检索结果-内蒙古大学图书馆

Computer, Communication and Control (IC4), International Conference on

作者： V. Nallarasan N. Arivazhagan R. Lakshminarayanan D Sharmila Nagaveni B Sangolgi Anand M Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Electronics and Communication Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering Faculty of Engineering and Technology (Exclusively for women) Sharnbasva University Kalaburagi India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chengalpattu India

The initial step in facial recognition and analysis systems often involves facial detection. Traditional methods like Haar cascades and directed gradient histograms relied on manually designed features, limiting their effectiveness in diverse image environments. However, the emergence of deep learning in computer vision has accelerated the development of face detection frameworks, significantly improving accuracy. Detecting small-scale faces, varying positions, occlusions, blurs, and partially obscured faces in uncontrolled settings remains a persistent challenge in face identification. To address this, we propose a new approach called “Visionary Net.” This single-stage face detector has undergone refinements, boosting both detection speed and accuracy. We tested Visionary Net on two well-known datasets: Mega Face and CelebA. Notably, on the Mega Face benchmark, our method achieved an impressive AP of 48.5 at a speed of 15.2 FPS using single-scale inference and an exceptional AP of 52.7 with multi-scale inference. Implementing it with the PyTorch framework resulted in a remarkable 97.3% accuracy in successfully detecting faces. Our comprehensive experiments show that Visionary Net surpasses existing models, demonstrating superior detection and recognition capabilities across various evaluation metrics. This innovative algorithm holds significant promise for robust face detection in challenging real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hybrid Improved Fully Homomorphic Encryption with AES to provide high security in Cloud computing

A hybrid Improved Fully Homomorphic Encryption with AES to p...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Ravindran K S. Nagendra Prabhu Department of Information Technology SRM Institute of Science and Technology Easwari Engineering College Chennai India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology

Since this information may be accessible by a third party and could compromise the client's information's confidentiality, there is a barrier between the customer and the true location of his information. The most often used approach to bridging this security gap has been to first encrypt online data using traditional methods before sending it to the cloud service provider. But to decrypt the information and complete the calculations that are required, the customer must give the server a secret key. Using homomorphic encryption, mathematical calculations can be made on encrypted information without having to first decode it. The electrocardiogram (ECG) measures and finds arrhythmias in the circulatory system. It differ from individual to individual, these characteristics are now employed for identification. So it's crucial to secure an ECG signal. A safety method known as Homomorphic Encryption (HE) handles encrypted information without the need for *** identical initial information findings are provided by HE. In this research, an Improved Fully Homomorphic Encryption (IFHE) technique using Advanced Encryption Standard (AES) is proposed for encoding the ECG measures to enhance safety while safeguarding the confidentiality of information while removing sharing key limitations. The information of the customer is encrypted in the cloud server discussed in this work, so required computations can be performed on the encrypted information. To do this, it is proposed that the method of assessment be added as a further layer of security to the AES technique, which then executes several homomorphic mathematical computations on the encrypted information in place of the initial information. To increase safety, a linear polynomial equation with changeable values is proposed for the assessment ***, the IFHEAES method has a 100% success rate in decryption (recovering the original signal) and 95.8% efficiency in categorization. Its decryption and enc

关键词：

来源：评论

学校读者我要写书评

暂无评论

Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning

Infer and Adapt: Bipedal Locomotion Reward Learning from Dem...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Feiyang Wu Zhaoyuan Gu Hanran Wu Anqi Wu Ye Zhao School of Computational Science and Engineering Georgia Institute of Technology Atlanta GA USA Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta GA USA College of Computing Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from demonstrations have shown promising results for robot learning in complex environments. While imitation learning of expert policies has been well-explored, the study of learning expert reward functions is largely under-explored in legged locomotion. This paper brings state-of-the-art Inverse Reinforcement Learning (IRL) techniques to solving bipedal locomotion problems over complex terrains. We propose algorithms for learning expert reward functions, and we subsequently analyze the learned functions. Through nonlinear function approximation, we uncover meaningful insights into the expert’s locomotion strategies. Furthermore, we empirically demonstrate that training a bipedal locomotion policy with the inferred reward functions enhances its walking performance on unseen terrains, highlighting the adaptability offered by reward learning.

关键词： Legged locomotion Training Robot motion Imitation learning Reinforcement learning Approximation algorithms Robot learning

来源：评论

学校读者我要写书评

暂无评论

An optimal piecewise cubic nonconforming finite element scheme for the planar biharmonic equation on general triangulations

引用

science China Mathematics 2021年第11期64卷 2579-2602页

作者： Shuo Zhang LSEC Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

This paper presents a nonconforming finite element scheme for the planar biharmonic equation,which applies piecewise cubic polynomials(P_(3))and possesses O(h^(2))convergence rate for smooth solutions in the energy norm on general shape-regular *** Dirichlet and Navier type boundary value problems are *** basis for the scheme is a piecewise cubic polynomial space,which can approximate the H^(4) functions with O(h^(2))accuracy in the broken H^(2) ***,a discrete strengthened Miranda-Talenti estimate(▽^(2)_(h)·,▽^(2)_(h)·)=(Δh·,Δh·),which is usually not true for nonconforming finite element spaces,is *** finite element space does not correspond to a finite element defined with Ciarlet’s triple;however,it admits a set of locally supported basis functions and can thus be implemented by the usual *** notion of the finite element Stokes complex plays an important role in the analysis as well as the construction of the basis functions.

关键词： biharmonic equation optimal cubic finite element scheme general triangulation discretized Stokes complex discrete strengthened Miranda-Talenti estimate

来源：评论

学校读者我要写书评

暂无评论

AlpaPICO: Extraction of PICO Frames from Clinical Trial Documents Using LLMs

arXiv

引用

arXiv 2024年

作者： Ghosh, Madhusudan Mukherjee, Shrimon Ganguly, Asmit Basuchowdhuri, Partha Naskar, Sudip Kumar Ganguly, Debasis School of Mathematical and Computational Sciences Indian Association for the Cultivation of Science India Computer Science and Engineering Indian Institute of Technology Patna India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering Jadavpur University India

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. More specifically, both of the proposed frameworks utilize AlpaCare as base LLM which employs both few-shot in-context learning and instruction tuning techniques to extract PICO-related terms from the clinical trial reports. We applied these approaches to the widely used coarse-grained datasets such as EBM-NLP, EBM-COMET and fine-grained datasets such as EBM-NLPrev and EBM-NLPh. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our projec

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Investigation on Preserving Privacy of Electronic Medical Record using Split Learning

引用

Procedia Computer science 2024年 233卷 614-622页

作者： Kiruthika M Abhishek Kumar Lalitha Krishnasamy Velliangiri Sarveshwaran Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu 603203 India Senior Manager IT Punjab National Bank New Delhi 110075 India Department of Computer Science and Engineering School of Engineering and Technology Christ University Bengaluru Karnataka 560074 India

Artificial Intelligence is deployed in multiple areas, including healthcare. Utmost research is done in AI enabled healthcare industry because of the demands like accurate result, data security, exact prediction, huge volume of data, etc. In conventional deep learning models, the training happens with the dataset that are stored in a single device. This requires a huge storage space and highly efficient machines to train the data. Usage of big data, demands for innovative models that can be deployed and used in confined storage. Split learning is one such collaborative distributed deep learning model that allows the data to be stored in a split fashion. Split learning supports desirable features like less storage, more privacy to raw data, ability to work with resource constraints, etc., making it suitable for storing electronic medical record of patients. This paper discusses the advantages of using split learning for healthcare, the possible configurations of split learning that supports data privacy in healthcare and finally discusses the open research challenges in implementing split learning for healthcare.

关键词： Split Learning Healthcare Privacy Security Patient data

来源：评论

学校读者我要写书评

暂无评论

Covariance-Based Device Activity Detection with Massive MIMO for Near-Field Correlated Channels

arXiv

引用

arXiv 2024年

作者： Wang, Ziyue Li, Yang Liu, Ya-Feng Ma, Junjie The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Shenzhen Research Institute of Big Data Shenzhen518172 China The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China

This paper studies the device activity detection problem in a massive multiple-input multiple-output (MIMO) system for near-field communications (NFC). In this system, active devices transmit their signature sequences to the base station (BS), which detects the active devices based on the received signal. In this paper, we model the near-field channels as correlated Rician fading channels and formulate the device activity detection problem as a maximum likelihood estimation (MLE) problem. Compared to the traditional uncorrelated channel model, the correlation of channels complicates both algorithm design and theoretical analysis of the MLE problem. On the algorithmic side, we propose two computationally efficient algorithms for solving the MLE problem: an exact coordinate descent (CD) algorithm and an inexact CD algorithm. The exact CD algorithm solves the one-dimensional optimization subproblem exactly using matrix eigenvalue decomposition and polynomial root-finding. By approximating the objective function appropriately, the inexact CD algorithm solves the one-dimensional optimization subproblem inexactly with lower complexity and more robust numerical performance. Additionally, we analyze the detection performance of the MLE problem under correlated channels by comparing it with the case of uncorrelated channels. The analysis shows that when the overall number of devices N is large or the signature sequence length L is small, the detection performance of MLE under correlated channels tends to be better than that under uncorrelated channels. Conversely, when N is small or L is large, MLE performs better under uncorrelated channels than under correlated ones. Simulation results demonstrate the computational efficiency of the proposed algorithms and verify the correctness of the analysis. Copyright © 2024, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Inverse Reinforcement Learning with the Average Reward Criterion

arXiv

引用

arXiv 2023年

作者： Wu, Feiyang Ke, Jingyang Wu, Anqi School of Computational Science and Engineering College of Computing Georgia Institute of Technology AtlantaGA30332 United States School of Computer Science College of Computing Georgia Institute of Technology AtlantaGA30332 United States

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent. Previous IRL methods assume that the expert is trained in a discounted environment, and the discount factor is known. This work alleviates this assumption by proposing an average-reward framework with efficient learning algorithms. We develop novel stochastic first-order methods to solve the IRL problem under the average-reward setting, which requires solving an Average-reward Markov Decision Process (AMDP) as a subproblem. To solve the subproblem, we develop a Stochastic Policy Mirror Descent (SPMD) method under general state and action spaces that needs O(1/Ε) steps of gradient computation. Equipped with SPMD, we propose the Inverse Policy Mirror Descent (IPMD) method for solving the IRL problem with a O(1/Ε2) complexity. To the best of our knowledge, the aforementioned complexity results are new in IRL. Finally, we corroborate our analysis with numerical experiments using the MuJoCo benchmark and additional control tasks. © 2023, CC BY.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

On the convergence of stochastic gradient descent with bandwidth-based step size

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 1990-2038页

作者： Xiaoyu Wang Ya-xiang Yuan Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China State Key Laboratory of Scientific/Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

We first propose a general step-size framework for the stochastic gradient descent(SGD) method: bandwidth-based step sizes that are allowed to vary within a banded region. The framework provides efficient and flexible step size selection in optimization, including cyclical and non-monotonic step sizes (e.g., triangular policy and cosine with restart), for which theoretical guarantees are rare. We provide state-of-the-art convergence guarantees for SGD under mild conditions and allow a large constant step size at the beginning of training. Moreover, we investigate the error bounds of SGD under the bandwidth step size where the boundary functions are in the same order and different orders, respectively. Finally, we propose a 1/t up-down policy and design novel non-monotonic step sizes. Numerical experiments demonstrate these bandwidth-based step sizes' efficiency and significant potential in training regularized logistic regression and several large-scale neural network tasks.

关键词： stochastic gradient descent bandwidth-based step size non-asymptotic convergence non-monotonic step size machine learning

来源：评论

学校读者我要写书评

暂无评论

Design of Approximate Multiplier Using Highly Compressed 5_2 Counter

Design of Approximate Multiplier Using Highly Compressed 5_2...

引用

Mobile computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Bathlin Nelmin N R S Shaji Hariprasad S Sudeshna Shettygari Vasan J K Vijayan V Department of Electronics and Communication Engineering University College of Engineering Nagercoil India Department of Computer Science and Engineering St. Xavier's Catholic College of Engineering Nagercoil India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Approximate computing effectively impacts low-power VLSI circuits by reducing circuit overhead. It introduces minimal error in the output, which does not significantly affect the application. This paper proposes an approximate multiplier constructed using 5_3 and 5_2 counters. The proposed 5_2 counter delivers two outputs instead of three, thereby achieving 60% compression. The overhead of the 5_2 counter circuit is reduced, achieving a power delay product (PDP) improvement of 18%. This reduction comes with an addition of an 6% error rate. The newly designed multiplier has less delay, where the Mean error distance (MED) is kept as low as possible. The complexity of the 5_2 counter is also reduced since the counter uses only a full adder and three gates. This is achieved by applying various error optimization mechanisms. The error parameters, (i) Error Distance (ED), and (ii) Mean Error Distance (MED) are analyzed and compared with existing works. The proposed multipliers are involved in image contrast application with better Peak Signal to Noise Ratio (PSNR) value.

关键词： Measurement PSNR Image coding Error compensation Very large scale integration Logic gates Delays Standards Optimization Mobile computing

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：