Attention Deeplabv3 model and its application into gear pitting measurement

An efficient visual detection method is explored in this study to address the low accuracy and efficiency of manual detection for irregular gear pitting. The results of gear pitting detection are enhanced by embedding two attention modules into Deeplabv3 + to obtain an improved segmentation model called attention Deeplabv3. The attention mechanism of the proposed model endows the latter with an enhanced ability for feature representation of small and irregular objects and effectively improves the segmentation performance of Deeplabv3. The segmentation ability of attention Deeplabv3+ is verified by comparing its performance with those of other typical segmentation networks using two public datasets, namely, Cityscapes and Voc2012. The proposed model is subsequently applied to segment gear pitting and tooth surfaces simultaneously, and the pitting area ratio is calculated. Experimental results show that attention Deeplabv3 has higher segmentation performance and measurement accuracy compared with the existing classical models under the same computing speed. Thus, the proposed model is suitable for measuring various gear pittings.

OptiDepthNet : A Real-time Unsupervised Monocular Depth Estimation Network

With the development of depth learning, the accuracy and effect of the algorithm applied to monocular depth estimation have been greatly improved, but the existing algorithms need a lot of computing resources. At present, how to apply the existing algorithms to UAV and its small robot is an urgent need.Based on full convolution neural network and Kitti dataset, this paper uses deep separable convolution to optimize the network architecture, reduce training parameters and improve computing speed. Experimental results show that our method is very effective and has a certain reference value in the development direction of monocular depth estimation algorithm.

Modified KNN-LVQ for Stairs Down Detection Based on Digital Image

Persons with visual impairments need a tool that can detect obstacles around them. The obstacles that exist can endanger their activities. The obstacle that is quite dangerous for the visually impaired is the stairs down. The stairs down can cause accidents for blind people if they are not aware of their existence. Therefore we need a system that can identify the presence of stairs down. This study uses digital image processing technology in recognizing the stairs down. Digital images are used as input objects which will be extracted using the Gray Level Co-occurrence Matrix method and then classified using the KNN-LVQ hybrid method. The proposed algorithm is tested to determine the accuracy and computational speed obtained. Hybrid KNN-LVQ gets an accuracy of 95%. While the average computing speed obtained is 0.07248 (s).

Research on Practical Intelligent Mode of Digital Image Economy Based on Improved Genetic Multilayer Neural Network

In the context of economic globalization and digitization, the current financial field is in an unprecedented complex situation. The methods and means to deal with this complexity are developing towards image intelligence. This paper takes financial prediction as the starting point, selects the artificial neural network in the intelligent algorithm and optimizes the algorithm, forecasts through the improved multilayer neural network, and compares it with the traditional neural network. Through comparison, it is found that the prediction success rate of the improved genetic multilayer neural network increases with the increase of the dimension of the input image data. This shows that, by adding more technical indicators as the input of the combined network, the prediction efficiency of the improved genetic multilayer neural network can be further improved and the advantage of computing speed can be maintained.

Study of a Privacy Preserving Logistic Regression Algorithm (PPLRA) For Data Privacy in the Context of Big Data

Regression algorithms are commonly used in machine learning. Based on encryption and privacy protection methods, the current key hot technology regression algorithm and the same encryption technology are studied. This paper proposes a PPLAR based algorithm. The correlation between data items is obtained by logistic regression formula. The algorithm is distributed and parallelized on Hadoop platform to improve the computing speed of the cluster while ensuring the average absolute error of the algorithm.

The Security of Cryptosystems Based on Error-Correcting Codes

Quantum computers are distinguished by their enormous storage capacity and relatively high computing speed. Among the cryptosystems of the future, the best known and most studied which will resist when using this kind of computer are cryptosystems based on error-correcting codes. The use of problems inspired by the theory of error-correcting codes in the design of cryptographic systems adds an alternative to cryptosystems based on number theory, as well as solutions to their vulnerabilities. Their security is based on the problem of decoding a random code that is NP-complete. In this chapter, we will discuss the cryptographic properties of error-correcting codes, as well as the security of cryptosystems based on code theory.

Increasing Information Entropy of Both Weights and Activations for the Binary Neural Networks

In terms of memory footprint requirement and computing speed, the binary neural networks (BNNs) have great advantages in power-aware deployment applications, such as AIoT edge terminals, wearable and portable devices, etc. However, the networks’ binarization process inevitably brings considerable information losses, and further leads to accuracy deterioration. To tackle these problems, we initiate analyzing from a perspective of the information theory, and manage to improve the networks information capacity. Based on the analyses, our work has two primary contributions: the first is a newly proposed median loss (ML) regularization technique. It improves the binary weights distribution more evenly, and consequently increases the information capacity of BNNs greatly. The second is the batch median of activations (BMA) method. It raises the entropy of activations by subtracting a median value, and simultaneously lowers the quantization error by computing separate scaling factors for the positive and negative activations procedure. Experiment results prove that the proposed methods utilized in ResNet-18 and ResNet-34 individually outperform the Bi-Real baseline by 1.3% and 0.9% Top-1 accuracy on the ImageNet 2012. Proposed ML and BMA for the storage cost and calculation complexity increments are minor and negligible. Additionally, comprehensive experiments also prove that our methods can be applicable and embedded into the present popular BNN networks with accuracy improvement and negligible overhead increment.

Photonic Matrix Computing: From Fundamentals to Applications

In emerging artificial intelligence applications, massive matrix operations require high computing speed and energy efficiency. Optical computing can realize high-speed parallel information processing with ultra-low energy consumption on photonic integrated platforms or in free space, which can well meet these domain-specific demands. In this review, we firstly introduce the principles of photonic matrix computing implemented by three mainstream schemes, and then review the research progress of optical neural networks (ONNs) based on photonic matrix computing. In addition, we discuss the advantages of optical computing architectures over electronic processors as well as current challenges of optical computing and highlight some promising prospects for the future development.

Application of Facebook’s Prophet Model for Forecasting Meteorological Data

The wildfire risk index was calculated based on current meteorological information, for example, temperature, humidity, and wind speed. Thus, meteorological data forecasting could help estimate the probability of fire occurrence or spreading speed to prevent large wildfires. This study predicts meteorological data (e.g., temperature, humidity, and wind speed) using Facebook's Prophet library. We trained the Prophet model using meteorological data between 2016 and 2018 in Goseong, Gangwon-do (where the wildfire occurred in 2019) and predicted meteorological data for the first four months in 2019. We obtained that Facebook's Prophet model was effective in computing speed and predicting the overall trend. However, it could not predict sudden irregular changes satisfactorily. Considering its rapidity, these results could play an important role in future research, especially as a basic research for time-series forecasting.

Comparative Analysis Study on SSD, HDD, and SSHD

In the Current Century, permeant storage devices and methods of storing data changed from traditional HDD to SDD. In this document, we discuss the merge of HDD and SSD. The Abbreviation of SSHD is called the solid-state hybrid disk. A mixture of both secondary devices to enhance the performance of the system. Inside the SSD, data movement events occur without any user input. Recent research has suggested that SSD has only the Replacement of secondary storage. HDD is also good in life span with longer life. It’s more reliable for long time data contained in this. HDD storage has typical magnetic fields for store data. SSD contains NAND flash memory to write the data in the drive. Based on the method and material of storing different. HDD and SSD feature well to upgrade with technology in Computer filed. For enhancing computing speed and excellent processing SSHD good to use in computer.Ratio increase of SSHD usage in current laptop and in computer system.