Least-squares method and deep learning in the identification and analysis of name-plates of power equipment

This article proposes a nameplate recognition method based on the least-squares method and deep learning algorithm character feature fusion. This method extracts the histogram of the edge direction of the character and constructs the histogram feature vector based on the wavelet transform deep learning algorithm. We use classifier training for the text recognition of the nameplate to segment the text into individual characters. Then, we extract the character features to build a template. Experiments prove that the algorithm meets the practical application needs of nameplate identification of power equipment and achieves the design goals.

Magnetic resonance imaging texture analysis in the quantitative evaluation of acute osteomyelitis of the mandibular bone

Objectives: Accurate assessment of radiological images can help in early diagnosis and therapy of suppurative osteomyelitis (OM). The purpose of this study was to apply texture analysis to MRI as a means of quantitatively evaluating acute OM of the mandible. Methods: We analyzed the data from 38 patients who complained of pain and underwent MRI between April 2017 and March 2019. From the MRIs of these patients, with (n = 19) and without OM (n = 19), 279 radiomics features were extracted using short tau inversion recovery, data of the regions of interest and analyzed with MaZda v. 3.3. 10 features, including one histogram feature (90th percentile), eight gray-level co-occurrence matrix features (Sum Averg), and one gray-level run-length matrix feature (Horzl_RLNonUni), were selected using Fisher coefficient and compared between the acute OM and non-OM groups. The two groups were compared using Mann–Whitney U test with p value set at 0.05. Results: All 10 radiomics features showed significant differences between the acute OM and non-OM groups (p < 0.05). Conclusions: MRI texture analysis has potential application in radiomics diagnosis of acute OM of the mandible.

Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification

We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum.

Adaptive Extraction Method Based on Time-Frequency Images for Fault Diagnosis in Rolling Bearings of Motor

In order to diagnose the faults of rolling bearings in motors via time-frequency analysis of bearing vibration signals quickly, this paper puts forward a method of extracting the main components from time-frequency images. A threshold is adaptively determined based on the gray histogram feature of the time-frequency images obtained from the vibration signals of the motor rolling bearings. Then, a mask template is generated by the threshold and a binarization processing. Based on a multiplication operation between the mask template and the original time-frequency image, the signal component with low energy in the time-frequency image is filtered out, and only the main components with high energy is remained for fault diagnosis, which is convenient for the subsequent identification of the faults for motor rolling bearings. The main components in the time-frequency images can be retained adaptively with the thresholds determined by the time-frequency images themselves.

Multiple Detection and Tracking of Multi Class Vehicles using Locality Sensitive Histogram.

Multiple object detection and tracking in a cluttered background is most important in vision-based applications. In this paper, the goal is to develop a classifier that detects and tracks multiple objects thereby ensuring robustness and accuracy. Locality Sensitive Histogram feature extraction is used, which adds contributions from all the pixels in an image. These features extracted are trained using decision tree classifier which performs with an accuracy of 97%. Experimental results demonstrate the objects tracked and detected under different scale and pose variations. Evaluation and comparison of the proposed method with various other techniques is performed using performance parameters. Results depict that the proposed technique outperforms with increased accuracy and is the top performer

File Fragment Classification using Content Based Analysis

One of the major components in Digital Forensics is the extraction of files from a criminal’s hard drives. To achieve this, several techniques are used. One of these techniques is using file carvers. File carvers are used when the system metadata or the file table is damaged but the contents of the hard drive are still intact. File carvers work on the raw fragments in the hard disk and reconstruct files by classifying the fragments and then reassembling them to form the complete file. Hence the classification of file fragments has been an important problem in the field of digital forensics. The work on this problem has mainly relied on finding the specific byte sequences in the file header and footer. However, classification based on header and footer is not reliable as they may be modified or missing. In this project, the goal is to present a machine learningbased approach for content-based analysis to recognize the file types of file fragments. It does so by training a Feed-Forward Neural Network with a 2-byte sequence histogram feature vector which is calculated for each file. These files are obtained from a publicly available file corpus named Govdocs1. The results show that content-based analysis is more reliable than relying on the header and footer data of files.

Measuring clock jitter and data signals for bit error detection in optical transceiver systems

This work demonstrates how to measure jitter using the eye diagram Analyzer histogram feature. Bit sequence generator is employed with the NRZ Pulse generator with the electrical jitter in order to measure the signal amplitude level. We have modulated the light signal from CW Laser with the electrical signal by Mach-Zehnder Modulator through 5 km fiber cables. The signal can be amplified with a gain of 7 dB with the presence of transimpedence amplifier. The combination of electrical signal and signal from noise source can be filtered by using the low pass Gaussian filter.