检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tao, Wei Zhou, Yucheng Wang, Yanlin Zhang, Hongyu Wang, Haofen Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Software Engineering Sun Yat-sen University Guangdong Zhuhai519082 China School of Big Data and Software Engineering Chongqing University Chongqing China College of Design and Innovation Tongji University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 220 Handan Road Shanghai200433 China

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. © 2024, CC BY.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

An advanced deep neural network for fundus image analysis and enhancing diabetic retinopathy detection

引用

Healthcare Analytics 2024年 5卷 100303-100303页

作者： Mehedi Shamrat, F M Javed Shakil, Rashiduzzaman Sharmin Hoque ovy, Nazmul Akter, Bonna Ahmed, Md Zunayed Ahmed, Kawsar Bui, Francis M. Moni, Mohammad Ali Department of Computer System and Technology University of Malaya Kuala Lumpur 50603 Malaysia Department of Computer Science and Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Software Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Computer Science and Engineering European University of Bangladesh Dhaka 1216 Bangladesh Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon S7N 5A9 SK Canada Group of Biophotomatiχ Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail 1902 Bangladesh Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia 4072 QLD Australia

Diabetic retinopathy (DR) involves retina damage due to diabetes, often leading to blindness. It is diagnosed via color fundus injections, but the manual analysis is cumbersome and error-prone. While computer vision techniques can predict DR stages, they are computationally intensive and struggle with complex data extraction. In this research, our prime objective was to automate the process of DR classification into its various stages using convolutional neural network (CNN) models. We employed the performance of fifteen pre-trained models with our novel proposed diabetic retinopathy network (DRNet13) model. We aimed to discern the most efficient model for accurate diabetic retinopathy (DR) staging based on fundus images from five DR classes. We preprocessed the image using a median filter for noise reduction and Gamma correction for image enhancement. We expanded our dataset from 3662 to 7500 images to create a more generalized training model through various augmentation techniques. We also evaluated multiple evaluation metrics, including accuracy, precision, F1-score, Sensitivity, Specificity, Area under the curve (AUC), Mean Squared Error (MSE), False Positive Rate (FPR), False Negative Rate (FNR), in addition to confusion matrices for an in-depth comparison of the performance of these models. Feature maps were employed to illuminate decision making areas in the DRNet13 model, which achieved a 97 % accuracy rate for DR detection, surpassing other CNN architectures in speed and efficiency. Despite a few misclassifications, the model's capability to identify critical features demonstrates its potential as an impactful diagnostic tool for timely and accurate identification of diabetic retinopathy. © 2024 The Authors

关键词： Classification Convolutional neural network Diabetic retinopathy network Diagnostic analytics Feature map

来源：评论

学校读者我要写书评

暂无评论

Evaluating BERT-based Pre-training Language Models for Detecting Misinformation

arXiv

引用

arXiv 2022年

作者： Anggrainingsih, Rini Hassan, Ghulam Mubashar Datta, Amitava Informatics Dept Faculty of Mathematics and Natural Sciences Sebelas Maret University Indonesia Department of Computer Science and Software Engineering University of Western Australia Australia

The rapid growth of internet technology and social media platforms has led to rapid changes in communication by providing many conveniences to users. Despite the comforts provided, it is challenging to control the quality of information due to the lack of supervision over all the information posted on online media. For instance, there are many problems in society because of the numerous rumours and the quick spread of fake news through online media. Manual checking is almost impossible given the vast number of posts made on online media and how quickly they spread. Therefore, there is a need for automated rumour detection technique to limit the adverse effects of spreading misinformation. Previous studies mainly focused on finding and extracting the significant features of text data and used standard supervised learning techniques or deep learning approaches to identify misinformation. However, extracting features is timeconsuming and not a highly effective process due to the nonavailability of some features, affecting the effectiveness and performance of the detection models. Therefore, this study proposes the BERT-based pre-trained language models to encode text data into vectors and utilise neural network models to classify these vectors to detect misinformation. Furthermore, the performance of different language models (LM) containing different number of trainable parameters were compared, including RoBERTa, BERT, and DistillBERT. The proposed technique is tested on different twitter and fake news datasets to represent short and long text data respectively. The study also proposes a standardised distribution ratio for taining, validation and testing of the model. The result of the proposed technique has been compared with the state-of-the-art techniques on the same datasets. The results show that the proposed technique performs better than the state-of-the-art techniques. Moreover, the choice of LM either with significantly large or small number of parameters do

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Status Update on Phishing Emails Awareness: Jordanian Case 21

Status Update on Phishing Emails Awareness: Jordanian Case

引用

7th International Conference on engineering and MIS, ICEMIS 2021

作者： Qasaimeh, Malik Al-Manaseer, Hana Al-Manaseer, Haya Alghanim, Firas Software Engineering Department Computer Information Technology Jordan University of Science and Technology Irbid22110 Jordan King Hussein School of Computing Sciences Princess Sumaya University for Technology Amman11941 Jordan

ISBN: (纸本)9781450390446

This study is a response to the rapid proliferation of high-risk phishing emails, representing one of the most dangerous cybercrimes and the primary medium for the deception of online users. This study aims to investigate the various characteristics of phishing email messages, and to measure Jordanian internet users' awareness and knowledge about these threats. To achieve these objectives, a quantitative approach was used based on an online survey that included a total of 1531 participants. The results showed that only a few participants had the ability to distinguish illegitimate from legitimate emails, as the majority of participants could not recognize illegitimate emails by answering with "legitimate email"or "I don't know". Similarly, only a few participants could distinguish phishing emails, with the majority being unable to recognize phishing emails by answering with "real email"or "I don't know". Therefore, more work to increase public awareness of phishing emails is recommended at the individual and institutional levels, so as to protect users from any possible phishing email threats. This study focuses on the aspects that are related to email phishing that include techniques used to generate such phishing emails on the basis of which we will identity preventive measures to protect Jordanian users and increase their awareness of phishing emails. © 2021 ACM.

关键词： Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Voxel-wise Adversarial Semi-supervised Learning for Medical Image Segmentation

arXiv

引用

arXiv 2022年

作者： Lee, Chae Eun Park, Hyelim Shin, Yeong-Gil Chung, Minyoung The Samsung Electronics Korea Republic of The Department of Computer Science and Engineering Seoul National University Korea Republic of The School of Software Soongsil University Korea Republic of

Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable largescale annotations in the medical domain. Recent semi-supervised approaches have demonstrated promising results by employing consistency regularization, pseudo-labeling techniques, and adversarial learning. These methods primarily attempt to learn the distribution of labeled and unlabeled data by enforcing consistency in the predictions or embedding context. However, previous approaches have focused only on local discrepancy minimization or context relations across single classes. In this paper, we introduce a novel adversarial learning-based semisupervised segmentation method that effectively embeds both local and global features from multiple hidden layers and learns context relations between multiple classes. Our voxel-wise adversarial learning method utilizes a voxel-wise feature discriminator, which considers multilayer voxel-wise features (involving both local and global features) as an input by embedding classspecific voxel-wise feature distribution. Furthermore, we improve our previous representation learning method by overcoming information loss and learning stability problems, which enables rich representations of labeled data. Our method outperforms current best-performing state-of-the-art semi-supervised learning approaches on the image segmentation of the left atrium (single class) and multiorgan datasets (multiclass). Moreover, our visual interpretation of the feature space demonstrates that our proposed method enables a well-distributed and separated feature space from both labeled and unlabeled data, which improves the overall prediction results. Copyright © 2022, The Authors. All rights reserved.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Melanoma Lesion Segmentation Using Multiparallel Depthwise Separable and Dilated Convolutions with Swish Activations

引用

Journal of Healthcare engineering 2023年第1期2023卷 1847115页

作者： Bukhari, Maryam Yasmin, Sadaf Habib, Adnan Cheng, Xiaochun Ullah, Farhan Yoo, Jaeseok Lee, Daewon Department of Computer Science Comsats University Islamabad Attock Campus Attock Pakistan Department of Computer Engineering Uet Taxila Taxila Pakistan Department of Computer Science Swansea University Bay Campus Fabian Way Wales SwanseaSA1 8EN United Kingdom School of Software Northwestern Polytechnical University Xian710072 China Graduate School of Advanced Imaging Science Chung-Ang University Seoul Korea Republic of School of Art and Technology College of Art and Technology Chung-Ang University Seoul Korea Republic of

Skin cancer remains one of the deadliest kinds of cancer, with a survival rate of about 18-20%. Early diagnosis and segmentation of the most lethal kind of cancer, melanoma, is a challenging and critical task. To diagnose medicinal conditions of melanoma lesions, different researchers proposed automatic and traditional approaches to accurately segment the lesions. However, visual similarity among lesions and intraclass differences are very high, which leads to low-performance accuracy. Furthermore, traditional segmentation algorithms often require human inputs and cannot be utilized in automated systems. To address all of these issues, we provide an improved segmentation model based on depthwise separable convolutions that act on each spatial dimension of the image to segment the lesions. The fundamental idea behind these convolutions is to divide the feature learning steps into two simpler parts that are spatial learning of features and a step for channel combination. Besides this, we employ parallel multidilated filters to encode multiple parallel features and broaden the view of filters with dilations. Moreover, for performance evaluation, the proposed approach is evaluated on three different datasets including DermIS, DermQuest, and ISIC2016. The finding indicates that the suggested segmentation model has achieved the Dice score of 97% for DermIS and DermQuest and 94.7% for the ISBI2016 dataset, respectively. © 2023 Maryam Bukhari et al.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning for Automated Selection of Anomaly Detectors for Semi-Supervised Datasets

arXiv

引用

arXiv 2022年

作者： Schubert, David Gupta, Pritha Wever, Marcel Software Engineering and IT Security Fraunhofer IEM Paderborn Germany Department of Computer Science Paderborn University Paderborn Germany MCML LMU Munich Munich Germany

In anomaly detection, a prominent task is to induce a model to identify anomalies learned solely based on normal data. Generally, one is interested in finding an anomaly detector that correctly identifies anomalies, i.e., data points that do not belong to the normal class, without raising too many false alarms. Which anomaly detector is best suited depends on the dataset at hand and thus needs to be tailored. The quality of an anomaly detector may be assessed via confusion-based metrics such as the Matthews correlation coefficient (MCC). However, since during training only normal data is available in a semi-supervised setting, such metrics are not accessible. To facilitate automated machine learning for anomaly detectors, we propose to employ meta-learning to predict MCC scores based on metrics that can be computed with normal data only. First promising results can be obtained considering the hypervolume and the false positive rate as meta-features. © 2022, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Using HLPC for parallelization of autonomous tests of WEB applications from its GUI 34

Using HLPC for parallelization of autonomous tests of WEB ap...

引用

34th European Modeling and Simulation Symposium, EMSS 2022

作者： Rossainz-López, Mario Islas-Fuentes, Jesús A. Pineda-Torres, Ivo Capel-Tuñón, Manuel Faculty of Computer Science Autonomous University of Puebla Av. San Claudio and 14 Sur Street San Manuel PueblaC.P. 72570 Mexico Software Engineering Department College of Informatics and Telecommunications ETSIIT University of Granada Daniel Saucedo Aranda s/n Granada18071 Spain

A proposal for parallelization of autonomous tests of Web applications from its graphical user interface (GUI) is presented to reduce its execution time since these increases exponentially due to the number of combinations that are generated with the different states of the fields, of the forms on the web application pages by creating a tree-like structure. It is proposed to use the model of high-level parallel compositions or HLPC as a suitable model of semi-automatic parallelization that defines a Treelike structure as a communication pattern between processes. The proposed HLPC, which we call HLPC-Tree, uses reinforcement learning that associates each node of the process tree as a slave object using the Q-Learning (QL) algorithm and achieves autonomous recognition of the fields of the forms and valid-invalid options to identify failures and display them with HTTP status codes. In addition, the Mechanize library is used to find the number of possible combinations through the states of the fields of the forms and to know how many nodes are generated at each level of the process tree in the HLPC-Tree when it grows in depth. Finally, the performance analysis of the proposed HLPC is shown with an analysis of the speedup and execution times in an 8-core machine to demonstrate good scalability in its accelerations compared to Amdahl's Law. © 2022 The Authors.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Framework for Pruning Transformers Via a Finite Admixture of Keys

A Probabilistic Framework for Pruning Transformers Via a Fin...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tan M. Nguyen Tam Nguyen Long Bui Hai Do Duy Khuong Nguyen Dung D. Le Hung Tran-The Nhat Ho Stan J. Osher Richard G. Baraniuk Department of Mathematics University of California Los Angeles USA Department of Electrical and Computer Engineering Rice University Houston USA FPT Software AI Center Ha Noi Vietnam College of Engineering and Computer Science Vin University Vietnam Applied Artificial Intelligence Institute Deakin University Geelong Australia Department of Statistics and Data Sciences The University of Texas Austin USA

Pairwise dot product-based self-attention is key to the success of transformers which achieve state-of-the-art performance across a variety of applications in language and vision, but are costly to compute. It has been shown that most attention scores and keys in transformers are redundant and can be removed without loss of accuracy. In this paper, we develop a novel probabilistic framework for pruning attention scores and keys in transformers. We first formulate an admixture model of attention keys whose input data to be clustered are attention queries. We show that attention scores in self-attention correspond to the posterior distribution of this model when attention keys admit a uniform prior distribution. We then relax this uniform prior constraint and let the model learn these priors from data, resulting in a new Finite Admixture of Keys (FiAK). The learned priors are used for pruning away redundant attention scores and keys in the baseline transformers, improving the diversity of attention patterns that the models capture. We corroborate the efficiency of transformers pruned with FiAK on the ImageNet object classification and WikiText-103 language modeling tasks. Our experiments demonstrate that transformers pruned with FiAK yield similar or better accuracy than the baseline dense transformers while being much more efficient in terms of memory and computational cost.

关键词： Computational modeling Memory management Signal processing Transformers Probabilistic logic Data models Acoustics

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

arXiv

引用

arXiv 2022年

作者： Nie, Lunyiu Sun, Jiuding Wang, Yanlin Du, Lun Hou, Lei Li, Juanzi Han, Shi Zhang, Dongmei Zhai, Jidong Department of Computer Science and Technology Tsinghua University China School of Software Engineering Sun Yat-Sen University China Microsoft Research Asia China

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising performance, previous PLM-based approaches often suffer from hallucination problems due to their negligence of the structural information contained in the sentence, which essentially constitutes the key semantics of the logical forms. Furthermore, most works treat PLM as a black box in which the generation process of the target logical form is hidden beneath the decoder modules, which greatly hinders the model’s intrinsic interpretability. To address these two issues, we propose to incorporate the current PLMs with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks, namely Semantic Anchor Extraction and Semantic Anchor Alignment, for training the hierarchical decoders and probing the model intermediate representations in a self-adaptive manner alongside the fine-tuning process. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines. More importantly, by analyzing the intermediate representations of the hierarchical decoders, our approach also makes a huge step toward the intrinsic interpretability of PLMs in the domain of semantic parsing. © 2022, CC BY-SA.

关键词： Syntactics

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：