检索结果-内蒙古大学图书馆

Fast recurrent neural network approach for automatic detection of lung nodules

AIP Conference Proceedings 2022年第1期2519卷

作者： Balachandra Pattnaik B. Suseela T. R. Ganesh Babu S. Anitha 1Department of Electrical and Computer Engineering Wollega University Nekemte Ethiopia Africa 2Department of Electronics and Communication Engineering Government Polytechnic College Keelakanavai Perambalur-621 104 India 3Department of Electronics and Communication Engineering Muthayammal Engineering College Rasipuram-637408. India 4Department of Electronics and Communication Engineering Muthayammal Engineering College Rasipuram-637408 India

The cancer death in concern to lung cancer is increased compared to other cancers worldwide. The presence of nodules in the lung indicates the chances of getting lung cancer in the future. In this paper, an accurate computer-Aided Detection (CAD) system for lung nodules detection using computer Tomography (CT) images is proposed. It consists of four important modules such as preprocessing; Two-Successive Segmentation Process (TS2P), Rule-Based Refinement Pass (RBRP), and Detection Module (***). The lung C.T. CT image is de-noised using the Wiener filter in the preprocessing module. In the TS2P module, the right and left lungs are segmented at first, and in the next stage, the nodules and vessels are segmented. Then, the RBRP module is designed to remove the vessels with the help of geometrical features. Finally, the nodules are detected using a deep learning approach in the ***. The proposed method is validated on 888 lung *** images, and a mean average precision of 96.75% and sensitivity of 97% with 2 false positives per image were obtained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cs-137 activity in fly ash from thermal electric power stations

引用

AIP Conference Proceedings 2022年第1期2466卷

作者： I. K. Ahmed H. N. B. Khalaf Y. A. M. Mostafa 1Department of Computer Networks Engineering College of Information Engineering Al-Nahrain University Iraq 2Department of Physics Faculty of Science Minia University 61519 El-Minia Egypt 3Ural Federal University Physics and Technology Institute 620078 Ekaterinburg Russia

Radioactive 137Cs has a great concern because of its long half-life (30.2 year) and its similarity to potassium which is an essential element for humans. It is well known that Cs is distributed in surface soils or specifically adsorbed on illicit clay minerals and finally enters to organisms. 137Cs is made through nuclear accidents and processes is an example of anthropogenic radionuclides. In the present work, 137Cs specific activity concentration is measured with a high efficiency gamma ray spectroscopy NaI(Tl) detector in fly ash samples from two thermal electric power stations in the south of Iraq (Al-Naserya and Al-Musaeb). The 137Cs specific activity concentration are founded with ranges from 20±4.8 Bq kg-1 to 120±27.6 Bq kg−1 at Al-Naserya and 17±4.4 Bq kg-1 to 86±19.8 Bq kg−1 at Al-Musaeb station. Some of these values are alerted us to take care about the received dose because these concentrations are higher than background and world-wide limit (37 Bq kg-1 From UNSCEAR). Also, the presented 137Cs specific activity concentration results point out an additional shot to the measured effective dose rate, which can be predicted to be the 137Cs and cosmic radiation. By accounting for the contribution of 137Cs in the estimated absorbed dose rate, applying the conversion coefficient 0.136 (nGy h−1 per Bq kg−1). If a human inhale the air every day for 70 years, the radiation dose must be less than the dose limit (1 mSv y−1). In case 137CS is present, the criterion is the activity of 137Cs /60≦1.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network-based MRI brain tumor classification system

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： M. Amanullah J. Visumathi Naresh Sammeta Maram Ashok 1Department of Information Technology Aalim Muhammed Salegh College of Engineering Chennai Tamil Nadu India 2Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India 3Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Tamil Nadu India 4Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India

A brain tumor, the cause of more death rate among all cancers, is diagnosed using uncontrollable cell growth and abnormal brain cell partitioning. The recent progress in Deep Learning (DL) neural network technology aids the health service department in medical imaging diagnose several death-causing diseases. The visual learning of image recognition manually may result in fault detection and can be overcome by the most prevalent task of machine learning. In our paper, the Convolutional Neural Network (CNN) model is designed with data augmentation and image processing techniques to identify the brain MRI scan images into cancerous or non-cancerous and classify various brain tumor types. The performance comparison of our proposed CNN model uses the Transfer Learning (TL) method. With a very small dataset, the experimental result shows that our model is very effective at low computational power with less complexity and achieves better accuracy compared to an existing model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Covid heuristic analysis using machine learning

引用

AIP Conference Proceedings 2022年第1期2393卷

作者： Pravin R. Kshirsagar Makarand Upadhyaya Pankaj Dadheech T. Yuvaraj C. A. Sathiya Moorthy 1Department of Electronics and Communication Engineering AVNIET Hyderabad India 2Department of management & marketing University of Bahrain Bahrain 3Computer science & Engineering Swami Keshvanand institute of technology Jaipur Rajasthan India 4Department of Electrical and Electronics Engineering Saveetha School of Engineering Chennai India 5Department of Electronics and Communication Engineering CMS College of engineering Namakkal India

The newer avid-19 corona virus created havoc for patients with a variety of complications that prompted health practitioners around the world to develop new technologies and treatment plans. Technologies based on Machine Learning (ML) have been a major factor in addressing complex issues and many businesses have been able to develop and adapt to the COVID-19 challenges. The diagnosis of illness can be used with different AI methods to monitor the present havoc. Since Machine Learning (ML) approaches have been commonly used in other domain fields, a great deal of demand is now being made for ML-supported diagnostic systems to screen, monitor, and forecast void-19 spread and find a cure. The article presents an overview of the role of ML to combat the virus so far, especially from the perspective of screening, prognosis, and vaccine.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement of smart grid technology using end-to-end reinforcement learning in deep q-network

引用

AIP Conference Proceedings 2022年第1期2555卷

作者： Dhruvi Bansal Mitashi Bansal Kusum Tharani Meenu Gupta Bhawna Goyal Ayush Dogra 1Department of Electrical & Electronics Engineering Bharati Vidyapeeth’s college of Engineering New Delhi India 110063 2Department of Computer Science & Engineering Amity School of Engineering & Technology Amity University Noida India 201313 3Department of Computer Science and Engineering Chandigarh University Punjab India 140413 4Department of ECE Chandigarh University Mohali India 140413 5Ronin Institute Montclair NJ USA 07043

This paper reviews the complex task problems which are out of reach for a simple machine. So, there is a need for a solution for such a problem, so the solution is Reinforcement Learning with deep Q-Network. Reinforcement learning techniques are now being researched for their applicability in a wide range of situations. Perhaps because of the rising complexity and unpredictability in the generation and distribution sector of power systems, traditional approaches frequently encounter congestion while attempting to handle decision and control issues that are out of reach for a basic machine. Deep Reinforcement Learning (DRL) is one of these data-driven approaches that is considered true Artificial Intelligence (AI). DRL is a hybrid of Deep Learning (DL) and Reinforcement Learning (RL). Our study examines the fundamental concepts, models, methods, and approaches of DRL. It also presents power system applications such as smart grids, energy management, demand response, the electricity market, operational control, and many others. Furthermore, current advancements in DRL, the coupling of RL with other classical techniques, and the prospects and problems of its applications in the power system are explored.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design & development of friction welding machine based on lathe machine

引用

AIP Conference Proceedings 2022年第1期2578卷

作者： Ade Sunardi Mariyana Mariyana Adhes Gamayel M. N. Mohammed Mohamad Zaenudin 1Department of Mechanical Engineering Faculty of Engineering & Computer Science Jakarta Global University Grand Depok City Boulevard Raya No. 2 St. Depok City 16412 West Java Indonesia 2Department of Engineering & Technology Faculty of Information Sciences and Engineering Management & Science University University Drive Off Persiaran Olahraga 40100 Shah Alam Selangor Malaysia

The search of most efficient process to combine one material with others through welding is undergoing extensive research. Whether using solid-state or fusion welding, both techniques appear to have their own advantages and disadvantages. In solid-state welding, techniques that involve friction between the two to be welded materials, friction welding, have been gaining attention from researchers, since these techniques introduce a solid-state welding with a time-efficient process, excellent mechanical properties, and filler-free. In this study, we developed a friction welding machine based on lathe machine. The friction welding machine is designed with three main subsystems, they are braking system, holder chuck, and hydraulic system. The subsystems are then embedded to a lathe machine, giving it ability to perform a friction welding process, through three simple steps: (1) two samples are hold separately, one on the holder of lathe machine, whilst the other one is hold by a holder chuck; (2) the rotational movement is generate by lathe machine, and when it is achieve its desired rotational speed, then the holder chuck is pushed by the force given by hydraulic system completed with pressure gauge to generate friction forces between the two sample; (3) the sample is then hold for friction for a desired time, giving it time to generate heat from the friction before it release after finish the friction process. A preliminary results of friction welding has indicated that it has excellent strength as indicate by tensile test result. This study shows

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet connected patient healthcare monitoring in smart phones using Raspberry Pi

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： Porandla Srinivas K. Kalimuthu C. Balarengadurai C. Viswanathan 1Department of Information Technology Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India 2Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu India 3Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Dundigal Telangana India 4Department of Computer Science and Engineering Chennai Institute of Technology Malayambakkam Tamil Nadu India

Today the Environment of health has established research and knowledge based on Technology-oriented wireless sensing node. Patients are confronted with the problem of unanticipated death because of the particular cause of cardiac difficulties and attacks that occur at the necessary time owing to a lack of adequate care for patients. In contemporary health industry, the use of medical gadgets is significant, which is causing a lot of disruption in the patient’s space as well as the doctor’s analysis. As a result, we highlight our major healthcare electronics initiatives in this paper, with an emphasis on electronic medical records. Uniqueness and ease of use characterize the designed systems, which were planned with a very high level of efficiency (so-called "smarter" gadgets). It was created as a handheld gadget to allow for real-time rescue in the event of an accident without the requirement for continuous patient care of the data. We also show a low-cost computerized healthcare practice that can analyze respiratory activities in real time, non-invasively, and continuously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Macro mechanical and water absorption properties of composite laminates with novolac resin and e-glass/sisal fibers

引用

AIP Conference Proceedings 2022年第1期2446卷

作者： A. Vivek Anand P. Velmurugan R. Arvind Singh S. Jayalakshmi K. Srinivas Rao P. S. Prem Kumar 1Department of Aeronautical Engineering MLR Institute of Technology Hyderabad India 2Department of Mechanical Engineering Shri Ram Murti Smarak College of Engineering UP India 3School of Mechanical and Electrical Engineering Wenzhou University China 4Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India 5Department of Aeronautical Engineering Kumaraguru College of Technology Coimbatore India

Natural fiber- reinforced composites are currently being researched for their selection and use in the industries spanning aerospace, automotive, ground transportation, and several other high- performance-critical end products. Two of the key reasons in favor for the selection and use of natural fibers are, their biodegradability coupled with an overall ease of availability that makes the production of engineered composites not only cost effective but also economically viable. However, the selection and use of natural fibers/matrix is curtailed primarily because of three competing drawbacks, namely (i) high moisture absorption, (ii) inferior mechanical properties, and (iii) poor interfacial bonding strength between fiber and matrix, when compared one-on-one with the synthetic fibers/matrix. Due to these reasons, natural fibers are often used in combination with synthetic fibers for engineering composites, so as to achieve a material that offers the possibility of improved performance at the desired level. In this research study, composite laminates with novolac resin and sisal/coir/E-glass fiber reinforcement (60:40) were fabricated using the hand lay-up method. The fabricated composite laminates were characterized for macromechanical properties, namely, tensile strength and water absorption test was conducted to explore the moisture absorption characteristics of composite laminates. Test results revealed the composite laminates with natural fibers/resins to possess many attributes in favor of their selection and use in structural components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel method of Braille-based system for visually impaired people

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： X. S. Asha Shiny K. Vanisree P. Sivakumar J. Lenin 1Department of Computer Science and Engineering Nalla Malla Reddy Engineering College Hyderabad Telangana India 2Department of Electronics and Communication Engineering Samskruti College of Engineering and Technology Telangana India 3Department of Electronics and Communication Engineering GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India 4Department of Information Technology Al Musanna College of Technology Muladdah Muscat Sultanate of Oman

This work mainly aims to solve many problems in communicating in the lives of a person with vision impairment. Most of us face India today as the home for the biggest number of blind people in the world. Day by day, technology is mostly developed in mobile communication, which has an important function to play. Only visually challenged persons can read the message on the touch screen of the display in the messaging application. However, the system quality is not acceptable since the blind persons are unable to properly distinguish the text. Braille technology is still utilised for reading purposes solely by the blinds. In our method of reading and answering messages from visually challenged persons utilising our Braille system. Blind persons can reach the messaging application on mobile phones like ordinary people with Braille technology. At the same time, keypads employing one message per user can deliver the information via Message simply based on the keypad selections. This technology allows untrained individuals to utilise the messaging application on a mobile system and then to utilise GSM to communicate with Easily Blind People.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Aided Data Driven Adaptive Target Detection for Channel Matrix-Based Cognitive Sonar

引用

Proceedings of Meetings on Acoustics 2022年第1期46卷

作者： Touseef Ali Akshay S. Bondre Christ D. Richmond 1School of Electrical Computer and Energy Engineering Arizona State University Tempe AZ 85281 USA tali4@asu.edu asbondre@asu.edu 2Department of Electrical and Computer Engineering Duke University Durham NC USA christ.richmond@duke.edu

Data driven-based approaches including deep neural networks (DNN) have shown promise in various fields. Such techniques tend to require significant training for good convergence. Model-based approaches, however, provide practical data efficient solutions often with insightful and intuitive interpretations. A hybrid approach that employs data driven techniques aided by knowledge from model-based approaches may help reduce required training and improve convergence rates. This work investigates the potential of deep learning techniques to detect radar targets while accelerating the learning process via use of expert/domain knowledge from model-based algorithms for channel matrix-based cognitive sonar/radar. The channel matrices characterize responses from target and clutter/reverberation. The architecture of the proposed DNN exploits the insights from the model-based generalized likelihood ratio test (GLRT) statistic presented in our previous work, and hence, the resulting DNN algorithm benefits from the merits of both the model-based and data-driven approaches. Our proposed DNN architecture utilizes the secondary data for clutter channel estimation via the maximum-likelihood approach, and thus, requires little to no retraining with the changing clutter environment. We compare the detection performance of model-aided deep learning-based algorithms with that of traditional model-based techniques and pure data-driven DNN approaches using receiver operating characteristic (ROC) curves from Monte Carlo simulations.

关键词：

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：