检索结果-内蒙古大学图书馆

Cyclic Transfer Learning for Mandarin-English Code-Switching Speech Recognition

IEEE Signal Processing Letters 2023年 30卷 1387-1391页

作者： Nga, Cao Hong Vu, Duc-Quang Luong, Huong Hoang Huang, Chien-Lin Wang, Jia-Ching National Central University Department of Computer Science and Information Engineering Taoyuan320 Taiwan Thai Nguyen University of Education Department of Computer Science and Information System Thai Nguyen7905218 Viet Nam Fpt University Department of Information Technology Can Tho900000 Viet Nam National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan

Transfer learning is a common method to improve the performance of the model on a target task via pre-training the model on pretext tasks. Different from the methods using monolingual corpora for pre-training, in this study, we propose a Cyclic Transfer Learning method (CTL) that utilizes both code-switching (CS) and monolingual speech resources as the pretext tasks. Moreover, the model in our approach is always alternately learned among these tasks. This helps our model can improve its performance via maintaining CS features during transferring knowledge. The experiment results on the standard SEAME Mandarin-English CS corpus have shown that our proposed CTL approach achieves the best performance with Mixed Error Rate (MER) of 16.3% on testman, 24.1% on testsge. In comparison to the baseline model that was pre-trained with monolingual data, our CTL method achieves 11.4% and 8.7% relative MER reduction on the testman and testsge sets, respectively. Besides, the CTL approach also outperforms compared to other state-of-the-art methods. © 1994-2012 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Images2Poem in different contexts with Dual-CharRNN

引用

CAAI Transactions on Intelligence Technology 2022年第4期7卷 685-694页

作者： Jie Yan Yuxiang Xie Xidao Luan Department of System Engineering National University of DefenseChangshaHunanChina Department of Mathematics and Computer Science Changsha UniversityChangshaHunanChina

Image to caption has attracted extensive research attention ***,image to poetry,especially Chinese classical poetry,is much more *** works mainly focus on generating coherent poetry without taking the contexts of poetry into *** this paper,we propose an Images2Poem with the Dual-CharRNN model which exploits images to generate Chinese classical poems in different ***,we first extract a few keywords representing elements from the given image based on multi-label image ***,these keywords are expanded to related ones with the planning-based ***,we employ Dual-CharRNN to generate Chinese classical poetry in different contexts.A comprehensive evaluation of human judgements demonstrates that our model achieves promising performance and is effective in enhancing poetry's semantic consistency,readability,and *** present an Images2Poem with the Dual-CharRNN model exploiting images to generate Chinese classical poems in different contexts,which effectively improves the semantic consistency,readability and aesthetics of the generated poetry.

关键词： computer vision deep learning image captioning poetry generation

来源：评论

学校读者我要写书评

暂无评论

Handwritten Prescription Recognition Using VGG Based Architecture with Bi-LSTM

Handwritten Prescription Recognition Using VGG Based Archite...

引用

2024 International Research Conference on Smart Computing and systems engineering, SCSE 2024

作者： Kavinda, Isuru Fernando, Harinda Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798350375688

Illegible handwriting on medical prescriptions poses a significant challenge, often leading to the misinterpretation of drug names and dosages. This issue primarily stems from doctors' use of Latin abbreviations, driven by time constraints during patient consultations. The resultant discrepancies in prescription interpretation can potentially expose patients to incorrect medications and dosages, leading to adverse effects. In response to this concern, this study proposes a novel system integrating Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) models. Promising findings are reported in this study, achieving a loss of 0.4874 and an accuracy of 0.83 in the latest trial. The final model offers a potential solution to the persistent problem of illegible prescriptions, enhancing patient safety in the healthcare domain. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Impact of Stuttering Event Representation on Detection Performance 2

The Impact of Stuttering Event Representation on Detection P...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-Banna, Abedal-Kareem Fang, Hui Shubita, Ahmad F. Arafah, Mohammad Eqteeshat, Amani Abuaisheh, Saif B. University Of Petra Department Of Ai And Data Science Jordan Loughborough University Department Of Computer Science United Kingdom University Of Petra Department Of Software Engineering Jordan University Of Petra Department Of Computer Science Jordan Malaya University Department Of Information System Malaysia

ISBN: (纸本)9798350394962

Stuttering or stammering is a common neurogenic, psychogenic fluency disorder wherein people have uncontrolled blocks on the natural flow of speech. Automatic Stuttering Event Detection (SED) is a widely recognised challenge due to the heterogenic and overlapped nature of stuttering speech. Therefore, this comparative study investigates the impact of stuttering event representation on detection performance. The paper evaluates the performance of SED and shows the impact of employing ASR pre-trained feature extractions on each stuttering event. Moreover, the paper provides different groups of experiments that evaluate the impact of three acoustic features, the Zero Crossing Rate (ZCR), the Spectral Flux Onset Strength Envelope (SFO), and Fundamental Frequency (FF) features, on SED performance. The paper demonstrates that the fusion of spectral and ASR features improves SED performance across all stuttering events by 8%. The F1 score of the Block class increased by approximately 10%, from 15% to 25%, while the word repetition and interjection increased by 8%. In addition, our experiments proved that the fusion of temporal features increased the average F1 score of SED by 2% across all stuttering events. The F1 score of the prolongation and sound repetition classes increased by 6% and 3%, respectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Detection and Severity Analysis of Corona and Pneumonia Using CNN with Wolf Optimization Algorithm 9

Deep Learning-Based Detection and Severity Analysis of Coron...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Kutti, M. Beula Karthick, T. Srmist Department of Computer Science And Engineering Chennai Kattankulathur India School of Computing Srmist Department of Datascience And Business System Chennai Kattankulathur India

ISBN: (纸本)9798350365092

Effective identification and severity analysis of two serious respiratory diseases-pneumonia and corona-are desperately needed, and this study attempts to fill that gap. Early diagnosis and treatment of many conditions depend critically on prompt intervention. Diagnoses are made slowly and subjectively by existing procedures, which frequently rely on human interpretation of medical imaging data. The existing methods for severity analysis do not have a cohesive structure. Our study presents an all-encompassing strategy to get around these restrictions. First, to improve the quality of the images, grayscale-based pre-processing is applied. Next, marker-based watershed segmentation is used to precisely locate anomalies. Feature extraction and categorization are done using a convolutional neural network, or CNN. Specifically, for severity analysis, we optimize the CNN parameters by including the Wolf Optimization Algorithm (WOA). Grayscale pre-processing guarantees the best possible picture quality;marker-based watershed segmentation improves the accuracy of lesion identification;CNN streamlines feature extraction;and WOA supports the study of disease severity. Python is used in the study's implementation, which takes advantage of its many machine learning frameworks and tools. The outcomes show how well the suggested methodology works for precisely identifying and evaluating the levels of corona and pneumonia. By integrating WOA with CNN, the shortcomings of current techniques are addressed and diagnostic accuracy and severity evaluation are improved. When compared to alternative approaches like CNN-SVM, Bayesian CNN, DCNN with BPNN, the suggested CNN with WOA (99.3%) shows an average accuracy gain of about 11.68%, demonstrating higher performance in disease diagnosis and severity analysis. This innovative method offers a methodical and effective framework for better patient treatment, which has the potential to advance the field of respiratory disease diagnostics. © 2

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Energy Aware Planning Approach Considering Cost of Electrical Energy for Sustainable Development 1

Energy Aware Planning Approach Considering Cost of Electrica...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Hossain, Md. Sabbir Shovon, Sazzadul Islam Islam Shayon, Md. Siamul Rumpa, Ummay Khadiza Hasan, Mahamudul Reza, Ahmed Wasif East West University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System MI United States

ISBN: (纸本)9798350377002

Given the rising cost of power and growing environmental concerns, optimizing energy utilization in manufacturing workshops has become increasingly significant. However, conventional approaches often neglect the potential for cost reduction within the power segment. This study proposes a linear programming model specifically designed for optimizing electrical costs. By strategically shifting production to off-peak hours, the model aims to minimize electricity costs while adhering to time constraints. A case study illustrates that this approach can achieve significant cost reductions and contribute to environmental sustainability by reducing greenhouse gas emissions during peak periods. Energy-aware planning is a crucial concept for achieving better utilization of resources and improving the quality of life in modern cities. This research represents a valuable step towards economical production and dependable environmental stewardship within the manufacturing industry. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Recommending Public Transit Route: Ant-Colony Optimization or Dijkstra?

Recommending Public Transit Route: Ant-Colony Optimization o...

引用

2023 International Conference on Modeling and E-Information Research, Artificial Learning and Digital Applications, ICMERALDA 2023

作者： Jabbar, Abdul Pinandito, Aryo Universitas Brawijaya Faculty of Computer Science Informatics Engineering Department Malang Indonesia Universitas Brawijaya Faculty of Computer Science Information System Department Malang Indonesia

ISBN: (纸本)9798350369359

Advances in algorithmic studies have been made recently, especially in the area of finding the shortest path. Despite taking a greedy approach, the Dijkstra algorithm is well recognized for its efficacy and has established itself as the industry standard for identifying the shortest path in a graph. Conversely, scientists have embraced the Ant-Colony Optimization (ACO) approach, which draws inspiration from the behavior of ants. This study examines the two methods and determines if, given equivalent resources, ACO can generate Dijkstra-like recommendations. Research data is subjected to both algorithms, and the outcomes are presented visually. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. In data measurement, Dijkstra is processed first to determine the best path, and then the ACO method is applied to produce findings that are similar to Dijkstra. Memory consumption, computation time, initial memory allocation, and final memory allocation are evaluation parameters. ACO is more efficient than Dijkstra in terms of execution time and number of pathways traversed, according to the study's repeated evaluation methodology. This iterative assessment procedure is carried out to address the possibility of single measurements resulting from the JavaScript Garbage Collector. The study's findings imply that a larger memory may be necessary for ACO to deliver the desired outcomes. These results could also be impacted by each algorithm's distinct qualities. © 2023 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation system controlling Through computer Vision 2

Smart Home Automation System controlling Through Computer Vi...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Hossain, Md. Sabbir Rumpa, Ummay Khadiza Sharma, Shatabdi Rashid, Mamunur Rahman, Habibur Shovon, Sazzadul Islam East West University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System MI United States

ISBN: (纸本)9798331529529

We are dwelling in the golden age of science development. Smart domestic automation has now ended up in the middle of enchantment in the lookup field. The guide machine of switching every so often motives an excessive strength loss. Keeping that in mind, we tried to make a computerized domestic which will now not require any remote, Bluetooth, or any kind of controlling device. In this paper, we have introduced a benchmark contrast of current some hardware the usage of the equal algorithm. For that, we tried to use some sensors, haar cascade documents, and some OpenCV codes for our design. After doing some processes we have chosen a layout that is convenient. In our chosen layout we tend to use a camera, laptop, ARDUINO and made human detection feasible the use of laptop vision. Through the digital camera, rooms are being monitored always, and from that actual time, the image processing presence of human beings is being determined by using the machine automatically. Finally, the microcontroller triggers in accordance with the decision, when it no longer locates any human in the room, it turns the lights, followers, off and on the opposite, it turns the lights, followers, on. © 2024 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Review of National Cybersecurity Policies: A Case Study on Asian Countries 1

Review of National Cybersecurity Policies: A Case Study on A...

引用

1st IEEE Karachi Section Humanitarian Technology Conference, Khi-HTC 2024

作者： Noor, Hera Seelro, Dodo Khan Ali, Syed Abbas NED University of Engineering & Technology Department of Computer Information System Engineering Karachi Pakistan Thar Institute of Engineering Science & Technology NED University of Engineering & Technology Karachi Pakistan

ISBN: (纸本)9798350373042

Accelerating the economic advantages of ICT is one of the finest methods for any nation to boost its economy. Due to the unique topography, governing laws, and cultural traditions of each nation, these colossal challenges must be confronted in each country. This comparative analysis aims to examine these aspects in further detail. To achieve the objectives of this study, research was conducted by collecting and analysing data from publicly accessible sources. This research compares Pakistan and other Asian countries' cybersecurity legislation, regulations, CERTs (national computer emergency response teams), CIIPs (computer intrusion prevention programs), and cyber security training and awareness. Among forty-eight Asian countries, the study focus on comparative analysis of major neighboring (developed or developing) countries of Pakistan such as Japan, China, Turkey, Iraq, Saudi Arabia, UAE, Nepal, Iran, Malaysia, Jordan, India, and Bangladesh. Cyber security has not been a major concern in Pakistan for a very long time, perhaps due to the way the government operates and how slowly it adapts to new technology. Many Asian countries have only ever released one version of their national cyber security plan, whilst Pakistan has never released anything;some other Asian countries are also added in this group. © 2024 IEEE.

关键词： Cybersecurity

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：