检索结果-内蒙古大学图书馆

A Fast and More Accurate Seed-and-Extension Density-Based Clustering Algorithm

IEEE Transactions on Knowledge and data engineering 2023年第6期35卷 5458-5471页

作者： Tung, Ming-Hao Chen, Yi-Ping Phoebe Liu, Chen-Yu Liao, Chung-Shou Research and Development Micron Technology Inc Hsinchu Taiwan Department of Computer Science and Information Technology La Trobe University Melbourne Australia Dept. Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan

Clustering algorithms have been widely studied in many scientific areas, such as data mining, knowledge discovery, bioinformatics and machine learning. A density-based clustering algorithm, called density peaks (DP), which was proposed by Rodriguez and Laio, outperforms almost all other approaches. Although the DP algorithm performs well in many cases, there is still room for improvement in the precision of its output clusters as well as the quality of the selected centers. In this study, we propose a more accurate clustering algorithm, seed-and-extension-based density peaks (SDP). SDP selects the centers that hold the features of their clusters while building a spanning forest, and meanwhile, constructs the output clusters in a seed-and-extension manner. Experiment results demonstrate the effectiveness of SDP, especially when dealing with clusters with relatively high densities. Precisely, we show that SDP is more accurate than the DP algorithm as well as other state-of-the-art clustering approaches concerning the quality of both output clusters and cluster centers while maintaining similar running time of the DP algorithm, particularly for a variety of time-series data. Moreover, SDP outperforms DP in the dynamic model in which data point insertion and deletion are allowed. From a practical perspective, the proposed SDP algorithm is obviously helpful to many application problems. © 1989-2012 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Hardware Deployable Classifier for Invasive Ductal Carcinoma using Tiny Machine Learning Model 16

Hardware Deployable Classifier for Invasive Ductal Carcinoma...

引用

16th International Conference on Sensing Technology, ICST 2023

作者： Gupta, Aham Gautam, Kanak Singh, Yash Pratap Singh, Bhoomika Wajid, Mohd Usman, Mohammed Aligarh Muslim University Zhcet Dept. of Electronics Engineering Aligarh India Aligarh Muslim University Zhcet Dept. of Electrical Engineering Aligarh India Galgotias College of Engg. & Tech Dept. of Computer Science Greater Noida India King Khalid University Dept. of Electrical Engineering Abha61411 Saudi Arabia

ISBN: (纸本)9798350395341

Breast Cancer is a global health concern, emphasizing the crucial importance of its early detection in improving patient treatment. This is especially true for the most frequently diagnosed type of breast cancer, Invasive Ductal Carcinoma (IDC), which has a high risk of spreading and significant mortality. Automation provides an opportunity to streamline the detection, improving efficiency and minimizing diagnostic errors. In this research paper, we proposed a low-computational Tiny Machine Learning (TinyML) model for the classification of IDC. Conventional methods for IDC classification, such as histopathological analysis and mammography, are time-consuming, costly, and subjective. Therefore, there is a need for an automated and accurate method for IDC classification that can be applied in a resource-limited environment. Our proposed TinyML model takes digital images of whole-mount breast cancer slide specimens and extracts the features necessary to classify them as IDC-(-ve) or IDC-(+ve). The TinyML model is evaluated using a publicly available dataset of Breast Histopathology Images and compared to the other Deep Learning (DL) models based on accuracy and computational complexity. The results show that our model achieved a high accuracy of 89.3% while maintaining limited processing power and memory. The successful deployment of the model on an embedded system like Raspberry Pi demonstrates that our TinyML model can be used in hardware resource- constrained environments, promising improved cancer diagnosis. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Effective Method to Detect DHCP Starvation Attack using Port Scanning

An Effective Method to Detect DHCP Starvation Attack using P...

引用

Next-Generation Computing, IoT and Machine Learning (NCIM), International Conference on

作者： Asaduzzaman Jony Abu Saleh Musa Miah Muhammad Nazrul Islam Dept. of Computer Science and Engineering Bangladesh University of Professionals (BUP) Dhaka Bangladesh Dept. of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan Dept. of Computer Science and Engineering Military Institute of Science and Technology (MIST) Dhaka Bangladesh

Nowadays, the DHCP starvation attack is a crucial attack that denied the services for the legitimate network user where the attacker mainly occupies all the IP addresses in the DHCP server pool. Most of the existing studies proposed ICMP (Internet Control Message Protocol) and the ARP (Address Resolution Protocol) based techniques to detect the DHCP starvation attack. However, the ICMP-based detection is ineffective if the client has an active host-based firewall that blocks the ICMP ECHO REQUEST, while the ARP-based detection does not work for DHCP networks separated by a DHCP relay agent and works only within the same or local network. Therefore, the objective of this research is to propose an effective technique to detect DHCP starvation attack detection through port scanning to address the limitations of ICMP and ARP-based detection methods. To attain this objective, this study first highlights the limitations of existing detection methods demonstrating insightful facts. Secondly, the study proposed a port scan-based DHCP starvation attack detection method for local and remote (relay) DHCP networks. Finally, the effectiveness and validation of the proposed techniques were demonstrated using the Multivendor Network Emulation Software (EVE-NG). The study showed that the proposed port scanning-based technique could accurately detect the DHCP starvation attack while overcoming the limitations of the ICMP and ARP techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OSHA: A General-purpose and Next Generation One-way Secure Hash Algorithm 22

OSHA: A General-purpose and Next Generation One-way Secure H...

引用

22nd IEEE/ACIS International Conference on computer and Information science, ICIS 2022

作者： Patgiri, Ripon National Institue of Technology Silchar Dept. of Computer Science & Engineering Assam Cachar788010 India

ISBN: (数字)9781665494632

ISBN: (纸本)9781665494632

Secure hash functions are widely used in cryptographic algorithms to secure against diverse attacks. A one-way secure hash function is used in the various research fields to secure, for instance, blockchain. Notably, most of the hash functions provide security based on static parameters and publicly known operations. Consequently, it becomes easier to attack by the attackers because all parameters and operations are predefined. The publicly known parameters and predefined operations make the oracle regenerate the key even though it is a one-way secure hash function. Moreover, the sensitive data is mixed with the predefined constant where an oracle may find a way to discover the key. To address the above issues, we propose a novel one-way secure hash algorithm, OSHA for short, to protect sensitive data against attackers. OSHA depends on a pseudo-random number generator to generate a hash value. Particularly, OSHA mixes multiple pseudo-random numbers to produce a secure hash value. Furthermore, OSHA uses dynamic parameters, which is difficult for adversaries to guess. Unlike conventional secure hash algorithms, OSHA does not depend on fixed constants. It replaces the fixed constant with the pseudo-random numbers. Also, the input message is not mixed with the pseudo-random numbers;hence, there is no way to recover and reverse the process for the adversaries. © 2022 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Simulating Mobile Robot Vision: An Analysis of RGB-D Versus RGB-Based Distance Accuracy and CPU Optimization

Simulating Mobile Robot Vision: An Analysis of RGB-D Versus ...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Minseok Kong Jiho Park Daye Lee Nikolaos Kourtzanidis Jungmin So Dept. Computer Science and Engineering Sogang University Seoul South Korea Dept. Artificial Intelligence Dongguk University Seoul South Korea Dept. Data Science Seoul National University Seoul South Korea Cyberworks Robotics Toronto Canada

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

From the perspective of mobile robot vision, to facilitate secure and seamless interactions between the robot and its environment, it is paramount to attain precise and metic-ulous distance estimation between the robot and the detected entities. Moreover, in the absence of GPUs, mobile robots are compelled to rely solely on CPU resources to manage vision-related tasks and other operational imperatives. To address the challenges above, we focused on reducing CPU usage in the vision system and analyzing distance estimation accuracy in two scenarios: leveraging RGB-D and RGB cameras. We executed real-time object detection targeting humans utilizing YOLOv8 Nano, subsequently undertaking a comparative analysis between the distance estimates derived through monocular dept. estimation using a MobileNetV2 model, trained on the KITTI dataset, and the distance measurements obtained from RGB-D cameras. Additionally, we optimized the deep learning models to reduce CPU usage, employing a hardware-specific technique, OpenVINO conversion, and both a hardware-specific and a hardware-agnostic strategy, Post-Training Quantization (PTQ). Consequently, we reduced CPU utilization by approximately 4.62% in the RGB-D scenario and 5.32% in the RGB scenario.

关键词： Accuracy Machine vision dept. measurement Robot vision systems Estimation Object detection Cameras Real-time systems Mobile robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis and Visualization of Eye movements in Patients with Glaucoma 7

Analysis and Visualization of Eye movements in Patients with...

引用

7th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2022

作者： Sandhiya, B. Amudha, J. Krishnan, Sajitha Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9781665489102

Glaucoma is one of the foremost causes that result in irreversible blindness. World Health Organisation (WHO) has estimated that around 4.5 million people are blind due to glaucoma. This vast number is because more than 90% of glaucoma cases are undiagnosed. Early-stage glaucoma detection system helps to identify the disease and prevent it from further blindness. The proposed system analyzed and visualized the eye movement patterns of glaucoma-affected participants using machine learning algorithms. The model collected eye-gaze patterns using an eye-tracking sensor and visualized them based on different eye gaze features. The model classified glaucoma and normal based on eye gaze data. The proposed model has incorporated different visualization techniques to understand how eye gaze patterns of normal and glaucoma differ while performing screen-based tasks such as Free-Viewing Task and Image Searching Task. The proposed system has also incorporated an interactive dashboard using Microsoft PowerBI Software. © 2022 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Manhole dept. Analysis and Logistics Planning using TA-Enabled IoT Cloud 7

Manhole Depth Analysis and Logistics Planning using TA-Enabl...

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Bhagyalakshmi, M. Benedict, Shajulin Indian Institute of Information Technology Kottayam Dept. of Computer Science and Engineering Kerala 686635 India

ISBN: (纸本)9781665421683

Smart cities have marked an incessant push to modernize technologies for easing citizens. Smarter manholes and planning the associated logistics have become a crucial component for assisting city authorities while coining decisions. This article proposes an automatic manhole dept. analysis system using sensors mounted on manhole units. The sensor data collected in cloud services are utilized to schedule logistics using the proposed Threshold Acceptance (TA) algorithm. The algorithm attempts to minimize the distance between manhole operation sites and to improve the cost efficiencies associated with the operations. The proposed method was experimented at the IoT Cloud Research laboratory;the proposed TA-enabled logistics schedule produced a faster logistics plan to rectify manhole issues of streets based on the IoT-enabled monitoring system. The experiments manifested the cost efficiency improvement of over 38 percent and distance efficiency of over 78 percent when compared to the traditional approaches of handling manhole issues. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Global COVID-19 Related Waste Challenges, Response Strategies, and Potential Opportunities

Global COVID-19 Related Waste Challenges, Response Strategie...

引用

World Environmental and Water Resources Congress 2022: Adaptive Planning and Design in an Age of Risk and Uncertainty

作者： Smith-Lambert, Leigh Ferguson, Izaria Albert, Lynal Dept. of Engineering and Computer Science Tarleton State Univ. StephenvilleTX United States

ISBN: (数字)9780784484258

ISBN: (纸本)9780784484258

As the world navigates the COVID-19 pandemic, the surge in waste generation, the varied composition of waste, and its subsequent management has presented several challenges to many communities. Waste management techniques and cultivating an awareness of the environmental and health impacts of mismanaged wastes have varied with location, economics, and priorities of the region. Risk mitigation efforts including the wearing of masks, lockdowns, and stay at home orders intended to contain the spread of the virus have resulted in several unintended environmental implications. With the rise in consumer plastic consumption, single use PPE, take away food orders, and online shopping, many households across the globe have reported an increase in waste. While developed countries have been able to approach the surge by utilizing and expanding current municipal waste management programs, countries lacking this existing infrastructure battle an increased risk of continued infection and magnified environmental issues through open landfills, groundwater contamination, and limited community awareness. Adopting appropriate methods of risk communication and encouraging participation from the public to manage waste issues is critical to protecting the environment by limiting contamination, improving community involvement in reducing landfill waste, and encouraging recycling. It is imperative to develop waste management solutions while continuing the promotion of sustainable habits, combating the current pandemic situation, and preparing for future episodic events. Our study focuses on analyzing episodic waste generation during the pandemic, management strategies adopted globally, and identifying areas of possible improvement and alternate strategies that can be implemented. © ASCE.

关键词： Groundwater

来源：评论

学校读者我要写书评

暂无评论

Predicting the Price Direction of Bitcoin Using Twitter data and Machine Learning 2

Predicting the Price Direction of Bitcoin Using Twitter Data...

引用

2nd IEEE International Conference on data science and computer Application, ICDSCA 2022

作者： Kanji, Abdul Mannan Chaudhary, Ishita Shankar, Rithika Lakshmi Srinivasa, Gowri Pes University Pes Center for Pattern Recognition Dept. of Computer Science and Engineering Bengaluru India

ISBN: (数字)9781665472005

ISBN: (纸本)9781665472005

Bitcoin is a decentralized digital currency that was intro- duced in 2009 and since then, has become increasingly popular as one of the most known and highly valued currencies. Contributing factors to its rise include crypto Twitter influencers. An engaged audience on Twitter seems to have an influence on the cryptocurrency market. In this paper, we analyze the impact that tweets have on the price of Bitcoin. Using word-clouds and candlestick plots, we gain insight into the factors that affect Bitcoin prices. We also use various machine learning techniques to automatically classify the sentiment in Tweets related to cryptocurrencies. We incorporate these and other relevant features to build and compare the performance of multiple machine learning models to predict the direction (increase or decrease) of the price of Bitcoin. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Management in Green VANETs: Ant-Inspired Routing Strategies with Local Search Optimization

Smart Traffic Management in Green VANETs: Ant-Inspired Routi...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Thangam, S. Jahnavi, M. Chandana, K. Dheeraj, K. Janet Kumari, J Jesy Saleem Raja, A. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India University of Technology and Applied Sciences-Shinas College of Computing and Information Sciences It Department Oman

ISBN: (纸本)9798350309140

Green Vehicular Ad-hoc Networks (VANETs) are gaining significance in smart mobility because of growing concerns about the environment. The research introduces a novel method for managing traffic in such networks by combining ant-inspired routing methods with local search optimization approaches. The solution, which draws inspiration from the efficient path-finding abilities of ants, facilitates decentralized communication and sharing of traffic data among cars. It allows rapid adaptation to changing traffic circumstances and environmental elements. Local search optimization enhances routing decisions by considering the near vicinity of each vehicle. Extensive simulations demonstrate notable enhancements in traffic efficiency, decreased congestion, and improved energy conservation as compared to conventional routing methods. The suggested solutions also enhance the development of environmentally friendly and enduring transportation networks. © 2024 IEEE.

关键词： Vehicular ad hoc networks

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：