检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Abeysinghe, Binu James, Jesin Watson, Catherine I. Marattukalam, Felix Dept. of Electrical Computer and Software Engineering The University of Auckland New Zealand

With the recent developments in speech synthesis via machine learning, this study explores incorporating linguistics knowledge to visualise and evaluate synthetic speech model training. If changes to the first and second formant (in turn, the vowel space) can be seen and heard in synthetic speech, this knowledge can inform speech synthesis technology developers. A speech synthesis model trained on a large General American English database was fine-tuned into a New Zealand English voice to identify if the changes in the vowel space of synthetic speech could be seen and heard. The vowel spaces at different intervals during the fine-tuning were analysed to determine if the model learned the New Zealand English vowel space. Our findings based on vowel space analysis show that we can visualise how a speech synthesis model learns the vowel space of the database it is trained on. Perception tests confirmed that humans could perceive when a speech synthesis model has learned characteristics of the speech database it is training on. Using the vowel space as an intermediary evaluation helps understand what sounds are to be added to the training database and build speech synthesis models based on linguistics knowledge. © 2022, CC BY.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

CDP: Selective Influential Nodes Based on Cliques in the Diffusion Process in Social Networks

CDP: Selective Influential Nodes Based on Cliques in the Dif...

引用

International Conference on Web Research (ICWR)

作者： Fatemeh Yazdanifar Hamid Ahmadi Beni Nikoo Salimi Asgarali Bouyer Dept. of Mathematics and Computer Science Amirkabir University of Technology Tehran Iran Dept. Software Engineering Azarbijan Shahid Madani University Tabriz Iran Dept. of the Electrical Electronics Electronics and Telecommunication Engineering and Naval Architecture University of Genoa Genoa Italy Dept. of Computer Engineering Azarbaijan Shahid Madani University Tabriz Iran

Influence maximization techniques emphasize selecting a set of influential nodes in order to maximize influence. Because the algorithms presented in this field ignore the topology of cliques for diffusion, there are two major challenges in influence maximization algorithms: optimal diffusion and computational overhead reduction. As a result, the CDP algorithm is presented in this article to address these issues. This algorithm first selects suitable cliques for diffusion based on their position and strategy in social networks. Furthermore, for each clique, a score is calculated based on the topological criteria of the clique, and suitable cliques are selected for diffusion by applying a threshold limit. The seed nodes are chosen from the cliques in the second step. To avoid the rich club phenomenon, only a few nodes from each clique are chosen as seed candidate nodes. Finally, the seed nodes are chosen based on the node’s topology and the strength of the node’s level one neighbor. In the experiment section, the CDP algorithm significantly outperforms the best algorithms presented in recent years in terms of influence spread rate and execution time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Based Monitoring System for Social engineering 3

AI Based Monitoring System for Social Engineering

引用

3rd International Conference on Advancements in Computing, ICAC 2021

作者： Yapa, K. Udara, S.W.I. Wijayawardane, U.P.B. Kularatne, K.N.P. Navaratne, N.M.P.P. Dharmaphriya, W. G. V. U Sri Lanka Institute of Information Technology Dept. of Computer System Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665408622

Social media is one of the most predominantly used online platforms by individuals across the world. However, very few of these social media users are educated about the adverse effects of obliviously using social media. Therefore, this research project, is to develop an advisory system for the benefit of the general public who are victimized by the adverse impacts of their ignorant and oblivious behavior on social media. The system was implemented using a decision tree model with the use of customized datasets;and for the proceeding operational implementations, Python programming language, Pandas, Natural Language Processing and TensorFlow were used. This advisory system can monitor user behaviors and generate customized awareness reports for the users based on category and level of their behaviors on social media. Furthermore, the system is also capable of generating graph reports of the use behavior fluctuations for the reference of the user. With the help of these customized awareness reports and the graph reports, the users can identify their potential vulnerabilities and improve their social media habits. © 2021 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Model for Screening Tuberculosis Disease

Convolutional Neural Networks Model for Screening Tuberculos...

引用

2021 International Conference of Technology, Science and Administration, ICTSA 2021

作者： Alawi, Abdulfattah E. Ba Al-Basser, Amer Sallam, Amer Al-Sabaeei, Amr Al-Khateeb, Hesham Taiz University Software Engineering Dept. Taiz Yemen Taiz University Mechatronics and Robotics Engineering Dept. Taiz Yemen Taiz University Computer Networks and Distributed System Dept. Taiz Yemen

ISBN: (纸本)9781665428620

Tuberculosis disease has a big concern and it is spreading quickly across the world. The secret for managing the condition is an accurate diagnosis. Acid quick staining, conventional approaches such as tuberculin skin test (TST), yield findings are unreliable or require more time to detect. This paper presents an automated solution that uses chest radiographs to diagnose tuberculosis. Chest radiographic images are used for tuberculosis diagnosis. Tuberculosis in chest radiographs is difficult to investigate under the current system of cavity identification, ribs, and diaphragm removal. By using a CNN-based model, the lung area is separated to resolve the problems. The proposed technique can classify chest x-ray (CXR) images as Tuberculosis (TB) infected or not. We analyzed 3500 CXR cases and 3500 normal cases with exposure to tuberculosis. Then, we built and trained our own CNN and found that the features map or heat-map generated from this network performed a slightly better job. The implementation was done in Tensorflow and Keras library. An accuracy of 98.71%, a sensitivity of 98.86%, and a specificity of 98.57% were achieved. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Online Trained Model of Tweets Expertise

Online Trained Model of Tweets Expertise

引用

Information Technology and Nanotechnology (ITNT), International Conference on

作者： Elena Mozaidze Sergei Zuev Petr Kabalyants Dept. of computer software and automated systems Belgorod State Technological University named after V.G. Shukhov Belgorod Russia Dept. of computer engineering and modelling V.I. Vernadsky Crimean Federal University Simferopol Russia

ISBN: (数字)9798350372939

ISBN: (纸本)9798350372946

The paper proposes a model for the examination of tweets (brief texts and messages) in Russian. The model is based on the authors' explorations on the identification of tweets meanings. The main idea is to apply the latest developed quantum machine learning method to the hierarchical classification models of texts. This approach avoids the text corpus necessity and supports the online learning due to the very design. The model proposed is tested in the experiment. The target content was given in the experiment and the model is used to measure the correspondence between the target topics and the test messages. The result of the experiment shows that the proposed method allows to distinguish the target content in the test text.

关键词： Natural languages Machine learning Information technology Nanotechnology

来源：评论

学校读者我要写书评

暂无评论

Fingerprint generation and authentication though Adaptive convolution generative adversarial network (ADCGAN)

Fingerprint generation and authentication though Adaptive co...

引用

International Multi-Topic ICT Conference (IMTIC)

作者： Syed Muhammad Nabeel Mustafa Syeda Sundus Zehra Alina Baber Maria Andleeb Siddiqui Dept. of Computer Science & Information Technology NED University of Engineering and Technology Karachi Pakistan Dept of Software Engineering Sir Syed University of Engineering and Technology karachi Pakistan

Fingerprints are crucial in identification of humans. The uniqueness of finger prints makes it an interesting subject. Fingerprints are termed as a technique used to define, assess, and quantify a person's physical and behavioral property. Deep learning has made its application in all the major fields such as natural language processing, computer vision and speech processing. Deep learning has also found its application in the important subject of fingerprint synthesis and biometric. The ever-growing complexity of fingerprint authentication issues, from cellphone authentication to airport security systems, seems to be best handled by these models. In recent years, deep learning-based models have been used more and more to raise the accuracy of various fingerprint recognition systems. The persuasive capacity of Generative Adversarial Networks (GANs) to generate believable instances can be credibly taken from an existing distribution of samples. GAN exhibits exceptional performance on data generation-based tasks and also encourages study in privacy and security. In this work, using Adaptive Deep Convolution Generative Adversarial Networks (ADCGAN), we develop a model that generates and authenticate the fingerprints. A Socofing dataset was trained on ADGAN model. The model gave 92% accuracy. The conduct of fingerprint research has been made possible due to ADGAN, without restrictions related to the confidential nature of biometric data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on measuring respiratory rate and volume using Thermal cameras

Research on measuring respiratory rate and volume using Ther...

引用

International Conference on Imaging, Signal Processing and Communication (ICISPC)

作者： Do-Kyeong Lee Nak-Jun Sung Min-Hyung Choi Seong-Jun Choi Jae-Sung Choi Min Hong dept. of Software Convergence Soonchunhyang University Asan Republic of Korea dept. of Computer Science University of Colorado Denver Denver USA dept. of Otolaryngology-Head and Neck Surgery College of Medicine Soonchunhyang University Cheonan Republic of Korea dept. of Internal Medicine Cheonan Hospital Soonchunhyang University Cheonan Republic of Korea dept. of Software Engineering Soonchunhyang University Asan Republic of Korea

ISBN: (数字)9798350367157

ISBN: (纸本)9798350367164

The purpose of this study is to measure human respiration non-contactly using a FLIR thermal camera. We measured respiration using the temperature change of gases in the air during exhalation. For 15 subjects, breathing was filmed from the side view of the face using a thermal camera, and filming was conducted for 1 minute when the subjects were able to breathe comfortably. As a result of experiments using the respiration measurement design method proposed in this study, the amount of color change due to gas movement in each pixel during exhalation was proportional to the amount of temperature change in the air. We were able to successfully measure breathing patterns, such as a certain amount of quantitative breathing volume and number of breaths, through color change.

关键词： Temperature measurement Gases Image color analysis Volume measurement Cameras Thermal conductivity Time measurement

来源：评论

学校读者我要写书评

暂无评论

Automated Weed Species Classification in Rice Cultivation Using Deep Learning

Automated Weed Species Classification in Rice Cultivation Us...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Hamdadur Rahman Mahbub Alam Khan Shakil Khan Zishad Hossain Limon Md Ismail Hossain Siddiqui Shimanto Krishna Chakroborty Shamim Forhad Abdullah Al-Sakib Sheikh Shemanto Afridi Shafiur Rahman Dept. of Management of Information System International American University CA USA Dept. of Management Information System Pacific State University CA USA Dept. of Business Analytics International American University CA USA Dept. of Computer Science Westcliff University Irvine CA USA Dept. of Engineering/Industrial Management Westcliff University Irvine CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Electrical and Electronics Engineering American International University Bangladesh Dept. of Information Technology Westcliff University CA USA Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Weeds in rice fields compete for essential resources such as water, nutrients, and light, leading to reduced crop yields, increased production costs, and environmental concerns. Traditional methods of weed detection are often labor-intensive, subjective, and inefficient, highlighting the need for automated approaches in precision agriculture. This study introduces an ensemble model designed for robust and accurate classification of rice weeds, addressing the shortcomings of conventional methods and enhancing detection scalability. The proposed ensemble model combines four deep learning architectures: EfficientNet-V2, SqueezeNet, InceptionResNet-v2, and DenseNet-201. By leveraging the complementary strengths of these models, we aim to improve performance. The study utilizes the Rice Field Weed Detection Dataset, which contains 3,632 high-resolution images that have been augmented to a total of 21,792 samples. Advanced preprocessing techniques such as resizing, normalization, and augmentation are applied to ensure effective feature extraction. Our model achieved a remarkable classification accuracy of 99.51%, significantly surpassing individual models and other state-of-the-art approaches. In addition, we developed a web-based application for real-time weed detection, providing a user-friendly platform for farmers and agricultural professionals to implement timely weed management strategies. This system supports sustainable farming by reducing the need for excessive herbicide use and promoting environmentally friendly practices. This research highlights the potential of ensemble deep learning for precise agricultural weed detection. Future work will focus on integrating diverse datasets and developing mobile applications to enhance accessibility and scalability.

关键词： Deep learning Accuracy Scalability Transfer learning Feature extraction Real-time systems Mobile applications Crop yield Water resources Farming

来源：评论

学校读者我要写书评

暂无评论

Robust Metabolic Syndrome Risk Index Based on Triangular Areal Similarity

Robust Metabolic Syndrome Risk Index Based on Triangular Are...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Shin, Hyunseok Shim, Simon Choo, Charles Hwang, Doosung Nah, Yunmook Oh, Sejong Dankook University Dept. of Computer Scinece Youngin Korea Republic of San Jose State University Dept. of Computer Engineering San Jose United States Dankook University Dept. of Software Scinece Youngin Korea Republic of Dankook University Dept. of Applied Computer Engineering Youngin Korea Republic of

ISBN: (纸本)9781665401265

Metabolic syndrome is a cluster of risk factors associated with certain cardiovascular diseases. It is a chronic disease and has become an important public health issue in many countries, as it is steadily increasing owing to urbanized diets and lifestyles. The current medical diagnostic methods focus on the diagnosis of metabolic syndrome itself;however, they are not suitable for measuring its progression. Several methods have been proposed for measuring the risk of metabolic syndrome aiming to solve this problem, including the 'Areal Similarity Degree' method. In this study, a robust risk index based on radar charts is proposed to overcome the weaknesses of the Areal Similarity Degree method. In the proposed method, the examination values are expressed as two types of triangles on 10 types of three-axis radar charts, and each area of the triangle is synthesized and used as a risk index. The performance of the proposed risk index is evaluated based on the data of 31,070 Korean adults obtained from the Korea Genome and Epidemiology Study health examinee (KoGES HEXA) dataset. The proposed risk index shows a high correlation with current medical diagnostic criteria, and a good diagnostic performance. It produces more stable and generalized risk index values than those from the basic Areal Similarity Degree method. In addition, its sample-independent characteristics are confirmed. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Distress Study Through Machine-Learning Techniques

Distress Study Through Machine-Learning Techniques

引用

2021 International Conference on Biomedical Innovations and Applications, BIA 2021

作者： Marinova, Ginka Kalcheva, Neli Technical University of Varna Dept. of Computer Science and Engineering Varna Bulgaria Technical University of Varna Dept. of Software and Internet Technologies Varna Bulgaria

ISBN: (纸本)9781665445818

Machine learning as a contemporary approach in research provides an opportunity to cover and process a large amount of data. This is a condition for the synthesis of reliable characteristic descriptors of distress. The process of model selection is a factor in achieving the necessary adequacy and improving the quality of results. Age is a risky reason to take into account the development of cancer. This paper analyzed classification models for predicting distress in patients with the oncological disease, segmented into three age groups. Experimental results of a study conducted on the age of the patient and assessment of distress, using three methods of machine-learning are presented. © 2022 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：