检索结果-内蒙古大学图书馆

4th Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, DravidianLangTech 2024

作者： Tabassum, Nafisa Khan, Mosabbir Hossain Ahsan, Shawly Hossain, Jawad Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering and Technology Bangladesh

ISBN: (纸本)9798891760783

Hate and offensive language in online platforms pose significant challenges, necessitating automatic detection methods. Particularly in the case of codemixed text, which is very common in social media, the complexity of this problem increases due to the cultural nuances of different languages. DravidianLangTechEACL2024 organized a shared task on detecting hate and offensive language for Telugu. To complete this task, this study investigates the effectiveness of transliteration-augmented datasets for Telugu code-mixed text. In this work, we compare the performance of various machine learning (ML), deep learning (DL), and transformer-based models on both original and augmented datasets. Experimental findings demonstrate the superiority of transformer models, particularly Telugu-BERT, achieving the highest f1-score of 0.77 on the augmented dataset, ranking the 1st position in the leader-board. The study highlights the potential of transliteration-augmented datasets in improving model performance and suggests further exploration of diverse transliteration options to address real-world scenarios. © 2024 Association for Computational Linguistics.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Lens-Oppositional Wild Geese Optimization Based Clustering Scheme for Wireless Sensor Networks Assists Real Time Disaster Management

引用

computer Systems science & engineering 2023年第7期46卷 835-851页

作者： R.Surendran Youseef Alotaibi Ahmad F.Subahi Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennaiIndia Department of Computer Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Computer Science University College of Al JamoumUmm Al-Qura UniversityMakkah21421Saudi Arabia

Recently,wireless sensor networks(WSNs)find their applicability in several real-time applications such as disaster management,military,surveillance,healthcare,*** utilization of WSNs in the disaster monitoring process has gained significant attention among research communities and ***-time monitoring of disaster areas using WSN is a challenging process due to the energy-limited sensor ***,the clustering process can be utilized to improve the energy utilization of the nodes and thereby improve the overall functioning of the *** this aspect,this study proposes a novel Lens-Oppositional Wild Goose Optimization based Energy Aware Clustering(LOWGO-EAC)scheme for WSN-assisted real-time disaster *** major intention of the LOWGO-EAC scheme is to perform effective data collection and transmission processes in disaster *** achieve this,the LOWGOEAC technique derives a novel LOWGO algorithm by the integration of the lens oppositional-based learning(LOBL)concept with the traditional WGO algorithm to improve the convergence *** addition,the LOWGO-EAC technique derives a fitness function involving three input parameters like residual energy(RE),distance to the base station(BS)(DBS),and node degree(ND).The proposed LOWGO-EAC technique can accomplish improved energy efficiency and lifetime of WSNs in real-time disaster management *** experimental validation of the LOWGO-EAC model is carried out and the comparative study reported the enhanced performance of the LOWGO-EAC model over the recent approaches.

关键词： Disaster management real-time applications wireless sensor networks clustering bioinspired algorithms

来源：评论

学校读者我要写书评

暂无评论

UAV Detection and Classification using Deep Learning Techniques with YOLOv8 4

UAV Detection and Classification using Deep Learning Techniq...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Priyanka, R. Pooja, M.R. Vidyavardhaka College of Engineering Department of Computer Science & Engineering Mysuru India

ISBN: (数字)9798331528348

ISBN: (纸本)9798350352931

Accurately detecting and tracking drones in real-time poses main challenges due to factors such as varying scales, perspectives, occlusions, and environmental conditions. The proposed implementation helps in the identification of UAV objects in images and video footage using Deep Learning [DL] techniques, specifically the YOLOv8 architecture, by gathering a diverse dataset of images and video clips from the Roboflow 100 object detection benchmark dataset. Then the process is followed by pre-processing the data using resizing, normalization, and augmentation, which will be next initialized to the YOLOv8 architecture with pre-trained weights to estimate the performance using accuracy, precision, recall, and f1-score. The system finally involves integrating the classification system with a user-friendly interface for visualization of detection and classification in real time, where it results in which type of the drone is detected. The system achieved accuracy above 0.9 for all the classes of drones with different lights background and backgrounds in both images and video. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network with Artificial Bee Colony Optimization For Plant Disease Detection and Classification 2

Deep Convolutional Neural Network with Artificial Bee Colony...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Anbazhagan, K. Eluri, Nageswara Rao Toomula, Srilatha Brindha, T.V. Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Andhra Pradesh Guntur India Rbvrr Women's' College Department of Computer Science and Engineering Hyderabad India Sri Venkateshwara College of Engineering and Tecyhnology Department of Computer Science and Engineering Tiruvallur India

ISBN: (纸本)9798350384277

Plant diseases pose severe risks to agricultural production and global food security. For prompt intervention and mitigation, early and precise disease detection is crucial. Due to the development of trustworthy computer vision and machine learning technologies, automated plant disease detection systems are currently considered a potential solution to this issue. In this study, we provide a unique Deep Convolutional Neural Networks (DCNN)-based method for diagnosing plant illnesses. Our DCNN model automatically extracts pertinent features from plant photos, making it possible to classify healthy and unhealthy plants accurately. The dataset used in this study comprises a sizable collection of images with labels that show different plant species affected by various diseases. To improve its generalization and robustness to changing environmental circumstances and imaging artifacts, the proposed model is trained utilizing a mix of data augmentation via Haralick Texture. The suggested method uses a deep CNN to extract high-level information from photos of plants, allowing it to recognize subtle patterns suggestive of various diseases. The CNN architecture has been extensively crafted and adjusted to achieve the best accuracy and efficiency. The CNN's hyperparameters are optimized using the ABCO (Artificial Bee Colony Optimization) approach to increase classification accuracy further. ABCO mimics honeybee foraging to explore the hyperparameter space and find the best parameters efficiently. This improves the DCNN-ABCO performance. The findings demonstrate high accuracy, precision, and recall across various illness classes, demonstrating the model's dependability for practical applications and its capacity to identify previously unidentified disease patterns. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SWFEM: Sparse Weighted Fine-Tuned Ensemble Model for Leaf Disease Detection 11th

SWFEM: Sparse Weighted Fine-Tuned Ensemble Model for Leaf D...

引用

11th International Symposium on Applied Computing for Software and Smart Systems, ACSS 2024

作者： Paul, Rakesh Ghosh, Susobhan Ghosh, Mridul Obaidullah, Sk Md Roy, Kaushik Department of Computer Science Debra Thana S. K. S Mahavidyalaya Debra India Department of Computer Science Dinabandhu Mahavidyalaya Bongaon India Department of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah India Department of Computer Science and Engineering Aliah University Kolkata India Department of Computer Science West Bengal State University Barasat India

ISBN: (纸本)9789819797615

Globally, the greatest concerns of farmers are plant diseases. A considerable loss of yield has an immediate impact on the economy. Machine learning models exhibited capabilities to detect plant diseases. To enhance the generalization, flexibility, and adaptability of machine learning models, an ensemble model was introduced to combine many models and produce an appropriate and optimal predictive solution. To achieve better accuracy in deep learning models, it is necessary to have a significant amount of training time and memory resources. This is frequently utilized in engineering fields. Nowadays, the computational burden of training multiple independent networks increases with the growing number of deep learning models. To address these computational challenges, we introduced pruning and tuning-based fast, cost-effective sparse ensemble networks. The popularity of sparse architecture has increased because of its low memory requirements and faster inference rates. To identify an appropriate subset of ensemble members to build a smaller ensemble model, pruning is used to refrain from retraining the model. To achieve this, we first trained a base network. After that, we clone the parent network and drastically reduce each child’s features to generate an ensemble of members with various topologies. We soon trained each successor network for a smaller number of epochs. An empirical investigation demonstrated how well our method works on the pruned ensemble model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Agriculture Deep learning Leaf disease Sparse fine-tuned ensemble

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Early Warning System for Landslide Prediction and Mitigation 7

Comparative Analysis of Early Warning System for Landslide P...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Krishna, Gayathri R. Nandini, D. Usha Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India St.Joseph's College of Engineering & Technology Department of Computer Science and Engineering Kerala India

ISBN: (纸本)9798350372816

An Early Warning System (EWS) is an integrated system that disseminates early warning information to lessen a natural catastrophe's impact, facilitating preparedness and reaction processes. To reduce the likelihood of landslides occurring, researchers can take several measures. These include proactive measures to reduce the probability of landslides, the placement of EWS where, in some situations, the risk to life exceeds acceptable limits, and structural engineering initiatives aimed at reducing the susceptibility of sensitive elements. The benefits and drawbacks of the current landslide EWS are the main objectives of this study. It first clarifies the early warning system framework's obvious standpoint. The overall analysis will help the researchers who want to focus on landslide early warning systems. © 2024 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Exploring Generation of Pronunciation Lexicon for Low-Resource Language Automatic Speech Recognition Based on Generic Phone Recognizer

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-8页

作者： Li, Jinpeng Chen, Xie Zhang, Weiqiang Department of Electronic Engineering Tsinghua University Beijing100084 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

The lexicon is an essential component in the hybrid automatic speech recognition (ASR) system. However, a high-quality lexicon requires significant efforts from the linguistic experts and is difficult to obtain, especially for low-resource languages. This paper addresses the problem of using a well-trained universal phone recognizer, obtained through the training of multilingual speech data and pronunciation lexicons, to generate pronunciation lexicons for low-resource languages driven by speech data. We propose a simple pipeline that utilizes this approach to generate pronunciation lexicons and apply them into ASR systems. The steps to generate the lexicon are simple and generic: apply the International Phonetic Alphabet (IPA) phone recognizer on the speech, then align it with the reference word sequence, followed by filtering to obtain a series of AUTO-subwords, using them to generate the AUTO-subword lexicon and the AUTO-IPA lexicon. We used the pronunciation lexicon generated for the hybrid system and for fine-tuning the pre-trained model. According to the experiment results, we are able to construct the lexicon without resourcing to linguistic experts. Furthermore, the generated lexicon is able to outperform grapheme-based lexicon and is comparable to expert lexicon. © Shanghai Jiao Tong University 2024.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Concurrent Learning-Based Neuroadaptive Robust Tracking Control of Wheeled Mobile Robot: An Event-Triggered Design

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1514-1525页

作者： Nath, Krishanu Bera, Manas Kumar Jagannathan, Sarangapani National Institute of Technology Department of Electronics and Instrumentation Engineering Silchar788010 India Missouri University of Science and Technology Department of Electrical and Computer Engineering RollaMO65409 United States

In this article, an event-based neuroadaptive robust tracking controller for a perturbed and networked differential drive mobile robot (DMR) is designed with concurrent learning. A radial basis function neural network (RBFNN), which approximates an unknown perturbation, is used to design an adaptive sliding mode controller. The RBFNN weights and sliding mode controller parameters are estimated online using an adaptive tuning law to ensure performance with reduced chattering. To improve the convergence of RBFNN weight estimation error, a concurrent learning-based adaptive law is derived, which uses measured online and recorded data. Furthermore, a suitable triggering condition is designed to achieve a reduced number of control computations while minimizing network resources without sacrificing the stability of the sampled data closed-loop control system. A finite sampling frequency is guaranteed for the designed triggering condition by establishing a positive lower bound on the inter-event execution time, which is equivalent to the Zeno-free behavior of the system. Finally, the proposed event-based neuroadaptive robust controller is implemented on a practical system (Q-bot 2e) to show the effectiveness of the proposed design. © 2020 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Battery Management System for Enhancing the Performance and Safety of Lithium-Ion Batteries 21

Battery Management System for Enhancing the Performance and ...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Binsalim, Haya Badaam, Salma Ahmed, Arbaz Abdulmajid, Mohammed Effat University Electrical and Computer Engineering Department Jeddah Saudi Arabia

ISBN: (纸本)9798350393569

Battery packs integrated into the grid offer a promising solution for energy storage, but their efficient operation requires precise monitoring and control, which is achieved through Battery Management Systems (BMS). This paper proposes a temperature-dependent second-order RC equivalent circuit model to reflect the battery's dynamic characteristics accurately. Then, a novel BMS design, incorporating Extended Kalman Filtering (EKF), a constant current-constant voltage (CCCV) charging, and a passive balancing algorithm to estimate the battery state of charge (SOC), balance voltage levels, and monitor thermal characteristics. The research also includes a comprehensive simulation study conducted in SIMULINK with the Simscape toolbox to assess the effectiveness of the analyzed BMS. The simulation results demonstrate the effictiveness of the proposed BMS design in monitoring the battery pack's state, maintains cell balancing, estimates SOC, and keeps the temperature and current levels within safe limits. This model can help guide a more efficient and accurate BMS design for future studies. © 2024 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

How does the digitalization of the SCOR model contribute to the efficiency of supply chain operations?

引用

Logistique et Management 2024年第4期32卷 194-214页

作者： Hrouga, Mustapha Said, Dhaou Department of Finance Operations and Marketing Brest Business School Brest France School of Electrical Engineering and Computer Science University of Ottawa Canada

Résumé: Les outils digitaux tels que la blockchain, l’Internet des objets (IoT) et le big data (BD) ont été largement utilisés pour digitaliser la logistique et la gestion de la chaîne d’approvisionnement (CA). En fait, la technologie blockchain peut offrir divers avantages tels que la confiance, la traçabilité et la transparence qui permettent d’améliorer les performances de la chaîne d’approvisionnement. En plus, l’IoT est considéré comme la technologie la plus encourageante pour suivre et partager des informations en temps réel entre tous les acteurs de la CA. Enfin, le BD est considéré comme un outil très puissant et efficace pour optimiser la CA et permet à plusieurs entreprises de contrôler et de traiter une énorme quantité de données. C’est pour ces raisons que dans cet article, nous proposons d’utiliser ces technologies numériques pour développer un modèle SCOR digital pour une CA efficace, intelligente et performante. Afin de mettre en lumière les performances de cette étude, un modèle SCOR est initialement présenté pour mettre en évidence les avantages et les impacts de ces trois technologies sur les principales activités de la CA, notamment plan, source, make, deliver et return. Ensuite, les trois technologies sont combinées où le cloud est utilisé comme PaaS (platform as service) afin de les connecter. Enfin, pour valider le modèle SCOR 4.0 proposé, nous avons présenté un exemple didactique avec une CA multi-échelons et demande déterministe. Les résultats ont montré que le modèle proposé a permis d’améliorer la visibilité de la CA et d’augmenter le niveau de satisfaction des clients. © 2024 KEDGE Business School.

关键词： Supply chain 4.0 Digitalisation Modèle SCOR Blockchain internet des objets Big data Supply chain 4.0 digitalization SCOR model blockchain Internet of Things big data

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：