检索结果-内蒙古大学图书馆

作者： Yeh, Chia-Hung Kang, Li-Wei Lee, Ming-Sui Lin, Cheng-Yang Department of Electrical Engineering National Sun Yat-sen University 804 Taiwan Graduate School of Engineering Science and Technology-Doctoral Program Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin 640 Taiwan Graduate Institute of Networking and Multimedia Department of Computer Science and Information Engineering National Taiwan University Taipei 106 Taiwan

Images/videos captured from optical devices are usually degraded by turbid media such as haze, smoke, fog, rain and snow. Haze is the most common problem in outdoor scenes because of the atmosphere conditions. This paper proposes a novel single image-based dehazing framework to remove haze artifacts from images, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze optical model, we propose to estimate atmospheric light via haze density analysis. We can then estimate transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free images can be recovered with lower computational complexity compared with the state-of-the-art approach based on patch-based dark channel prior. ©2013 Optical Society of America.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting 3

Single Layer & Multi-layer Long Short-Term Memory (LSTM) Mod...

引用

3rd International Conference on computer science and Computational Intelligence, ICCSCI 2018

作者： Salman, Afan Galih Heryadi, Yaya Abdurahman, Edi Suparta, Wayan Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Engineering Faculty of Science and Technology Sanata Dharma University Yogyakarta55282 Indonesia

Weather forecasting has gained attention many researchers from various research communities due to its effect to the global human life. The emerging deep learning techniques in the last decade coupled and the wide availability of massive weather observation data have motivated many researches to explore hidden hierarchical pattern in the large volume of weather dataset for weather forecasting. The purposes of this research are to build a robust and adaptive statistical model for forecasting univariate weather variable in Indonesian airport area and to explore the effect of intermediate weather variable related to accuracy prediction using single layer Long Short Memory Model (LSTM) model and multi layers LSTM model. The proposed forecasting model is an extension of LSTM model by adding intermediate variable signal into LSTM memory block. The premise is that two highly related patterns in input dataset will rectify the input patterns so make it easier for the model to learn and recognize the pattern from the training dataset. In an effort to achieve a robust model for learning and recognizing weather pattern, this research will also explore various architectures such as single layer LSTM and Multiple Layer LSTM (4 layers LSTM). The dataset is weather variable data collected by Weather Underground at Hang Nadim Indonesia airport. This research used visibility as predicted data and temperature, pressure, humidity, dew point as intermediates data. The best model of LSTM in this experiment is multiple layers LSTM and the best intermediate data is pressure variable. Using the pressure variable this model has gained the validation accuracy 0.8060 and RMSE 0.0775. © 2018 The Authors. Published by Elsevier Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

An Improvement Data Hiding Scheme Based on Formula Fully Exploiting Modification Directions and Pixel Value Differencing Method 11

An Improvement Data Hiding Scheme Based on Formula Fully Exp...

引用

11th Asia Joint Conference on Information Security, AsiaJCIS 2016

作者： Kuo, Wen-Chung Li, Jyun-Jia Wang, Chun-Cheng Wuu, Lih-Chyau Huang, Yu-Chih Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Taiwan Graduate School of Engineering Science and Technology Doctoral Program National Yunlin University of Science and Technology Taiwan Department of Information Management Tainan University of Technology Taiwan

ISBN: (纸本)9781509022854

Recently, a modified data hiding scheme based on pixel value differencing and improving exploiting modification directions is proposed by Shen and Huang. There are two major contributions in this scheme. One is to enhance the embedding rate and good embedding capacity and the other is an optimization problem used to solve the overflow/ underflow problem. In fact, they propose the similar brute force method to solve overflow/underflow problem in their proposed scheme. To overcome the overflow/underflow problem exactly, we will propose the close form to solve this problem in this paper. Then, an improvement data hiding scheme based on FFEMD (Formula Fully Exploiting Modification Directions) and pixel value differencing method is proposed. According to our analysis, it is not only to keep the advantages of Shen-Huang scheme but also to use the close form to solve the overflow/ underflow problem. © 2016 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection 7

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

7th International Congress on Ambient Intelligence, Software engineering, and e-Health and Mobile Health, AmITIC 2024

作者： Jiménez-Delgado, E. Quesada-López, C. Méndez-Porras, A. Lara-Petitdemange, A. Alfaro-Velasco, J. Graduate Program in Computer Science and Informatics University of Costa Rica Costa Rica Technological Institute of Costa Rica Computer Engineering Department Costa Rica School of Computer Science and Informatics University of Costa Rica Costa Rica

ISBN: (纸本)9798350364538

In this study, two deep learning models for automatic tattoo detection were analyzed;a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

UAV-Aided Data Acquisition Using Gaining-Sharing Knowledge Optimization Algorithm

引用

computers, Materials & Continua 2022年第9期72卷 5999-6013页

作者： Rania M Tawfik Hazem A.A.Nomer M.Saeed Darweesh Ali Wagdy Mohamed Hassan Mostafa Wireless Intelligent Networks Center(WINC) School of Engineering and Applied SciencesNile UniversityGiza12677Egypt School of Information Technology and Computer Science(ITCS) Nile UniversityGiza12677Egypt Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Department of Mathematics and Actuarial Science School of Science and EngineeringThe American University in CairoEgypt Electronics and Communications Engineering Department Cairo UniversityEgypt University of Science and Technology Nanotechnology and Nanoelectronics ProgramZewal City of Science and TechnologyOctober Gardens6th of OctoberGiza12578Egypt

Unmanned Aerial Vehicles(UAVs)provide a reliable and energyefficient solution for data collection from the Narrowband Internet of Things(NB-IoT)***,the UAV’s deployment optimization,including locations of the UAV’s stop points,is a necessity to minimize the energy consumption of the UAV and the NB-IoT devices and also to conduct the data collection *** this regard,this paper proposes GainingSharing Knowledge(GSK)algorithm for optimizing the UAV’s *** GSK,the number of UAV’s stop points in the three-dimensional space is encapsulated into a single individual with a fixed length representing an entire *** superiority of using GSK in the tackled problem is verified by simulation in seven *** provides significant results in all seven scenarios compared with other four optimization algorithms used before with the same ***,the NB-IoT is proposed as the wireless communication technology between the UAV and IoT devices.

关键词： NB-IoT UAV GSK stop points optimization

来源：评论

学校读者我要写书评

暂无评论

Mathematical representation of emotion using multimodal recognition model with deep multitask learning

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2020年第12期140卷 1343-1351页

作者： Harata, Seiichi Sakuma, Takuto Kato, Shohei Computer Science Program Department of Engineering Graduate School of Engineering Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan Frontier Research Institute for Information Science Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan

To emulate human emotions in robots, the mathematical representation of emotion is important for each component of affective computing, such as emotion recognition, generation, and expression. In a method that learns DNN from unimodality and represents emotions by vectors of continuous values (Emotional Space), the acquired Emotional Space is likely to depend on the modality, and considering the number of dimensions of Emotional Space is necessary. In this study, we aim at the acquisition of modality independent Emotional Space. We propose a method of acquiring Emotional Space by integrating multimodalities on a DNN and combining the emotion recognition task and unification task of Emotional Space of each modality. Through the experiments with audio-visual data, we confirmed in various dimensions of Emotional Space that there are differences in Emotional Space acquired from unimodality, and the proposed method can acquire a modality independent Emotional Space. We also investigated the compatibility of the recognition and the unification score by changing the number of dimensions of Emotional Space. Finally, we indicate the proposed method can acquire sufficient Emotional Space with a small number of dimensions, such as five or six dimensions, under this paper's experimental conditions. © 2020 The Institute of Electrical Engineers of Japan.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Magnetic resonance imaging of irreversible electroporation in tubers

Magnetic resonance imaging of irreversible electroporation i...

引用

12th Mediterranean Conference on Medical and Biological engineering and Computing, MEDICON 2010

作者： Hjouj, Mohammad Rubinsky, Boris Center for Bioengineering School of Computer Science Engineering Hebrew University of Jerusalem Israel Department of Mechanical Engineering Graduate Program in Biophysics University of California Berkeley United States

ISBN: (纸本)9783642130380

Purpose: A preliminary study on the magnetic resonance (MRI) characteristics of (vegetable) tissue NTIRE is an emerging minimally invasive surgery technique for tissue ablation in which, microsecond, high electrical field pulses form permanent nano-scale defects in the cell membrane. Materials and Methods: The potato is used as the simplest conceivable first order tissue model for studying the MRI characteristics of electroporation, because while made of structured cells it does not have blood flow, it is relatively homogeneous and cell damage is readily visible through a natural oxidation process of the intracellular enzymes.. Clinical NTIRE sequences were applied to potato tubers and MRI sequences of the treated area were compared with colorimetric photographs. Results: A comparison of T1 weighted, T2 weighted, fluid attenuation inversion recovery (FLAIR) and short TI inversion recovery (STIR) of NTIRE shows that T1 weighted signals, such as FLAIR, produce brighter images of the treated areas. In contrast the images of the treated areas are completely lost with liquids enhancing and fat eliminating sequences, such as STIR. Conclusion: MRI can image tissue treated by NTIRE. A possible explanation for the findings is that by producing nanoscale defects in the cell membrane lipid bilayer, NTIRE causes an enhanced signal from the cell membrane lipids that in the treated cells are not bound anymore in a restrictive liquidgel membrane structure and have more degrees of freedom. © 2010 International Federation for Medical and Biological engineering.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards bio-inspired place recognition over multiple spatial scales

Towards bio-inspired place recognition over multiple spatial...

引用

2013 Australasian Conference on Robotics and Automation, ACRA 2013

作者： Chen, Zetao Jacobson, Adam Erdem, Uʇur M. Hasselmo, Michael E. Milford, Michael School of Electrical Engineering and Computer Science Queensland University of Technology Australia Center for Memory and Brain and Graduate Program for Neuroscience Boston University United States

ISBN: (纸本)9780980740448

This paper presents a new multi-scale place recognition system inspired by the recent discovery of overlapping, multi-scale spatial maps stored in the rodent brain. By training a set of Support Vector Machines to recognize places at varying levels of spatial specificity, we are able to validate spatially specific place recognition hypotheses against broader place recognition hypotheses without sacrificing localization accuracy. We evaluate the system in a range of experiments using cameras mounted on a motorbike and a human in two different environments. At 100% precision, the multiscale approach results in a 56% average improvement in recall rate across both datasets. We analyse the results and then discuss future work that may lead to improvements in both robotic mapping and our understanding of sensory processing and encoding in the mammalian brain.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

E-payment for Jakarta Smart Public Transportation, Using the Point System for E-Commerce 2

E-payment for Jakarta Smart Public Transportation, Using the...

引用

2nd International Conference on computer, science, engineering, and Technology, ICComSET 2019

作者： Anwar, Nizirwan Rasjidin, Roesfiansjah Najoan, Daniel Stephanus Rolando, Christopher Tamimmanar Warnars, Harco Leslie Hendric Spits Faculty of Computer Science Esa Unggul University Jakarta11510 Indonesia Faculty of Engineering Esa Unggul University Jakarta11510 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia

The ease of using transportation is one of the most critical things in the city with a significant population like Jakarta. The growth of the population in Jakarta is increased rapidly. The wage that Many transportations are causing a traffic jam in Jakarta. The government suggests that people use public transportation for their mobility. However, people choose to use their vehicles rather than public transportation. The main reason is that public transportation cannot guarantee the arriving time, whether it is on time or not. Many people move on to online transportation services. However, the massive growth of online transportation is still a contradiction as public transportation. People in Jakarta need faster mobility to go. This research is trying to make a system for public transport without any delay and hard to use it. This problem can be solved by building a new system. This system required e-wallet for payment in public transportation. This E-Wallet will search the possible route from the nearest location to the destination - only the public transport where there is a station that can use it. By using QR-Code generated by e-wallet on the mobile phone, people can scan it directly to a machine located in the station. This method will make a transaction faster than ever. Moreover, people can enjoy another feature like cashback and redeem the prize by a point system. In this era, e-commerce is dominating the market for purchasing something. This is also the attraction of the system. This system is also required excellent facilities from the government so that people can enjoy it. © Published under licence by IOP Publishing Ltd.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

The Implementation of TOGAF for Enterprise System Planning on XYZ Campus

The Implementation of TOGAF for Enterprise System Planning o...

引用

2023 International Conference on Networking, Electrical engineering, computer science, and Technology, IConNECT 2023

作者： Sirait, Tamsir Hasudungan Lumban Gaol, Ford Supangkat, Suhono Harso Ranti, Benny Bina Nusantara University Binus Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University Computer Science Department Jakarta Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Universitas Indonesia Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350331172

Universities can employ information technology as one means of achieving their goals and objectives. Universities can get advantages from information technology, such as effective resource management and information management for decision-making. However, don't forget that the campus must consider what technology is appropriate to assist them achieve their goals, particularly in the current industrial era 4.0 where technology is available with many different choices. The campus requires an enterprise architecture in order to design, manage, and coordinate information technology infrastructure, applications, and processes strategically and thoroughly. The adoption of enterprise information system architecture (EA) is also intended to improve the quality of services provided to internal and external stakeholders. In this case, Enterprise Architecture can help an organization to match its information technology resources with business processes and strategies to achieve their goals. This research was conducted using TOGAF ADM, also known as the Open Group Architecture Framework Architecture Development Method. This method offers best practices for creating enterprise architecture and emphasizes several steps that include creating an architectural vision, information systems, business architecture modeling to help XYZ campus manage all their information technology. © 2023 IEEE.

关键词： Information management

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：