检索结果-内蒙古大学图书馆

IEEE Transactions on Field Robotics 2025年 2卷 270-287页

作者： Olivier Gamache Jean-Michel Fortin Matěj Boxan François Pomerleau Philippe Giguère Department of Computer Science and Software Engineering Université Laval Québec QC Canada

Reproducibility is a cornerstone of scientific progress, as it enables fair comparisons between algorithms through the development of detailed solutions and datasets. However, standard datasets often present limitations, particularly due to the fixed nature of input data sensors, which makes it difficult to compare methods that actively adjust sensor parameters to suit environmental conditions. This is the case with automatic-exposure (AE) methods, which rely on environmental factors to influence the image acquisition process. As a result, AE methods have traditionally been benchmarked in an online manner, rendering experiments nonreproducible. Building on our previous work, we propose a methodology that utilizes an emulator capable of generating images at any exposure time. This approach leverages BorealHDR, a unique multiexposure stereo dataset, along with its new extension, in which data were acquired along a repeated trajectory at different times of the day to assess the impact of changing illumination. In total, BorealHDR covers 13.4km over 59 trajectories in challenging lighting conditions. The dataset also includes lidar-inertial odometry-based maps with pose estimation for each image frame, as well as global navigation satellite system (GNSS) data for comparison. We demonstrate that by using images acquired at various exposure times, we can emulate realistic images with a root-mean-square error (RMSE) below 1.78% compared to ground truth images. Using this offline approach, we benchmarked eight AE methods, concluding that the classical AE method remains the field’s best performer. To further support reproducibility, we provide in-depth details on the development of our backpack acquisition platform, including hardware, electrical components, and performance specifications. In addition, we share valuable lessons learned from deploying the backpack over more than 25 km across various environments. Our code and dataset are available online at this link: https:/

关键词： Cameras Trajectory Simultaneous localization and mapping Visualization Benchmark testing Reproducibility of results Lighting Heuristic algorithms Global navigation satellite system Emulation

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem 30

Benchmarking Hallucination in Large Language Models based on...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Sun, Yuhong Yin, Zhangyue Guo, Qipeng Wu, Jiawen Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai AI Laboratory China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (纸本)9782493814104

Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://***/Yuki-Asuuna/UMWP. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Using Letter Positional Probabilities to Assess Word Complexity

SSRN

引用

SSRN 2024年

作者： Dalvean, Michael Coleman Department of Computer Science and Software Engineering Australia

Word complexity is defined in a number of different ways. Psycholinguistic, morphological and lexical proxies are often used. Human ratings are also used. The problem here is that these proxies do not measure complexity directly, and human ratings are susceptible to subjective bias. In this study we contend that some form of 'latent complexity' can be approximated by using samples of simple and complex words. We use a sample of 'simple' words from primary school picture books and a sample of 'complex' words from high school and academic settings. In order to analyse the differences between these classes, we look at the letter positional probabilities (LPPs). We find strong statistical associations between several LPPs and complexity. For example, simple words are significantly (p © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Search for Extraterrestrial Intelligence as One-Shot Hypothesis Testing 57

Search for Extraterrestrial Intelligence as One-Shot Hypothe...

引用

57th Annual Conference on Information sciences and Systems, CISS 2023

作者： George, Ian Chen, Xinan Varshney, Lav R. Coordinated Science Laboratory Department of Electrical and Computer Engineering UrbanaIL United States

ISBN: (纸本)9781665451819

Both the search for extraterrestrial intelligence (SETI) and messaging extraterrestrial intelligence (METI) struggle with a strong indeterminacy in what data to look for and when to do so. This has led to attempts at finding both fundamental mathematical limits for SETI as well as benchmarks regarding specific signals. Due to the natural correspondence, previous information-theoretic work has been formulated in terms of communication between extraterrestrial and human civilizations. In this work, we instead formalize SETI as a detection problem, specifically (quantum) one-shot asymmetric hypothesis testing. This framework holds for all detection scenarios-in particular, it is relevant for detection of any technosignature, including quantum mechanical signals. To the best of our knowledge, this is the first work to consider the applicability of SETI for quantum signals. Using this formalism, we are able to unify the analysis of fundamental limits and benchmarking specific signals. To show a distinction between METI and SETI, we show that significantly weaker signals may be useful in detection in comparison to communication. Furthermore, the framework is computationally efficient, so it can be implemented by practicing astrobiologists. © 2023 IEEE.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Predictive Classification Model of Crop Yield Data Using Artificial Neural Network 5

Predictive Classification Model of Crop Yield Data Using Art...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Kanagaraj, R. Elakiya, E. Kumaresan, A. Selvakumar, J. Suganya, J. Shruthi, K. School of Computer Science and Engineering Vellore Institute of Technology Vellore India Vellore Institute of Technology Department of Computer Science and Engineering Chennai India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Mailam Engineering College Mailam India Bosch Global Software Technologies Coimbatore India

ISBN: (纸本)9798350321425

Agriculture is under tremendous pressure to produce more productivity with fewer resources as a result of the expanding global population. Decision-making along the entire supply chain needs to be improved considering competing economic, environmental, and societal demands. Data from satellites, drones, sensors, and other sources must be processed in order to make informed judgments. However, sophisticated machine learning and data analytics methods must be used due to the complexity and volume of the data. This initiative covers crucial duties in yield prediction and precision agriculture. Management zones are areas of a field that have high inter-regional variability and low intra-regional variability, dividing the field into uniform zones for which agronomic practices should be modified independently. For fertilizer optimization and post-harvest logistics, yield prediction is crucial. In order to make up for the nutrients that have been taken out of the soil, fertilizer type and quantity must be adjusted accordingly. The yield data is also essential for enhancing harvesting, shipping, storage, and sales. So, utilizing web scraping and convolution neural networks, the proposed model has been forecast yields from input satellite photos. The result of investigations is illustrated that the artificial neural network algorithm is used to predicting the agricultural data rules and powerfully decrease the error rate from crop yield data. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Masked Image Self-Learning and Knowledge Distillation for Source-Free Unsupervised Domain Adaptation in Crowd Counting 2

Masked Image Self-Learning and Knowledge Distillation for So...

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Zeng, Jia Ma, Chaoqun Shao, Penghui Qing, Anyong Wang, Yang Southwest Jiaotong University School of Electrical Engineering Chengdu China Concordia University Department of Computer Science and Software Engineering Montreal Canada

ISBN: (纸本)9798350331417

Unsupervised Domain Adaptation (UDA) techniques leverage labeled data from a source domain to adapt to unlabeled data from a target domain, offering a primary solution for addressing cross-domain challenges in crowd counting. However, in real-world scenarios, accessing source data during the model adaptation process within the target domain can be impractical due to privacy and security concerns. This gives rise to a practical yet challenging issue known as Source-Free Unsupervised Domain Adaptation (SFUDA), where model adaptation is limited to the utilization of an existing source model and unlabeled target data. To tackle this challenge, we propose an algorithm that combines mask image self-learning and knowledge distillation to address SFUDA in crowd counting effectively. Specifically, the student model uses masked images to self-learn at both feature and output levels, exploring clues and contextual relationships around masked image blocks to predict occluded areas. Furthermore, we employ knowledge distillation to boost the model's performance within the teacher-student framework, encompassing feature extraction and density map generation stages. To mitigate cumulative errors, we stochastically recovery a subset of parameters from the source model. We conducted extensive experiments to compare our approach with a modified SFUDA algorithm, and the results demonstrate competitive performance across multiple datasets. © 2023 IEEE.

关键词： Crowd counting Domain adaptation Knowledge distillation Self-learning Source-free

来源：评论

学校读者我要写书评

暂无评论

Decision making framework for heterogeneous QoS information: an application to cloud service selection

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2915-2934页

作者： Tiwari, Rohit Kumar Kumar, Rakesh Baranwal, Gaurav Buyya, Rajkumar Department of Computer Science and Engineering Madan Mohan Malaviya University of Technology Gorakhpur273010 India Department of Computer Science BHU Varanasi India Cloud Computing and Distributed Systems Laboratory School of Computing and Information Systems University of Melbourne Melbourne Australia

In recent times, appropriate decision-making in challenging and critical situations has been very well supported by multicriteria decision-making (MCDM) methods. The technique for order of preference by similarity to ideal solution (TOPSIS) is the most widely used MCDM method for solving decision problems. However, it restricts decision-makers to use only one type of Quality of Service (QoS) information, and it suffers from the rank reversal problem. Restriction to only one type of QoS makes the decision problems more challenging, as it restricts the decision-makers freedom. Further, the rank reversal problem makes the decision result unreliable. To address these issues of TOPSIS, we have proposed a reliable rank reversal robust modular TOPSIS (RMo-TOPSIS). RMo-TOPSIS allows crisp, interval, fuzzy, intuitionistic and neutrosophic fuzzy QoS metrics. It does not suffer from the rank reversal problem. Cloud computing provides computing services on-demand basis without involving maintenance by its users. The availability of many cloud service providers and their services makes cloud service selection a challenging problem. To validate RMo-TOPSIS, we select the cloud service selection consisting of different types of QoS metrics as an application. Experiments on cloud service selection show consistency and accuracy in results obtained by RMo-TOPSIS and its robustness against rank reversal. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Deciphering urban traffic impacts on air quality by deep learning and emission inventory

引用

Journal of Environmental sciences 2023年第2期124卷 745-757页

作者： Wenjie Du Lianliang Chen Haoran Wang Ziyang Shan Zhengyang Zhou Wenwei Li Yang Wang School of Software Engineering University of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China Alibaba Inc. Hangzhou 310052China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China CAS Key Laboratory of Urban Pollutant Conversion Department of environmental science and EngineeringUniversity of Science and Technology of ChinaHefei 230026China USTC-CityU Joint Advanced Research Center Suzhou 215123China

Air pollution is a major obstacle to future sustainability,and traffic pollution has become a large drag on the sustainable developments of future ***,combined with the large volume of real-time monitoring data,we propose a deep learning model,iDeepAir,to predict surface-level PM2.5 concentration in Shanghai megacity and link with MEIC emission inventory creatively to decipher urban traffic impacts on air *** model exhibits high-fidelity in reproducing pollutant concentrations and reduces the MAE from 25.355μg/m^(3) to 12.283μg/m^(3) compared with other *** identifies the ranking of major factors,local meteorological conditions have become a nonnegligible ***-wise relevance propagation(LRP)is used here to enhance the interpretability of the model and we visualize and analyze the reasons for the different correlation between traffic density and PM_(2.5) concentration in various regions of ***,As the strict and effective industrial emission reduction measurements implementing in China,the contribution of urban traffic to PM_(2.5) formation calculated by combining MEIC emission inventory and LRP is gradually increasing from 18.03%in 2011 to 24.37% in 2017 in Shanghai,and the impact of traffic emissions would be ever-prominent in 2030 according to our *** also infer that the promotion of vehicular electrification would achieve further alleviation of PM_(2.5) about 8.45% by 2030 *** insights are of great significance to provide the decision-making basis for accurate and high-efficient traffic management and urban pollution control,and eventually benefit people’s lives and high-quality sustainable developments of cities.

关键词： PM_(2.5)concentration forecast Traffic emissions Deep learning Attention mechanism New energy vehicles

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Machine Learning-Based Model for Conversational Sentiment Classification

引用

computers, Materials & Continua 2022年第8期72卷 2323-2339页

作者： Sami Ullah Muhammad Ramzan Talib Toqir A.Rana Muhammad Kashif Hanif Muhammad Awais Department of Computer Science Government College University Faisalabad38000Pakistan Department of Computer Science and IT The University of Lahore54590Pakistan School of Computer Sciences Universiti Sains Malaysia(USM)11800PenangMalaysia Department of Software Engineering Government College University Faisalabad38000Pakistan

In the current era of the internet,people use online media for conversation,discussion,chatting,and other similar *** of such material where more than one person is involved has a spate challenge as compared to other text analysis *** are several approaches to identify users’emotions fromthe conversational text for the English language,however regional or low resource languages have been *** Urdu language is one of them and despite being used by millions of users across the globe,with the best of our knowledge there exists no work on dialogue analysis in the Urdu ***,in this paper,we have proposed a model which utilizes deep learning and machine learning approaches for the classification of users’emotions from the *** accomplish this task,we have first created a dataset for the Urdu language with the help of existing English language datasets for dialogue *** that,we have preprocessed the data and selected dialogues with common *** the dataset is prepared,we have used different deep learning and machine learning techniques for the classification of *** have tuned the algorithms according to the Urdu language *** experimental evaluation has shown encouraging results with 67%accuracy for the Urdu dialogue datasets,more than 10,000 dialogues are classified into five emotions i.e.,joy,fear,anger,sadness,and *** believe that this is the first effort for emotion detection from the conversational text in the Urdu language domain.

关键词： Dialogue analysis conversational opinion mining sentiment analysis sentiment analysis in Urdu language deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Innovating Project Management: AI Applications for Success Prediction and Resource Optimization 2nd

Innovating Project Management: AI Applications for Success P...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Tarawneh, Monther AbdAlwahed, Huda AlZyoud, Faisal Computer Science Department Isra University Amman Jordan Software Engineering Department Isra University Amman Jordan Information Technology Department Tafilah Technical University Tafila Jordan

ISBN: (纸本)9783031569494

The revolution of Artificial Intelligence (AI) has made transformative changes in all industries. The field of software engineering has great benefit from AI by Automat all process. Applying Artificial intelligence (AI) technologies, particularly Deep Neural Network (DNN) models, to project management will transform traditional methodologies to new ways. This work investigates how AI can be used within project management to better allocate resources, estimate time, and predict costs. Data from many recourses used to improve accuracy in project planning, refine how risks are managed, and develop new methods. Data includes real projects portfolio, open-source data, and simulated data. The integration of AI in project management examines project success and client satisfaction. This work shows 99% accuracy for learning and 78% for testing of predicting project success and highlights the need to constantly update methods to effectively use the big potential changes AI can bring to project management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep neural networks

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：