检索结果-内蒙古大学图书馆

2nd ieee conference on information technology and data science, citds 2022

作者： Perez-Gamboa, Sonia Sun, Qingquan Ghasemkhani, Amir California State University Sch. of Computer Science and Eng. San Bernardino United States

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Sensor based human activity recognition has obtained more attentions due to its low-cost, low-data throughput, and immunity to environmental effects. However, traditional work in this field mainly focuses on the recognition of simple and small volume human activities. This work targets complicated, correlated and larger size of human activity recognition. In this paper, a multi-layer hybrid deep learning model is built with convolutional neural networks (CNN) and long short-term memory (LSTM). The multi-layer architecture improves the learning and exploration capacity of local features and temporal dependencies, and the hybrid architecture enriches the diversity for data fusion. In addition, Bayesian optimization is applied to the hybrid model to get the optimal parameters and best performance. The experimental results demonstrate the effectiveness of the proposed model with a recognition rate of 89% for 27 correlated activities. Its performance is better than traditional machine learning and other hybrid deep learning models. © 2022 ieee.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Using Hybrid Learning for Industrial IoT 2

Anomaly Detection Using Hybrid Learning for Industrial IoT

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Takele, Atallo Kassaw Villanyi, Balazs Budapest University of Technology and Economics Department of Electronics Technology Budapest Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

The industrial internet of things (IIoT) enhances industrial and manufacturing operations by using smart sensors and actuators. However, it is hampered due to the energy efficiency requirements, real time performance requirements in a dynamic environment, and maintaining the security of applications. Security is a serious issue nowadays and is mostly caused by abnormal traffic of some nodes. For detecting those abnormalities, there are two basic machine learning approaches, namely Federated and Centralized Learning. Centralized Learning has better performance, but it has a privacy issue since edge devices send data to the server. On the other hand, Federate Learning obviates privacy issues, but it has less performance due to the resource limitation of edge devices. In this study, a typical hybrid learning based abnormality detection framework has been proposed in which edge devices undertake Federated Learning with a limited number of datasets and the edge server will use the periodically collected aggregated data from edge devices. For security reasons, edge devices share their data after a certain period of time when the time value of the data has declined. We have used Long Short Term Memory (LSTM) Autoencoders with two different datasets (a smaller for edge devices and a larger for the edge server) for the demonstration. The experimental result shows that the size of the dataset affects the predicting performance and resource utilization in an anomaly detection model. © 2022 ieee.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Fog Computing for Geographically Distributed Smart Cities 2

Leveraging Fog Computing for Geographically Distributed Smar...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Gargees, Rasha S. University of Missouri Department of Electrical Engineering & Computer Science ColumbiaMO United States

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Recently, the emergence of smart cities (SC), where data streams come from various geographically distributed places, has posed new challenges. Cloud Computing provides excellent services for smart cities, such as powerful computation and storage. However, processing the geographically distributed data using cloud computing only is not an ideal solution in some cases. Additionally, moving all the big raw data to the remote cloud is another challenge for cloud computing since there will be shortcomings in terms of delay and high bandwidth consumption. A solution that allows fog-to-cloud or fog-to-fog communication can address these limitations as fogs are typically located locally near the data sources. However, the questions related to the efficient frameworks design, workload distribution, cost, and various key technologies and communication challenges remain. To this end, this research investigates the impact of fog, employing our proposed architecture, on the efficient utilization and management of resources in highly distributed systems through experiments. The comparison showed that fog computing reduces the cost in terms of time and resource utilization. Additionally, the collaboration of autonomous agents locally (within one fog) or globally (across multiple fogs and cloud) supports scalability and automation. It also facilitates large-scale data processing across various real-world distributed locations. © 2022 ieee.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based anomaly detection for imaging in autonomous vehicles 2

Deep learning-based anomaly detection for imaging in autonom...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Kapusi, Tibor Peter Kovacs, Laszlo Hajdu, Andras University of Debrecen Faculty of Informatics Department of Data Science and Visualization Debrecen Hungary Nvidia Deep Learning Institute Certified Instructor Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Autonomous driving and self-driven vehicles have become among the most pursued research areas in recent years. Nowadays, various driving tasks can be solved by applying the newest machine learning techniques such as line tracking, traffic sign recognition, automated speed adjustment, and parking. However, difficult visual conditions and anomalies can cause problems in selected algorithms, which may occur unexcepted and failure operations in these cases. It is also expected not just very expensive to do such kinds of experiments, but these problematic conditions are also lead to dangerous traffic situations at the same time. We made an effort to put these kinds of studies into a cost-effective and safe model-scale environment. This paper introduces an anomaly detection method capable of recognizing abnormal and burnt-out objects in image scenes. Our proposed method is based on a fast neural network architecture using YOLO layers to detect regions. Our experiments demonstrate the capabilities and detection accuracy of the designed neural network, called anomalyNet, with the complete training and evaluation process. In the study, we work with publicly available datasets, but our model-sized track and DAVE (University of Debrecen Autonomous VehiclE) play an important role also. © 2022 ieee.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Towards an in-network GPU-accelerated packet processing framework 2

Towards an in-network GPU-accelerated packet processing fram...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Voros, Peter Kis, David Hudoba, Peter Pongracz, Gergely Laki, Sandor Elte Eötvös Loránd University Hungary Ericsson Research Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Software-defined networking and data-plane programmability have opened up the possibilities for switches to be used for novel applications that are different than simple packet forwarding. Various tasks from low-level robot control to signal and data processing can be offloaded to network devices. In the past years, solutions exploiting programmable switching ASIC, FPGA or the combination of both have emerged. In this paper, we propose a GPU-accelerated switch design for supporting payload processing tasks in the network. The proposed design combines the processing capabilities of GPUs and the kernel-bypass library DPDK. We define different image processing use cases that can benefit from in-network computing, allowing execution without the need for an external server. The proposed method cannot only make the overall system performance better, but also reduce the power consumption since it requires less hardware elements. We evaluate and compare three models: Traditional external server with GPU in the local network, DPDK accelerated version of the previous model and the proposed GPU-accelerated in-network computing switch model. We investigate several benchmarks including both component-level and system-wide analysis. The examined use cases are related to video stream processing tasks like box blurring, Gaussian blurring and edge detection, demonstrating the performance improvement of our proposed design. © 2022 ieee.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sensor design and integration into small sized autonomous vehicle 2

Sensor design and integration into small sized autonomous ve...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Kovacs, Laszlo Baranyai, David Giraszi, Tamas Majoros, Tamas Kovacs, Adam Vagner, Mate Palkovics, Denes Berczes, Tamas University of Debrecen Nvidia Deep Learning Institute Certified Instructor Department of Data Science and Visualization Faculty of Informatics Debrecen Hungary University of Debrecen Department of Data Science and Visualization Faculty of Informatics Debrecen Hungary University of Debrecen Faculty of Informatics Debrecen Hungary University of Debrecen Department of It Systems and Networks Faculty of Informatics Debrecen Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

Autonomous vehicles use several different kinds of sensors to get information about the surrounding area. With sensors and artificial intelligence, the autonomous vehicle tries to find the optimal decision as close as possible to the appropriate behavior. Because of the huge amount of data, the usage of modern machine learning and data-driven approaches is necessary. Although computing big data is not easily handled especially onboard a vehicle, the critical mass of the diverse data generated from different sources is essential. In the field of autonomous vehicles, there have not been standards yet, but the range of applied sensors is well-known. Most systems use a combination of cameras, radar, and LIDAR (Light Detection and Ranging) sensors that transmit data to a central computer that detects the environment around the car. Self-driving development could be supported with model-sized self-driving vehicles because of the complexity of the area. The development of autonomous vehicles consists of security, communication, and data processing issues. Mistakes are increasing the risks of potential accidents. The realistic environment which can be simulated or built makes it possible that the learned behavior can be carried across the platforms while the differences in the sizes are not playing an important role in the matter of learning. The previous reason causes the model-size self-driving development to be more cost-effective. In our work, we developed a self-driving model car with different types of sensors. Measurement data from them can be used to improve the self-driving capabilities of the vehicle. © 2022 ieee.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Joint Transmission Coordinated Multipoint on Mobile Users in 5G Heterogeneous Network 2

Joint Transmission Coordinated Multipoint on Mobile Users in...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Tandra, Tahmina Khanom Tajrian, Fehima Hossain, Afia Kawser, Mohammad Tawhid Akram, Mohammad Rubbyat Shams, Abdullah Bin Islamic University of Technology Gazipur1704 Bangladesh Robi Axiata Ltd Dhaka1212 Bangladesh University of Toronto TorontoONM5S 3G8 Canada

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

To broaden user experience and support a wide range of bandwidth hungry devices cellular operators are adopting 5G network. However, the predominance of Inter-Cell Interference (ICI) in 5G stands as a hurdle for cell edge UEs. With increase in UE velocity, the effect of Doppler shift becomes more prominent, resulting in a significant drop in cell edge and mean data rates. A potential solution to improve the network service quality in the cell edge and reduce the impact of ICI for mobile users is to provide the UE with the best signal quality through coordination among multiple eNodeBs (eNB) located in different cell sites i.e., by virtually forming a massive antenna array with the coordinated eNB, a technique popularly known as Joint Transmission Coordinated Multipoint (JT CoMP). This paper investigates the performance of JT CoMP based heterogeneous network (HetNet) for UEs at different velocities while closed loop spatial multiplexing (CLSM) is active. With the inclusion of CLSM in JT CoMP, the obtained momentary channel state information can be utilized by coordinated eNBs for appropriate network gain enhancement. The simulation results demonstrate significant improvement in mean throughput and cell edge throughput for a CoMP based HetNet compared to a non-CoMP based HetNet with respect to UE velocity. The effectiveness of CLSM is found to degrade as UE velocity increases which is expected due to poor feedback capabilities of high velocity UEs. In contrast, simulation results show that the CLSM integrated inter-site based JT CoMP network provides improved reception for high velocity, while the intrasite-based CoMP network delivers better service at lower velocities. © 2022 ieee.

关键词： Velocity

来源：评论

学校读者我要写书评

暂无评论

Frequent Itemsets Mining Using Vertical Index List

Frequent Itemsets Mining Using Vertical Index List

引用

2009 2nd ieee International conference on Computer science and information technology（ICCSIT 2009）

作者： Supatra Sahaphong Department of Computer Science Faculty of ScienceRamkhamhaeng University

ISBN: (纸本)9781424445196

In this paper,I propose a new approach to mine all frequent itemsets that performs database scanning only once to construct data *** structure uses the conceptual of vertical data layout to contain transaction *** changing of minimal support is not effected by the data structure and rescan of database is not *** proposed algorithm has the ability to find frequent itemsets without generation of candidate *** obtains complete and correct frequent *** examples of all definitions and correctness proving are provided.

关键词： data minin Association rule mining Frequent itemsets mining Vertical data layout Algorithm.

来源：评论

学校读者我要写书评

暂无评论

Detection of false data injection attack in power information physical system based on SVM-GAB algorithm

引用

ENERGY REPORTS 2022年 8卷 1156-1164页

作者： Xiong, Xiaoping Hu, Siding Sun, Di Hao, Shaolei Li, Hang Lin, Guangyang Univ Guangxi Univ Sch Elect Engn Nanning 530004 Guangxi Peoples R China

Cyber physical power system (CPPS) is highly dependent on information and communication technology, which makes it vulnerable to network attacks. Among them, false data injection attack (FDIA) is not easy to be found by traditional bad data detection methods, and becomes one of the main threats to the safe operation of power systems. However, the high complexity, large amount of data and transient characteristics of CPPS put forward higher requirements for the accuracy and efficiency of FDIA detection method. Therefore, in view of the characteristics of CPPS, this paper proposes SVM-GAB (Support Vector Machines-Gentle Adaboost) algorithm to effectively detect FDIA. Through the effective dimension reduction and classification of the measured data, the real-time and high-precision detection of FDIA is realized. This algorithm is compared with mainstream detection algorithms in ieee-14 and ieee-39 standard systems. The results show that the false alarm rate of this algorithm is reduced by at least 25% compared with the traditional detection algorithm, and the accuracy and real-time performance of the proposed detection algorithm are verified by experiments. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://***/licenses/by/4.0/). Peer-review under responsibility of the scientific committee of the 2021 The 2nd International conference on Power Engineering, ICPE, 2021.

关键词： Cyber physical power system (CPPS) information security False data injection attack (FDIA) UMAP SVM-GAB

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Secure Deletion in Flash Memories

An Algorithm for Secure Deletion in Flash Memories

引用

2009 2nd ieee International conference on Computer science and information technology（ICCSIT 2009）

作者： S.Subha 3-1-100 Vidyanagar Colony Tirupati-517502 A.P.India

ISBN: (纸本)9781424445196

Flash memories find wide use in storing data in any *** deletion in flash memories involves making the data unreliable on the *** contents get deleted in the flash memory,time is consumed in deleting the data on the flash *** paper proposes a method to make the contents of the deleted blocks in the flash memory *** proposed method can be used for any algorithm used for data security in terms of error detection and *** method involves introducing appropriate number of errors in the data and control bits of the blocks of data making data recovery impossible.

关键词： Error Inception File deletion

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：