scholarly journals ACIMS: Analog CIM Simulator for DNN Resilience

Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 686
Author(s):  
Dong Ding ◽  
Lei Wang ◽  
Zhijie Yang ◽  
Kai Hu ◽  
Hongjun He
Keyword(s):  
Energy Efficient ◽  
Fault Injection ◽  
Experimental Results ◽  
Hardware Accelerators ◽  
The Real ◽  
Analog Computing ◽  
Real Hardware ◽  
Computationally Intensive ◽  
Hardware Faults

Analog Computing In Memory (ACIM) combines the advantages of both Compute In Memory (CIM) and analog computing, making it suitable for the design of energy-efficient hardware accelerators for computationally intensive DNN applications. However, their use will introduce hardware faults that decrease the accuracy of DNN. In this work, we take Sandwich-Ram as the real hardware example of ACIM and are the first to propose a fault injection and fault-aware training framework for it, named Analog Computing In Memory Simulator (ACIMS). Using this framework, we can simulate and repair the hardware faults of ACIM. The experimental results show that ACIMS can recover 91.0%, 93.7% and 89.8% of the DNN’s accuracy drop through retraining on the MNIST, SVHN and Cifar-10 datasets, respectively; moreover, their adjusted accuracy can reach 97.0%, 95.3% and 92.4%.

Verification of Fault Control Measures Based on Fault Injection for MCU Control System

2014 ◽  
Vol 484-485 ◽  
pp. 325-331
Author(s):  
Dao Sen Niu ◽  
Xiao Dong Liu ◽  
Shou Qun Sun ◽  
Yang Liu
Keyword(s):  
Control System ◽  
Fault Diagnosis ◽  
Fault Injection ◽  
Short Circuit ◽  
Experimental Results ◽  
Control Measures ◽  
Level Variation ◽  
Software Fault ◽  
Hardware Faults ◽  
Software Measures

To verify the validity of fault control measures, a verification platform with software fault injection and hardware fault injection is developed to conduct fault diagnosis measures for MCU control system. For the faults occurring in the internal units of a controller, program debugger is employed to simulate software or hardware faults by varying the data; for the faults occurring in peripheral circuits, a circuit of fault-settings is employed to simulate hardware faults, i.e., open-/short-circuit and electrical level variation. This verification platform is applied to evaluate software measures to control the faults/errors in accordance with IEC60335/IEC60730/UL1998/CSA22.2.08, and a case of induction cooker is presented shows how it works. Experimental results show that the verification platform runs stably and accurately, and has a big value in practice.

МODERNIZATION TECHNOLOGY REPAIRING ACENTRIFUGAL WATER PUMP

2018 ◽  
pp. 48-51
Author(s):  
Sh.U. Yuldashev ◽  
D.T. Abdumuminova
Keyword(s):  
Production Process ◽  
Technological Process ◽  
Energy Efficient ◽  
Technical Support ◽  
Ultrasonic Processing ◽  
Water Pump ◽  
The Real ◽  
Technological Processes ◽  
Efficient Management ◽  
Pump Shaft

The article provides an overview of the principle of the pump D630-90, as well as methods for studying the real conditions of technical support to improve maintainability and optimize technological processes and systems. A technological process for the restoration of the shaft of a centrifugal water pump has been developed and an algorithm for managing it has been proposed, on the basis of which the system for energy-efficient management of the recovery area has been implemented. Also in the article some questions of use, metal-filled compound SK812, and also application of ultrasonic processing of a surface of a shaft of the centrifugal water pump of mark D630-90 are mentioned and considered. The developed technological process of pump shaft restoration showed that it is characterized by simplicity, it fits well into the production process of repair and can be widely used in repair shops.

scholarly journals A Multi-Resolution Approach to GAN-Based Speech Enhancement

2021 ◽  
Vol 11 (2) ◽  
pp. 721
Author(s):  
Hyung Yong Kim ◽  
Ji Won Yoon ◽  
Sung Jun Cheon ◽  
Woo Hyun Kang ◽  
Nam Soo Kim
Keyword(s):  
Speech Enhancement ◽  
Optimal Solution ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
The Real ◽  
Multi Scale ◽  
Adversarial Networks ◽  
Speech Characteristics ◽  
Conventional Methods ◽  
Convex Property

Recently, generative adversarial networks (GANs) have been successfully applied to speech enhancement. However, there still remain two issues that need to be addressed: (1) GAN-based training is typically unstable due to its non-convex property, and (2) most of the conventional methods do not fully take advantage of the speech characteristics, which could result in a sub-optimal solution. In order to deal with these problems, we propose a progressive generator that can handle the speech in a multi-resolution fashion. Additionally, we propose a multi-scale discriminator that discriminates the real and generated speech at various sampling rates to stabilize GAN training. The proposed structure was compared with the conventional GAN-based speech enhancement algorithms using the VoiceBank-DEMAND dataset. Experimental results showed that the proposed approach can make the training faster and more stable, which improves the performance on various metrics for speech enhancement.

scholarly journals GazeEMD: Detecting Visual Intention in Gaze-Based Human-Robot Interaction

Robotics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 68
Author(s):  
Lei Shi ◽  
Cosmin Copot ◽  
Steve Vanlanduit
Keyword(s):  
Cognitive Load ◽  
Real World ◽  
Robotic Manipulator ◽  
Similarity Score ◽  
Human Robot Interaction ◽  
Experimental Results ◽  
The Other ◽  
Robot Interaction ◽  
Run Length ◽  
The Real

In gaze-based Human-Robot Interaction (HRI), it is important to determine human visual intention for interacting with robots. One typical HRI interaction scenario is that a human selects an object by gaze and a robotic manipulator will pick up the object. In this work, we propose an approach, GazeEMD, that can be used to detect whether a human is looking at an object for HRI application. We use Earth Mover’s Distance (EMD) to measure the similarity between the hypothetical gazes at objects and the actual gazes. Then, the similarity score is used to determine if the human visual intention is on the object. We compare our approach with a fixation-based method and HitScan with a run length in the scenario of selecting daily objects by gaze. Our experimental results indicate that the GazeEMD approach has higher accuracy and is more robust to noises than the other approaches. Hence, the users can lessen cognitive load by using our approach in the real-world HRI scenario.

PERFORMANCE ANALYSIS OF THE SUPERCOMPUTER BASED ON RASPBERRY PI NODES

2021 ◽  
pp. 76-86
Author(s):  
Hai
Keyword(s):  
Performance Analysis ◽  
Energy Efficient ◽  
Multicore Processors ◽  
Electrical Power ◽  
Experimental Results ◽  
Raspberry Pi ◽  
Cooling Towers ◽  
Cluster Architecture ◽  
Cooling Technology ◽  
Almost All

In this paper, a new Raspberry PI supercomputer cluster architecture is proposed. Generally, to gain speed at petaflops and exaflops, typical modern supercomputers based on 2009-2018 computing technologies must consume between 6 MW and 20 MW of electrical power, almost all of which is converted into heat, requiring high cost for cooling technology and Cooling Towers. The management of heat density has remained a key issue for most centralized supercomputers. In our proposed architecture, supercomputers with highly energy-efficient mobile ARM processors are a new choice as it enables them to address performance, power, and cost issues. With ARM’s recent introduction of its energy-efficient 64-bit CPUs targeting servers, Raspberry Pi cluster module-based supercomputing is now within reach. But how is the performance of supercomputers-based mobile multicore processors? Obtained experimental results reported on the proposed approach indicate the lower electrical power and higher performance in comparison with the previous approaches.

scholarly journals An Efficient Fault-Tolerant Multi-Bus Data Scheduling Algorithm Based on Replication and Deallocation

2016 ◽  
Vol 16 (2) ◽  
pp. 69-84
Author(s):  
Chafik Arar ◽  
Mohamed Salah Khireddine
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Fault Tolerant ◽  
Scheduling Algorithm ◽  
Experimental Results ◽  
Data Scheduling ◽  
Heterogeneous Architectures ◽  
Hardware Faults

Abstract The paper proposes a new reliable fault-tolerant scheduling algorithm for real-time embedded systems. The proposed scheduling algorithm takes into consideration only one bus fault in multi-bus heterogeneous architectures, caused by hardware faults and compensated by software redundancy solutions. The proposed algorithm is based on both active and passive backup copies, to minimize the scheduling length of data on buses. In the experiments, this paper evaluates the proposed methods in terms of data scheduling length for a set of DAG benchmarks. The experimental results show the effectiveness of our technique.

Sign in / Sign up

Export Citation Format

Share Document