检索结果-内蒙古大学图书馆

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Saifullah, Shoffan Drezewski, Rafal Institute of Computer Science AGH University of Science and Technology Kraków Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta Indonesia

This research aims to improve the performance of convolutional neural network (CNN) in medical image segmentation that will detect specific parts of the body's anatomical structures. Medical images have drawbacks, such as the image's variability, quality, and complexity. We developed image preprocessing scenarios using Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and the hybrid approaches (HE-CLAHE and CLAHE-HE). We propose CNN with image enhancement for image segmentation and evaluate its performance on Lung CT-Scan and Chest X-ray datasets, which totaled 267 and 3616 images, respectively, and had ground truth. The experimental results indicate that the optimal cumulative distribution function (CDF) value of HE is 0 to 39, and the clip limit of CLAHE is 0.01. CNN produces the best segmentation with the addition of the CLAHE-HE approach. This method can increase the accuracy by 1.23 percentage points (training) and 3.22 percentage points (testing) for Lung CT-Scan images. Meanwhile, for Chest X-ray images, the training and testing accuracy increased by 1.58 and 0.96 percentage points. In addition, the proposed medical image segmentation approach using the CNN method with CLAHE-HE obtained the values of comparative coefficients DSC (dice similarity coefficient), and SSIM (structural similarity index measurement) of only about 0.92 and 0.97, respectively. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： CNN CT-Scan Histogram Analysis Image Enhancement Medical Image Segmentation X-Ray

来源：评论

学校读者我要写书评

暂无评论

A Review and Analysis of Localization Techniques in Underwater Wireless Sensor Networks

引用

computers, Materials & Continua 2023年第6期75卷 5697-5715页

作者： Seema Rani Anju Anupma Sangwan Krishna Kumar Kashif Nisar Tariq Rahim Soomro Ag.Asri Ag.Ibrahim Manoj Gupta Laxmi Chandand Sadiq Ali Khan Department of CSE Guru Jambheshwar University of Science&TechnologyHisar125001India Department of Hydro and Renewable Energy Indian Institute of Technology RoorkeeIndia College of Computer Science and Information Systems Institute of Business ManagementKorangi Creek RoadKarachi75190SindhPakistan Faculty of Computing and Informatics Universiti Malaysia SabahJalan UMSKota Kinabalu88400SabahMalaysia Department of Electronics and Communication Engineering JECRC UniversityJaipurRajasthanIndia Computer Science Department UBIT Karachi UniversityKarachi75270Pakistan

In recent years,there has been a rapid growth in Underwater Wireless Sensor Networks(UWSNs).The focus of research in this area is now on solving the problems associated with large-scale *** of the major issues in such a network is the localization of underwater *** is required for tracking objects and detecting the *** is also considered tagging of data where sensed contents are not found of any use without *** is useless for application until the position of sensed content is *** article’s major goal is to review and analyze underwater node localization to solve the localization issues in *** present paper describes various existing localization schemes and broadly categorizes these schemes as Centralized and Distributed localization schemes ***,a detailed subdivision of these localization schemes is ***,these localization schemes are compared from different *** detailed analysis of these schemes in terms of certain performance metrics has been discussed in this *** the end,the paper addresses several future directions for potential research in improving localization problems of UWSN.

关键词： Underwater wireless sensor networks localization schemes node localization ranging algorithms estimation based prediction based

来源：评论

学校读者我要写书评

暂无评论

Annealing-Based Optimization for Selecting Training Space in Ensemble Learning 10

Annealing-Based Optimization for Selecting Training Space in...

引用

10th International Conference on Advanced informatics: Concept, Theory and Application, ICAICTA 2023

作者： Yulianti, Lenny Putri Trisetyarso, Agung Santoso, Judhi Surendro, Kridanto School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia School of Computer Science Bina Nusantara University Department of Mathematics Jakarta Indonesia

ISBN: (纸本)9798350329919

Ensemble learning integrates many learners to achieve better performance, however, it can increase the complexity dramatically. Redundant learners should be pruned to reduce ensemble complexity while allowing for increased accuracy. There are two common ways to achieve this, which include selecting the optimal training space and the optimal trained learners. This study contributes to reducing redundant learners by selecting the optimal training space using annealing-based optimization. The optimal training space was defined by 1) measuring the similarity between training spaces (clusters) and 2) searching for the best set of training spaces by minimizing the similarity between the selected training spaces. The proposed method was tested on 10 datasets from the UCI repository and compared to five state-of-The-Art random subspace methods. The results showed that the proposed method could reduce the size of the ensemble while significantly increasing its accuracy. © 2023 IEEE.

关键词： Annealing

来源：评论

学校读者我要写书评

暂无评论

Depth and Pitch Control of Autonomous Underwater Glider Using Model Predictive Control with ARX Model

Depth and Pitch Control of Autonomous Underwater Glider Usin...

引用

2023 International Conference on Electrical Engineering and informatics, ICEEI 2023

作者： Jeremy, Jason Hidayat, Egi Muhammad Idris Siregar, Simon Trilaksono, Bambang Riyanto Habibullah, Natsir School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Telkom University Faculty of Applied Science Department Computer Engineering Bandung Indonesia

ISBN: (纸本)9798350381290

Autonomous Underwater Gliders (AUGs) are extensively developed vehicles capable of prolonged exploration and observation in complex marine environments. Control of the AUG is challenging due to its slow response system and its constraints. In this research, a linear model representation of AutoRegressive eXogenous input (ARX) will be constructed using input and output data from the AUG system, built Model Predictive Control (MPC), analyzed the performance, comparing with traditional Proportional-Integral-Derivative (PID). The objective is to enhance setpoint tracking accuracy and minimize energy to extend exploration time while faced with constraints. Simulation results reveal MPC exhibits potential setpoint tracking, low overshoot as low as 0.6% up to 0.3m/s maximum depth rate, has relatively low input changes indicating good efficiency compared to PID. MPC approach effectively addresses slow response systems, managing momentum, and handling actuator constraints commonly encountered in AUG. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Palm Oil Maturity Classification Using K-Nearest Neighbors Based on RGB and L*a*b Color Extraction 27

Palm Oil Maturity Classification Using K-Nearest Neighbors B...

引用

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Saifullah, Shoffan Prasetyo, Dessyanto Boedi Indahyani Drezewski, Rafal Dwiyanto, Felix Andika Institute of Computer Science AGH University of Science and Technology Kraków Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta Indonesia

This study aims to classify the maturity level of oil palm using the K-Nearest Neighbors (KNN) method based on the extraction of RGB and L*a*b color features. This classification determines the optimal oil production based on the color of the palm. However, this process is often carried out by humans, so sorting is not optimal because it is done manually, and it takes a long time. Thus, we propose automatic detection using machine learning based approach. In this study, the image processing methods are used to classify the level of oil palm maturity. The process starts with taking 150 photos with a smartphone. Each of them is then grouped into 3 classes, namely ripe (50), intermediate (50), and unripe (50). The oil palm image is pre-processed using the segmentation method (removing background), resizing, and cropping. Then, color features using RGB and L*a*b are extracted. Each of these extracted color features becomes input in the training and testing process of the KNN algorithm and is validated using k-fold cross-validation, with the results of accuracy being 95.4% and 97.4%. The combination of KNN and L*a*b color extraction approaches has better accuracy than KNN and RGB in terms of model accuracy (by 2-4.8 percentage points). © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Color Extraction Image Processing K-Nearest Neighbors L*a*b Palm Oil Maturity Classification RGB

来源：评论

学校读者我要写书评

暂无评论

Learning teamwork based on leader’s instructions and coercion in the continuous space pursuit problem

引用

Transactions of the Japanese Society for Artificial Intelligence 2021年第5期36卷 1-10页

作者： Matsunami, Natsuki Okuhara, Shun Ito, Takayuki Department of Computer Science Nagoya Institute of Technology Japan Department of Social Informatics Kyoto University Japan

In multi-agent environments, reinforcement learning (RL) has shown strong potential especially with the recent developments. However, there exist different difficulties in developing cooperation among learning agents in practical environment, typically that includes continuous space, partial observability and competitive situation. Therefore, in this research, we focus on the cooperative behavior on Predator-Prey game which is widely used as one of the typical simulations of Multi-agent environment. Especially, we focus on predators that their goal is to catch a prey. We propose Leader-Follower model that employs leader’s instruction and coercion, and investigate how they cooperate with each other to achieve their goal considering the prey’s policy using a model of RL. To train policies in an effective manner, we applied curriculum learning during learning process. Evaluation and analysis of cooperation in dynamic environment is also challenging. We use agents’ trajectory to evaluate predators’ team performance in addition to the total number of capturing prey. We confirmed that our proposed method can introduce effective teamwork of predators through learning. © 2021, Japanese Society for Artificial Intelligence. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Role of Enabling Technologies in Soft Tissue Engineering: A Systematic Literature Review

引用

IEEE Engineering Management Review 2022年第4期50卷 155-169页

作者： Sood, Sandeep Kumar Rawat, Keshav Singh Sharma, Girish National Institute of Technology Kurukshetra Department of Computer Applications Haryana Kurukshetra136119 India Central University of Haryana Computer Sciences and Information Technology Haryana Mahendragarh123031 India Central University of Himachal Pradesh School of Mathematics Computers and Information Science Computer Science and Informatics Himachal Pradesh Dharamshala176215 India

3D printing processes employed in soft tissue engineering are rapidly evolving and gaining commercialization for the artificial synthesis of organs and tissues to bridge the gap of the supply of organ donors and healthcare systems worldwide. This article intends to analyze the current use of Industry 4.0 enabling technologies viz;cloud manufacturing, Internet of Medical Things, soft robotics, and cyber-physical system in tissue engineering from the perspective of the development of soft tissue using novel biomaterials, different approaches/techniques involving 3D printing, benefit to society, and supply chain management. A systematic literature review is conducted on the dataset of Scopus indexed scientific literature since inception, which provides insights on critical concepts, present status, research frontiers and possible adoption challenges. This article provides managerial significance to the business managers and practitioners in terms of latest research developments, strategy formulation, opting of best business model, cause-effect relationships, and help the organizations to focus for achieving a path of circular economy, simulation, collaboration, monitoring, prediction, and optimized production planning and control, stimuli-response traits and biodegradability of biomaterials, efficiency, reliability and safety of scaffolds, and faster development by way of smart manufacturing. © 1973-2011 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning for Mirai botnet detection based on long short-term memory and XGBoost

引用

International Journal of Cognitive Computing in Engineering 2024年第1期5卷 153-160页

作者： Vajrobol, Vajratiya Gupta, Brij B. Gaurav, Akshat Chuang, Huan-Ming Institute of Informatics and Communication University of Delhi India International Center for AI and Cyber Security Research and Innovations. Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Ronin Institute MontclairNJ United States Department of Information Management National Yunlin University of Science and Technology Yunlin Taiwan Symbiosis International University Pune India Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Dehradun India

In today's world, where digital threats are on the rise, one particularly concerning threat is the Mirai botnet. This malware is designed to infect and command a collection of Internet of Things (IoT) devices. The use of Mirai attacks has intensified in recent times, thus threatening the smooth operation of numerous devices that are connected to a network. Such attacks carry adverse consequences that include interference with services or the leakage of confidential information. To fight this growing threat, smart and flexible detection techniques are required to counter the new methods cyber attackers use. The aim of this research is to develop a resilient defense against Mirai botnet attacks. The Long Short Term Memory term (LSTM) and XGBoost combined have the best performance of 97.7% accuracy score. With this combination, the aim is to strengthen our cyber defenses against sophisticated and dynamically operating Mirai botnets to further enhance the security of our digital world. © 2024

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

Examining the Effectiveness of Academic Title Verification: A Case Study 24th

Examining the Effectiveness of Academic Title Verification: ...

引用

24th International Multidisciplinary Conference on Reliability and Statistics in Transportation and Communication, RelStat 2024

作者： Panges, Ioannis Liagkou, Vasiliki Stamatiou, Yannis Stylios, Chrysostomos Department of Informatics and Telecommunications of the University of Ioannina Kostakoi Arta Greece Computer Technology Institute and Press "Diophantus" Rio Greece Business Administration Department of the University of Patras Patras Greece ATHENA Research Center Institute of Industrial System Patras Patras Greece

ISBN: (纸本)9783031875311

In the ever-changing realm of identity management, the incorporation of privacy-preserving technologies has become increasingly vital. Despite significant advancements in identity management systems and access control mechanisms designed to protect user data in accordance with recent GDPR guidelines, their implementation faces challenges due to complexity and non-compliance with existing identity management standards. Furthermore, the absence of user-friendly interfaces in these systems hinders widespread adoption, highlighting a critical flaw in their design and usability. In this paper, we present a use-case scenario for postgraduate and doctoral applications that utilize a highly efficient, scalable, and user-friendly identity management system that gives formal security, and privacy guarantees to all parties. The goal is to enhance the user experience and promote the adoption of best practices in the field. This system empowers users by allowing them to control their digital identities through secure, decentralized storage of verifiable credentials on their mobile devices. We hope this work will be a significant step forward in the evolution of identity management, offering a more secure and user-friendly alternative to existing systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis and Remediation of Insecure Direct Object References (IDOR) Vulnerabilities in Android APIs 1

Comprehensive Analysis and Remediation of Insecure Direct Ob...

引用

1st IEEE International Conference on Cryptography, informatics, and Cybersecurity, ICoCICs 2023

作者： Yulianto, Semi Abdullah, Roni Reza Soewito, Benfano Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia National Institute of Science and Technology Faculty of Informatics Engineering Jakarta12630 Indonesia Bina Nusantara University Binus Graduate Program. Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350339437

The escalating visibility of secure direct object reference (IDOR) vulnerabilities in API security, as indicated in the compilation of OWASP Top 10 API Security Risks, highlights a noteworthy peril to sensitive data. This study explores IDOR vulnerabilities found within Android APIs, intending to clarify their inception while evaluating their implications for application security. This study combined the qualitative and quantitative approaches. Insights were obtained from an actual penetration test on an Android app into the primary reasons for IDOR vulnerabilities, underscoring insufficient input validation and weak authorization methods. We stress the frequent occurrence of IDOR vulnerabilities in the OWASP Top 10 API vulnerability list, highlighting the necessity to prioritize them in security evaluations. There are mitigation recommendations available for developers, which recognize its limitations involving a possibly small and homogeneous selection of tested Android applications, the testing environment that could cause some inaccuracies, and the impact of time constraints. Additionally, the study noted insufficient threat modeling and root cause analysis, affecting its generalizability and real-world relevance. However, comprehending and controlling IDOR dangers can enhance Android API security, protect user data, and bolster application resilience. © 2023 IEEE.

关键词： Sensitive data

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：