2021 5th Conference on Information and Communication Technology (CICT)最新文献_第2页

Methodology for Identification of Quality of clean-Cut surface for IS2062HR sheet metal blanking using Random Forest IS2062HR板材冲裁表面质量的随机森林识别方法

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672340

Vijaya Patill, Pradip P. Patil, Nilesh Ingale, Hema Date

{"title":"Methodology for Identification of Quality of clean-Cut surface for IS2062HR sheet metal blanking using Random Forest","authors":"Vijaya Patill, Pradip P. Patil, Nilesh Ingale, Hema Date","doi":"10.1109/CICT53865.2020.9672340","DOIUrl":"https://doi.org/10.1109/CICT53865.2020.9672340","url":null,"abstract":"In the instance of sheet metal blanking, poor cut-surface quality of a blanked surface might cause fit difficulties in the assembly. Due to the uneven surface, cracks may occur, resulting in a loss of surface quality and dimensional precision. The quality of clean-cut surface is investigated using four parameters: punch penetration, shear angle, fracture angle, and burr height are considered for the present study. The depth of punch penetration is gradually raised to identify where the crack starts. Shear angle, fracture angle, and punch penetration following punching, as well as burr height, are considered input factors. On the power press, the uni-punch tool is utilized as a cutting tool, and the processing material is IS2062HR sheet metal. The objective of this work is to use the surface roughness value to classify cut-surface quality into three categories for decision making on fit for assembly operation. To forecast the quality of cut surface, a classification model is created using the Random Forst Classifier method of the Machine Learning approach. The Gini and Entropy index method revealed that the model is 93 percent accurate.","PeriodicalId":265498,"journal":{"name":"2021 5th Conference on Information and Communication Technology (CICT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115695071","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

An Efficient Transfer Learning Based Approach for Detecting the Abnormal Fundus Images 一种基于迁移学习的眼底异常图像检测方法

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672382

Pratik Joshi, M. V

{"title":"An Efficient Transfer Learning Based Approach for Detecting the Abnormal Fundus Images","authors":"Pratik Joshi, M. V","doi":"10.1109/CICT53865.2020.9672382","DOIUrl":"https://doi.org/10.1109/CICT53865.2020.9672382","url":null,"abstract":"The vision disabilities are seemingly increasing and prevalent across the world. The current diagnosis require a manual expert for diagnosis. The advancement regarding research in AI for healthcare applications has been focused in recent years. The retinal fundus imaging system is used to capture the retinal images. Those retinal fundus images can be used to detect the vision impairments. Prior research has thoroughly investigated regarding detecting the particular type of disease such as diabetic retinopathy, cataract, glaucoma etc. However, only a little research has been conducted to classify a given retinal image into normal and abnormal fundus image. In this paper, a novel transfer learning based method to detect the abnormal fundus image has been proposed. The EfficientNetV2 has been used as classification model, which aids in classifying the normal and abnormal fundus images. To our knowledge, the EfficientNetV2 has not been used as a transfer learning model before. The proposed model has been evaluated against the recent state-of-the-art models including transformers and multi layer perceptron(MLP) based models which have been found to be working well on the image classification task. It has been observed that convolutional neural networks are still performing better than the recent transformer based models and MLP based models for detecting abnormal fundus images. The proposed model has achieved 95 % accuracy on the dataset received from a hospital.","PeriodicalId":265498,"journal":{"name":"2021 5th Conference on Information and Communication Technology (CICT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114238123","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

A 2.4GHz LNA Design for 802.11 WLAN Applications 用于802.11 WLAN应用的2.4GHz LNA设计

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672358

D. S. Babu, M. Reddy, G. Ramesh, Dv Srihari Babu, S. Daula, G. Khan

{"title":"A 2.4GHz LNA Design for 802.11 WLAN Applications","authors":"D. S. Babu, M. Reddy, G. Ramesh, Dv Srihari Babu, S. Daula, G. Khan","doi":"10.1109/CICT53865.2020.9672358","DOIUrl":"https://doi.org/10.1109/CICT53865.2020.9672358","url":null,"abstract":"Over the last decade, the front-end design in the RF transceiver has become a major role and is greatly enhancing the data rate of the transceiver. RF design is augmenting due to the fast-growing wireless communications markets. For a motivated potential design required data rate, low latency, gain, stability, and linearity considerations must converge. Being different wings of technology, the RF design, and its implementation is a difficult task even though such long research on RF and Microwave theory. CMOS technology has made unique considerable progress since its development in the mid-sixties. Over ten years after the fact, during the seventies, the first industrial products were made available in the market. Today, CMOS technology is a widely accepted standard for innovation and the versatile market of computerized ICs. The essential ambition of RF communication is to transmit and receive information through analog RF front ends. LNAs are found in an environment to amplify weak signals which are operating in numerous operational frequencies such as Bluetooth devices, cordless telephones, some radio equipment, and wireless keyboards. In this paper, with associated trade-offs in RF design, a systematic method for designing an LNA block with accurate MOS transistor sizing and computation of precise passive components is presented.","PeriodicalId":265498,"journal":{"name":"2021 5th Conference on Information and Communication Technology (CICT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124708324","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

A Method for Weather Forecasting Using Machine Learning 一种使用机器学习的天气预报方法

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672403

Prathyusha, Zakiya, Savya, Tejaswi, Neena Alex, Sobin C C

{"title":"A Method for Weather Forecasting Using Machine Learning","authors":"Prathyusha, Zakiya, Savya, Tejaswi, Neena Alex, Sobin C C","doi":"10.1109/CICT53865.2020.9672403","DOIUrl":"https://doi.org/10.1109/CICT53865.2020.9672403","url":null,"abstract":"Agriculture is a sector that plays a crucial role in the economies of many countries around the globe, like India where it contributes 16% of the total economy. Weather forecasting is one of the challenges faced by this sector, due to its dynamic and turbulent nature, the statistical methods fail to provide forecasting at an accurate precision. This paper aims to develop an accurate way to predict the temperature forecast using machine learning techniques especially using Long Short Term memory networks (LSTM). Despite the advances made, there are still significant obstacles to overcome in expanding the use of weather forecasts in the agricultural sector due to the dynamics in climate changes. These include the need for improved model accuracy, quantitative evidence of the utility of climate predictions as instruments for agricultural risk management and addressing major chances of disease incidence which are usually seasonal and depends on parameters like temperature and rainfall. The goal of this study is to forecast parameters that could help farmers to make an informed decision so as to reduce the losses by taking required proactive measures. This paper provides a detailed analysis of weather forecasting techniques and explores future research goals in this field.","PeriodicalId":265498,"journal":{"name":"2021 5th Conference on Information and Communication Technology (CICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128571211","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

Comparing different deep learning backbones for segmentation of lung nodules 比较不同深度学习主干在肺结节分割中的应用

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672439

R. Suji, W. Godfrey, J. Dhar

引用次数: 1

Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks 基于深度神经网络有效层微调的天体分类

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672430

Sabeesh Ethiraj, B. K. Bolla

{"title":"Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks","authors":"Sabeesh Ethiraj, B. K. Bolla","doi":"10.1109/CICT53865.2020.9672430","DOIUrl":"https://doi.org/10.1109/CICT53865.2020.9672430","url":null,"abstract":"The SDSS-IV dataset contains information about various astronomical bodies such as Galaxies, Stars, and Quasars captured by observatories. Inspired by our work on deep multimodal learning, which utilized transfer learning to classify the SDSS-IV dataset, we further extended our research in the fine tuning of these architectures to study the effect in the classification scenario. Architectures such as Resnet-50, DenseNet-121 VGG-16, Xception, EfficientNetB2, MobileNetV2 and NasnetMobile have been built using layer wise fine tuning at different levels. Our findings suggest that freezing all layers with Imagenet weights and adding a final trainable layer may not be the optimal solution. Further, baseline models and models that have higher number of trainable layers performed similarly in certain architectures. Model need to be fine tuned at different levels and a specific training ratio is required for a model to be termed ideal. Different architectures had different responses to the change in the number of trainable layers w.r.t accuracies. While models such as DenseNet-121, Xception, EfficientNetB2 achieved peak accuracies that were relatively consistent with near perfect training curves, models such as Resnet-50,VGG-16, MobileNetV2 and NasnetMobile had lower, delayed peak accuracies with poorly fitting training curves. It was also found that though mobile neural networks have lesser parameters and model size, they may not always be ideal for deployment on a low computational device as they had consistently lower validation accuracies. Customized evaluation metrics such as Tuning Parameter Ratio and Tuning Layer Ratio are used for model evaluation.","PeriodicalId":265498,"journal":{"name":"2021 5th Conference on Information and Communication Technology (CICT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134423161","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: 7

An Improved Adaptive Exponential Functional Link based NAEC 一种改进的自适应指数函数链接NAEC

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672418

Srikanth Burra, Asutosh Kar

引用次数: 0

Design of a Non-Orthogonal multi-band Carrierless Amplitude and Phase Modulated Indoor Visible Light Communication System using Adaptive Equalizers 基于自适应均衡器的非正交多频带无载波调幅调相室内可见光通信系统设计

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672376

S. S, Srijith Kanakambaran

引用次数: 1

Joint Relay Selection and Precoder Designing for Energy-Efficient MIMO-CRNs 节能mimo - crn联合继电器选择与预编码器设计

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672375

Shikha Maurya, M. Bansal

引用次数: 1

Versatile Circuit Designs of Digital Modulator and Demodulator 数字调制器和解调器的通用电路设计

2021 5th Conference on Information and Communication Technology (CICT) Pub Date : 2021-12-10 DOI: 10.1109/CICT53865.2020.9672385

Tadde Sandeep, M. M.

引用次数: 1