检索结果-内蒙古大学图书馆

8th International Conference on computer Vision Theory and Applications, VISAPP 2013

作者： Madhogaria, Satish Schikora, Marek Koch, Wolfgang Dept. Sensor Data and Information Fusion Fraunhofer FKIE Wachtberg Germany Department of Computer Science Technical University of Munich Munich Germany

ISBN: (纸本)9789898565471

Vehicle detection in aerial images plays a key role in surveillance, transportation control and traffic monitoring. It forms an important aspect in the deployment of autonomous Unmanned Aerial System (UAS) in rescue and surveillance missions. In this paper, we propose a two-stage algorithm for efficient detection of cars in aerial images. We discuss how sophisticated detection technique may not give the best result when applied to large scale images with complicated backgrounds. We use a relaxed version of HOG (Histogram of Oriented Gradients) and SVM (Support Vector Machine) to extract hypothesis windows in the first stage. The second stage is based on discriminatively trained part-based models. We create a richer model to be used for detection from the hypothesis windows by detecting and locating parts in the root object. Using a two-stage detection procedure not only improves the accuracy of the overall detection but also helps us take complete advantage of the accuracy of sophisticated algorithms ruling out it's incompetence in real scenarios. We analyze the results obtained from Google Earth dataset and also the images taken from a camera mounted beneath a flying aircraft. With our approach we could achieve a recall rate of 90% with a precision of 94%.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals 41

SleepFM: Multi-modal Representation Learning for Sleep Acros...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Thapa, Rahul He, Bryan Kjær, Magnus Ruud Moore, Hyatt Ganjoo, Gauri Mignot, Emmanuel Zou, James Department of Biomedical Data Science Stanford University United States Department of Computer Science Stanford University United States Department of Health Technology Technical University of Denmark Denmark Department of Psychiatry and Behavioral Sciences Stanford University United States

Sleep is a complex physiological process evaluated through various modalities recording electrical brain, cardiac, and respiratory activities. We curate a large polysomnography dataset from over 14,000 participants comprising over 100,000 hours of multi-modal sleep recordings. Leveraging this extensive dataset, we developed SleepFM, the first multi-modal foundation model for sleep analysis. We show that a novel leave-one-out approach for contrastive learning significantly improves downstream task performance compared to representations from standard pairwise contrastive learning. A logistic regression model trained on SleepFM’s learned embeddings outperforms an end-to-end trained convolutional neural network (CNN) on sleep stage classification (macro AUROC 0.88 vs 0.72 and macro AUPRC 0.72 vs 0.48) and sleep disordered breathing detection (AUROC 0.85 vs 0.69 and AUPRC 0.77 vs 0.61). Notably, the learned embeddings achieve 48% top-1 average accuracy in retrieving modality clip pairs from 90,000 candidates. This work demonstrates the value of holistic multi-modal sleep modeling to fully capture the richness of sleep recordings. SleepFM is open source and available at https://***/rthapa84/sleepfmcodebase. Copyright 2024 by the author(s)

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Implementation of database Massively Parallel Processing System to Build Scalability on Process data Warehouse

引用

Procedia computer science 2018年 135卷 68-79页

作者： Fajar Ciputra Daeng Bani Suharjito Diana Abba Suganda Girsang Computer Science Department BINUS Graduate Program- Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

The problem with telecommunications companies today is that transactional data is more extensive than existing source tables. This makes business reporting less efficient and overwhelms query processing results in data warehouses so that they do not meet business requirements. The fast and complex evolution of the digital world must be scalable to the data warehouse process, so that the authors implement it in the data warehouse using massive parallel processing (MPP) with the Greenplum database, so that business users can get reports faster and more optimally. This case study explains how the MPP system implements and measures the performance of the Greenplum database by performing complex queries in the data warehouse with parallel processing. Therefore, this case study analyzes whether the use of MPP systems can measure the scalability of throughput and the response time in the data warehouse so that system performance in the Greenplum database remains stable for daily, weekly, and monthly operations.

关键词： data Warehouse Massively parallel processing Greenplum ETL

来源：评论

学校读者我要写书评

暂无评论

A Modal Distribution Study of Violin Vibrato 23

A Modal Distribution Study of Violin Vibrato

引用

23rd International computer Music Conference, ICMC 1997

作者： Mellody, Maureen Wakefield, Gregory H. Applied Physics Program University of Michigan United States Department of Electrical Engineering and Computer Science University of Michigan United States

A high-resolution time-frequency distribution is applied to the study of violin vibrato. Our analysis indicates that the frequency modulation induced by the motion of the stopped finger on the string is accompanied by a significant amplitude variation in each partial of that note. We suggest that this amplitude modulation results from the densely-spaced wood resonances of the violin body. Amplitude and frequency estimates for each partial are extracted from the time-frequency surface and used in an additive resynthesis model to generate synthesized violin vibrato. © 1997 International computer Music Conference, ICMC Proceedings. All rights reserved.

关键词： computer music

来源：评论

学校读者我要写书评

暂无评论

Analysis and Classification of Network Security Attacks Using Domain Generation Algorithm

Analysis and Classification of Network Security Attacks Usin...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Gomathi, S. Samundeeswari, S. Ponmanirai, S. Nanthini, S. Vandayar Engineering College Department of Computer Science and Engineering Thanjavur India Saveetha School of Engineering Simats University Department of Computational Intelligence Thandalam India Saveetha School of Engineering Simats University Department of Department of Data Science Thandalam India

ISBN: (纸本)9798350313987

In the realm of cybersecurity, the evolution of network attacks necessitates innovative approaches for threat prediction and mitigation. Traditional methods often fall short in identifying novel attack patterns or adapting swiftly to emerging threats. This study explores the application of Domain Generative Algorithms (DGAs) in the context of network attack prediction. DGAs leverage advanced machine learning techniques to generate synthetic data samples representing various network attack scenarios. By training generative models on diverse and large-scale datasets comprising both historical attack data and benign network traffic, the algorithms learn intricate patterns intrinsic to different types of attacks. Through, systematic analysis of these synthetic attack instances, IDS and IPS algorithms can be fine-tuned to recognize subtle attack patterns that might elude conventional signature-based detection methods. This research underscores the pivotal role of DGAs in revolutionizing the landscape of network attack prediction. By harnessing the power of generative algorithms, organizations can proactively strengthen their cybersecurity posture, effectively mitigating the risks posed by an ever-evolving spectrum of network attacks. © 2023 IEEE.

关键词： data Traffic Denial of Services Domain Generation Algorithm Malware Network security Pattern Analysis

来源：评论

学校读者我要写书评

暂无评论

On database intrusion detection: A query analytics-based model of normative behavior to detect insider attacks 2017

On database intrusion detection: A query analytics-based mod...

引用

7th International Conference on Communication and Network Security, ICCNS 2017

作者： Khan, Lmuhammad Imran Foley, Simon N. Sullivan, Barry O. Insight Centre for Data Analytics Department of Computer Science University College Cork Ireland IMTAtlantique LabSTICC Universite Bertange Loire Rennes France

ISBN: (纸本)9781450353496

One of the challenges in database security is timely detection of an insider attack. This gets more challenging in the case of sophisticated/expert insiders. Behavioral-based techniques have shown promising results in detecting insider attacks. Most of the behavioral-based techniques consider a query in isolation in order to model an insider's normative behavior thus only detecting malicious behavior that is limited to single query. A recently proposed approach considers sequences of queries to model an insider's normative behavior by using n-grams that capture shortterm correlations in an application [1]. However, behavioral-based approaches, including the n-gram approach, are vulnerable to mimicry attacks whereby a sophisticated inside attacker can craft a sequence of statements to mimic normal behavior as a set of legitimate transactions. Thus, a mechanism to detect this types of mimicry attack is desirable. In this paper, we first demonstrate an example mimicry attack on an n-gram based approach and then propose a behavioral-based technique that facilitate its detection. The proposed technique complements existing behavioral-based approaches including the n-gram approach and it can be deployed independently. Experiments are presented whereby a queryanalytics model is used to construct normative behavior from query logs of a synthetic banking application system. Initial results indicate that the proposed model to construct normative behavior is effective in detecting insider attacks conforming to a demonstrated mimicry attack. © 2017 Association for Computing Machinery.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

On computing aggregate functions for nested historical relations in heterogeneous databases environment

On computing aggregate functions for nested historical relat...

引用

2005 International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA'05

作者： Chung, Ping-Tsai Hsiao, Hsin-Hua Department of Computer Science Long Island University NY United States American Express Corp Data Warehousing Group NY United States

ISBN: (纸本)9781932415605

We study a generalization nested relational databases which are managing temporal variation of complex objects with imprecise information in heterogeneous databases environment. It combines the research in nested relational databases, temporal databases, and corporate data warehousing for database applications. We define and extend a set of temporal relational aggregate operators over nested historical relational data model. Properties and computations of these aggregate functions are showed. Finally, we discuss the computational complexities for computing some temporal relational aggregate operators over nested historical relational database model.

关键词： data warehouses

来源：评论

学校读者我要写书评

暂无评论

Human Anatomy Learning Systems Using Augmented Reality on Mobile Application

引用

Procedia computer science 2018年 135卷 80-88页

作者： Michael H Kurniawan Suharjito Diana Gunawan Witjaksono Computer Science Department BINUS Graduate Program- Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Students generally experience difficulties in learning human body anatomy due to constraints to visualize the body anatomy from 2D into 3D image. This research aims to develop a human anatomy learning system using augmented reality technology. By using this system, it is expected that students can easily understand the anatomy of the human body using a 3D image visualization. The method used in this system is augmented reality marker on mobile computing platform. The marker is captured by taking a picture. Then, the captured image is divided into pieces and the pattern is matched with images stored in the database. In this research, we use Floating Euphoria Framework and combine it with the SQLite database. Augmented reality anatomy system of the human body has features that can interactively display the whole body or parts of the human organs. To evaluate the usefulness of the application, we tested the augmented reality anatomy system with high school students and medical students for learning the anatomy of the human body. The results show that the human anatomy learning system with interactive augmented reality visualization helps students learn human anatomy more easily.

关键词： Augmented Reality Human Anatomy Learning Android Application

来源：评论

学校读者我要写书评

暂无评论

The Contribution of Assessment Platform Technology to Promote Teacher's Work in Schools 6

The Contribution of Assessment Platform Technology to Promot...

引用

6th International Conference on Interactive Digital Media, ICIDM 2020

作者： Zamahsari, Gamal Kusuma Putikadyanto, Agus Purnomo Ahmad Maulana, Fairuz Iqbal Bina Nusantara University Faculty of Economics and Communication Communication Science Department Jakarta11480 Indonesia Institute of Islamic Religion Madura Indonesian Language Education Study Program Pamekasan69371 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728149288

This study examines the efficiency of summative assessment in schools utilizing the *** assessment platform. The objectives of this study were (1) to describe staff efficiency on summative assessment using *** in schools, and (2) to describe the time efficiency on summative assessment using *** in schools. This study uses a qualitative design. The location of this research is Junior High School 3 Malang. data were collected through observation, document study, and interviews. Interviews were conducted with the vice-principal of the curriculum field. Investigation of validity data used triangulation, with additional interviews to the curriculum team and teachers at the school. Summative assessments using the *** platform show the more efficient in terms of staff's work as much as 17% compared to conventional summative assessment and a time efficiency of 44% compared to conventional assessments. The use of technology saves time from the planning, processing, and reporting stages of the assessment. The greatest efficiency is in the summative assessment processing stage because the costs of correcting or scanning student work, changing grades, and analyzing question items are not done manually. The use of technology with the *** platform for summative assessment in schools can be an alternative solution to promote teacher work. © 2020 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Logistic Regression and Decision Tree Models for Lung Cancer Prediction Using Survey data

Evaluation of Logistic Regression and Decision Tree Models f...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Narayana, K.E. Jayashree, K. ThavaVinu, A. Sindhuja, M. Jaeyalakshmi, M. Rajalakshmi Engineering College Department of Information Technology Tamilnadu Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Chennai India Prathyusha Engineering College Department of Information Technology Chennai India Acharya University Department of Computer Science and Engineering Karakul Uzbekistan Rajalakshmi Engineering College Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798331522988

Lung cancer is one of the most deadly and ubiquitous forms of cancer globally. Early detection can make a significant difference in survival rates, prognosis, etc. Background The present study compares the performance of logistic regression and decision trees using a survey-based dataset for predicting lung cancer. This dataset has a total of 284 cases with 16 features;behavioral patterns, symptomatic data, and demographic details. Logistic regression is a binary classification algorithm that uses input features to model the probability of lung cancer presence given these input features using for example a sigmoid function. Using Decision Trees can identify significant fields in a dataset while reducing Gini Impurity for models that categorize patients based on feature values. The performance of both models is evaluated according to accuracy, F1-score, precision, and recall measures. From the preliminary results, it looks like the Decision Tree works a little better than the logistic regression model which gets an accuracy of 94%, but this one does with more accuracy (97%). This result emphasizes the inclusion of logistic regression within this context, as it may be able to predict lung cancer with greater accuracy. Additionally, to ensure the generalization and robustness of the model, further investigation and trials will focus on optimizing performance through ensemble approaches, hyperparameter tuning, and cross-validation. This comparative analysis demonstrates the effectiveness of machine learning techniques in developing prediction models for early lung cancer detection, an important step toward a quick and appropriate intervention. © 2024 IEEE.

关键词： Lung cancer

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：