检索结果-内蒙古大学图书馆

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Haque, Mahmudul Nyeem, Hussain Ovi, Tareque Bashar Nahid, Al Molla, Md. Sabbir Hossain Tuhin, Md. Tanjim Mahmud Shahab, Fardin Alam, Ayat Subah Alam, Saadia Binte Mirpur Cantonment Dhaka1216 Bangladesh Independent University Department of Computer Science and Engineering Dhaka1229 Bangladesh Independent University Bangladesh Center for Computational & Data Sciences Dhaka1229 Bangladesh

ISBN: (纸本)9798350388282

Detecting and classifying violence is crucial for public safety and addressing societal violence. DL models have greatly improved the automation of violence detection systems by effectively capturing intricate visual patterns. However, the quality and diversity of the training data greatly impact the effectiveness of these models. Existing datasets may be biased towards specific situations, limiting their practical use. To address this limitation, we introduce the Movie Clip (MC) dataset to enhance the generalisability of Automated Violence Detection and Classification (AVDC) systems. The MC dataset encompasses a broad spectrum of near-real-world violent actions, incorporating diverse demographics, environmental circumstances, and cultural elements extracted from movies. Consequently, it accurately reflects the complexity and diversity of real-world violent scenarios. The potential of the new dataset is investigated against its existing counterparts, like Hockey Fight (HF) and AIRTLab datasets. These datasets are used to train the ConvLSTM models based on the VGG16 and VGG19 architectures. The proposed dataset significantly improves AVDC model generalisation, outperforming the generalisability of current datasets, thereby advancing violence detection and facilitating the development of more robust and efficient AVDC systems. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Trapping-influenced photoluminescence intensity decay in semiconductor nanoplatelets 6

Trapping-influenced photoluminescence intensity decay in sem...

引用

6th International Conference on Metamaterials and Nanophotonics, METANANO 2021

作者： Kurilovich, A.A. Mantsevich, V.N. Stevenson, K.J. Chechkin, A.V. Palyulin, V.V. Center for Energy Science and Technology Skolkovo Institute of Science and Technology Moscow121205 Russia Chair of Semiconductors and Cryoelectronics and Quantum Technology Center Physics department Lomonosov Moscow State University Moscow119991 Russia Institute for Physics and Astronomy University of Potsdam Potsdam-GolmD-14476 Germany Akhiezer Institute for Theoretical Physics National Science Center Kharkov Institute of Physics and Technology" Kharkov61108 Ukraine Center for Computational and Data-intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

We present a diffusion-based simulation model for explanation of long time power-law decay of photoluminescence (PL) emission intensity in semiconductor nanoplatelets. In our model the shape of emission curves is an outcome of interplay of recombination, diffusion and trapping of excitons. At short times the excitons diffuse freely following the normal diffusion behaviour. The emission decay is purely exponential and is defined by recombination. At long times the transition into the subdiffusive motion happens and the emission occurs due to the release of excitons from surface traps. A power-law tail for intensity is a consequence of the release. The crossover from onelimit to another is controlled by diffusion properties. The approach reproduces the properties of experimental curves measured for different nanoplatelet systems. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Excitons

来源：评论

学校读者我要写书评

暂无评论

Adaptive gradient methods with dynamic bound of learning rate 7

Adaptive gradient methods with dynamic bound of learning rat...

引用

7th International Conference on Learning Representations, ICLR 2019

作者： Luo, Liangchen Xiong, Yuanhao Liu, Yan Sun, Xu MOE Key Lab of Computational Linguistics School of EECS Peking University China College of Information Science and Electronic Engineering Zhejiang University China Department of Computer Science University of Southern California United States Center for Data Science Beijing Institute of Big Data Research Peking University China

Adaptive optimization methods such as ADAGRAD, RMSPROP and ADAM have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGRAD to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of ADAM and AMSGRAD, called ADABOUND and AMSBOUND respectively, which employ dynamic bounds on learning rates to achieve a gradual and smooth transition from adaptive methods to SGD and give a theoretical proof of convergence. We further conduct experiments on various popular tasks and models, which is often insufficient in previous work. Experimental results show that new variants can eliminate the generalization gap between adaptive methods and SGD and maintain higher learning speed early in training at the same time. Moreover, they can bring significant improvement over their prototypes, especially on complex deep networks. The implementation of the algorithm can be found at https://***/Luolc/AdaBound. © 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

SMOTE Oversampling and Near Miss Undersampling Based Diabetes Diagnosis from Imbalanced dataset with XAI Visualization 28

SMOTE Oversampling and Near Miss Undersampling Based Diabete...

引用

28th IEEE Symposium on Computers and Communications, ISCC 2023

作者： Nayan, Nasim Mahmud Islam, Ashraful Islam, Muhammad Usama Ahmed, Eshtiak Hossain, Mohammad Mobarak Alam, Md Zahangir University of Information Technology and Sciences Department of Computer Science and Engineering Bangladesh Independent University Center for Computational and Data Sciences Bangladesh School of Computing and Informatics University of Louisiana at Lafayette United States Independent University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350300482

This study investigated the predictive ability of ten different machine learning (ML) models for diabetes using a dataset that was not evenly distributed. Additionally, the study evaluated the effectiveness of two oversampling and undersampling methods, namely the Synthetic Minority Oversampling Technique (SMOTE) and the Near-Miss algorithm. Explainable Artificial Intelligence (XAI) techniques were employed to enhance the interpretability of the model's predictions. The results indicate that the extreme gradient boosting (XGB) model combined with SMOTE oversampling technique exhibited the highest accuracy and an F1-score of 99% and 1.00 respectively. Furthermore, the utilization of XAI methods increased the dependability of the model's decision-making process, rendering it more appropriate for clinical use. These results imply that integrating XAI with ML and oversampling techniques can enhance the early detection and management of diabetes, leading to better diagnosis and intervention. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DronePick: Object picking and delivery teleoperation with the drone controlled by a wearable tactile display

arXiv

引用

arXiv 2019年

作者： Ibrahimov, Roman Tsykunov, Evgeny Shirokun, Vladimir Somov, Andrey Tsetserukou, Dzmitry Intelligent Space Robotics Laboratory Skolkovo Institute of Science and Technology Moscow Russia Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow Russia

We report on the teleoperation system DronePick which provides remote object picking and delivery by a human-controlled quadcopter. The main novelty of the proposed system is that the human user continuously gets the visual and haptic feedback for accurate teleoperation. DronePick consists of a quadcopter equipped with a magnetic grabber, a tactile glove with finger motion tracking sensor, hand tracking system, and the Virtual Reality (VR) application. The human operator teleoperates the quadcopter by changing the position of the hand. The proposed vibrotactile patterns representing the location of the remote object relative to the quadcopter are delivered to the glove. It helps the operator to determine when the quadcopter is right above the object. When the "pick" command is sent by clasping the hand in the glove, the quadcopter decreases its altitude and the magnetic grabber attaches the target object. The whole scenario is in parallel simulated in VR. The air flow from the quadcopter and the relative positions of VR objects help the operator to determine the exact position of the delivered object to be picked. The experiments showed that the vibrotactile patterns were recognized by the users at the high recognition rates: the average 99% recognition rate and the average 2.36s recognition time. The real-life implementation of DronePick featuring object picking and delivering to the human was developed and tested. Copyright © 2019, The Authors. All rights reserved.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Vocal Call Locator Benchmark (VCL) for localizing rodent vocalizations from multi-channel audio 38

Vocal Call Locator Benchmark (VCL) for localizing rodent voc...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Peterson, Ralph E. Tanelus, Aramis Ick, Christopher Mimica, Bartul Francis, Niegil Ivan, Violet J. Choudhri, Aman Falkner, Annegret L. Murthy, Mala Schneider, David M. Sanes, Dan H. Williams, Alex H. NYU Center for Neural Science United States Flatiron Institute Center for Computational Neuroscience United States NYU Center for Data Science United States Princeton Neuroscience Institute United States NYU Tandon School of Engineering United States Columbia Univsersity United States

Understanding the behavioral and neural dynamics of social interactions is a goal of contemporary neuroscience. Many machine learning methods have emerged in recent years to make sense of complex video and neurophysiological data that result from these experiments. Less focus has been placed on understanding how animals process acoustic information, including social vocalizations. A critical step to bridge this gap is determining the senders and receivers of acoustic information in social interactions. While sound source localization (SSL) is a classic problem in signal processing, existing approaches are limited in their ability to localize animal-generated sounds in standard laboratory environments. Advances in deep learning methods for SSL are likely to help address these limitations, however there are currently no publicly available models, datasets, or benchmarks to systematically evaluate SSL algorithms in the domain of bioacoustics. Here, we present the VCL Benchmark: the first large-scale dataset for benchmarking SSL algorithms in rodents. We acquired synchronized video and multi-channel audio recordings of 767,295 sounds with annotated ground truth sources across 9 conditions. The dataset provides benchmarks which evaluate SSL performance on real data, simulated acoustic data, and a mixture of real and simulated data. We intend for this benchmark to facilitate knowledge transfer between the neuroscience and acoustic machine learning communities, which have had limited overlap. © 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

An adaptive algorithm for quantum circuit simulation

arXiv

引用

arXiv 2019年

作者： Schutski, Roman Oseledets, Ivan Lykov, Danil Center for Computational and Data-Intensive Science and Engineering Skoltech Skolkovo Innovation Center Moscow Region121205 Moscow Institute of Physics and Technology Dolgoprudny Moscow Region141701

Efficient simulation of quantum computers is essential for the development and validation of near-term quantum devices and the research on quantum algorithms. Up to date, two main approaches to simulation were in use, based on either full state or single amplitude evaluation. We propose an algorithm that efficiently interpolates between these two possibilities. Our approach elucidates the connection between quantum circuit simulation and partial evaluation of expressions in tensor algebra. Copyright © 2019, The Authors. All rights reserved.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

Late and Early Blight Diseases Identification of Potatoes with a Light Weight Hybrid Transfer Learning Model

Late and Early Blight Diseases Identification of Potatoes wi...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Siddique, Abu Zobayer Bin Das, Shoibal Tabassum, Poonam Tasir, All Moon Roy, Shovon Rahman, Md. Saifur Mridha, M.F. Islam, Ashraful Bangladesh University of Business and Technology Department of Computer Science and Engineering Dhaka Bangladesh American International University-Bangladesh Department of Computer Science Dhaka Bangladesh Independent University Bangladesh Center for Computational and Data Sciences Dhaka Bangladesh

ISBN: (纸本)9798350337617

Potatoes are one of the world's most important commodities, and leaf maladies such as early and late blight can substantially reduce their yield and quality. Hence, both farmers and researchers must prioritize quick and precise illness diagnosis. In our research, we propose a strategy based on transfer learning for classifying toxic and diseased potato leaf tissue. We specifically used our dataset of potato leaf photos to fine-tune the Mobile-Net model, which was a pre-trained convolutional neural network. To enhance the model's functionality, we also added a few more layers. Our study found that, in comparison to other state-of-the-art methods, our methodology outperformed them all by achieving a multi-class classification accuracy of 99%. Our method can be used to detect and monitor potato leaf maladies in real-world situations, which could eventually contribute to enhancing potato productivity and food security. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Fast Volume Integral Equation Solver with Linear Basis Functions for the Accurate Computation of Electromagnetic Fields in MRI

arXiv

引用

arXiv 2019年

作者： Georgakis, Ioannis P. Giannakopoulos, Ilias I. Litsarev, Mikhail S. Polimeridis, Athanasios G. Skoltech Center for Computational Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia Q Bio RedwoodCA94063 United States

Objective: This paper proposes a stable volume integral equation (VIE) solver based on polarization/magnetization currents, for the accurate and efficient computation of the electromagnetic scattering from highly inhomogeneous and high contrast objects. Methods: We employ the Galerkin Method of Moments to discretize the formulation with discontinuous piecewise linear basis functions on uniform voxelized grids, allowing for the acceleration of the associated matrix-vector products in an iterative solver, with the help of FFT. Results: Numerical experiments are conducted to study the accuracy and convergence properties of the proposed framework. Their results are compared against standard low order (piecewise constant) discretization schemes, a more conventional VIE formulation based on electric flux densities, and a commercial software package that employs the finite difference time domain method. Conclusion: The results illustrate the superior accuracy and wellconditioned properties of the proposed scheme. Significance: The developed solver can be applied to accurately analyze complex geometries, including realistic human body models, typically used in modeling the interactions between electromagnetic waves and biological tissue, that arise in magnetic resonance scanners. Copyright © 2019, The Authors. All rights reserved.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Hierarchical bucket tree: An efficient account structure for blockchain-based system

Hierarchical bucket tree: An efficient account structure for...

引用

作者： Chen, Weili Zheng, Zibin Ma, Mingjie He, Pinjia Zhou, Yuren Bian, Jing School of Data and Computer Science National Engineering Research Center of Digital Life Sun Yat-sen University Guangzhou510006 China Department of Computer Science ETH Zurich Switzerland School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China

Systems built on top of blockchain are often inefficient. One reason for the inefficiency is that these systems include too many hash operations. To address this problem, we conduct an empirical study on the transaction history of a real-world blockchain-based system (i.e., Ethereum), which contains 300,821 accounts and 14,240,095 transactions. We found that the account usage frequency is highly heterogeneous. Based on this finding, this paper presents hierarchy bucket tree (HBT), an efficient account structure with user transaction behaviour information embedded, to reduce the number of hash operations and thus enhance the efficiency of blockchain-based systems. Extensive experiments have been conducted and the experimental results show that HBT reduces hash operations by nearly 80% compared with the existing account structure. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Blockchain

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：