检索结果-内蒙古大学图书馆

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Nayaka, Premkumar Hegde, Anusha Bhowmik, Biswajit National Institute of Technology Karnataka Ishwarchandra Vidyasagar Ait Lab Brics Laboratory Department of Computer Science and Engineering Surathkal India National Institute of Technology Karnataka Brics Laboratory Department of Computer Science and Engineering Surathkal India

ISBN: (纸本)9798331528201

The Peer-to-peer (P2P) lending platform allows borrowers to connect directly with lenders outside traditional banking systems. Therefore, for the sustainability of these platforms, they must accurately assess the credit risk and profitability of the loans. Various credit scoring techniques, including Logistic Regression, neural networks, and ensemble methods, can be used to estimate the likelihood of borrower default. It is imperative to analyze the profit the lenders generated and enhance the credit scoring so that the investors face minimum loss. Once the profit analysis is done, then it is crucial to advise the investors about the portfolio of loans. This paper presents recent credit scoring, profit scoring, and portfolio optimization trends for P2P lending. We highlight the significant issues in incorporating machine learning models into credit scoring systems. The analysis emphasizes the need for a data-driven approach to perfecting lending practices, thus benefiting both borrowers and investors in the rapidly changing P2P landscape. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Multi-label Textual Data Augmentation Using BERT Based on Transformer Model 1

引用

13th International Conference on Information Systems and Advanced Technologies, ICISAT 2023

作者： Rouabhi, Roumaissa Hammami, Nacer Eddine Azizi, Nabiha Benzebouchi, Nacer Eddine Chaib, Rim LabGed Laboratory Badji Mokhtar University Annaba Algeria Computer Engineering Department College of Engineering and Computer Science Mustaqbal University Buraydah Saudi Arabia

ISBN: (数字)9783031605918

ISBN: (纸本)9783031605901

In recent years, the healthcare field has taken a turn towards the AI domain, with applications such as image segmentation and medical report classification leading researchers to delve deeper into this area. On the other hand, the natural language processing has taken another turn with the arrival of the transformer models, the deep learning pre-trained models on a large corpus of documents, permitting an optimal use of medical text documents. However, the lack of diversification in text data more specifically multilabel data can be a constraint to get performant results. In this study, we are utilizing BioBERT for multilabel text classification, with the aim of achieving more refined results by implementing a data augmentation approach using a BERT-based transformer model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust graph‐based localization for industrial Internet of things in the presence of flipping ambiguities

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1140-1149页

作者： Mian Imtiaz ul Haq Ruhul Amin Khalil Muhannad Almutiry Ahmad Sawalmeh Tanveer Ahmad Nasir Saeed Faculty of Electrical Engineering Swedish College of Engineering and TechnologyWah CanttPakistan Department of Electrical Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawarPakistan Department of Electrical Engineering Remote Sensing UnitNorthern Border UniversityArarSaudi Arabia Data Science and Artificial Intelligence Department‐College of Science and Information Technology Irbid National UniversityIrbadJordan Innovation Education and Research Center for On‐Device AI Software(Bk21) Department of Computer Science and EngineeringChungnam National UniversityDaejeonRepublic of Korea Department of Electrical and Communication Engineering United Arab Emirates University(UAEU)Al AinUnited Arab Emirates

Localisation of machines in harsh Industrial Internet of Things(IIoT)environment is necessary for various ***,a novel localisation algorithm is proposed for noisy range measurements in IIoT *** position of an unknown machine device in the network is estimated using the relative distances between blind machines(BMs)and anchor machines(AMs).Moreover,a more practical and challenging scenario with the erroneous position of AM is considered,which brings additional uncertainty to the final position ***,the AMs selection algorithm for the localisation of BMs in the IIoT network is *** those AMs will participate in the localisation process,which increases the accuracy of the final location ***,the closed‐form expression of the proposed greedy successive anchorization process is derived,which prevents possible local convergence,reduces computation,and achieves Cramér‐Rao lower bound accuracy for white Gaussian measurement *** results are compared with the state‐of‐the‐art and verified through numerous simulations.

关键词： Cramér‐Rao lower bound greedy successive anchorization industrial internet of things localization

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Performance of ResNet and DenseNet for Obstacle Avoidance and Path Following on a Mobile Robot Using Embedded GPUs

A Comparison of the Performance of ResNet and DenseNet for O...

引用

2024 IEEE International Conference on Agents, ICA 2024

作者： Ma, Shengjun Karkal, Pawan Sudhir Ma, Jing Alam, Fakhrul Auckland University of Technology Electrical and Electronic Engineering Department Auckland New Zealand Auckland University of Technology Computer Science and Software Engineering Department Auckland New Zealand

ISBN: (纸本)9798331539917

In this study, we evaluated the performance of deep learning-based navigation models on an novel platform that combines the Jetson Xavier NX with an RC four-wheel-drive car for autonomous driving. Focusing on data collection and model training using a single-camera setup, obstacle avoidance and path navigation were prioritised. The study compares the effectiveness of ResNet18, ResNet34, and DenseNet121 models by analysing training time, accuracy, obstacle avoidance efficiency, and path navigation capabilities. The results highlight the computational advantages of the Jetson Xavier NX over the Jetson Nano, demonstrating enhanced real-time processing and decision-making capabilities. This integration of the Jetson Xavier NX with an RC vehicle not only improves overall performance but also introduces a novel approach to autonomous vehicle development. The findings offer valuable insights into optimising deep learning models and hardware configurations for improved autonomous navigation. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Behavior Trees and State Machines in Robotics Applications

引用

IEEE Transactions on software engineering 2023年第9期49卷 4243-4267页

作者： Ghzouli, Razan Berger, Thorsten Johnsen, Einar Broch Wasowski, Andrzej Dragule, Swaib Chalmers University of Technology Department of Computer Science and Engineering Gothenburg40530 Sweden Ruhr University Bochum Faculty of Computer Science Bochum44801 Germany Chalmers University of Gothenburg Department of Computer Science and Engineering Gothenburg40530 Sweden University of Oslo Department of Informatics Oslo0316 Norway IT University of Copenhagen Software Development Group Copenhagen2300 Denmark

Autonomous robots combine skills to form increasingly complex behaviors, called missions. While skills are often programmed at a relatively low abstraction level, their coordination is architecturally separated and often expressed in higher-level languages or frameworks. State machines have been the go-to language to model behavior for decades, but recently, behavior trees have gained attention among roboticists. Originally designed to model autonomous actors in computer games, behavior trees offer an extensible tree-based representation of missions and are claimed to support modular design and code reuse. Although several implementations of behavior trees are in use, little is known about their usage and scope in the real world. How do concepts offered by behavior trees relate to traditional languages, such as state machines? How are concepts in behavior trees and state machines used in actual applications? This paper is a study of the key language concepts in behavior trees as realized in domain-specific languages (DSLs), internal and external DSLs offered as libraries, and their use in open-source robotic applications supported by the Robot Operating System (ROS). We analyze behavior-tree DSLs and compare them to the standard language for behavior models in robotics: state machines. We identify DSLs for both behavior-modeling languages, and we analyze five in-depth. We mine open-source repositories for robotic applications that use the analyzed DSLs and analyze their usage. We identify similarities between behavior trees and state machines in terms of language design and the concepts offered to accommodate the needs of the robotics domain. We observed that the usage of behavior-tree DSLs in open-source projects is increasing rapidly. We observed similar usage patterns at model structure and at code reuse in the behavior-tree and state-machine models within the mined open-source projects. We contribute all extracted models as a dataset, hoping to inspire the commu

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Channel-Feedback-Free Transmission for Downlink FD-RAN:A Radio Map Based Complex-Valued Precoding Network Approach

引用

China Communications 2024年第4期21卷 10-22页

作者： Zhao Jiwei Chen Jiacheng Sun Zeyu Shi Yuhang Zhou Haibo Xuemin(Sherman)Shen School of Electronic Science and Engineering Nanjing UniversityNanjing 210023China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310058China Department of Mathematics and Theories Peng Cheng LaboratoryShenzhen 518000China Department of Electrical and Computer Engineering University of WaterlooWaterlooOntarioN2L 3G1Canada

As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network ***,with the decoupling of uplink base stations and downlink base stations in FDRAN,the traditional transmission mechanism,which relies on real-time channel feedback,is not suitable as the receiver is not able to feedback accurate and timely channel state information to the *** paper proposes a novel transmission scheme without relying on physical layer channel ***,we design a radio map based complex-valued precoding network(RMCPNet)model,which outputs the base station precoding based on user *** comprises multiple subnets,with each subnet responsible for extracting unique modal features from diverse input ***,the multimodal embeddings derived from these distinct subnets are integrated within the information fusion layer,culminating in a unified *** also develop a specific RMCPNet training algorithm that employs the negative spectral efficiency as the loss *** evaluate the performance of the proposed scheme on the public DeepMIMO dataset and show that RMCPNet can achieve 16%and 76%performance improvements over the conventional real-valued neural network and statistical codebook approach,respectively.

关键词： beamforming complex neural networks deep learning FD-RAN

来源：评论

学校读者我要写书评

暂无评论

Experimental and numerical study of geothermal rainwater tanks for buildings passive cooling 18

Experimental and numerical study of geothermal rainwater tan...

引用

18th IBPSA Conference on Building Simulation, BS 2023

作者： Striegel, Lucas Bouvenot, Jean-Baptiste Walther, Edouard Nowamooz, Hossein HVAC and Energy Engineering Department Strasbourg France Civil Engineering Department Strasbourg France The Engineering science computer science and imaging Laboratory Icube Laboratory Illkirch France

This communication presents the study of a new hybrid system composed of a buried rainwater tank thermally activated through a water-to-water heat exchanger. This low-tech solution, scarcely studied in the literature (variable level of atmospheric water volume), performs the passive cooling of buildings and reduces domestic water network consumption (for non-potable uses). Experimental results retrieved from two at-scale prototypes are presented. Then, the discussion focusses on the numerical model built and its validation thanks to the experimental results. Sensitivity analysis used for model improvement will also be discussed. © 2023 *** rights reserved.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

An Evaluation System for Large Language Models based on Open-Ended Questions 11

An Evaluation System for Large Language Models based on Open...

引用

11th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2024

作者： Cao, Zhiyuan Ma, Zeyu Chen, Mingang Computer and Information Engineering College Shanghai Polytechnic University Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer software Technology Mathematical and Science College Shanghai Normal University Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer software Technology Shanghai China

ISBN: (纸本)9798350376982

We designed a large language model evaluation system based on open-ended questions. The system accomplished multidimensional evaluation of LLMs using open-ended questions, and it presented evaluation results with evaluation reports. Currently, the evaluation of large-scale language models often exists with two prominent limitations: (1) The evaluation methods are often single-minded, resulting in less credible results. (2) Most evaluations are based on datasets with closed-ended questions, treating generative large language models as discriminative models, which fails to adequately reflect the high output flexibility characteristic of these models. For these two limitations, we proposed an evaluation system for LLMs based on open-ended questions. Our experiments on the adapted open-source datasets demonstrated the effectiveness of this system. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

MedNetV3: A Deep Learning Model for MRI Brain Tumor Detection with MobileNetV3 and Advanced Data Augmentation 21

MedNetV3: A Deep Learning Model for MRI Brain Tumor Detectio...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Tariq, Hussain Ahmed Fengli, Zhang Salim Shakib, Muhamud Md Javed, Iram School of Information and Software Engineering University of Electronic Science and Technology of China China University of Agriculture Department of Computer Science Faisalabad Pakistan

ISBN: (纸本)9798331519254

In this paper, we present a novel deep learning model medical network (MedNetV3) developed for brain tumor detection. It incorporates advanced data augmentation techniques based on the MobileNetV3 architecture. MedNetV3 is developed for higher classification accuracy at the cost of slightly lower computational efficiency and is therefore suitable for clinical use. The proposed model overcomes the class imbalance problem and can make the model robust to the variations of MRI scans included in the extensive data augmentation methods, such as random rotations, flips. The proposed model trained and evaluated using a publicly available MRI dataset. It achieved a high Area Under the Curve (AUC) value of 0.99 for both the Precision-Recall and Receiver Operating Characteristic (ROC) curves. The results show that MedNetV3 is effective in correctly distinguishing brain tumors and therefore has the potential to be used in medical image classification. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automated Short Answer Grading with Prompt-Driven Augmentation and Prompt Adaptive Oversampling 27th

Enhancing Automated Short Answer Grading with Prompt-Driven...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Afeefa, P.P. Hazari, Raju Das, Pranesh Machine Learning Laboratory Department of Computer Science and Engineering National Institute of Technology Calicut Kozhikode India

ISBN: (纸本)9783031781186

Automated Short Answer Grading (ASAG) comes under automatic answer script evaluation where the answer length is limited from one phrase to one paragraph. The main task in ASAG is generating a good sentence embedding for both the student and the reference answers. The existing works on the embedding creation perform better when using different deep-learning techniques and language models. However, the deep-learning techniques’ performance mainly depends on the training set size and quality. Most of the publicly available datasets typically have a limited number of reference and student answer pairs. To automate the dataset expansion, text augmentation techniques can be used. Conventional methods like back-translation, synonym replacement, and random deletion may replace some important technical words with other non-relevant terms, resulting in a loss of contextual meaning. We propose a new augmentation strategy for the ASAG datasets using LLM (Large Language Model) prompting. The effect of the proposed strategy is analysed on sentence transformer fine-tuning. We experimented with four different sizes of augmented training sets to determine the impact of the size of augmented training data on fine-tuning the sentence transformer model. Results indicate that sentence transformer fine-tuned using a 50% prompt-driven augmented dataset generates better embeddings. After having good embeddings, the traditional classifiers can be used to classify the student answers to different scores. We introduce "Prompt Adaptive Oversampling (PAO)" to address the class imbalance issue during grade classification. The effectiveness of the proposed strategy is analysed on two different public datasets: SPRAG, and Mohler-ASAG. The proposed method performs better while training highly imbalanced datasets. The source code of this work is available here. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

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：