检索结果-内蒙古大学图书馆

作者： Bakhshmand, Saeed M. Eagleson, Roy De Ribaupierre, Sandrine Biomedical Engineering Graduate Program University of Western Ontario LondonON Canada Department of Electrical and Computer Engineering University of Western Ontario LondonON Canada Department of Clinical Neurological Sciences University of Western Ontario LondonON Canada

Non-invasive assessment of cognitive importance has been a major challenge for planning of neurosurgical procedures. In the past decade, in vivo brain imaging modalities have been considered for estimating the 'eloquence' of brain areas. In order to estimate the impact of damage caused by an access path towards a target region inside of the skull, multi-modal metrics are introduced in this paper. Accordingly, this estimated damage is obtained by combining multi-modal metrics. In other words, this damage is an aggregate of intervened grey matter volume and axonal fibre numbers, weighted by their importance within the assigned anatomical and functional networks. To validate these metrics, an exhaustive search algorithm is implemented for characterising the solution space and visually representing connectional cost associated with a path initiated from underlying points. In this presentation, brain networks are built from resting state functional magnetic resonance imaging (fMRI) and deterministic tractography. their results demonstrate that the proposed approach is capable of refining traditional heuristics, such as choosing the minimal distance from the lesion, by supplementing connectional importance of the resected tissue. This provides complementary information to help the surgeon in avoiding important functional hubs and their anatomical linkages;which are derived from neuroimaging modalities and incorporated to the related anatomical landmarks.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Implementation Graph Database Framework for Credit Card Fraud Detection 8

Implementation Graph Database Framework for Credit Card Frau...

引用

8th International Conference on computer Science and Computational Intelligence, ICCSCI 2023

作者： Mauliddiah, Nurrahmi Suharjito Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia

Credit card use is becoming more and more commonplace every day. Financial organizations and credit card customers lose a lot of money because of complicated illegal transactions. Fraudsters constantly stay on top of new technology to quickly perpetrate fraud against customer transaction patterns. We analyze credit card transaction networks and identify suspicious patterns, such as transactions connected to multiple accounts or unusual transaction patterns, transactions made at unusual times, and to monitor credit card transactions in real-time and quickly identify suspicious transactions. TigerGraph is used to analyze data, display results on a dashboard, and send notifications via email. One meth'\ Vc 1``13-od commonly used in anomaly detection is to compare data values against the standard deviation. In this research, we explain the use of TigerGraph as a platform for anomaly detection above the standard deviation, as well as the use of the Louvain algorithm in finding merchant communities used by fraudsters. The data used in this study comes from Sparkov simulation data obtained from Kaggle. Our results show that by using TigerGraph, we managed to achieve a very high accuracy rate of 99.77%, precision 82.84%, recall 72.38%, and f1-score 77,26% in predicting transaction fraud on Sparkov simulation data. This is much better than the results reported in a paper that uses the supervised machine learning method with the AdaBoost algorithm which achieves the highest accuracy of 77%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Alert Credit card fraud detection Dashboard TigerGraph

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of using social networks platform for learning support: An example of Facebook

Feasibility study of using social networks platform for lear...

引用

20th International Conference on computers in Education, ICCE 2012

作者： Chan, Chien-Lung Fu, Wen-Erh Lai, K. Robert Tseng, Shu-Fen Department of Information Management Yuan Ze University Taiwan Department of Computer Science and Engineering Yuan Ze University Taiwan Graduate Program in Social Informatics Yuan Ze University Taiwan

ISBN: (纸本)9789810746490

In this study, we explored the students' computer-supported collaborative learning behavior based on the Facebook platform. Sixty two senior college students major in Information Management took Decision Support System (DSS) class. Besides the lectures and class discussion, the students participated in the DSS Facebook for collaborative learning. We found that students' characteristics (e.g., gender and mindset of learning) are important factors to affect their Facebook usage behavior and learning performance. The students using DSS Facebook more often get better performance in their final projects, learning satisfaction and the online communication behavior survey. We also found that gender affects the usage of social networks platform. For instance, male students use social networks platform several times per week and get better performance in online communication, learning satisfaction and creativity self-efficacy.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

High embedding reversible data hiding scheme for JPEG

High embedding reversible data hiding scheme for JPEG

引用

6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2010

作者： Kuo, Wen-Chung Kuo, Shao-Hung Wuu, Lih-Chyau Depart. of Computer Science and Information Engineering National Formusa University Yunlin 632 Taiwan Graduate School of Engineering Science Technology Doctoral Program National YunLin University of Science and Technology Yunlin 640 Taiwan

ISBN: (纸本)9780769542225

Both Data hiding and data compression are very important technologies in the field of image processing. It seems that there is no relationship between data hiding and data compression because most of the data hiding mechanisms focus on information security and the data compression mechanisms emphasize the compression ratio. In fact, they are closely related. Until now, there are many literatures to discuss the secret data how to be embedded into the media image. Unfortunately, the stego-image's size will be increased when the media image is hidden a lot of secret data. In order to overcome this disadvantage, a reversible data hiding scheme based on EMD data hiding and JPEG compression technology will be proposed in this paper. According to the experimental results, we can prove that our proposed scheme still keeps high embedding capacity, security and good compression ratio. © 2010 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Theoretical Modelling of Smart Meter Privacy Protection with Multi-meter Energy Routing 4

Theoretical Modelling of Smart Meter Privacy Protection with...

引用

4th IEEE International Conference on Smart Internet of Things, SmartIoT 2020

作者： Ergen, Cankut Gulbahar, Burhan Ozyegin University Graduate School of Engineering and Science MSc Program of Computer Science Istanbul34794 Turkey Ozyegin University Applied Research Center of Technology Products Istanbul34794 Turkey

ISBN: (纸本)9781728165141

Potential of intrusion during smart meter data collection is an important problem for household privacy in next-generation smart homes. There are various privacy protection methods such as hiding the real usage with renewable batteries (RBs) and encrypted communication. There are privacy threats due to the detection of the energy transfer through RBs while encryption-based methods result in high computational complexity. In this study, a novel privacy improvement mechanism is proposed based on the routing of energy through multiple smart meters among multiple houses in a neighborhood. The optimization of privacy based on uniform randomization is theoretically modeled and some heuristic solutions are presented. In this method, energy transfer is randomly distributed among multiple smart meters, real usage of a house is buffered with the RB and smart meter indices are randomly selected. In numerical simulations, privacy improvement is shown by utilizing the random selection of smart meter indices for randomizing the energy routing and the buffers of RBs. Furthermore, energy privacy (EP) metric validating the simulation results is defined. Energy routing with multiple smart meters provides a practical and low complexity privacy protection mechanism for next-generation smart grid architectures. © 2020 IEEE.

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

Supporting differentiated resilience classes in multilayer networks 12

Supporting differentiated resilience classes in multilayer n...

引用

12th International Conference on the Design of Reliable Communication Networks, DRCN 2016

作者： Alashaikh, Abdulaziz Tipper, David Gomes, Teresa Graduate Telecommunications and Networking Program University of Pittsburgh PittsburghPA15260 United States Department of Electrical and Computer Engineering University of Coimbra INESC Coimbra Coimbra3030-290 Portugal

ISBN: (纸本)9781467384964

The concept of providing differentiated classes of resilient services over communications networks has received a lot of attention in the literature. A number of proposals tried to address the problem by provisioning different classes of services with different protection schemes. However, most of these works are applied to a single layer and lack cross layer coordination in multilayer scenarios. In addition, there is an increasing need for supporting services with very high resilience requirements over future communications networks. This, however, has to be done in a cost efficient manner and without over-engineering the network. In this paper, we introduce a novel approach that simplifies the whole design and achieves both high resilience and differentiation. Our approach, utilizes the spine concept idea of embedding a subnetwork at the physical layer with comparatively high availability link and node values [1]. This lays a foundation for differentiation between multiple classes of flows. Then, cross layer mapping and spine-aware routing are performed in a way that transfers this differentiation capability to the upper layer network and flows. We provide two joint routing-mapping optimization formulations and evaluate their performance in a multilayer scenario. © 2016 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

NONDETERMINISTIC STACKS IN NEURAL NETWORKS

arXiv

引用

arXiv 2023年

作者： DuSell, Brian Graduate Program in Computer Science and Engineering Notre DameIN United States

Human language is full of compositional syntactic structures, and although neural networks have contributed to groundbreaking improvements in computer systems that process language, widely-used neural network architectures still exhibit limitations in their ability to process syntax. To address this issue, prior work has proposed adding stack data structures to neural networks, drawing inspiration from theoretical connections between syntax and stacks. However, these methods employ deterministic stacks that are designed to track one parse at a time, whereas syntactic ambiguity, which requires a nondeterministic stack to parse, is extremely common in language. In this dissertation, we remedy this discrepancy by proposing a method of incorporating nondeterministic stacks into neural networks. We develop a differentiable data structure that efficiently simulates a nondeterministic pushdown automaton, representing an exponential number of computations with a dynamic programming algorithm. Since it is differentiable end-to-end, it can be trained jointly with other neural network components using standard backpropagation and gradient descent. We incorporate this module into two predominant architectures: recurrent neural networks (RNNs) and transformers. We show that this raises their formal recognition power to arbitrary context-free languages, and also aids training, even on deterministic context-free languages. Empirically, neural networks with nondeterministic stacks learn context-free languages much more effectively than prior stack-augmented models, including a language with theoretically maximal parsing difficulty. We also show that an RNN augmented with a nondeterministic stack is capable of surprisingly powerful behavior, such as learning cross-serial dependencies, a well-known non-context-free pattern. We demonstrate improvements on natural language modeling and provide analysis on a syntactic generalization benchmark. This work represents an important step towa

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Two new ways of Discriminant Feature Transform

Two new ways of Discriminant Feature Transform

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology

作者： Nattapong Jundang Surachai Ongkittikul The Computer Engineering Graduate Program Faculty of Engineering Mahanakorn University of Technology Department of Computer Engineering Mahanakorn University of Technology

ISBN: (纸本)9781479929948

In this paper, we present the encoding produces technique for texture recognition. This produces are developed with the purpose to replaced the previous method. Firstly, we encode image informations by VTT (Volume Trace Transform), and trace functionals are chosen by RL (Reinforce Learning). The number of VTT results are extracted by the amount of trace functionals. Secondly, we present P-DFT (Plus-Discriminant Feature Transform) and S-DFT (Square-Discriminant Feature Transform) accumulate result's VTT and constructs 2-D histogram. Finally, The histogram is compared by chi-square test and in conclusion will present the accuracy of recognition rate of both methods based on brodatz texture database.

关键词： Trace transform Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of YOLOv8 and EfficientDet4 Algorithms in Detecting the Ripeness of Oil Palm Fruit Bunch 10

Comparison of YOLOv8 and EfficientDet4 Algorithms in Detecti...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Priyadi, Muhammad Reza Azhar Suharjito Bina Nusantara University BINUS Online Learning Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master of Industrial Engineering Industrial Engineering Department Jakarta11480 Indonesia

ISBN: (纸本)9798350339543

Despite Indonesia's leading position in palm oil processing, the inaccurate assessment of oil palm fruit maturity poses challenges in determining the optimal harvest timing and maintaining product quality. With advancements in information technology, including image processing and object detection techniques like YOLO and EfficientDet, there is potential for automated and precise identification of palm fruit maturity. To explore this, the authors conducted research to identify the most suitable algorithm for detecting the ripeness of palm oil fruit. The study utilized a dataset consisting of 8299 images with six maturity levels, employing augmentation techniques to increase image variability. Results show that YOLO V8s outperformed EfficientDet Lite 4 in terms of object detection precision, achieving higher mean average precision (mAP) scores. YOLO V8s showed a 4% improvement in mAP@50 and a 16% improvement in mAP@50-95 compared to EfficientDet Lite 4. YOLO V8s achieved a mAP of 0.978 for mAP@50 and 0.765 for mAP@50-95, surpassing EfficientDet Lite 4. However, EfficientDet Lite 4 had an advantage in terms of class accuracy and bounding box placement, as indicated by smaller box loss and cIs- loss values. YOLO V8s also demonstrated better frames per second (FPS) performance, ranging from 10 to 15 FPS, compared to EfficientDet Lite 4. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Multi Soft-sensor Approach for the Development of Emergencies Detection Units on the Edge 6

A Multi Soft-sensor Approach for the Development of Emergenc...

引用

6th IEEE International Workshop on Metrology for Industry 4.0 and IoT, MetroInd4.0 and IoT 2023

作者： Oliveira, Franklin Costa, Daniel G. Assis, Flavio Silva, Ivanovitch Federal University of Bahia Graduate Program in Mechatronics Salvador Brazil University of Porto INEGI Faculty of Engineering Porto Portugal Federal University of Rio Grande Do Norte Department of Computer Engineering and Automation Natal Brazil

ISBN: (纸本)9798350396577

The adoption of multi-sensor hardware units to detect different types of emergencies in complex scenarios such as Industry 4.0 and Smart Cities is a recent development trend, which have demanded research efforts to optimize the way these units are assembled, configured, and deployed. However, although their expected advantages, usual multi-sensors emergency-oriented approaches may be constrained by the tight association between physical sensor devices and the emergency detection process. Therefore, this paper proposes an innovative approach to concurrently detect multiple emergencies exploiting the concept of soft-sensor modules, which are implemented on Emergency Detection Units (EDUs) as concurrent tasks along with a high-priority emergency alerting task. The soft-sensor concept defines physical sensors as ordinary input data streams, which will be processed according to the defined algorithms by each particular soft-sensor, allowing detection decisions to be performed on the edge. In order to support the practical exploitation of this concept, a formal specification based on Petri Nets is defined, modeling the concurrent operation of the tasks within an EDU. A proof of concept is also designed based on the affordable Raspberry Pi Pico microcontroller, demonstrating how the proposed approach would behave when two soft-sensors are implemented in a typical detection unit. © 2023 IEEE.

关键词： Industry 4.0

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：