness is that no single group should be over-represented among the cluster-centers. This, and much more general clustering problems, can be formulated with "knapsack" and "partition" constraints. We develop new randomized algorithms targeting such problems, and study two in particular: multi-knapsack median and multi-knapsack center. Our rounding algorithms give new approximation and pseudoapproximation algorithms for these *** key technical tool, which may be of independent interest, is a new tail bound analogous to Feige (2006) for sums of random variables with unbounded variances. Such bounds can be useful in inferring properties of large networks using few samples.

关键词： dependent rounding clustering fairness

来源：评论

学校读者我要写书评

暂无评论

An Approach on Data Visualization and Data Mining with Regression Analysis 1st

An Approach on Data Visualization and Data Mining with Regre...

引用

1st International Conference on Mathematical Modeling and Computational science, ICMMCS 2020

作者： Suseendran, G. Doss, Srinath Pal, Souvik Dey, Niti Quang Cuong, Ton Department of Information Technology Vels Institute of Science Technology & Advanced Studies Chennai India Faculty of Computing Botho University Gaborone Botswana Department of Computer Science and Engineering Global Institute of Management and Technology Krishnanagar India VNU University of Education National University Vietnam Hanoi Viet Nam

ISBN: (纸本)9789813343887

Right off the bat, the ideas and arrangement about imagined information mining innovation expounds in this paper, data mining at that point the innovation and regression analysis technology and the visualization data, what’s more, are talked about;finally, the use of data mining addressed in combination with sliding bearing wear coefficient testing, regression analysis technology and data visualization. In this paper structure, a framework to actualize data mining technology for visualized data mining under the web condition. Data visualization helps to explore data with some satisfactory results in a powerful way. Also, as a part of the data reduction process by combining data, a significant role has been played by data visualization. The linear and nonlinear regression analyses are used in this method, and application research progresses to proving the factors in our methods. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data visualization

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：