检索结果-内蒙古大学图书馆

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

IEEE Transactions on Neural Networks and Learning Systems 2023年第8期34卷 5122-5132页

作者： Huang, Shih-Chia Hoang, Quoc-Viet Le, Trung-Hieu National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology International Graduate Program in Electrical Engineering and Computer Science Taipei10608 Taiwan Hung Yen University of Technology and Education Faculty of Information Technology Hungyen 17000 Viet Nam

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Quality Analysis the E-PASTI System to Determine the Condition of the System and information Quality

Quality Analysis the E-PASTI System to Determine the Conditi...

引用

2019 International Conference of Science and information technology in Smart Administration, ICSINTeSA 2019

作者： Nugraha, Bayu Marleny, Finki Dona Sfenrianto, Sfenrianto Edwina, Cinthya Information System Program Faculty of Science and Technology Sari Mulia University South Kalimantan Banjarmasin Indonesia Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia

The purpose of this study is to evaluate the quality of secretarial, financial and staffing information systems at the Directorate General of AHU, known as the E-PASTI system. There are two variables analysed, namely system quality and information quality. Data collection using questionnaires that distributed to 123 employees who used the E-PASTI system but returned 93 questionnaires. Data quality analyst uses descriptive quantitative method. The results of the study are several conditions related to the system and information quality of E-PASTI. The quality can be a reference for the AHU Directorate General to improve the quality of E-PASTI that suits the needs of employees. © Published under licence by IOP Publishing Ltd.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

A light-weight ranger intrusion detection system on wireless sensor networks

A light-weight ranger intrusion detection system on wireless...

引用

5th International Conference on Genetic and Evolutionary Computing, ICGEC2011

作者： Hsieh, Chia-Fen Huang, Yung-Fa Chen, Rung-Ching Graduate Institute of Informatic Doctoral Program Choayang University of Technology Taichung Taiwan Department of Information and Communication Engineering Choayang University of Technology Taichung Taiwan Department of Information Management Choayang University of Technology Taichung Taiwan

ISBN: (纸本)9780769544496

In recent years, a lot of research concerns with the wireless sensor networks (WSN). With the increasing usages of WSN applications such as health care and disaster reporting, security requirements, wireless communication has become more critical. Researchers of intrusion detection system on WSN have suggested that systems' detecting mechanisms would likely affect their detections effective and lifetime of whole networks. Ontology can collect and organize the attributes of attacks However, those methods have empirically documented the link between ontology concept and lightweight Intrusion Detection System (IDS) is scant. Therefore, the aim of this paper attempts to explore how intrusion detection system about ontology and light-weight IDS are related. The manager constructs relationship of sensor nodes on ontology to detect Sybil attack. Combine light-weight IDS the ranger method to reduce energy consumption and the isolation tables avoid detecting anomaly repeatedly. We proposed a lightweight ontology-based IDS, which improves existence shortcomings of IDS on WSN effectively. © 2011 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Decision Support Systems Selection of Soang Superior Brood Using Weighted Product (WP) and Simple Additive Weighting (SAW) Method 4

Decision Support Systems Selection of Soang Superior Brood U...

引用

4th International Conference on Energy, Environment, Epidemiology and information System, ICENIS 2019

作者： Ramadiani Kurniawan, Reynaldi Kridalaksana, Awang Harsa Jundillah, Muhammad Labib Faculty of Computer Science and Information Technology Mulawarman University Samarinda Indonesia Magister Program of Information System School of Post Graduate Studies Diponegoro University Semarang Indonesia

Gurame Soang Latin name Osphronomus Labirynthici gouramy including fish, that as the fish have gills and breathing apparatus in the form of additional gills (Labyrinth). One important factor in fish farming Soang Gurame is holding elections. Superior brood has characteristics identical, to distinguish it needs to experience since it is quite difficult. Some of the assessment factors in selecting a superior brood that could be considered in the cultivation of the fish farmers Gurame Soang as ideal weight, physical disability, movement of fish, the shape of the head, and the body color. All of these factors combined to get an assessment that could help the decision making process fish Gurame Soang superior sires. This study used two methods that have selected the calculation accuracy of the decision-making process. The method used is the Weighted Product and Simple Additive weighting. The results of the research that has been done, it can be concluded the total number of alternative Gurame Soang superior sires data as many as 10 fish, and obtained the results of testing the level of accuracy by using the results of data from a breeder Gurame Soang superior sires, Method of Weighted Product got an accuracy of 80% and methods Simple Additive weighting got an accuracy of 60%. © The Authors, published by EDP Sciences, 2019.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Inference of pressure ulcer stage and texture on an image training set

引用

Pattern Recognition and Image Analysis 2016年第3期26卷 558-564页

作者： Guadagnin, R.V. Santana, L.A. Neves, R.S. MSc Program on Information Technology and Knowledge Management Catholic University of Brasília Brasília DF Brazil MSc Program on Sciences for Health at School of Health Sciences Brasília DF Brazil Head of Scientific Starting Program–PIBIC Health Sciences Graduate School Brasília DF Brazil

Health assistance depends essentially on effective information providing for professionals. Presently visual information plays an outstanding role concerning patients’ status without necessity of invading procedures. The diagnosis related to stage and texture in pressure ulcers (PU) is considered as a classification procedure, based on the image colors. As a training set this study captured 18 PU images from nine persons. RGB mean values were adopted as features to characterize the images. Classification used an ID3 similar algorithm. It achieved 83.3% accuracy concerning color and stage, as well as 88.9% concerning color and texture. So the technique was effective for automatic determination of PU stage and PU texture based on its color. © 2016, Pleiades Publishing, Ltd.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Analysis of Seismic Hazard Prediction Using Non Parametric Conic Multivariate Adaptive Regression Splines (C-Mars) Methods 1

Analysis of Seismic Hazard Prediction Using Non Parametric C...

引用

1st International Conference on Advanced information Scientific Development, ICAISD 2020

作者： Priyanto, Dadang Zarlis, Muhammad Mawengkang, Herman Efendi, Syahril Graduate Program of Computer Science Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

The data mining process requires a data set that can be used in determining a number of specific patterns to gain new knowledge. Large data sets (Big data) require special methods to get effective results. Included in this study are using big data related to the earthquake in Lombok. Earthquake research, especially in Lombok, is needed because Lombok is on three active plates in Indonesia, so that the danger of earthquake damage can be minimized. Earthquake data obtained from the Geophysical Station (BMKG) of Mataram has different characteristics and is complex, an appropriate method is needed, namely by detecting a non-parametric method with the Multivariate Adaptive Regression Spline (MARS). The use of the backward stepwise algorithm with the Conical Quadratic programming (CQP) framework of MARS, referred to as CMARS (Conic Multivariate Adaptive Regression Splines), is used for optimizing the results. The conclusions of this study are 1. A mathematical model with a total of 12 basis functions (BF) has contributed to the prediction analysis of the PGA dependent variable. 2. Contributions of the influence of independent variables on the PGA value are the epicenter distance (R e pi) of 100% and the Magnitude (Mw) of 31.08608%, while the temperature of the incident location (SUHU) of 5.48525% and depth (Depth) of 3,52988%. 3. Acquired areas that haveearthquake hazard levels in the order of the most vulnerable are Malaka, Genggelang, Tegal Maja, Senggigi and Mangsit. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Cascade of genetic algorithm and decision tree for cancer classification on gene expression data

Cascade of genetic algorithm and decision tree for cancer cl...

引用

37th International Conference on Computers and Industrial Engineering 2007

作者： Yeh, Jinn-Yi Chang, Der-Ming Department of Management Information Systems National Chiayi University Taiwan Department and Graduate Program of BioIndustry Technology Da-Yeh University Taiwan

ISBN: (纸本)9781627486811

Cancer classification through gene expression data analysis has emerged as an active area of research recently. Gene expression is the process of transcribing a gene's DNA sequence into RNA. A gene's expression level indicates the approximate number of copies of that gene's RNA produced in a cell. This is thought to correlate with the amount of the corresponding protein made. The expression of a gene provides a measure of activity of a gene under certain biochemical conditions. For example, cancers are usually reflected in the change of the expression values of certain genes. Recent studies on molecular level classification of tissues have produced remarkable results, and indicated that gene expression assays could significantly aid in the development of efficient cancer diagnosis and classification platforms. However, cancer classification based on the DNA array data is still a difficult problem. The main challenge is the overwhelming number of genes relative to the number of training samples. This implies that we must deal with a huge number of irrelevant genes. An efficient algorithm is required to reduce the computational overhead. The other challenge is from the presence of noise inherent in the data set. It makes accurate classification of data more difficult when the sample size is small. This paper applies genetic algorithms (GA) for selecting a group of relevant genes from cancer microarray data. Then the decision tree based cancer classifier is built on top of these selected genes. The performance of this approach is evaluated by comparing with other gene selection methods (e.g., t-statistics, GS method, and information gain) using the publicly available gene expression data set such as Colon, Leukemia, Lymphoma, Lung and central nervous system (CNS). Experimental results indicate that the cascade of GA and decision tree has the highest accuracy rate among different methods.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Find the Best Rule of Time Series Data Mining with Cluster Analysis 3

Find the Best Rule of Time Series Data Mining with Cluster A...

引用

3rd International Conference on Computational Science and information Management, ICoCSIM 2019

作者： Buaton, Relita Zarlis, Muhammad Mawengkang, Herman Efendi, Syahril Graduate Program of Computer Science Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

Data mining is an analytical process of knowledge discovery in large and complex data sets. Many studies wish to explore data, to find information so that knowledge can be obtained through the grouping process, classification, rules discovery, associations and data mining visualization which shows similarity. Periodic data often occurs in business applications and sciences that has big size, high dimension and continuously updated. The similarity in periodic data is based on several approaches. One of common approaches is to transform periodic series into other domains so that dimensions are reduced, followed by index mechanism. Many studies of time series do not give optimal result because limited to extracting data not able to represent time series and its pattern which is then change into rules. Rules can be found in time series data, but they are still constrained by over fitting and difficult to present. It causes time series data and non linier function of data mining decision can't be optimal. The basic idea in the method proposed is to do periodic discretization for sub-sequential formation. These sub-sequences are grouped through a measure of similarity. The simple rule-finding technique is applied to obtain hidden rules in the temporal pattern. The optimal time series data expected to generate the uncertainty trend, previously unknown and can be used to make decisions or forecasting in the future. © Published under licence by IOP Publishing Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Envisioning the Future of Collaboration for Banking and FinTech Industry 5

Envisioning the Future of Collaboration for Banking and FinT...

引用

5th IEEE International Conference on Computer and Informatics Engineering, IC2IE 2022

作者： Legowo, Mercurius Broto Sorongan, Fangky Antoneous Subanidja, Steph Perbanas Institute Information System Study Program Faculty of Information Technology Jakarta Indonesia Perbanas Institute Accounting Study Program Faculty of Economic and Business Jakarta Indonesia Post Graduate School Perbanas Institute Master of Management Program Jakarta Indonesia

ISBN: (数字)9781665453387

ISBN: (纸本)9781665453387

This study aims to envision the future of banking and the FinTech industry collaboration by the triggers for change based on trends watching in current conditions. Envisioning is the ability to describe the impact of changes in the business environment caused by the various trigger changes observed in trend watching. The current conditions and the triggers of change based on trend-watching are issues and considerations in envisioning collaboration between banking and the Fintech industry. The research methodology uses a descriptive method with a qualitative approach. The study surveyed 100 respondents, each representing the banking and FinTech sectors, who understand the issues related to the collaboration of the two industries. In addition, to complement the survey data, this study also conducted Focus Group Discussions and In-depth Interviews as a qualitative approach. The study's results by analyzing current conditions and triggers of change based on trend watching will represent a picture of the future of banking and FinTech industry collaboration. This research will expect a significant contribution to government regulations/policies and a positive contribution and support on the IT/IS side, especially in applied technology and architecture/business models for collaboration in the future of collaboration banking and the FinTech Industry that follow. © 2022 IEEE.

关键词： Laws and legislation

来源：评论

学校读者我要写书评

暂无评论

Risk Management of Bank and FinTech Collaboration: A Phenomenological Research 6

Risk Management of Bank and FinTech Collaboration: A Phenome...

引用

6th International Conference on Computer and Informatics Engineering, IC2IE 2023

作者： Legowo, Mercurius Broto Sorongan, Fangky Antoneus Subanidja, Steph Institute of Perbanas Study Program of Information System Faculty of Information Technology Jakarta Indonesia Institute of Perbanas Study Program of Accounting Faculty of Economic and Business Jakarta Indonesia Post Graduate School Institute of Perbanas Program of Master of Management Jakarta Indonesia

ISBN: (纸本)9798350345162

Banking and Fintech are encouraged to collaborate to fill each other's deficiencies and further grow the digital economy. This collaboration will create benefits for both banks, Fintech, and customers. However, this collaboration also comes with risks. The Financial Services Authority has stated that several risk phenomena can occur in the collaboration of banks and Fintech. First, no law guarantees the protection and exchange of customer personal data. Second, the risk of customer data leakage. Third, the risk of cyberattacks. The fourth is the risk of outsourcing. This research aims to analyze the risk phenomenon of bank and fintech collaboration through the Enterprise Risk Management Framework approach. This study uses a phenomenological research approach, which is a study to study how individuals subjectively experience and give meaning to the phenomenon. Data analysis based on this phenomenon data uses qualitative methods involving banking and fintech practitioners. The results of this study describe the phenomenon of risks that occur in banking-fintech collaboration, as approached by the Enterprise Risk Management framework. Proper risk management will minimize risks when the Bank collaborates with FinTech. This study hopefully contributes to making brief policy recommendations on bank and fintech collaboration risk management for Indonesian financial regulators. © 2023 IEEE.

关键词： bank collaboration ERM framework fintech risk 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：