检索结果-内蒙古大学图书馆

2021 International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021

作者： Anta, Vito Lauda Putra Liestyo, Ivander Albert Warnars, Harco Leslie Hendric Spits Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Binus Graduate Programme Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728195377

Jakarta as the Indonesian capital city has extreme average rainfall in 2020, based on data from the DKI Jakarta Representative Central Bureau of Statistics and the meteorology, climatology, and geophysics agency. From year to year, the city of Jakarta has not been spared from floods which have seriously disrupted the activities of the people of Jakarta. Flood disasters greatly disrupt people's economic activities and cause various other problems including public health problems, one of which is causing infectious diseases. In such a case, this research work proposes a mobile application for flood disaster monitoring that will help the Jakarta government to maintain the flood as real flood information in Jakarta. The Jakarta city government and the residents of the city of Jakarta can work hand in hand using mobile application technology to combat this flood problem and enable the Jakarta city government to quickly overcome any reported flood problems. The proposed mobile application was modeled with a use case and class diagrams. © 2021 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

A cloud-native framework for globally distributed capture and analysis of Internet Background Radiation

A cloud-native framework for globally distributed capture an...

引用

Iberian Conference on Information Systems and Technologies (CISTI)

作者： Fabricio Bortoluzzi Barry Irwin Carla Merkle Westphall Department of Applied Computing Noroff University College Kristiansand Norway Postgraduate Programme in Computer Science Federal University of Santa Catarina Florianoópolis Brazil Department of Computer Science Rhodes University Grahamstown South Africa

Among the existing methods for analysing internet traffic, one focuses on unsolicited and often harmful packets, referred to as Internet Background Radiation (IBR). IBR data can be captured by using cloud-based computing instances to listen for incoming packets and recording the received headers and contents in files using the PCAP format. No services are run on these hosts so all traffic can be regarded as non-legitimate. This work presents the research plan for capturing a year-long sample of the IBR arriving to up to 1500 geographically distributed sensors across a major service cloud provider. In combination with collection, a data analysis pipeline will be constructed to enable the querying of most relevant quantitative and qualitative aspects of the resulting dataset. The ultimate goal is to answer “how is the IBR characterised when captured within the context of cloud computing?”. Results will include packet distribution according to the properties of the network, transport, and application layers, together with an evaluation of traffic linking to botnet activity such as Mirai and Moobot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The geometric relationship between root length and root surface area determined from digital tooth models

引用

computers in Biology and Medicine 2025年 191卷 110189-110189页

作者： Wei Chan, Chloe Xiao Leow, Wee Kheng Cheng, Alan Ho-lun Chiong Foong, Kelvin Weng Discipline of Orthodontics Faculty of Dentistry National University of Singapore Singapore Department of Computer Science School of Computing National University of Singapore Singapore Orthodontics Residency Training Programme Faculty of Dentistry National University of Singapore Singapore

Aim: This study investigated the correlation between root length (RL) and root surface area (RSA) in permanent maxillary and mandibular teeth to understand the impact of external apical root resorption. Materials and methods: Three-dimensional (3D) models of human teeth, representing a Japanese male adult population, were sourced from a commercial provider and segmented into individual roots. A Python algorithm calculated root surface area (RSA) at simulated root lengths by virtually shortening the roots in 1 mm increments. The total RSA (tRSA) was determined by combining the circumferential root surface area (cRSA) with the cross-sectional area (CSA). Results: Maxillary and mandibular first molars exhibited the largest tRSAs in their respective arches. In the initial 3 mm of simulated root shortening, five of seven maxillary and mandibular tooth types exhibited minimal tRSA reduction, averaging less than 7 %. Beyond 3 mm, tRSA reduction became more pronounced, an average of 19.4 % for maxillary teeth and 27.77 % for mandibular teeth. CSA significantly contributes to tRSA;the average CSA proportion increases progressively with greater root length reduction, particularly when it exceeds 8 mm. Conclusion: RSA together with CSA, not just root length, is a crucial consideration when assessing the clinical impact from root length reduction. Generally, when root length loss is up to 20 % (∼3 mm), more than 90 % of the tRSA remains. Teeth with higher CSA proportions, such as molars, are better equipped to retain periodontal support despite substantial RL loss, owing to their broader girth. © 2025 The Authors

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Integrating Imaging and Clinical Data for Parkinson's Disease Diagnosis using Deep Learning

Integrating Imaging and Clinical Data for Parkinson's Diseas...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： D. Divya Pravin R. Kshirsagar Tan Kuan Tak Quadri Noorulhasan Naveed Department of Computer Science and Engineering Jerusalem College of Engineering Chennai India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Nagpur India Electrical Power Engineering Programme Singapore Institute of Technology Singapore Department of Computer Science and Engineering King Khalid University Saudi Arabia

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

That disorder affecting the nervous system, Parkinson's disorder can worsen with time and cause a host of health problems. Parkinson's disease diminishes cerebral function and may induce physical complications in senior individuals. Parkinson's disease can induce a range of disorders by impairing neurological in nature, behavioral, and physiological systems. Physical structures exhibit minimal damage at early diagnosis, complicating the prediction of Parkinson's illness in its initial stages based solely on physical observation. Recent studies on electroencephalogram (EEG) signs in the identification of Parkinson's illness have revealed significant aspects pertinent to early detection. Electroencephalography (EEG) is a multifaceted signal comprising several non-linear and non-stationary elements. Subsequently, an auto-encoder-based deep extraction of features method is employed to derive the spatial and temporal attributes from the four frequency partitions. Additionally, statistical and spectral attributes are obtained. The gathered attributes are utilized to analyze notable patterns associated with Parkinson's disease. Optimal weighted feature fusion is achieved through the precise adjustment of weights. The proposed DLB-LSTM (Densely Located Bidirectional Long Short Term Memory) employs weighted features so that we can identify PD. To impede the progression of Parkinson's disease, the algorithm autonomously learns from the signals and delivers targeted outcomes.

关键词： Deep learning Parkinson's disease Imaging Bidirectional long short term memory Feature extraction Nervous system Electroencephalography Physiology Informatics

来源：评论

学校读者我要写书评

暂无评论

Coordination of Intelligent Mobile Robots for Human-Agent-Robot Teamwork in 6G

Coordination of Intelligent Mobile Robots for Human-Agent-Ro...

引用

IEEE Future Networks World Forum (FNWF)

作者： Amin Ebrahimzadeh Martin Maier Roch H. Glitho CIISE Concordia University Montréal Canada Optical Zeitgeist Laboratory INRS Montréal Canada Computer Science Programme University of Western Cape Capetown South Africa

ISBN: (数字)9798350379495

ISBN: (纸本)9798350379501

Now that 5G mobile networks are rolled out, early studies have started to speculate about 6G and its key driving applications. These studies demonstrate that 6G will sit at the crossroads of communications, computation, intelligentization, and robotization. In 6G, it is expected that the nature of mobile devices will change significantly and intelligent mobile robots will play a more profound role. In this paper, after identifying the key driving technologies of 6G, we shed some light on the role of the Tactile Internet in the 6G era and give insights into how and to what extent we may reduce task completion time in a human-agent-robot teamwork scenario while paying particular attention to the decomposability of physical tasks.

关键词： 6G mobile communication Tactile Internet Robot kinematics Benchmark testing Mobile handsets Teamwork Mobile robots Resource management Object recognition Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior

arXiv

引用

arXiv 2024年

作者： Yu, Yi Wang, Yufei Yang, Wenhan Guo, Lanqing Lu, Shijian Duan, Ling-Yu Tan, Yap-Peng Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Pengcheng Laboratory Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Computer Science and Engineering Nanyang Technological University Singapore School of Computer Science Peking University Beijing China

Recent advancements in deep learning-based compression techniques have demonstrated remarkable performance surpassing traditional methods. Nevertheless, deep neural networks have been observed to be vulnerable to backdoor attacks, where an added pre-defined trigger pattern can induce the malicious behavior of the models. In this paper, we propose a novel approach to launch a backdoor attack with multiple triggers against learned image compression models. Drawing inspiration from the widely used discrete cosine transform (DCT) in existing compression codecs and standards, we propose a frequency-based trigger injection model that adds triggers in the DCT domain. In particular, we design several attack objectives that are adapted for a series of diverse scenarios, including: 1) attacking compression quality in terms of bit-rate and reconstruction quality;2) attacking task-driven measures, such as face recognition and semantic segmentation in downstream applications. To facilitate more efficient training, we develop a dynamic loss function that dynamically balances the impact of different loss terms with fewer hyper-parameters, which also results in more effective optimization of the attack objectives with improved performance. Furthermore, we consider several advanced scenarios. We evaluate the resistance of the proposed backdoor attack to the defensive pre-processing methods and then propose a two-stage training schedule along with the design of robust frequency selection to further improve resistance. To strengthen both the cross-model and cross-domain transferability on attacking downstream CV tasks, we propose to shift the classification boundary in the attack loss during training. Extensive experiments also demonstrate that by employing our trained trigger injection models and making slight modifications to the encoder parameters of the compression model, our proposed attack can successfully inject multiple backdoors accompanied by their corresponding triggers int

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion

Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uni...

引用

International Conference on computer Vision (ICCV)

作者： Weng Fei Low Gim Hee Lee The NUS Graduate School's Integrative Sciences and Engineering Programme (ISEP) Institute of Data Science (IDS) National University of Singapore Department of Computer Science National University of Singapore

Event cameras offer many advantages over standard cameras due to their distinctive principle of operation: low power, low latency, high temporal resolution and high dynamic range. Nonetheless, the success of many downstream visual applications also hinges on an efficient and effective scene representation, where Neural Radiance Field (NeRF) is seen as the leading candidate. Such promise and potential of event cameras and NeRF inspired recent works to investigate on the reconstruction of NeRF from moving event cameras. However, these works are mainly limited in terms of the dependence on dense and low-noise event streams, as well as generalization to arbitrary contrast threshold values and camera speed profiles. In this work, we propose Robust e-NeRF, a novel method to directly and robustly reconstruct NeRFs from moving event cameras under various real-world conditions, especially from sparse and noisy events generated under non-uniform motion. It consists of two key components: a realistic event generation model that accounts for various intrinsic parameters (e.g. timeindependent, asymmetric threshold and refractory period) and non-idealities (e.g. pixel-to-pixel threshold variation), as well as a complementary pair of normalized reconstruction losses that can effectively generalize to arbitrary speed profiles and intrinsic parameter values without such prior knowledge. Experiments on real and novel realistically simulated sequences verify our effectiveness. Our code, synthetic dataset and improved event simulator are public.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review on regular clocking scheme in quantum dot cellular automata

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2024年 8卷

作者： Goswami, Mrinal Sharma, Tonmoy Jyoti Boruah, Arpita Nath Programme of Computer Science and Engineering Faculty of Engineering Assam down town University Sankar Madhab Path Gandhi Nagar Panikhaiti Assam Guwahati India

Quantum-dot cellular automata (QCA) is a novel and emerging nanotechnology that explores the potential of using quantum dots as information carriers in computing devices. The information transfer, as well as timing synchronization of the QCA circuit, is controlled by clocks. Despite this, most of the work done in QCA does not consider the proper layout of the underlying clocking circuit required. Hence, it ends up with QCA circuits with irregular clock zones, which is not suitable for fabrication. However, for efficient design and to provide proper routing options within the clock zones, a regular, scalable clocking scheme is needed. Without a well-defined and regular clocking zone, the QCA circuit designs are incomplete and not a standard fabrication candidate. In this regard, several regular clocking schemes in QCA are discussed in the literature. In this survey, a systematic review of those clocking schemes will be investigated. A detailed comparison of these schemes is also discussed based on design architecture and fabrication point of view. © 2024 The Author(s)

关键词： QCA Clocking Quantum-dot cellular automata (QCA) Regular Clocking

来源：评论

学校读者我要写书评

暂无评论

Real-Time Anomaly Detection Using Distributed Tracing in Microservice Cloud Applications

Real-Time Anomaly Detection Using Distributed Tracing in Mic...

引用

IEEE International Conference on Cloud Networking (CLOUDNET)

作者： Mahsa Raeiszadeh Amin Ebrahimzadeh Ahsan Saleem Roch H. Glitho Johan Eker Raquel A. F. Mini CIISE Concordia University Montréal Canada Computer Science Programme University of Western Cape Capetown South Africa Ericsson Research Lund Sweden

Distributed tracing plays a vital role in microservice infrastructure, and learning-based trace analysis has been utilized to detect anomalies within such systems. However, existing approaches for learning-based trace-based anomaly detection face certain limitations. Some assume that trace patterns can be learned solely from normal executions, while others depend on anomaly injection to generate labeled traces categorized as normal or anomalous. However, in practical scenarios, anomalies may also happen during the normal execution. Moreover, a wide variety of anomalies may occur in practice, which cannot be captured solely through anomaly injection. To address these issues, we propose a Trace-Driven Anomaly Detection (TDAD) approach based on a Span Causal Graph (SCG) representation, which trains a model using a Graph Neural Network (GNN) and Positive and Unlabeled (PU) learning. This technique allows the model parameters to be optimized by estimating the underlying data distribution. As a result, TDAD can be effectively trained using a small number of labeled anomalous traces along with a relatively large number of unlabeled traces. Our evaluation reveals that TDAD outperforms not only the existing unsupervised trace-based anomaly detection methods by 11.9% in terms of F 1 -score but also a supervised learning-based benchmark by 12x in terms of detection time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Provisioning In-Network Computing Enabled Slices for Holographic Applications in Next-Generation Networks

arXiv

引用

arXiv 2023年

作者： Aghaaliakbari, Fatemeh Ait Hmitti, Zakaria Rayani, Marsa Gherari, Manel Glitho, Roch H. Elbiaze, Halima Ajib, Wessam Ciise Concordia University QC Montreal Canada Computer Science Programme University of Western Cape Cape Town South Africa QC Montreal Canada

Applications such as holographic concerts are now emerging. However, their provisioning remains highly challenging. Requirements such as high bandwidth and ultra-low latency are still very challenging for the current network infrastructure. In-network computing (INC) is an emerging paradigm that enables the distribution of computing tasks across the network instead of computing on servers outside the network. It aims at tackling these two challenges. This article advocates the use of the INC paradigm to tackle holographic applications' high bandwidth and low latency challenges instead of the edge computing paradigm that has been used so far. Slicing brings flexibility to next-generation networks by enabling the deployment of applications/verticals with different requirements on the same network infrastructure. We propose an architecture that enables the provisioning of INC-enabled slices for holographic-type application deployment. The architecture is validated through a proof of concept and extensive simulations. Our experimental results show that INC significantly outperforms edge computing when it comes to these two key challenges. In addition, low jitter was maintained to preserve the hologram's stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Next generation 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：