检索结果-内蒙古大学图书馆

1st IEEE Mysore Sub Section International Conference, MysuruCon 2021

作者： Darshini, P. Mohana Kumar, S. Raghavendra, C.G. Krishna Prasad, S.J. Kavitha, H. Divakara, S.S. Ramaiah Institute of Technology Dept. of Computer Science Bangalore India Ramaiah Institute of Technology Bangalore Dept. of Computer Science Bangalore India Ramaiah Institute of Technology Dept. of Electronics and Communication Bangalore India Ramaiah Institute of Technology Dept. of Electronics and Telecommunication Bangalore India Siddaganga Institute of Technology Dept. Infomation and Science Tumkur India Coorg Institute of Technology Dept. of Electronics and Communication Ponnampet India

ISBN: (纸本)9780738146621

The devices of the organization such as laptops, desktops and mobiles are connected to the internet are vulnerable to cyber attacks, attacking on these components may lead to security breach, credential theft, malware implantation, DDoS attack, man in middle attacks, ransomware attacks and many more. Therefore, to defend against these attacks there requires proper security controls in place to detect the threats in the business environment. Security Threats generally propagates through various SQL Injection, Cross Site Scripting or unauthorized excessive login into any servers. These could lead company to huge loss of information and revenue. Suspicious emails are the most dangerous way to attack on any organization by employing techniques such as phishing, fraud, Spam and spoofing the email headers. These emails are sent through outside company environment. It poses extensive threats and it can be a major setback. This work explores confident ways to automate the process of cyber security threat and change in a rules-set. With the help of proposed cyber tool to remediate false positives response time against every attack, these helps the organizations to minimize the suspicious attack. © 2021 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Enhanced integral imaging 3D dept. map by using SRCNN 13

Enhanced integral imaging 3D depth map by using SRCNN

引用

13th International Conference on Information and Communication technology Convergence, ICTC 2022

作者： Uchino, Hideaki Lee, Jaehoon Kim, Hyun-Woo Honda, Kazuaki Cho, Myungjin Lee, Min-Chul Kyusyu Institute of Technology Dept. of Computer Science and Networks Fukuoka Iizuka Japan School of ICT Robotics and Mechanical Engineering Iitc Hankyong National University Anseong Kyonggi-do Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

In this paper, we propose a method that can generate a three-dimensional (3D) dept. map accurately by using an integral imaging technique through low-resolution elemental images. The conventional method may produce an accurate 3D dept. map when it utilizes high-resolution images. However, if the elemental image has low resolution, it can cause the shifting pixel error when it reconstructs the 3D image by using volumetric computational reconstruction (VCR). Therefore, it may not provide a high-quality 3D dept. map through the reconstructed image. To solve this problem, our proposed method utilizes a machine learning technique that can enhance the resolution of the elemental image. Our proposed method enlarged the low-resolution elemental image. Then, it generates the high-resolution image through the super-resolution convolution neural network (SRCNN). Therefore, it can reduce the shifting pixel error and it can generate various reconstructed images according to the dept.. Finally, it can generate an accurate 3D dept. map through the error-reduced 3D image. To prove our proposed dept. map accuracy, we implement the simulation experiment and evaluate the image through the image quality metric. © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Sentiment Analysis Exploring BART Models

Zero-Shot Sentiment Analysis Exploring BART Models

引用

Big Data, Cloud Computing, Data science & engineering (BCD)

作者： Konstantinos Kyritsis Isidoros Perikos Michael Paraskevas Electrical and Computer Engineering Dept. Computer Technology Institute and Press "Diophantus" University of Peloponnese Patras Greece Computer Engineering and Informatics Department University of Patras Patras Greece

The BART model is an advanced adaptation of transformers introduced by Facebook. It has incorporated elements from both BERT and GPT transformers, enabling significant advancements in language understanding and general speech processing. Utilizing both encoder and decoder components, BART proves versatile for various tasks, including translation, text completion, automatic sentence generation, entity recognition, sentiment analysis, and more. In this study, we focus on the study of pretrained models, BART and a modified version called distilbart, in the context of Zero-Shot Text Classification. In the experimental study we dive into the Zero-Shot technique applied to various pretrained Transformers. Our analysis demonstrates that, depending on the Model we utilize, we can achieve F1 scores of up to 88%, showcasing the model's effectiveness in discerning classes for this Sentiment Analysis problem using the Zero-Shot Text Classification technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition

arXiv

引用

arXiv 2024年

作者： Wang, Chien-Chun Chen, Li-Wei Chou, Cheng-Kang Lee, Hung-Shin Chen, Berlin Wang, Hsin-Min Dept. Computer Science and Information Engineering National Taiwan Normal University Taiwan Institute of Computer Science Academia Sinica Taiwan United-Link Co. Ltd. Taiwan

While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and conditions. To mitigate this issue, we propose a novel channel-aware data simulation method for robust ASR training. Our method harnesses the synergistic power of channel-extractive techniques and generative adversarial networks (GANs). We first train a channel encoder capable of extracting embeddings from arbitrary audio. On top of this, channel embeddings are extracted using a minimal amount of target-domain data and used to guide a GAN-based speech synthesizer. This synthesizer generates speech that faithfully preserves the phonetic content of the input while mimicking the channel characteristics of the target domain. We evaluate our method on the challenging Hakka Across Taiwan (HAT) and Taiwanese Across Taiwan (TAT) corpora, achieving relative character error rate (CER) reductions of 20.02% and 9.64%, respectively, compared to the baselines. These results highlight the efficacy of our channel-aware data simulation method for bridging the gap between source- and target-domain acoustics. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

TB Chest X-Ray Diagnostic Technique Using Deep Learning

TB Chest X-Ray Diagnostic Technique Using Deep Learning

引用

Delhi Section Conference (DELCON), IEEE

作者： Manish Kumar Goyal Dhananjay Kumar Yadav Khushmeen Kaur Brar Manisha Mittal Ananta Ojha Laith H. Alzubaidi Ashish Pathani Dept. of Computer Science & Application Vivekananda Global University Jaipur India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Dept. of Electronics and Communication Engineering Chandigarh University Mohali India Guru Tegh Bahadur Institute of Technology New Delhi India Dept. of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India The Islamic University Najaf Iraq Department of Civil Engineering Uttaranchal Institute of Technology Uttaranchal University Dehradun India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

The bacteria Mycobacterium tuberculosis is responsible for the infectious illness tuberculosis (TB). Although the lungs are the primary organs affected, the kidneys, bones, and brain may also be affected. Whenever an infected person coughs, sneezes, or talks, small droplets comprising the bacteria are released into the air and spread through the airborne system. The elimination of tuberculosis (TB) remains a problem due to factors such medication resistance, co-infection with HIV, and scarce resources in high-burden configurations, even with substantial efforts to treat the disease. As a major worldwide health concern, tuberculosis (TB) necessitates quick and precise diagnosis in order to be effectively managed. This study aimed to develop a TB detection model using chest X-ray images obtained from ***, utilizing Google's Collaboration Platform. The model was trained to recognize patterns within the TB chest X-rays to efficiently recognize TB within patients in order to be treated in time. We introduce a technique for transfer learning that proves preferable to the traditional methodology of adopting ImageN et weights. The hybrid methodology utilizes best first search technique in fusion with ResNet 50 model. The SVM classifier is used for categorizing the classes. An accuracy of 93.91 % is attained.

关键词： Support vector machines Tuberculosis Lungs Transfer learning X-rays Bacteria Pattern recognition X-ray imaging Medical diagnostic imaging Kidney

来源：评论

学校读者我要写书评

暂无评论

Sleep Assessment Trial in a High Air-Quality Nap-Box based on Clean Unit System Platform (CUSP) 12

Sleep Assessment Trial in a High Air-Quality Nap-Box based o...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Zhou, Z. Wu, H. Hsieh, T. Liang, S. Yamaguchi, H. Ishibashi, A. National Cheng Kung University Dept. of Computer Science and Information Engineering Tainan Taiwan Koyoju Plywood Corporation Asahikawa Japan Hokkaido University Research Institute for Electronic Science Sapporo Japan Hokkaido University Graduate School of Science Dept. of Condensed Mater Physics Sapporo Japan C'Stec Corporation Sapporo Japan

ISBN: (纸本)9798350340181

A new closed-air-system enabled by clean unit system platform (CUSP) and Gas-Exchange-Membrane (GEM) is demonstrated to be versatile for sleep assessment, or in general, improving Quality-of-Life (QOL). In a new high air-quality CUSP-GEM system called Nap-Box, sleep assessment has been performed successfully for subjects taking a nap virtually in standing position, for the first time in the world, thanks to the 4-point-supporting configuration introduced in the Nap-Box. The sleep assessment results suggest that taking short sleep in Nap-Box is of potential interest for decreasing sleepiness and helping alertness restoration. © 2023 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

‘Do Not Disturb’: An Implication Design To Be Alerted But Less Stress

‘Do Not Disturb’: An Implication Design To Be Alerted But ...

引用

International Seminar on Application for technology of Information and Communication (ISemantic)

作者： Weerachaya Jarupreechachan Kotcharat Kitchat Thattapon Surasak Dept. of Computer Engineering Faculty of Engineering at Kamphaeng Saen Kasetsart University Nakhon Pathom Thailand Dept. of Computer Science and Information Engineering National Central University Taoyuan Taiwan Dept. of Computer and Information Science Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

The pervasive utilization of smartphones, while augmenting personal and professional communications, also elicits mental stress and disrupts the work-life balance. Users necessitate staying connected to critical updates without undue disruption, necessitating an optimized, user-friendly smartphone interface. However, current "Do Not Disturb (DND)" features fall short of providing the desired customization options, thereby contributing to heightened anxiety and diminished productivity. Consequently, this study proposes a design modification to the DND mode by incorporating an "Exceptional Apps Notification", feature thereby aiding in alleviating stress and enhancing focus by permitting essential alerts from selected apps or contacts. In other words, the users only need to turn off notifications for specific applications, not every application. This approach addresses the problem of users fearing they will miss some important notifications. Therefore, the design process employed principles of selective attention and color theory, and user experience was assessed through questionnaires and psycho-physiological feedback. Early findings suggest the potential for stress reduction, albeit with opportunities for further optimization, such as including a memory feature for user preferences and allowing selective access for specific contacts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality with Internet of Things

Augmented Reality with Internet of Things

引用

2021 International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021

作者： Sureshkumar, S. Agash, C.P. Ramya, S. Kaviyaraj, R. Elanchezhiyan, S. Sri Krishna College of Engineering and Technology Dept of Computer Science Coimbatore India Paavai Engineering College Department of Computer Science and Engineering Namakkal India Srm Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781728195377

Today technological changes make the probability of more complex things made into simple tasks with more accuracy in major areas and mostly in Manufacturing Industry. Internet of things contributes its major part in automation which helps human to make life easy by monitoring and directed to a related person with in a fraction of second. Continuous advances and improvement in computer vision, mobile computing and tablet screens have led to a revived interest in Augmented Reality the Augmented Reality makes the complex automation into an easier task by making more realistic real time animation in monitoring and automation on Internet of Things (eg like temperature, time, object information, installation manual, real time testing).In order to identify and link the augmented content, like object control of home appliances, industrial appliances. The AR-IoT will have a much cozier atmosphere and enhance the overall Interactivity of the IoT environment. Augmented Reality applications use a myriad of data generated by IoT devices and components, AR helps workers become more competitive and productive with the realistic environment in IoT. Augmented Reality and Internet of Things together plays a critical role in the development of next generation technologies. This paper describes the concept of how Augmented Reality can be integrated with industry(AR-IoT)4.0 and how the sensors are used to monitoring objects/things contiguously round the clock, and make the process of converting real-time physical objects into smart things for the upcoming new era with AR-IoT. © 2021 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Lung Nodule Segmentation and Classification Using Conv-Unet Based Deep Learning

Lung Nodule Segmentation and Classification Using Conv-Unet ...

引用

Network, Multimedia and Information technology (NMITCON) International Conference on

作者： Akash V Monish Sai. R Amith K B Jayanthi M.G. Prashanth Kannadaguli Dept. of Artificial Intelligence and Machine Learning Cambridge Institute of Technology Bangalore India Dept. of Information Science and Engineering Cambridge Institute of Technology Bangalore India Dept. of Computer Science and Engineering Cambridge Institute of Technology Bangalore India Dhaarini Academy of Technical Education Bangalore India

This paper proposes a Convolutional U-Net architecture, a variation of the standard U-Net architecture for the segmentation of lung nodules and classification using Deep learning on computerized Tomography (CT) scans. The Primary steps employed are Preprocessing, Segmentation and Classification of nodules. In the preprocessing step, the lung region is segmented using techniques such as normalization, median filtering, Kmeans clustering, morphological and thresholding operations to extract lung Region of Interest (ROI) and nodule masks. The Conv-Unet design adds more convolutional layers to the standard U -Net architecture to help capture complicated patterns and boundaries of lung nodules for more accurate segmentation. Categorization of the segmented lung nodules is done using a CNN network on the LIDC-IDRI, and LUNA16 dataset. Overall, this model achieves a dice score of 62% and classification accuracy of 82% displaying appropriate performance in comparison with other variations of the U-Net architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study on Effect of COVID-19 and AI tools to Detect Coronavirus from Chest Medical Images 5

A Study on Effect of COVID-19 and AI tools to Detect Coronav...

引用

5th International Conference on Information Systems and computer Networks, ISCON 2021

作者： Choudhury, Amitava Negi, Alok Bhowmik, Tanmay University of Petroleum and Energy Studies School of Computer Science Dehradun India National Institute of Technology Department of Computer Science Uttrakhand India Bennett University Dept. of Computer Science Engineering Greater Noida India

ISBN: (纸本)9781665403412

In December 2019, an outbreak of a series of severe respiratory illness was found in Wuhan, Hubei Province, China. It was due to a novel coronavirus, now identified as SARS-CoV-2. The virus is human-to-human transmissible and that is why it has created a pandemic. Due to the continuous increasing death toll, several governments have been compelled to execute complete lockdown throughout the countries and followed by a social separation. The lack of tailored treatment remains an issue. Usually, patients above the age of 65 are more vulnerable to serious illnesses, according to epidemiological studies, whereas children have lesser symptoms. Depending on the present scenario of coronavirus disease, World Health Organization (WHO) advised to implement precautionary measures to defend self and other population. It has been also instructed to take legal action if some careless personnel do not abide with the guidelines of WHO and respective government of his country. A covid detection mechanism from X-ray images is presented in this paper, where a deep convolutional neural network has been utilized to determine whether a person is a covid patient or not. The proposed model accomplishes more than 96% accuracy, which proofs the goodness of the proposed work. © 2021 IEEE.

关键词： Coronavirus

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：