检索结果-内蒙古大学图书馆

An attention-augmented driven modified two-fold U-net anomaly detection model for video surveillance systems

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第11期83卷 32019-32040页

作者： Sharma, Preeti Gangadharappa, M. Guru Gobind Singh Indraprastha Univ Elect & Commun Delhi India Netaji Subhas Univ Technol Elect & Commun East Campus Delhi India

We propose an effective strategy for detecting and localizing anomalous behavior using a modified end-to-end two-stage encoder-decoder U-shaped network. By building the model from scratch for the detection, segmentation, and classification of an anomalous event in video sequences. The encoder model is helpful for feature extraction which is input to the bottleneck block. The resulting feature maps serve as input to the decoder path which is responsible for transposing feature maps to the original image. For precise localization of anomaly, we included the augmentation feature of both images and their masks in the proposed U-net model. In a two-stage U-net network, the first model is useful for the detection of video frames while the same U-net model is used in the second stage for augmentation of detected video frames from first model, which provides segmentation and classification of images. This precise symmetric path-based architecture is useful in good spatial localization of anomalous events. We apply a pixel-based threshold value for Intersection over Union score to distinguish the pixels. Pixels having values greater than the threshold are considered anomalous or otherwise normal with an IoU score of 0. We have evaluated our two-stage U-net model performance on three benchmark standard datasets and compared performance with the Conventional U-net model, and Attention-U-net models without augmentation features. Our method combines spatial details and deep features that yield an improved accuracy of 99.15%, a mean intersection over union score of 82.33 and 99% ROC values that are higher as compared to other methods.

关键词： Image augmentation Anomaly detection Video surveillance encoder-decoder model Localization

来源：评论

学校读者我要写书评

暂无评论

Research on Personalized AEB Strategies Based on Self-Supervised Contrastive Learning

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第2期25卷 1303-1316页

作者： Li, Haotian Jin, Hui Beijing Inst Technol Dept Mech Engn Beijing 100081 Peoples R China

In this paper, a driving style recognition method based on self-supervised contrastive learning was developed. Traditional machine learning models cannot directly accept time series data of variables as inputs, and therefore, artificially constructed statistical variables are required. The driving style recognition model proposed in this paper can directly input the raw time-series data, which can more fully preserve the driving information. On the basis of three driving styles recognition, a style factor model was designed to make the driving style continuous, and the forgetting factor was introduced to synthesize the style factor under the most recent data and the style factor under the historical data. The implementation of personalized AEB strategies involved three steps: First, using the emergency factor as an indicator, the aggressive braking strategy line was obtained statistically. Then, according to the data from calm drivers and moderate drivers, the corresponding encoder-decoder models were established to predict the longitudinal relative distance and longitudinal relative velocity. Finally, based on the aggressive braking strategy line and the encoder-decoder models, the calm braking strategy and the moderate braking strategy were designed. The proposed AEB strategies achieved a higher rate of collision avoidance than the classic Mazda, Honda, and Berkeley strategies. When the risk of collision is eliminated from test samples, on average, compared with the aggressive strategy, the calm strategy is 1.05 s earlier, while the moderate strategy is 0.58 s earlier. Such results are more in line with the expectations of different drivers, and the personalized AEB system can improve driver acceptance.

关键词： Vehicles Safety Data models Collision avoidance Brakes Analytical models Predictive models Driving style self-supervised contrastive learning model encoder-decoder model AEB strategy

来源：评论

学校读者我要写书评

暂无评论

Salient object detection via multi-scale attention CNN

引用

NEUROCOMPUTING 2018年 322卷 130-140页

作者： Ji, Yuzhu Zhang, Haijun Wu, Q. M. Jonathan Harbin Inst Technol Shenzhen Grad Sch Dept Comp Sci Shenzhen Peoples R China Univ Windsor Dept Elect & Comp Engn Windsor ON Canada

Fully convolutional network (FCN) based semantic segmentation models have largely inspired most recent works in the field of salient object detection. However, the lack of context information summarization can degrade the prediction accuracy of the final saliency map. Moreover, the information loss of downsampling operations of FCN-based models results in the loss of details of the final saliency map, such as edges of the saliency object. In this paper, we proposed a novel deep convolutional neural network (CNN) by introducing a spatial and channel-wise attention layer into a multi-scale encoder-decoder framework. The attention CNN layer can align the context information between the feature maps at different scales and the final prediction of the saliency map. In addition, a structure with multiple scale side-way outputs was designed to produce more accurate edge-preserving saliency maps by integrating saliency maps at different scales. Experimental results demonstrated the effectiveness of the proposed model on several benchmark datasets. Additional experimental results also validated the potential and feasibility of applying our trained saliency model to other object-driven vision tasks as an efficient preprocessing step. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Saliency detection encoder-decoder model Multi-scale attention CNN

来源：评论

学校读者我要写书评

暂无评论

An adaptive optimization method toward batch-wise variable set point of outlet moisture content for the tobacco drying process

引用

DRYING TECHNOLOGY 2023年第13期41卷 2156-2170页

作者： Gao, Yulei Wang, Tianyu Zhou, Xiaolong Li, Mian Zhang, Chiyuan Qin, Peng Yang, Yaojing Zhang, Libin Hongta Tobacco Grp Co Ltd Yuxi Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China

The tobacco drying process in the cigarette production has an important effect on the final product quality. Therefore, the intelligent control methods have been widely investigated to ensure the stability of tobacco's outlet moisture content. The existing work mostly uses a relatively fixed set point of the outlet moisture content for different tobacco batches, which can lead to unforeseen product quality after several processes following the drying process and inaccessible amount of dehydration for the rotary dryer. Some tobacco moisture prediction methods have been studied recently while the relationship with the intelligent control methods remain largely unexplored. To deal with these issues, a novel method is proposed in this paper to identify the optimal set point of the drying outlet moisture content for each tobacco batch. An encoder-decoder model is first developed to forecast the post-drying moisture trajectory. Then, an adaptive filter with specially designed mechanisms and a confidence interval of the dehydration level are constructed to obtain the design constraints. Based on all above, a constrained optimization problem is formulated and solved by the genetic algorithm. Extensive experiments on 895 tobacco batches from a large cigarette factory are carried out, which involves both algorithmic evaluation and field test. It turns out that the proposed method achieves the superior performance and leads to an improvement of the product quality in real production.

关键词： Tobacco drying process final product quality optimal set point encoder-decoder model adaptive filter genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Keyphrase Generation With CopyNet and Semantic Web

引用

IEEE ACCESS 2020年 8卷 44202-44210页

作者： Zhu, Xun Lyu, Chen Ji, Donghong Wuhan Univ Sch Cyber Sci & Engn Minist Educ Key Lab Aerosp Informat Secur & Trusted Comp Wuhan 430072 Peoples R China Jianghan Univ Sch Math & Comp Sci Wuhan 430056 Peoples R China Guangdong Univ Foreign Studies Collaborat Innovat Ctr Language Res & Serv Guangzhou 510420 Peoples R China

Keyphrases provide core information for users to understand the document. Most previous works utilize machine learning based methods for keyphrases extraction and achieve promising performance. However, these methods focus on identify keyphrases from the input text, and can not extract keyphrases that do not appear in the text. In this paper, we present an encoder-decoder framework, which incorporating copying mechanism, to generate keyphrases for the given text. This framework (CopyNet) integrates the generation part and copying part. The generation part generates the keyphrase from the predefined vocabulary, and the copy part gets the keyphrases from the source text. Furthermore, we improve the CopyNet by using different probability of the two parts. To incorporate more related information for keyphrase generation, the automatically built keyphrase semantic web is merged into the dataset to participate in the training process of the neural network. Semantic similarity based and word co-occurrence based methods are used for keyphrase semantic web construction. We build a large-scale biomedical keyphrase dataset to evaluate the system performance. Experiments show that our improved CopyNet can achieve better performance with different portions of the generation and copying part, and the incorporation of the semantic web also effectively improves the keyphrase generation.

关键词： Task analysis Semantic Web Decoding Semantics Vocabulary Transforms Neural networks Keyphrase generation encoder-decoder model copying mechanism semantic web

来源：评论

学校读者我要写书评

暂无评论

Neural Dialogue model with Retrieval Attention for Personalized Response Generation

引用

Computers, Materials & Continua 2020年第1期62卷 113-122页

作者： Cong Xu Zhenqi Sun Qi Jia Dezheng Zhang Yonghong Xie Alan Yang School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science University of Science and Technology BeijingBeijing100083China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Amphenol AssembleTech HoustonTX 77070US

With the success of new speech-based human-computer interfaces,there is a great need for effective and friendly dialogue agents that can communicate with people naturally and ***,the lack of personality and consistency is one of critical problems in neural dialogue *** this paper,we aim to generate consistent response with fixed profile and background information for building a realistic dialogue *** on the encoder-decoder model,we propose a retrieval mechanism to deliver natural and fluent response with proper information from a profile ***,in order to improve the efficiency of training the dataset related to profile information,we adopt a method of pre-training and adjustment for general dataset and profile *** model is trained by social dialogue data from *** to both automatic and human evaluation metrics,the proposed model significantly outperforms standard encoder-decoder model and other improved models on providing the correct profile and high-quality responses.

关键词： Dialogue system LSTM encoder-decoder model attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Boosting image caption generation with feature fusion module

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第33-34期79卷 24225-24239页

作者： Xia, Pengfei He, Jingsong Yin, Jin Univ Sci & Technol China Hefei Peoples R China

Image caption generation has been considered as a key issue on vision-to-language tasks. Using the classification model, such as AlexNet, VGG and ResNet as the encoder to extract image features is very common in previous work. However, there is an explicit gap in image feature requirements between caption task and classification task, and has not been widely concerned. In this paper, we propose a novel custom structure, named feature fusion module (FFM), to make the features extracted by the encoder more suitable for caption task. We evaluate the proposed module with two typical models, NIC (Neural Image Caption) and SA (Soft Attention), on two popular benchmarks, MS COCO and Flickr30k. It is consistently observed that FFM is able to boost the performance, and outperforms state-of-the-art methods over five metrics.

关键词： Image caption Feature fusion module encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Response type selection for chat-like spoken dialog systems based on LSTM and multi-task

引用

SPEECH COMMUNICATION 2021年 133卷 23-30页

作者： Ohta, Kengo Nishimura, Ryota Kitaoka, Norihide Anan Coll Natl Inst Technol Anan Japan Tokushima Univ Tokushima Japan Toyohashi Univ Technol Toyohashi Aichi Japan

We propose a method of automatically selecting appropriate responses in conversational spoken dialog systems by explicitly determining the correct response type that is needed first, based on a comparison of the user's input utterance with many other utterances. Response utterances are then generated based on this response type designation (back channel, changing the topic, expanding the topic, etc.). This allows the generation of more appropriate responses than conventional end-to-end approaches, which only use the user's input to directly generate response utterances. As a response type selector, we propose an LSTM-based encoder-decoder framework utilizing acoustic and linguistic features extracted from input utterances. In order to extract these features more accurately, we utilize not only input utterances but also response utterances in the training corpus. To do so, multi-task learning using multiple decoders is also investigated. To evaluate our proposed method, we conducted experiments using a corpus of dialogs between elderly people and an interviewer. Our proposed method outperformed conventional methods using either a point wise classifier based on Support Vector Machines, or a single-task learning LSTM. The best performance was achieved when our two response type selectors (one trained using acoustic features, and the other trained using linguistic features) were combined, and multi-task learning was also performed.

关键词： Spoken dialog system Response type selection encoder-decoder model Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Influence of Geodemographic Factors on Electricity Consumption and Forecasting models

引用

IEEE ACCESS 2022年 10卷 70456-70466页

作者： Singh, Jitender Pal Alam, Omar Yassine, Abdulsalam Trent Univ Peterborough ON K9L 0G2 Canada Trent Univ Dept Comp Sci Peterborough ON K9L 0G2 Canada Lakehead Univ Software Engn Dept Thunder Bay ON P7B 5E1 Canada

The residential sector is a major consumer of electricity, and its demand will rise by 65 percent by the end of 2050. The electricity consumption of a household is determined by various factors, e.g. house size, socio-economic status of the family, size of the family, etc. These factors play a critical role in analyzing the energy consumption causalities in the residential sector for better energy prediction models, effective price policy implementations, and improved customer engagement in energy efficiency programs. However, determining the effect of demographic factors on energy consumption is a challenging prospect. First, it is not trivial to study the causes of energy consumption variation, even for similar size residential houses, without analyzing the impact of interdependencies between demographic factors on energy consumption behavior. Second, to achieve higher accuracy of energy prediction models, it is necessary to identify key geodemographic factors that influence these models. Previous studies have only identified a limited number of socio-economic and dwelling factors. In this paper, we study the significance of 826 geodemographic factors on electricity consumption for 4917 homes in the City of London. Geodemographic factors cover a wide array of categories e.g. social, economic, dwelling, family structure, health, education, finance, occupation, and transport. Using Spearman correlation, we have identified 354 factors that are strongly correlated with electricity consumption. We also examine the impact of using geodemographic factors in designing forecasting models. In particular, we develop an encoder-decoder LSTM model which shows improved accuracy with geodemographic factors. We believe that our study will help energy companies design better energy management strategies.

关键词： Biological system modeling Predictive models Forecasting Energy consumption Urban areas Smart meters Companies Socio-economic factors geodemographic factors electricity forecasting encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Clustering-based Sequence to Sequence model for GenerativeQuestion Answering in a Low-resource Language

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2023年第2期22卷 1-14页

作者： Bidgoly, Amir Jalaly Amirkhani, Hossein Baradaran, Razieh Univ Qom Dept Informat Technol & Comp Engn PO *** Qom Iran

Despite the impressive success of sequence to sequence models for generative question answering, they need a vast amount of question-answer pairs during training, which is hard and expensive to obtain, especially for low-resource languages. In this article, we present a framework that exploits the semantic clusters among the question-answer pairs to compensate for the lack of enough training data. In the training phase, the questionanswer pairs are clustered, and a cluster predictor is trained to identify the cluster each question belongs to. Then, a sequence to sequence model is trained, where there is a different generator for each cluster in the decoder component. During the test phase, the cluster of the input question is first identified using the trained cluster predictor, and the appropriate decoder is exploited. Our experiments on a Persian religious dataset show that the proposed method outperforms the standard sequence to sequence model by a large margin in terms of ROUGE and BLEU scores. This is traced back to the lower number of words in each cluster, leading to a reduction in the number of effective parameters each generator needs to learn, which help the model learn from fewer training data with less overfitting.

关键词： Generative question answering low-resource language clustering deep learning encoder-decoder model

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：