检索结果-内蒙古大学图书馆

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Choudhary, Doddapaneni Meghana Ashwini, Bugata Sai Rasagna Devi, Kavuluri Leela Kedareswari, Kotte Kiran, Musunuru Hari Srinivas, Pvvs Koneru Lakshmaiah Education Foundation Department of Computer Science and Information Technology Andhra Pradesh Vaddeswaram522502 India Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Data Science Andhra Pradesh Vaddeswaram522502 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522502 India

ISBN: (纸本)9798350367720

This study focuses on the use of ml techniques to unravel the complexity of lymph node classification, which is an important part of oncology due to its different subtypes and different treatments. This study aims to develop an accurate classification model for different types of lymphoma using image datasets in the "TRAIN_DIR"and "TEST_DIR"maps. The research combines methods such as support vector machine (SVM), decision trees, logistic regression, and naive Bayes and performs rigorous and effective training methods to optimize the performance of models. Advanced preprocessing methods and data augmentation techniques are used to improve the model's ability to detect subtle changes in biopsy images, ultimately aiming to increase diagnostic accuracy and support self-healing strategies. This approach has the potential to improve clinical decision-making and patient care in lymphoma management. Diagnose and fix problems. The study combined machine learning algorithms to analyze biopsy images to accurately classify lymphoma subtypes. The training model focuses on improving the sensitivity and specificity of subtype detection, which is important for creating an effective patient-based treatment plan. Using the computational power of support vector machines, decision trees, logistic regression, and naive Bayes, this research can help improve oncology diagnostic tools, reducing diagnostic uncertainty and supporting more treatments. The aim of this research is to advance the work of personalized medicine by creating a powerful computational model that can reliably distinguish between lymphoma subtypes. By automating and improving the accuracy of subtype classification through machine learning, the research aims to streamline diagnostic workflows and help make timely diagnostic decisions. © 2024 IEEE.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

"Nyctophy": Assessing the effectiveness of serious game for nyctophobia based on virtual reality by usability and heart rate monitoring

引用

Procedia computer science 2024年 245卷 185-192页

作者： Elshad Ryan Ardiyanto Patrick Alexander Edyth Novian Putra Dimas Ramdhan Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta

Nyctophobia is a phobia of the dark and is common among children but also found in adults. While the phobia itself is commonly known, the diversity of its treatment is still minimal. As technology has reached its highest point, numerous inventions and innovations have emerged in the medical sector. This study aimed to examine the usability of Virtual Reality and Keyboard and Mouse as an interface using the Extended Reality Game Usability Questionnaire (XR-GUQ) in Nyctophobia therapy and to analyze the heart rate response, impact, and implications using t-test Paired/Wilcoxon Signed Rank. Thirty-four Bina Nusantara University students from various backgrounds completed the test using interfaces and a smartwatch. They were divided into two groups, high- and low fear, using the modified Acrophobia Questionnaire (AQ), which resulted in a significant difference. The XR-GUQ result was insignificant in all variables, which indicates similar usability scores on both interfaces. The t-test Paired/Wilcoxon Signed Rank test revealed a significant difference between the high- and low-fear groups when using the Virtual Reality interface compared to the Keyboard and Mouse interface. This significant difference was found within each group regardless of the interface used. This research shows similar scores in terms of usability but a significant difference in heart rate response with the help of a serious game to give a new sensation of phobia therapy.

关键词： Nyctophobia Virtual Reality Keyboard and Mouse Usability Heart Rate Serious Game Effectiveness

来源：评论

学校读者我要写书评

暂无评论

A Study Of Dynamic Thresholds Power Detection Spectrum Sensing Techniques In CRN 9

A Study Of Dynamic Thresholds Power Detection Spectrum Sensi...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Keerthika, J. AnandaKumar, H. Priya, V. Yuvalatha, S. Gayathri, N. Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Dr NGP Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Business System Sathyamangalam India

ISBN: (纸本)9798350397376

A Cognitive radio is the mobile communication technologies which help to utilize the efficient need of radio spectrum origin. The performance of CRN is significantly impacted by the spectrum sensing function. The problem of bandwidth has risen as a more specific one with breakthroughs in remote communications. By forgiving unlicensed users to usage the available spectrum in primary networks is the solution to the CR Technology. An innovative method for enhancing the electromagnetic spectrum's use efficiency, cognitive radio is a encouraging technology. Spectrum sensing has high spectral resolution capabilities and aids in the detection of the spectrum holes. The various methodologies are used to enhance the spectrum sensing essence. These techniques are distinguished by a sensing threshold, which is crucial to the performance of the sensing. The most important element in selecting the best threshold to optimize spectrum sensing performance is the dynamic threshold in the proposed system's spectrum detection algorithm. The energy earned from the licensed user over a precise time of observation, then the dynamic threshold is commutated between two levels. The estimation of the noise ambiguity factor forms the basis for threshold evaluations. These criteria are used to hike the likelihood of detection and contraction the possibility of false alarms. © 2023 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

SELF-JOINT SUPERVISED LEARNING 10

SELF-JOINT SUPERVISED LEARNING

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Kardan, Navid Hill, Mitchell Shah, Mubarak Center for Research in Computer Vision Department of Computer Science Department of Statistics and Data Science University of Central Florida United States

Supervised learning is a fundamental framework used to train machine learning systems. A supervised learning problem is often formulated using an i.i.d. assumption that restricts model attention to a single relevant signal at a time when predicting. This contrasts with the human ability to actively use related samples as reference when making decisions. We hypothesize that the restriction to a single signal for each prediction in the standard i.i.d. framework contributes to well-known drawbacks of supervised learning: making overconfident predictions and vulnerability to overfitting, adversarial attacks, and out-of-distribution data. To address these limitations, we propose a new supervised learning paradigm called self-joint learning that generalizes the standard approach by modeling the joint conditional distribution of two observed samples, where each sample is an image and its label. Rather than assuming samples are independent, our models explicitly learn the sample-to-sample relation of conditional independence. Our framework can naturally incorporate auxiliary unlabeled data to further improve the performance. Experiments on benchmark image datasets show our method offers significant improvement over standard supervised learning in terms of accuracy, robustness against adversarial attacks, out-of-distribution detection, and overconfidence mitigation. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Service Oriented Fuzzy Decision Model for Road Traffic Engineering 9

Service Oriented Fuzzy Decision Model for Road Traffic Engin...

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Utama, Ditdit Nugeraha Zaki, Fauzan Affan Munjeri, Intan Juliani Putri, Nidya Utami Bina Nusantara University BINUS Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia UIN Syarif Hidayatullah Information Systems Department Jakarta Indonesia

ISBN: (纸本)9798350370126

A number of attempts have already been implemented formally to solve road traffic congestion. However, the objective strategy type of road traffic engineering could not be proven truly. Try and error is one inefficient way in road traffic engineering to degrade the level of congestion. The study was conducted to propose a new service-oriented model (SOM) that combines fuzzy-logic and water flow algorithm methods (called FWFA). The method combination was operated as the main method to construct the decision model for selecting the objective strategy in road traffic engineering. Also, service-oriented architecture (SOA) is realized to implement such a constructed model practically. The Model can suggest the most optimal strategy decision in road traffic engineering. Here, a main traffic road of Juanda in area Ciputat, Tangerang Selatan, province Banten, Indonesia;was selected as a research object in this study. The constructed SOM for road traffic engineering was structurally delivered in this paper. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Critical (P5, dart) -Free Graphs 16th

Critical (P5, dart) -Free Graphs

引用

16th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2023

作者： Xia, Wen Jooken, Jorik Goedgebeur, Jan Huang, Shenwei College of Computer Science Nankai University Tianjin300071 China Tianjin Key Laboratory of Network and Data Security Technology Nankai University Tianjin300071 China Department of Computer Science KU Leuven Campus Kulak-Kortrijk Kortrijk8500 Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent9000 Belgium

ISBN: (纸本)9783031496134

Given two graphs H1 and H2, a graph is (H1, H2) -free if it contains no induced subgraph isomorphic to H1 nor H2. A dart is the graph obtained from a diamond by adding a new vertex and making it adjacent to exactly one vertex with degree 3 in the diamond. In this paper, we show that there are finitely many k-vertex-critical (P5, dart) -free graphs for k≥ 1. To prove these results, we use induction on k and perform a careful structural analysis via Strong Perfect Graph Theorem combined with the pigeonhole principle based on the properties of vertex-critical graphs. Moreover, for k∈ { 5, 6, 7 } we characterize all k-vertex-critical (P5, dart) -free graphs using a computer generation algorithm. Our results imply the existence of a polynomial-time certifying algorithm to decide the k-colorability of (P5, dart) -free graphs for k≥ 1 where the certificate is either a k-coloring or a (k+ 1 ) -vertex-critical induced subgraph. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Resisting Visual Hacking: A Novel Graphical Password Authentication System 3

Resisting Visual Hacking: A Novel Graphical Password Authent...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Jebakumar Immanuel, D. Ramalingam, V. Tharun Kumar, P. Iyer, Akash Narayanan, M.S. Karpagam Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore641 105 India Sns College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350322842

Password-based authentication is a widely used method to ensure security and privacy in computer applications. However, the selection of weak passwords and insecure input methods by users is considered the 'weakest link' in the authentication process. Instead of employing arbitrary alphanumeric sequences, individuals tend to opt for passphrases that are either mnemonic or abbreviated in nature. With the proliferation of web and mobile applications, users can access these applications at any time and from anywhere with various devices. Although this convenience is highly desirable, it also increases the likelihood of passwords being exposed to Visual Hacking. The forms of attack may be executed through either direct visual observation or the utilization of external recording devices in order to obtain the user's login information. In response to this issue, our team has devised an authentication system that centers on graphical passwords and is made to combat the threat of Visual Hacking. The system incorporates a three-layered security mechanism, comprising color and pattern matching functionalities in conjunction with password verification. This makes it highly challenging for potential attackers to deduce or limit the password even amidst numerous camera-based hacking attempts. Additionally, we have created and put to the test a prototype of the system to assess its user-friendliness. Our experimental results indicate that our system can resist Visual Hacking more effectively than previous authentication systems while still maintaining a high degree of usability and security. © 2023 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning 41

Catapults in SGD: spikes in the training loss and their impa...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhu, Libin Liu, Chaoyue Radhakrishnan, Adityanarayanan Belkin, Mikhail Department of Computer Science UCSD United States Halicioğlu Data Science Institute UCSD United States Harvard University United States Broad Institute of MIT and Harvard United States

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD).We provide evidence that the spikes in the training loss of SGD are "catapults", an optimization phenomenon originally observed in GD with large learning rates in (Lewkowycz et al., 2020).We empirically show that these catapults occur in a low-dimensional subspace spanned by the top eigenvectors of the tangent kernel, for both GD and ***, we posit an explanation for how catapults lead to better generalization by demonstrating that catapults promote feature learning by increasing alignment with the Average Gradient Outer Product (AGOP) of the true ***, we demonstrate that a smaller batch size in SGD induces a larger number of catapults, thereby improving AGOP alignment and test performance. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Selection in Associative Classification-A Review and Comparative Analysis 24

Feature Selection in Associative Classification-A Review and...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Alazaidah, Raed Al-Qerem, Ahmad Qasem, Mais Haj Al-Shaikh, Ala'a Almilli, Nabeel Injadat, MohammadNoor Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan

ISBN: (纸本)9798350384307

Feature selection is one of the most important and significant steps that highly affects the final accuracy of any classification model. It aims to determine the most significant features that help in accurately predicting the class label for any new case. This research aims to survey and identify the best feature selection method that suits algorithms belong to Associative Classification (AC). Hence, nine different feature selection methods have been evaluated and compared using five AC based algorithms with respect to Accuracy metric. Results revealed that ABB-IEP and ABB-LIU methods show the best performance with datasets that contain nominal features only, while Relief feature selection method showed the best Accuracy with datasets that comprise Real and Integer features. © 2023 IEEE.

关键词： associative classification classification data mining data science feature selection pre-processing

来源：评论

学校读者我要写书评

暂无评论

Towards an integrated risk analysis security framework according to a systematic analysis of existing proposals

引用

Frontiers of computer science 2024年第3期18卷 199-216页

作者： Antonio SANTOS-OLMO Luis Enrique SÁNCHEZ David G.ROSADO Manuel A.SERRANO Carlos BLANCO Haralambos MOURATIDIS Eduardo FERNÁNDEZ-MEDINA GSyA Research Group University of Castilla-La ManchaCiudad Real 13071Spain Institute for Analytics and Data Science University of EssexColchester CO43SQUK Alarcos Research Group University of Castilla-La ManchaCiudad Real 13071Spain ISTR Research group Department of Computer Science and ElectronicsUniversity of CantabriaSantander 39005Spain

The information society depends increasingly on risk assessment and management systems as means to adequately protect its key information *** availability of these systems is now vital for the protection and evolution of ***,several factors have led to an increasing need for more accurate risk analysis *** are:the speed at which technologies evolve,their global impact and the growing requirement for companies to *** analysis processes must consequently adapt to these new circumstances and new technological *** objective of this paper is,therefore,to present the results of an exhaustive analysis of the techniques and methods offered by the scientific community with the aim of identifying their main weaknesses and providing a new risk assessment and management *** analysis was carried out using the systematic review protocol and found that these proposals do not fully meet these new *** paper also presents a summary of MARISMA,the risk analysis and management framework designed by our research *** basis of our framework is the main existing risk standards and proposals,and it seeks to address the weaknesses found in these *** is in a process of continuous improvement,as is being applied by customers in several European and American *** consists of a risk data management module,a methodology for its systematic application and a tool that automates the process.

关键词： information security management security system security risk assessment and 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：