scholarly journals An Integrated Process for Verifying Deep Learning Classifiers Using Dataset Dissimilarity Measures

2021 ◽  
Vol 11 (2) ◽  
pp. 1-21
Author(s):  
Darryl Hond ◽  
Hamid Asgari ◽  
Daniel Jeffery ◽  
Mike Newman
Keyword(s):  
Deep Learning ◽  
Dynamic Testing ◽  
Autonomous Systems ◽  
System Level ◽  
Integrated Process ◽  
Dissimilarity Measures ◽  
Classifier Performance ◽  
On Line ◽  
Artificial Neural Network Ann ◽  
Ann Classifier

The specification and verification of algorithms is vital for safety-critical autonomous systems which incorporate deep learning elements. We propose an integrated process for verifying artificial neural network (ANN) classifiers. This process consists of an off-line verification and an on-line performance prediction phase. The process is intended to verify ANN classifier generalisation performance, and to this end makes use of dataset dissimilarity measures. We introduce a novel measure for quantifying the dissimilarity between the dataset used to train a classification algorithm, and the test dataset used to evaluate and verify classifier performance. A system-level requirement could specify the permitted form of the functional relationship between classifier performance and a dissimilarity measure; such a requirement could be verified by dynamic testing. Experimental results, obtained using publicly available datasets, suggest that the measures have relevance to real-world practice for both quantifying dataset dissimilarity, and specifying and verifying classifier performance.

A Computer Vision-Based Method for Classification of Red Meat Quality After Nitrosamine Appendage

2021 ◽  
pp. 2150005
Author(s):  
Monika Arora ◽  
Parthasarathi Mangipudi
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Food Samples ◽  
Red Meat ◽  
Support Vector ◽  
Svm Classifier ◽  
Deep Convolutional Neural Networks ◽  
Improved Performance ◽  
Artificial Neural Network Ann ◽  
Ann Classifier

Nitrosamine is a carcinogenic chemical used as a preservative in red meat whose identification is an ordeal. This paper presents a computer vision-based non-destructive method for identifying quality disparities between preservative treated and untreated (control) red meat. To access the discrepancy in the quality of red meat, both traditional machine learning and deep learning-based methods have been used. Support vector machine (SVM) classifier and artificial neural network (ANN) models have been used to detect the presence of nitrosamine in test samples. The paper also made use of different pre-trained deep convolutional neural networks (DCNN) with transfer learning approach such as ResNet-34, ResNet-50, ResNet-101, VGG-16, VGG-19, AlexNet and MobileNetv2 to examine the presence of nitrosamine in the food samples. While the ANN classifier performed better in comparison to the SVM classifier, the highest testing accuracy and F1-score were obtained using the deep learning model, ResNet-101 with 95.45% and 96.54%, respectively. The experimental results demonstrate an improved performance in comparison to the existing methods; indicating the feasibility of the proposed work for food quality control in real-time applications.

scholarly journals Intelligent long-term performance analysis in power electronics systems

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Saeed Peyghami ◽  
Tomislav Dragicevic ◽  
Frede Blaabjerg
Keyword(s):  
Performance Indicator ◽  
Thermal Characteristics ◽  
Operating Conditions ◽  
System Level ◽  
Power Electronic ◽  
Reliability Modeling ◽  
Artificial Neural Network Ann ◽  
Long Term Performance ◽  
Term Performance

AbstractThis paper proposes a long-term performance indicator for power electronic converters based on their reliability. The converter reliability is represented by the proposed constant lifetime curves, which have been developed using Artificial Neural Network (ANN) under different operating conditions. Unlike the state-of-the-art theoretical reliability modeling approaches, which employ detailed electro-thermal characteristics and lifetime models of converter components, the proposed method provides a nonparametric surrogate model of the converter based on limited non-linear data from theoretical reliability analysis. The proposed approach can quickly predict the converter lifetime under given operating conditions without a further need for extended, time-consuming electro-thermal analysis. Moreover, the proposed lifetime curves can present the long-term performance of converters facilitating optimal system-level design for reliability, reliable operation and maintenance planning in power electronic systems. Numerical case studies evaluate the effectiveness of the proposed reliability modeling approach.

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

scholarly journals Design of a Microwave Lowpass – Bandpass Filter using Deep Learning and Artificial Intelligence

2021 ◽  
Vol 3 (1) ◽  
pp. 1-16
Author(s):  
Saeed Roshani ◽  
◽  
Hossein Heshmati ◽  
Sobhan Roshani ◽  
◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Insertion Loss ◽  
Dual Band ◽  
Transmission Zeros ◽  
Compact Size ◽  
Electrical Devices ◽  
Low Pass ◽  
Artificial Neural Network Ann ◽  
Better Than

In this paper, a lowpass – bandpass dual band microwave filter is designed by using deep learning and artificial intelligence. The designed filter has compact size and desirable pass bands. In the proposed filter, the resonators with Z-shaped and T-shaped lines are used to design the low pass channel, while coupling lines, stepped impedance resonators and open ended stubs are utilized to design the bandpass channel. Artificial neural network (ANN) and deep learning (DL) technique has been utilized to extract the proposed filter transfer function, so the values of the transmission zeros can be located in the desired frequency. This technique can also be used for the other electrical devices. The lowpass channel cut off frequency is 1 GHz, with better than 0.2 dB insertion loss. Also, the bandpass channel main frequency is designed at 2.4 GHz with 0.5 dB insertion loss in the passband.

scholarly journals Palmprint Recognition in Uncontrolled and Unco-operative Environment

2021 ◽  
Vol 9 (8) ◽  
pp. 1711-1718
Author(s):  
Jayakrishnan S Kumar
Keyword(s):  
Deep Learning ◽  
Learning Rule ◽  
Industrial Applications ◽  
Palmprint Recognition ◽  
User Cooperation ◽  
Victim Identification ◽  
Palmprint Identification ◽  
On Line ◽  
End To End ◽  
Area Unit

Abstract: On-line palmprint recognition and latent palmprint identification unit two branches of palmprint studies. The previous uses middle-resolution footage collected by a camera in an exceedingly} very well-controlled or contact-based surroundings with user cooperation for industrial applications and so the latter uses high resolution latent palmprints collected in crime scenes for rhetorical investigation. However, these two branches do not cowl some palmprint footage that have the potential for rhetorical investigation. Attributable to the prevalence of smartphone and shopper camera, further proof is at intervals the variability of digital footage taken in uncontrolled and uncooperative surroundings. However, their palms area unit typically noticeable. To visualize palmprint identification on footage collected in uncontrolled and uncooperative surroundings, a novel palmprint info is established Associate in nursing AN end-to-end deep learning rule is projected. The new data named NTU Palmprints from the net (NTU-PI-v1) contains 7881 footage from 2035 palms collected from the net. The projected rule consists of Associate in Nursing alignment network and a feature extraction network and is end-to-end trainable. The projected rule is compared with the progressive on-line palmprint recognition ways that and evaluated on three public contactless palmprint infos, IITD, CASIA, and PolyU and a couple of new databases, NTU-PI-v1 and NTU contactless palmprint info. The experimental results showed that the projected rule outperforms the current palmprint recognition ways that. Keywords: Biometrics, criminal and victim identification, forensics, palmprint recognition

Characteristic of Fuzzy, ANN, and ANFIS for Brushless DC Motor Controller: An Evaluation by Dynamic Test

2021 ◽  
Vol 13 (6) ◽  
Author(s):  
◽  
Andi Setiawan ◽  
Bayu Rudiyanto ◽  
Satryo Budi Utomo ◽  
Muji Muji Setiyo ◽  
...  
Keyword(s):  
Fuzzy Logic Controller ◽  
Fuzzy Inference ◽  
Dynamic Testing ◽  
Dynamic Test ◽  
Absolute Error ◽  
Inference System ◽  
Brushless Dc ◽  
Average Value ◽  
Constant Torque ◽  
Artificial Neural Network Ann

Brushless DC (BLDC) motors are the most popular motors used by the industry because they are easy to control. BLDC motors are generally controlled by artificial controls such as Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). However, the performance of the BLDC control system in previous studies was compared separately with their respective parameters, making it difficult to evaluate comprehensively. Therefore, in order to investigate the characteristic performance of Fuzzy, ANN, and ANFIS, this article provides a comparison of these artificial controls. Two scenarios of the dynamic tests are conducted to investigate control performance under constant torque-various speed and constant speed-various torque. By dynamic testing, characteristics of Fuzzy, ANN, and ANFIS can be observed as real applications. The testing parameters are: Settling Time, Overshoot and Overdamp (in the graph and average value), and then statistic performance are: Integral Square Error (ISE), Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Mean Absolute Error (MAE). The test result in scenario 1 showed that the ANN has a better performance compared to other controllers with the MAE, IAE, ITAE, and ISE value of 31.3003; 105.6280; 208.0630; and 5,7289 e4, respectively. However, in scenario 2, ANN only has a better performance compared to other controllers on just a few parameters. In scenario 2, ANN is indeed able to maintain speed but it has a more ripple value than ANFIS. Even so, the ripple that occurs in ANN does not have too much value compared to the setpoint. Therefore, the MAE value of the ANN is smaller than the ANFIS (18.8937 of ANN and 28.4685 of ANFIS).

Advanced SiP Packaging Technologies of IPD for Mobile Applications

2010 ◽  
Vol 2010 (DPC) ◽  
pp. 1-20
Author(s):  
Geun Sik Kim ◽  
Kai Liu ◽  
Flynn Carson ◽  
Seung Wook Yoon ◽  
Meenakshi Padmanathan
Keyword(s):  
High Performance ◽  
Low Cost ◽  
Autonomous Systems ◽  
System Level ◽  
Design And Technology ◽  
Wafer Level ◽  
Future Technology ◽  
Rf Transceivers ◽  
And Performance ◽  
3D Stacking

IPD technology was originally developed as a way to replace bulky discrete passive components, but it¡¯s now gaining popularity in ESD/EMI protection applications, as well as in RF, high-brightness LED silicon sub-mounts, and digital and mixed-signal devices. Already well known as a key enabler of system-in-packages (SiPs), IPDs enable the assembly of increasingly complete and autonomous systems with the integration of diverse electronic functions such as sensors, RF transceivers, MEMS, power amplifiers, power management units, and digital processors. The application area for IPD will continue to evolve, especially as new packaging technology, such as flipchip, 3D stacking, wafer level packaging become available to provide vertical interconnections within the IPD. New applications like silicon interposers will become increasingly significant to the market. Currently the IPD market is being driven primarily by RF or wireless packages and applications including, but not limited to, cell phones, WiFi, GPS, WiMAX, and WiBro. In particular, applications and products in the emerging RF CMOS market that require a low cost, smaller size, and high performance are driving demand. In order to get right products in size and performance, packaging design and technology should be considered in device integration and implemented together in IPD designs. In addition, a comprehensive understanding of electrical and mechanical properties in component and system level design is important. This paper will highlight some of the recent advancements in SiP technology for IPD and integration as well as what is developed to address future technology requirements in IPD SiP solutions. The advantage and applications of SiP solution for IPD will be presented with several examples of IPD products. The design, assembly and packaging challenges and performance characteristics will be also discussed.

Sign in / Sign up

Export Citation Format

Share Document