检索结果-内蒙古大学图书馆

10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023

作者： Recalcati, Pietro Garcea, Fabio Piano, Luca Lamberti, Fabrizio Morra, Lia Politecnico di Torino Department of Control and Computer Engineering Torino Italy

ISBN: (纸本)9798350345032

Deep neural networks are increasingly used in a wide range of technologies and services, but remain highly susceptible to out-of-distribution (OOD) samples, that is, drawn from a different distribution than the original training set. A common approach to address this issue is to endow deep neural networks with the ability to detect OOD samples. Several benchmarks have been proposed to design and validate OOD detection techniques. However, many of them are based on farOOD samples drawn from very different distributions, and thus lack the complexity needed to capture the nuances of real-world scenarios. In this work, we introduce a comprehensive benchmark for OOD detection, based on ImageNet and Places365, that assigns individual classes as in-distribution or out-of-distribution depending on the semantic similarity with the training set. Several techniques can be used to determine which classes should be considered in-distribution, yielding benchmarks with varying properties. Experimental results on different OOD detection techniques show how their measured efficacy depends on the selected benchmark and how confidence-based techniques may outperform classifier-based ones on near-OOD samples. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Giobergia at Multi-Task Transformer Tuning for Joint Conspiracy Theory Detection and Classification 8

Giobergia at Multi-Task Transformer Tuning for Joint Conspir...

引用

8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop, EVALITA 2023

作者： Giobergia, Flavio Department of Control and Computer Engineering Politecnico di Torino Turin Italy

Conspiracy theories, prevalent in contemporary society, often propagate misinformation and distrust, impacting public opinion and decision-making processes. In this paper, we present an automated approach to detect and classify conspiracy theories in Italian to address the Automatic Conspiracy Theory Identification (ACTI) task. Our methodology leverages a transformer-based architecture trained on a multi-task problem to tackle the challenging task of conspiracy theory identification. Through this multi-task learning framework, we aim to build a single model capable of addressing both the detection and the classification tasks simultaneously. We show that tackling both problems in a multi-task setting results in improved performance w.r.t. simple transformer-based solutions. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Update Strategy for KCF 11

An Adaptive Update Strategy for KCF

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Xu, Xiaochun Lin, Nixuan Chen, Dingrong Liu, Min Su, Nanling Minjiang University College of Computer and Control Engineering Fuzhou350108 China

ISBN: (纸本)9798350326277

Great advance has been achieved to improve the CF-based trackers, most of them ignore to improve update scheme. The update scheme plays an important role in tracking, which helps the tracker adapt the change of target. This paper presents an adaptive update strategy by introducing the peak to sidelobe ratio (PSR) for kernelized correlation filter (KCF) tracker. It helps the KCF based trackers adapt to appearance changes and achieves excellent tracking performance under complex changes. The extensive evaluations on OTB2015 benchmark show that our tracker significantly enhances the tracking performance. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research, Implementation and Analysis of Source Code Metrics in Rust-Code-Analysis 23

Research, Implementation and Analysis of Source Code Metrics...

引用

23rd IEEE International Conference on Software Quality, Reliability, and Security, QRS 2023

作者： Ardito, Luca Ballario, Marco Valsesia, Michele Politecnico di Torino Department of Control and Computer Engineering Torino Italy

ISBN: (纸本)9798350319583

The software industry is proliferating at an unprecedented pace, with a massive volume of software being released every day. Among the manifold challenges faced by software engineering researchers, one of the most significant is maintaining and enhancing software quality. Software metrics, designed to quantify various aspects of software, are essential in achieving this goal. They provide developers with a comprehensive snapshot of a codebase's status throughout its evolution, thereby facilitating timely intervention and continual improvement. Tools like Rust-Code-Analysis (RCA), developed and maintained by Mozilla, serve as crucial aids in this endeavour. RCA is a static code analyser that scrutinises a source code without executing it and computes a series of source code metrics, which quantitatively assess code characteristics such as complexity, maintainability, and robustness. The present article seeks to contribute to this area by undertaking a threefold task. Firstly, we intend to explore new source code Java metrics that can be integrated into RCA. We have chosen Java language due to its not yet declined pervasiveness in many industrial software and world of smartphones. The metrics will be selected based on their potential to provide valuable insights into codebase status and facilitate optimisation. Once the new metrics have been identified, the second part of our task involves implementing these metrics within RCA's library and also accessed through its CLI. This involves the coding and integration of the metrics using the modern Rust language, taking advantage of its unique features like memory safety without garbage collection, and data concurrency. Finally, to ascertain the effectiveness and reliability of metrics, we conduct an evaluation using diverse Java repositories. This involves studying the values generated by these metrics across repositories of varying sizes and levels of activity. From the smallest library to large-scale applications, our an

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

GINN: Towards Gender InclusioNeural Network

GINN: Towards Gender InclusioNeural Network

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Berta, Matteo Vacchetti, Bartolomeo Cerquitelli, Tania Politecnico di Torino Department of Control and Computer Engineering Turin Italy

ISBN: (纸本)9798350324457

Today's data-driven systems and official statistics often oversimplify the concept of gender, reducing it to binary data, with far-reaching implications for policy development and equitable access to services. This simplification can lead to misclassification and discrimination against individuals who identify as *** are working to advance our research in this area to develop new, more equitable approaches that can avoid discrimination based on gender identity. Within this research framework, our primary focus is on mitigating the problem of underrepresentation and, in some cases, the complete absence of non-binary individuals in data *** this goal in mind, we present the GINN Gender InclusioNeural Network. This is our first attempt to develop an equitable neural network that accurately identifies gender in a multiclass context and includes individuals whose gender identity does not fall on the binary spectrum. To achieve this goal, we conducted a comprehensive comparative analysis of several fine-tuned neural network models. Our goal was to gain a deep understanding of the crucial distinguishing features in gender identify classification and to highlight the limitation of current methods using explainable AI *** initial results are promising and demonstrate the effectiveness of a fine-tuned EfficientNetB0 model in accurately categorizing images of individuals into their self-reported gender, but we are skeptical about the application in a real-world scenario because of the amount of data available about non-binary people at the moment. © 2023 IEEE.

关键词： Automatic Gender Recognition Gender Equality Neural Network Non-Binary

来源：评论

学校读者我要写书评

暂无评论

Multimodal Intent Recognition Based on Contrastive Learning 16th

Multimodal Intent Recognition Based on Contrastive Learning

引用

16th International Conference on Service Science, ICSS 2023

作者： Wu, Yuxuan Liu, Zhizhong Su, Zhaohui Song, Xiaoyu School of Computer and Control Engineering Yantai University Yantai264005 China

ISBN: (纸本)9789819944019

Multimodal intent recognition plays a critical role in service science as it enables the achievement of more intelligent and personalized services. Recently, multimodal intent recognition has become a hot topic, and some research has been carried out on this topic. However, most existing research methods focus on exploring intra-modal or inter-modal interactions, which ignore the relationship between multimodal samples. To address this issue, we propose an approach for Multimodal Intent Recognition Based on Contrastive Learning (MIRCL). Firstly, the original samples and augmented samples are separately fed into crossmodal Transformer modules for multimodal feature fusion. The resulting fused multimodal features are then used for contrastive learning. Meanwhile, the fused multimodal features of the original samples are passed into a multimodal information bottleneck (MIB) module for intent recognition. Finally, the contrastive learning task and intent recognition task are jointly trained to optimize the whole model. We carried out comprehensive validation tests based on the publically available dataset MIntRec to prove the superiority of our proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

A Review of Evaluation Metrics Algorithmic Used in Scholarly Research Recommender System 4

A Review of Evaluation Metrics Algorithmic Used in Scholarly...

引用

4th International Multidisciplinary Information Technology and engineering Conference, IMITEC 2024

作者： Ovono, Gerald Zuva, Travos Otunniyi, Temidayo Faculty of Applied and Computer Sciences Department of Computer South Africa VaalUniversity of Technology Faculty of Engineering and Technology Department of Process Control and Computer Systems South Africa

ISBN: (纸本)9798350387988

The exponential growth of academic publications has made scholarly research recommender systems indispensable tools for researchers. These systems rely on diverse evaluation metrics to assess their effectiveness and relevance. This paper provides a comprehensive review and analysis of these metrics, categorizing them into accuracy, ranking, diversity, user-centric, coverage, temporal, and computational metrics. By employing a mixed-methods approach, combining systematic literature review and empirical analysis, we identify the prevalence and application of these metrics across various scholarly domains such as literature, conferences, and reviewers. Our findings highlight the widespread use of traditional metrics like precision, recall, and Fl-score, while emphasizing the growing importance of novel metrics such as unexpectedness and serendipity, especially in literature and conference recommendations. We also underscore the domain-specific nature of metric selection, with user-centric evaluations more prominent in literature recommendations, and ranking-focused metrics dominant in conference and reviewer recommendations. Furthermore, the study reveals a significant gap in the use of temporal and computational metrics, suggesting key areas for future research. This review offers valuable insights for researchers and practitioners, guiding them in metric selection and highlighting potential directions for enhancing the effectiveness, adaptability, and user satisfaction of scholarly recommender systems. © 2024 IEEE.

关键词： Algorithms Evaluation Metrics Novelty Recommender Systems Scholarly Research Serendipity

来源：评论

学校读者我要写书评

暂无评论

Research on Magnetic Circuit and Electromagnetic Performance of Combined-Pole Less-Rare-Earth Permanent-Magnet Synchronous Machine Used for Fully Electric Unmanned Aerial Vehicle

Research on Magnetic Circuit and Electromagnetic Performance...

引用

2023 IEEE Transportation Electrification Conference and Expo, Asia-Pacific, ITEC Asia-Pacific 2023

作者： Wang, Weinan Fu, Lingfang Wang, Shuo Zhu, Liangkuan Liu, Yiqi Wei, Jian Northeast Forestry University College of Computer and Control Engineering Harbin China

ISBN: (纸本)9798350314274

The combined-pole less-rare-earth permanent-magnet synchronous machine (CP-LRE-PMSM) has a series of advantages, such as better sinusoidal air-gap field, reduced reliance on rare-earth permanent-magnet materials. and lower cost. This paper firstly founds CP-LRE-PMSM's equivalent magnetic circuit model, then the calculation formulas of air-gap field are deduced, meanwhile the model accuracy is examined by finite element analysis (FEA). After that, based on machine performance requirements used for fully electric unmanned aerial vehicle (FE-UAV), the electromagnetic performance of CP-LRE-PMSM is analyzed. The total harmonics distortion (THD) and fundamental component of air-gap field versus permanent magnet width, permanent magnet thickness and flux-barrier position angle are studied, respectively. The torque characteristics and the machine efficiency map are investigated, which provides the reference for theoretical analysis and design of the CP-LRE-PMSM © 2023 IEEE.

关键词： Rare earths

来源：评论

学校读者我要写书评

暂无评论

A stacking-based model for the spread of Botryosphaeria laricina

引用

Journal of Forestry Research 2025年第1期36卷 427-443页

作者： Hongwei Zhou Shibo Zhang Meng Xie Xiaodong Li Yifan Chen Wenhao Dai College of Computer and Control Engineering Northeast Forestry UniversityHarbin 150040People’s Republic of China Key Laboratory of National Forestry and Grassland Administration On Forest and Grassland Pest Monitoring and Warning Center for Biological Disaster Prevention and ControlNational Forestry and Grassland AdministrationShenyang 110034People’s Republic of China

Botryosphaeria laricina(larch shoot blight)was first identified in 1973 in Jilin Province,*** disease spread rapidly and caused considerable damage because its pathogenesis was unknown at the time and there were no effective controls or quarantine *** present,it shows a spreading trend,but most research can only conduct physiological analyses within a relatively short period,combining individual influencing ***,methods such as neural network models,ensemble learning algorithms,and Markov models are used in pest and disease prediction and ***,there may be fitting issues or inherent limitations associated with these *** study obtained *** data at the county level from 2003 to *** dataset was augmented using the SMOTE algorithm,and then algorithms such as XGBoost were used to select the significant features from a combined set of 12 features.A new stacking fusion model has been proposed to predict the status of *** model is based on random forest,gradient boosted decision tree,CatBoost and logistic regression *** accuracy,recall,specificity,precision,F_(1) value and AUC of the model reached 90.9%,91.6%,90.4%,88.8%,90.2%and 96.2%.The results provide evidence of the strong performance and stability of the *** is mainly found in the northeast and this study indicates that it is spreading *** means should be used promptly to prevent further damage and spread.

关键词： Botryosphaeria laricina Data augmentation Feature selection Stacking Status of spread

来源：评论

学校读者我要写书评

暂无评论

Quantum Kernel Estimation With Neutral Atoms For Supervised Classification: A Gate-Based Approach 4

Quantum Kernel Estimation With Neutral Atoms For Supervised ...

引用

4th IEEE International Conference on Quantum Computing and engineering, QCE 2023

作者： Russo, Marco Giusto, Edoardo Montrucchio, Bartolomeo Politecnico di Torino Department of Computer and Control Engineering Turin Italy

ISBN: (纸本)9798350343236

Quantum Kernel Estimation (QKE) is a technique based on leveraging a quantum computer to estimate a kernel function that is classically difficult to calculate, which is then used by a classical computer for training a Support Vector Machine (SVM). Given the high number of 2-local operators necessary for realizing a feature mapping hard to simulate classically, a high qubit connectivity is needed, which is not currently possible on superconducting devices. For this reason, neutral atom quantum computers can be used, since they allow to arrange the atoms with more freedom. Examples of neutral-atom-based QKE can be found in the literature, but they are focused on graph learning and use the analogue approach. In this paper, a general method based on the gate model is presented. After deriving 1-qubit and 2-qubit gates starting from laser pulses, a parameterized sequence for feature mapping on 3 qubits is realized. This sequence is then used to empirically compute the kernel matrix starting from a dataset, which is finally used to train the SVM. It is also shown that this process can be generalized up to N qubits taking advantage of the more flexible arrangement of atoms that this technology allows. The accuracy is shown to be high despite the small dataset and the low separation. This is the first paper that not only proposes an algorithm for explicitly deriving a universal set of gates but also presents a method of estimating quantum kernels on neutral atom devices for general problems using the gate model. © 2023 IEEE.

关键词： Support vector machines

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：