Optical Memory and Neural Networks最新文献

Application of Deep Neural Network Structures in Semantic Segmentation for Road Scene Understanding 深度神经网络结构在道路场景语义分割中的应用

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020108

Qusay Sellat, Kanagachidambaresan Ramasubramanian

引用次数: 0

Detection and Prediction of Breast Cancer Using Improved Faster Regional Convolutional Neural Network Based on Multilayer Perceptron’s Network 基于多层感知器网络的改进更快区域卷积神经网络乳腺癌检测与预测

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020054

Poonam Rana, Pradeep Kumar Gupta, Vineet Sharma

{"title":"Detection and Prediction of Breast Cancer Using Improved Faster Regional Convolutional Neural Network Based on Multilayer Perceptron’s Network","authors":"Poonam Rana, Pradeep Kumar Gupta, Vineet Sharma","doi":"10.3103/S1060992X23020054","DOIUrl":"10.3103/S1060992X23020054","url":null,"abstract":"One of the most frequent causes of death for women worldwide is breast cancer. In most cases, breast cancer can be quickly identified if certain symptoms emerge. But many women with breast cancer don’t show any symptoms. So, it is very critical to detect this disease in early stage also numerous radiologists are needed to diagnose this disease which is quite expensive for the majority of cancer hospitals. To address these concerns, the proposed methodology creates a Faster-Regional Convolutional Neural Network (Faster-RCNN) for recognizing breast cancer. Ultrasound images are collected and pre-processed utilizing resizing, adaptive median filter, histogram global contrast enhancement and high boost filtering. Image resizing is utilized to change the image size without cutting anything out. Adaptive median filter is utilized to remove unwanted noise present in the resized image. Histogram global contrast enhancement is used to enhancing the contrast level of the image. High boost filtering is utilized to sharpening the edges present in the image. After that, pre-processed images are fetched as an input to Faster R-CNN, which extract the features and segment the accurate region of the tumour. These segmented regions are classified using Multilayer Perceptron’s for detecting whether the patients are affected by breast cancer or not. According to the experimental study, the proposed approach achieves 97.1% correctness, 0.03% error, 91% precision and 93% specificity. Therefore, the developed approach attains better performance compared to other existing approaches. This prediction model helps to detect breast cancer at early stage and improve patient’s living standard.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"32 2","pages":"86 - 100"},"PeriodicalIF":0.9,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"4895873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving the Performance of Human Part Segmentation Based on Swin Transformer 改进基于Swin变压器的人体部位分割性能

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020030

Juan Du, Tao Yang

{"title":"Improving the Performance of Human Part Segmentation Based on Swin Transformer","authors":"Juan Du,  Tao Yang","doi":"10.3103/S1060992X23020030","DOIUrl":"10.3103/S1060992X23020030","url":null,"abstract":"One of the current challenges in deep learning is semantic segmentation. Moreover, human part segmentation is a sub-task in image segmentation, which differs from traditional segmentation to understand the human body’s intrinsic connections. Convolutional Neural Network (CNN) has always been a standard feature extraction network in human part segmentation. Recently, the proposed Swin Transformer surpasses CNN for many image applications. However, few articles have explored the performance of Swin Transformer in human part segmentation compared to CNN. In this paper, we make a comparison experiment on this issue, and the experimental results prove that even in the area of human part segmentation and without any additional trick, the Swin Transformer has good results compared with CNN. At the same time, this paper also combines the Edge Perceiving Module (EPM) currently commonly used in CNN with Swin Transformer to prove that Swin Transformer can see the intrinsic connection of segmented parts. This research demonstrates the feasibility of applying Swin Transformer to the part segmentation of images, which is conducive to advancing image segmentation technology in the future.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"32 2","pages":"101 - 107"},"PeriodicalIF":0.9,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"4898556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Filters Based on Defect Modes by 1D Star Waveguides Defective System 基于一维星形波导缺陷系统缺陷模式的滤波器

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020029

Y. Ben-Ali, Y. Errouas, I. El Kadmiri, Z. Rahou, A. Hallaoui, D. Bria

{"title":"Filters Based on Defect Modes by 1D Star Waveguides Defective System","authors":"Y. Ben-Ali, Y. Errouas, I. El Kadmiri, Z. Rahou, A. Hallaoui, D. Bria","doi":"10.3103/S1060992X23020029","DOIUrl":"10.3103/S1060992X23020029","url":null,"abstract":"In this paper, we present a theoretical study of the properties of defect modes in one-dimensional defective photonic star waveguides (SWGs). Both symmetrically and asymmetrically stacked defective SWGs are considered in the analysis. The properties of the defect modes are studied through the calculation of the frequency-dependent transmittance. We have also explored the effects of defect length and permittivity, as well as the position of the defect and the number of resonators grafted onto the SWGs on the number of defect modes, their transmission, and their quality factor. The findings demonstrate that geometric defects result in two modes of maximum transmission with a high-quality factor (({{Q}_{1}} = 358) and ({{Q}_{2}} = 1550)). However, when there are both geometric and material defects, the quality factor of the second filter ({{Q}_{2}}) improved from 1550 to 2203, while the quality factor of the first filter ({{Q}_{1}})remains almost unchanged. Moreover, when only material defects are present, two electromagnetic filters with maximum transmission and high-quality factor (({{Q}_{1}} = 1708) and ({{Q}_{2}} = 9085)) can be obtained.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"32 2","pages":"108 - 125"},"PeriodicalIF":0.9,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"4895869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Text-Text Neural Machine Translation: A Survey 文本-文本神经机器翻译研究综述

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020042

Ebisa Gemechu, G. R. Kanagachidambaresan

引用次数: 0

Optimized Lung Nodule Prediction Model for Lung Cancer Using Contour Features Extraction 基于轮廓特征提取的肺癌肺结节预测模型优化

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020091

Faiyaz Ahmad, U. Hariharan, S. Karthick, Vaibhav Eknath Pawar, S. Sharon Priya

{"title":"Optimized Lung Nodule Prediction Model for Lung Cancer Using Contour Features Extraction","authors":"Faiyaz Ahmad, U. Hariharan, S. Karthick, Vaibhav Eknath Pawar,  S. Sharon Priya","doi":"10.3103/S1060992X23020091","DOIUrl":"10.3103/S1060992X23020091","url":null,"abstract":"Lung cancer is one of the most complicated diseases in human assessment. It affects the lives of humans critically. For the treatment of the lungs and prevention of the disease, it is important for an accurate and timely diagnosis of the disease. In most aspects, it was not as successful as the traditional method, which uses past medical history. Classification techniques are effective and reliable in categorizing affected lungs and people with normal lungs. But unfortunately failed to provide proper nodule location as this became a tedious task to find it. In the proposed method, Hybrid Particle Swarm Optimization-Lung Nodule Candidate (HPSO-LNDC) Detection depends on the diagnostic system using disease image data set for lung segmentation assessment. Initially, the input Data images are pre-processed to reduce the computational complexity of the system. Then, those segmented images are subject to the proposed HPSO-LNDC model. To solve the problem of accuracy, so many researchers have used slicing techniques, but most of these techniques are stuck in the local minima and suffer from premature convergence. Therefore the HPSO-LNDC model is integrated with the Hybrid PSO to reduce loss function occurring in the lung nodule detection architecture. Such a combination helps the HPSO-LNDC to avoid low similarity values. The proposed algorithm is simulated using the MATLAB tool and tested experimentally. It is defined as accuracy, detection level and Dice Similarity Coefficient (DSC). Results show that HPSO-LNDC with 85% accuracy and DSC of 90% was better than conventional methods.","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"32 2","pages":"126 - 136"},"PeriodicalIF":0.9,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"4895882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Recognition of Mentally Pronounced Russian Phonemes Using Convolutional Neural Networks and Electroencephalography Data 利用卷积神经网络和脑电图数据识别俄语语音

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X23020066

L. E. Seleznyev, A. A. Chupakhin, V. A. Kostenko, A. O. Shevchenko, A. V. Vartanov

引用次数: 1

Design and Simulation of a Reconfigurable Multifunctional Optical Sensor 可重构多功能光学传感器的设计与仿真

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-06-23 DOI: 10.3103/S1060992X2302008X

Shaher Dwik, G. Sasikala, S. Natarajan

{"title":"Design and Simulation of a Reconfigurable Multifunctional Optical Sensor","authors":"Shaher Dwik, G. Sasikala, S. Natarajan","doi":"10.3103/S1060992X2302008X","DOIUrl":"10.3103/S1060992X2302008X","url":null,"abstract":"Generally, in Visible Light Communication (VLC) systems, Position Sensitive Device (PSD) sensor is used only for tracking purposes. However, the tracking process functions until both transmitter and receiver align, thus the PSD sensor remains idle for a long time. This interval can be exploited to achieve other functions by modifying its architecture. In this paper, a modification of the PSD structure has been achieved to make it able to perform energy harvesting and data acquisition as well as tracking. As the PSD is mainly formed of an array of photodiodes, our main idea is to use transistors to switch between the two modes of operation of the photodiodes (photoconductive and photovoltaic). Furthermore, switching between the output pins could be achieved depending on the desired function. The proposed sensor can extend the battery lifetime, increase the integration and the functionality, and reduce the physical size of the system. Simulation using MATALB was performed to validate the concept of the proposed structure and its operation. The results showed that the proposed sensor works successfully and it can be considered for further manufacturing levels. The presented sensor might be used in Free Space Optical (FSO) communication like cube satellite, or even in Underwater Wireless Optical Communication (UWOC).","PeriodicalId":721,"journal":{"name":"Optical Memory and Neural Networks","volume":"32 2","pages":"147 - 157"},"PeriodicalIF":0.9,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"4898691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Density Function of Weighted Sum of Chi-Square Variables with Trigonometric Weights 三角加权卡方变量和的密度函数

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-04-02 DOI: 10.3103/S1060992X23010071

V. I. Egorov, B. V. Kryzhanovsky

引用次数: 0

Lidar Measurement of the Raman Differential Cross Section by Hydrogen Molecules 氢分子拉曼微分截面的激光雷达测量

IF 0.9

Optical Memory and Neural Networks Pub Date : 2023-04-02 DOI: 10.3103/S1060992X23010034

V. E. Privalov, V. G. Shemanin

引用次数: 0