检索结果-内蒙古大学图书馆

2022 Conference on Research in Adaptive and Convergent Systems, RACS 2022

作者： Wang, Shao-Hua Yiu, Wei-Liang Tu, Chia-Heng Chang, Da-Wei Lee, Wei-Hsun Dept. of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Dept. of Transportation and Communication Management Science National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781450393980

While vehicle-to-everything technology has been proposed to improve road traffic efficiency and safety, it would suffer from the low coverage during an early stage of vehicle-to-everything deployment. The infrastructure-based solutions have been developed to tackle the problem by gathering traffic status on a roadside unit and broadcasting the detected information to nearby connected vehicles. In this work, we aim to augment such an infrastructure-centric design by proposing a multiple applications software framework to broadcast the sensed traffic conditions to connected vehicles in the vicinity. In addition, we propose a software module to improve the handling of multiple applications for the roadside unit. We have evaluated the proposed software in indoor tests, which shows that the framework can significantly improve traffic safety while conforming to the performance specifications of the standards defined by the Society of Automotive Engineers. © 2022 ACM.

关键词： Vehicle to Everything

来源：评论

学校读者我要写书评

暂无评论

Tuning the feedback controller gains is a simple way to improve autonomous driving performance

arXiv

引用

arXiv 2024年

作者： Liang, Wenyu Baldivieso, Pablo R. Drummond, Ross Shin, Donghwan Dept. of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Dept. of Computer Science University of Sheffield Sheffield United Kingdom

Typical autonomous driving systems are a combination of machine learning algorithms (often involving neural networks) and classical feedback controllers. Whilst significant progress has been made in recent years on the neural network side of these systems, only limited progress has been made on the feedback controller side. Often, the feedback control gains are simply passed from paper to paper with little re-tuning taking place, even though the changes to the neural networks can alter the vehicle’s closed loop dynamics. The aim of this paper is to highlight the limitations of this approach;it is shown that retuning the feedback controller can be a simple way to improve autonomous driving performance. To demonstrate this, the PID gains of the longitudinal controller in the TCP autonomous vehicle algorithm are tuned. This causes the driving score in CARLA to increase from 73.21 to 77.38, with the results averaged over 16 driving scenarios. Moreover, it was observed that the performance benefits were most apparent during challenging driving scenarios, such as during rain or night time, as the tuned controller led to a more assertive driving style. These results demonstrate the value of developing both the neural network and feedback control policies of autonomous driving systems simultaneously, as this can be a simple and methodical way to improve autonomous driving system performance and robustness. © 2024, CC BY.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Eggplant Disease Diagnosis Using a Robust Ensemble of Transfer Learning Architectures

Eggplant Disease Diagnosis Using a Robust Ensemble of Transf...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md Ismail Hossain Siddiqui Zishad Hossain Limon Shakil Khan Mahbub Alam Khan Hamdadur Rahman Shimanto Krishna Chakroborty Shamim Forhad Abdullah Al-Sakib S M Arafat Rahman Shafiur Rahman Dept. of Engineering/Industrial Management Westcliff University Irvine CA USA Dept. of Computer Science Westcliff University Irvine CA USA Dept. of Business Analytics International American University CA USA Dept. of Management Information System Pacific State University USA Dept. of Management of Information System International American University USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Electrical and Electronics Engineering American International University Bangladesh Dept. of Information Technology Westcliff University USA Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Eggplant diseases present major challenges to agricultural productivity, leading to yield losses and threatening farmers livelihoods. Traditional diagnostic methods tend to be resource-intensive, subjective, and often inaccurate, making them unsuitable for large-scale use. This study addresses these shortcomings by proposing an Ensemble Transfer Learning (ETL) approach for precise classification of eggplant diseases. The model combines the strengths of ConvNeXt, EfficientNetV2, NFNet, and RegNet architectures, enhancing generalization and minimizing overfitting. Two datasets containing over 19,800 images were utilized for training and validation, with advanced preprocessing and data augmentation techniques applied to ensure high input data quality and model robustness. To assess performance, evaluation metrics such as accuracy, F1-score, MCC, and PR-AUC were used. The model achieved an impressive classification accuracy of 99.76%, surpassing state-of-the-art methods and demonstrating strong generalization across various conditions. A web-based application was also developed, enabling real-time disease diagnostics through a user-friendly interface. This application provides farmers with actionable insights, promoting sustainable farming practices by reducing crop losses and minimizing the need for chemical interventions. However, its reliance on high-quality labeled images limits its applicability in uncontrolled environments. Future research will aim to integrate more diverse datasets and develop mobile-based solutions to enhance scalability and usability. This study emphasizes the potential of ensemble transfer learning to transform agricultural disease diagnosis and improve crop productivity.

关键词： Productivity Accuracy Transfer learning Crops computer architecture Real-time systems Medical diagnosis Chemicals Diseases Farming

来源：评论

学校读者我要写书评

暂无评论

Slang Word Detection in the Context of User Profiling in the Social Media Platformes

Slang Word Detection in the Context of User Profiling in the...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Bikram Samanta Ritika Shil Alok Ranjan Pal Antara Pal Dept. of Computer Science & Engg. College of Engg. & Management Kolaghat India Dept. of Computer Science Engg. Atharva College of Engineering Mumbai India

On social media platforms, people express their views in various ways, sometimes using formal words and sometimes in informal form. The informal conversations may contain jargon words i.e. slang words which might be improper for all kinds of audience. In this work, an attempt has been made to identify slang words in a text, posted on the social media platform. The overall experiment has been carried out in 4 modules. In module-1, the suspicious words from the posted text have been identified using minimum edit distance. This experiment has been implemented by the help of a dataset of printable slang words collected from Kaggle. In module-2, the topic of discussion has been analyzed by using a knowledge based approach. This part of the experiment has been carried out by creating a newspaper archive from the online repository of the "Times of India" newspaper. But, this knowledge based strategy could not produce an appreciable accuracy at its baseline. Therefore, as a modification of this technique, in module-3, the context analysis task has been implemented combining knowledge based approach and machine learning based approach. In module-4, the module-1 and module-3 are merged to tag a suspicious word with its level of abusiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Classification of Offensive Meme Content and Analysis

Two-Stage Classification of Offensive Meme Content and Analy...

引用

Conference on Information and Communication Technology (CICT)

作者： S V Sivaananth Sivagireeswaran S Sindhu Ravindran Fizza Ghulam Nabi Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Dept. of Industrial Engineering and Management University of Punjab Lahore Pakistan

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

Memes are generally understood as a blend of visual and textual elements and have become an effective medium of communication on social media. However, this ease of communication has also led to challenges in content moderation, particularly with the spread of hate speech, aggressive content, and cyberbullying. Traditional moderation tools often rely on models that focus solely on text or image data, which is inadequate for the multimodal nature of memes. This research proposes a multimodal meme classifier that leverages Stacked LSTM for textual analysis and VGG-16 for visual features, integrating both modalities to enhance classification accuracy. By integrating lexical and visual information, the model captures the full context of memes, enabling it to effectively distinguish between offensive and non-offensive content. The dual-pathway approach offers a significant improvement over single-pathway methods, demonstrating promising classification performance on a curated meme dataset. This solution shows great potential for real-time integration in content moderation systems, enabling efficient detection of offensive memes. Its multimodal framework is very promising on the growing demand for robust systems capable of moderating multimodal content in harmful online activities.

关键词： Visualization Accuracy Hate speech Cyberbullying Real-time systems Data models Information and communication technology Long short term memory Context modeling

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate LSTM Meta-modeling of TNF-induced Tumor Resistance In Vitro

Fast and Accurate LSTM Meta-modeling of TNF-induced Tumor Re...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Marco P. Abrate Riccardo Smeriglio Roberta Bardini Alessandro Savino Stefano Di Carlo Dept. of Cell and Developmental Biology University College London London UK Dept. of Control and Computer Engineering Politecnico di Torino Turin Italy

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Multi-level, hybrid models and simulations, among other methods, are essential to enable predictions and hypothesis generation in systems biology research. However, the computational complexity of these models poses a bottleneck, limiting the applicability of methodologies relying on large number of simulations, such as the Optimization via Simulation (OvS) of complex biological processes. Meta-models based on approximate surrogate models simplify multi-level simulations, maintaining accuracy while reducing computational costs. Among Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM) networks are well suited to handle sequential data, which often characterizes biological simulations. This paper presents an LSTM-based surrogate modeling approach for multi-level simulations of complex biological processes. Validation relies on the simulation of Tumor Necrosis Factor (TNF) administration to a 3T3 mouse fibroblasts tumor spheroid based on PhysiBoSS 2.0, a hybrid agent-based multi-level modeling framework. Results show that the proposed LSTM meta-model is accurate and fast compared with the simulator. In fact, it infers simulated behavior with an average relative error of 7.5%. Moreover, it is at least five orders of magnitude faster. Even considering the cost of training, this approach provides a faster, more accurate, and reusable surrogate of multi-scale simulations in computationally complex tasks, such as model-based OvS of biological processes.

关键词： Training Accuracy Biological system modeling Computational modeling Biological processes Metamodeling Predictive models Data models Long short term memory Tumors

来源：评论

学校读者我要写书评

暂无评论

Modi Script Recognition Using Convolutional Neural Networks and VGG16: A Deep Learning Approach for Historical Script Analysis

Modi Script Recognition Using Convolutional Neural Networks ...

引用

International Conference on Computing Communication control and Automation (ICCUBEA)

作者： Prathmesh Sainath Chidrawar Vidhya Dhamdhere Dept. of Computer Engineering G H Raisoni College of Engineering and Management Pune India

Recognizing historical scripts is a challenging task that requires specialized techniques due to the unique characteristics and variations present in these scripts. The Modi script, a historic script used to write the Marathi language in India, is presented in this research as a deep learning solution for the recognition of the script utilizing convolutional neural networks (CNNs) and the VGG16 architecture. The proposed approach consists of several steps. First, a diverse dataset of Modi script samples is collected, encompassing various characters, words, and sentences written in the script. The dataset is preprocessed to ensure consistency and enhance the model's robustness, including resizing, grayscale conversion, normalization, and data augmentation techniques. After that, the dataset is partitioned into three sets: training, validation, and testing. The VGG16 architecture is employed as the base model for feature extraction, leveraging its ability to learn low-level and high-level features from images. By obtaining handwritten examples from the IEEE Dataport collection, the dataset (training images) for the characters is updated. The model is trained using the training dataset, and hyperparameter tuning is performed using the validation set to optimize its performance. The testing dataset is used to measure the trained model's performance in identifying the Modi script by assessing metrics including accuracy, precision, recall, and F1 score. The performance of the model is assessed, and any updates or modifications that are required to increase the model's accuracy are implemented. The developed model can be deployed for prediction on unseen Modi script images, enabling the recognition of characters or words within the script. This approach provides a promising solution for historical script analysis and contributes to the preservation and understanding of the Modi script's cultural and linguistic heritage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Variable Step-Size Hybrid Adaptive Nonlinear Filter for Solar Radiation Prediction

A Variable Step-Size Hybrid Adaptive Nonlinear Filter for So...

引用

International Conference on Systems and Informatics (ICSAI)

作者： Y. Xiao L. Ma K. Khorasani Dept. of Management & Information Systems Prefectural University of Hiroshima Hiroshima Japan Dept. of Electrical & Computer Engineering Concordia University Montreal Canada

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

In this paper, a new hybrid adaptive nonlinear filter (HANF) scheme with variable step sizes (VSS) is proposed for solar radiation prediction. Our methodology consists of a Volterra filter and a functional link artificial neural network (FLANN) filter. The Volterra filter with the first- and second-order kernels is included, that is capable of expressing both linearity and nonlinearity. The FLANN filter can handle the nonlinearity that may be expressed by higher-order exponential terms that the Volterra filter with a limited number of kernels is unable to deal with. The VSSs are introduced in the two filters to allow the HANF to enjoy desirable tracking capability such that the time-varying nonlinearity underlying the nonlinear phenomena can be detected and tracked. The proposed VSS-HANF is applied to a real hourly solar radiation time sequence to confirm its improved prediction performance as compared to its counterpart with fixed step sizes.

关键词： Accuracy Finite impulse response filters Adaptive filters Weather forecasting Linearity Nonlinear filters Artificial neural networks Solar radiation Kernel Informatics

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap between Trust–Region Methods (TRMs) and Linesearch Based Methods (LBMs) for Nonlinear Programming: Quadratic Sub–Problems

SSRN

引用

SSRN 2022年

作者： Fasano, Giovanni Piermarini, Christian Roma, Massimo Dept. of Management Ca’ Foscari University of Venice Italy Dept. of Computer Control and Management Engineering Sapienza University of Rome Italy

We consider the solution of a recurrent sub–problem within both constrained and unconstrained Nonlinear Programming: namely the minimization of a quadratic function subject to linear constraints. This problem appears in a number of LBM frameworks, and to some extent it reveals a close analogy with the solution of trust–region sub–problems. In particular, we refer to a structured quadratic problem where five linear inequality constraints are included. We show that our proposal retains an appreciable versatility, despite its particular structure, so that a number of different real instances may be reformulated following the pattern in our proposal. Moreover, we detail how to compute an exact global solution of our quadratic sub–problem, exploiting first order KKT conditions. © 2022, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Indoor Real-Time Location System for Efficient Location Tracking Using IoT

Indoor Real-Time Location System for Efficient Location Trac...

引用

2022 IEEE World Conference on Applied Intelligence and Computing, AIC 2022

作者： Verma, Sunny Raj, Tej Joshi, Kapil Raturi, Preeti Anandaram, Harishchander Gupta, Ashulekha Dev Bhoomi Uttarakhand University Dept. of Electronics & Communication Engineering Dehradun India Uttaranchal University Dept. of Computer Science & Engineering Dehradun India Tula's Institute of Technology Dept. of Computer Science & Engineering Dehradun India Amrita Vishwa Vidyapeetham Centre for Excellence in Computational Engineering and Networking Tamil Nadu Coimbatore India Graphic Era University Dept. of Management Studies Dehradun India

ISBN: (数字)9781665479882

ISBN: (纸本)9781509050017

Researchers have broadened the focus of RFID technology development because to the growing need for low-cost edge devices to bridge the physical-digital gap. In addition to item identification, researchers have explored the use of RFID tags for low-power wireless sensing, localization, and activity inference. A security system utilized today is not powerful enough to provide a real-time alert after identifying a problem. Movement detection is a technology for detecting a change in the environment relative to an object. Sensor-based applications can be used to watch activity and receive alerts when movement is detected, which solves the issue and saves time and money. RFID technology is used to track the location of people or things in an interior setting in real time. A reader and several tags, each of which can house a number of sensors, make up an RFID system. In this research, we present the iLocate framework for the IoT, a recently developed real-time locating framework using dynamic RFID for resource the board in indoor settings. iLocate used ubidots to assist with a broad range RFID organization. Our exploratory findings and the actual project have both shown the prevalence. Location tracking indoors will be more effective using this iLocate framework. © 2022 IEEE.

关键词： Internet of things

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：