The problem of detecting fake (false) information passing through various channels of the Internet is becoming increasingly important task. One of the most dangerous types of such information is targeted propaganda, w...
详细信息
ISBN:
(纸本)9781665426060
The problem of detecting fake (false) information passing through various channels of the Internet is becoming increasingly important task. One of the most dangerous types of such information is targeted propaganda, which always has a specific purpose and uses specially prepared resources. To protect a person from such informational influence, we can use already developed tools and algorithms. This article considers the main features of information propaganda and approaches to combating it; the effectiveness of several well-known modern algorithms for recognizing fake news; the comparative efficiency analysis of these algorithms in the context of possibility of their application for counteracting purposeful information influences is carried out. Based on the study, the most promising algorithm for recognizing information propaganda in social networks was selected. This will allow to build more efficient systems of detecting fake news that are delivered in scope of information propaganda campaigns as a part of information warfare in social media networks.
This paper addresses H ∞ state estimation problem for a class of discrete-time stochastic delayed systems subject to deception attacks over sensor networks. We consider the scenario where the sensor output and estim...
详细信息
ISBN:
(数字)9781728190044
ISBN:
(纸本)9781728190051
This paper addresses H ∞ state estimation problem for a class of discrete-time stochastic delayed systems subject to deception attacks over sensor networks. We consider the scenario where the sensor output and estimator output are transmitted to its corresponding estimator and other estimators, respectively, over two different digital channels. To cope with the problem of constrained bandwidth, the event-triggering ideas are implemented on both sensor-to-estimator and estimator-to-estimator channels. Meanwhile, we consider there is an attacker that possibly corrupts the measurement output. Under these circumstances, we aim to design the state estimator such that the exponential mean-square stability with H ∞ performance is satisfied. By virtue of Lyapunov-Krasovskii functional, we can derive the explicit estimator parameters by solving a set of linear matrix inequalities (LMIs). Finally, a numerical example is established to verify our theoretical results.
This work proposes a new ultra low-power fault detection system, suitable for extreme edge or in-sensorcomputing. The system is composed of a hybrid HW/SW architecture: a hardware auto-encoder (AE) is always on at th...
详细信息
This work proposes a new ultra low-power fault detection system, suitable for extreme edge or in-sensorcomputing. The system is composed of a hybrid HW/SW architecture: a hardware auto-encoder (AE) is always on at the edge for anomaly detection (AD), and of a software convolutional neural network (CNN) is activated only if the anomaly is detected for its classification. To achieve low area and energy requirements, the AE exploits an original partially binarization scheme, while the CNN shares the feature extraction module with the AE. The implementation of the AE on a Xilinx Artix-7 FPGA demonstrates that it is capable to manage in real-time sensors with a maximum Output Data Rate (ODR) of 365 kHz with a power dissipation of 122 mW. Best synthesis results with TSMC CMOS 65 nm standard cells show a power consumption of $138\ \mu\mathrm{W}/\text{MHz}$ and an area occupation of 0.49 mm 2 when real-time operations are set, enabling the possibility to integrate the complete HW accelerator in the auxiliary circuitry that typically equips inertial MEMS and on the same die. Comparisons with the current literature show that the proposed system obtains state-of-the-art performances in terms of accuracy and compactness.
The Internet of Robotic Things (IoRT) has emerged as a game-changing player in the fourth industrial revolution (Industry 4.0) in which the robotic automation technologies are integrated with and reinforced by advance...
详细信息
ISBN:
(纸本)9781665442084
The Internet of Robotic Things (IoRT) has emerged as a game-changing player in the fourth industrial revolution (Industry 4.0) in which the robotic automation technologies are integrated with and reinforced by advanced computing paradigms like cloud/fog/IoT in order to maximize productivity of production chains of smart robotic agents in factories. A single robotic agent can comprise hundreds of sensors and actuators, and production processes performed by multiple agents can demand high computational costs, possibly only via remote resources in cloud or fog computing layers. In this context, it is paramount of importance to assimilate the performance of such computing paradigms for production chains of robotic agents in industrial factories and to provide IoRT system designers with assessment tools to comprehend and anticipate the operational performance of their projects at different development stages. This paper proposes an M/M/c/K model for the performance evaluation of IoRT systems integrated with fog-cloud computing paradigms. Focusing on routing strategies, we demonstrated that the proposed model allows evaluating how different configurations of components in an IoRT architecture impact the performance of the system using the performance metrics including mean response time, component utilization, number of messages, and drop rate. The performance modeling and evaluation of a specific IoRT in this paper can help computing system administrators to design and adopt advanced cloud/fog/IoT computing paradigms to maximize manufacturing productivity in industrial factories.
E-Voting or electronic voting is a means for the election process to be conducted without the use of traditional paper ballots. The e-voting process, to be implemented in a large-scale scenario, requires the addressin...
详细信息
Various investigations on wireless sensor networks (WSNs) have been conducted. However, only a few of these studies were related to quality of service (QoS). QoS control for WSNs is defined as the control of the numbe...
详细信息
Recent advancements in Artificial Intelligence have brought “Deep Learning” frameworks to be a cornerstone for the 4th Industrial Revolution along with “Big Data” platform technologies such as Apache Hadoop. Howev...
Recent advancements in Artificial Intelligence have brought “Deep Learning” frameworks to be a cornerstone for the 4th Industrial Revolution along with “Big Data” platform technologies such as Apache Hadoop. However, efficient processing of deep learning applications has become challenging as the overall sizes of data and model increase rapidly. To address this problem, we can leverage big data platforms that have successfully provided stable storage and data processing capability during the past decade. In this paper, we present design and implementation of MeLoN (Multi-tenant dEep Learning framework On yarN) that can effectively run distributed deep learning applications on top of the big data platform Hadoop. MeLoN takes expected GPU memory usages of a deep learning application as an input parameter, and employs a GPU over-provisioning policy that can improve the overall resource utilization. Evaluation results show that MeLoN can improve the overall system throughput for concurrently running multiple deep learning applications in a Hadoop cluster. MeLoN can bring many interesting research issues related to profiling of expected GPU memory usages of deep learning applications, storage optimizations for deep learning processing, supporting complex deep learning related jobs based on queuing systems which can ultimately contribute to a new data processing framework in the YARN-based Hadoop ecosystem. In this paper, we present design and implementation of MeLoN (Multi-tenant dEep Learning framework On yarN) that can effectively run distributed deep learning applications on top of the big data platform Hadoop. MeLoN takes expected GPU memory usages of a deep learning application as an input parameter, and employs a GPU over-provisioning policy that can improve the overall resource utilization. Evaluation results show that MeLoN can improve the overall system throughput for concurrently running multiple deep learning applications in a Hadoop cluster. MeLoN can bring m
Smart Building and its applications have become one of the essential ways of delivering a better quality of life and environment nowadays. The smart construction of building use the technology to share information bet...
详细信息
Nowadays, some applications need CNN inference on resource-constrained edge devices that may have very limited memory and computation capacity to fit a large CNN model. In such application scenarios, to deploy a large...
详细信息
ISBN:
(纸本)9781450391634
Nowadays, some applications need CNN inference on resource-constrained edge devices that may have very limited memory and computation capacity to fit a large CNN model. In such application scenarios, to deploy a large CNN model and perform inference on a single edge device is not feasible. A possible solution approach is to deploy a large CNN model on a (fully) distributed system at the edge and take advantage of all available edge devices to cooperatively perform the CNN inference. We have observed that existing methodologies, utilizing different partitioning strategies to deploy a CNN model and perform inference at the edge on a distributed system, have several disadvantages. Therefore, in this paper, we propose a novel partitioning strategy, called Vertical Partitioning Strategy, together with a novel methodology needed to utilize our partitioning strategy efficiently, for CNN model inference on a distributed system at the edge. We compare our experimental results on the YOLOv2 CNN model with results obtained by the existing three methodologies and show the advantages of our methodologies in terms of memory requirement per edge device and overall system performance. Moreover, our experimental results on other representative CNN models show that our novel methodology utilizing our novel partitioning strategy is able to deliver CNN inference with very reduced memory requirement per edge device and improved overall system performance at the same time.
The data driven services in industrial automation systems are transforming the world of automation industry by optimizing industrial processes and providing Value Added Services (VASs) with the grace of Industry 4.0, ...
详细信息
暂无评论