Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708303
Pranitha Garlapati, B. Yamuna, Karthi Balasubramanian
In decoding of Bose-Chaudhuri-Hocquenghem codes, Peterson’s algorithm is more efficient for codes with single, double and triple error correcting capabilities. Numerous methods were proposed to reduce the hardware complexity caused due to the inversion operation involved in the Peterson’s algorithm. In this paper, a low complex hardware BCH decoder using inversion-less Peterson’s algorithm presented in literature is designed and its performance is verified with the Matlab results. An attempt is made to design a low power version of this low complex BCH decoder by replacing the parallel Chien search architecture in the decoder with the two-step p-parallel Chien search approach that is originally used in literature with the Berlekamp-Massey Algorithm. For use with the inversion-less Peterson’s algorithm the parallel Chien search architecture has been modified and the resultant decoder has shown a power reduction of up to 42 percentage with a moderate increase in area by 10 percentage.
{"title":"A Low Power Hard Decision Decoder for BCH Codes","authors":"Pranitha Garlapati, B. Yamuna, Karthi Balasubramanian","doi":"10.1109/ICACC-202152719.2021.9708303","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708303","url":null,"abstract":"In decoding of Bose-Chaudhuri-Hocquenghem codes, Peterson’s algorithm is more efficient for codes with single, double and triple error correcting capabilities. Numerous methods were proposed to reduce the hardware complexity caused due to the inversion operation involved in the Peterson’s algorithm. In this paper, a low complex hardware BCH decoder using inversion-less Peterson’s algorithm presented in literature is designed and its performance is verified with the Matlab results. An attempt is made to design a low power version of this low complex BCH decoder by replacing the parallel Chien search architecture in the decoder with the two-step p-parallel Chien search approach that is originally used in literature with the Berlekamp-Massey Algorithm. For use with the inversion-less Peterson’s algorithm the parallel Chien search architecture has been modified and the resultant decoder has shown a power reduction of up to 42 percentage with a moderate increase in area by 10 percentage.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129879712","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708191
Vishnu Vijay, Rohan Mathew George, Sneha Joe, Swetha Shajee Dominic, R. Joseph, Sherin Sunil Jose, Simi Zerine Sleeba, Arun Ashok
Global Positioning System (GPS) receivers constitute a topic of great importance since they have applications in many fields of science and industry to determine the users position, velocity and time. In order to determine position, GPS receivers needs to know the navigation message which is obtained by demodulating the received signal. Demodulating process requires the local harmonic signal and the received signal to have a phase alignment of relatively high accuracy. In this paper we focus on the digital design of the Signal Tracking Loop of a customized GPS receiver. We present a novel implementation of the Carrier Discriminator used in the signal tracking loop using CORDIC Algorithm which reduces the computational complexity of mathematical operations.
{"title":"Implementation of Low Complexity Signal Tracking Loop of a GPS Receiver Using CORDIC Algorithm","authors":"Vishnu Vijay, Rohan Mathew George, Sneha Joe, Swetha Shajee Dominic, R. Joseph, Sherin Sunil Jose, Simi Zerine Sleeba, Arun Ashok","doi":"10.1109/ICACC-202152719.2021.9708191","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708191","url":null,"abstract":"Global Positioning System (GPS) receivers constitute a topic of great importance since they have applications in many fields of science and industry to determine the users position, velocity and time. In order to determine position, GPS receivers needs to know the navigation message which is obtained by demodulating the received signal. Demodulating process requires the local harmonic signal and the received signal to have a phase alignment of relatively high accuracy. In this paper we focus on the digital design of the Signal Tracking Loop of a customized GPS receiver. We present a novel implementation of the Carrier Discriminator used in the signal tracking loop using CORDIC Algorithm which reduces the computational complexity of mathematical operations.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117200578","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708356
C. L. Palson, R. K. Sreelal, D. D. Krishna, B. R. Jose
The rise of new generation communication systems requires high-quality signal transmission with significantly less signal distortion. Hence to ensure the quality, a tri-band Negative Group Delay Circuit (NGDC) is designed utilizing bandstop characteristics to compensate for the undesired positive group delays. In this work, L and U shaped stubs are etched on the 50 Ohm transmission line to generate NGD. Further, a memristor is connected across a slot to bring about tunability to the group delays, wherein it acts as a tunable resistance.
{"title":"Memristor based Tunable Negative Group Delay Circuit","authors":"C. L. Palson, R. K. Sreelal, D. D. Krishna, B. R. Jose","doi":"10.1109/ICACC-202152719.2021.9708356","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708356","url":null,"abstract":"The rise of new generation communication systems requires high-quality signal transmission with significantly less signal distortion. Hence to ensure the quality, a tri-band Negative Group Delay Circuit (NGDC) is designed utilizing bandstop characteristics to compensate for the undesired positive group delays. In this work, L and U shaped stubs are etched on the 50 Ohm transmission line to generate NGD. Further, a memristor is connected across a slot to bring about tunability to the group delays, wherein it acts as a tunable resistance.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122555798","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708369
S. Bala Naga Pranav, T. R. Kaushek Kumar, J. Hari Prakash, S. Sharan, M. Ganesan
To understand the freshness of fruits and vegetables, there is always a necessity to build a device that can automate the process of detecting the freshness. The objective of this paper is to build a device that measures the quality of fruit and vegetables and provides an output based on its edibility. Arduino UNO (microprocessor) along with MQ2, MQ4 (gas sensors Mĭngăn Qǐ lai 2, 4) and IR (Infra-Red) sensors are used to detect the concentration of Methane (CH4) and Ethylene (C2H4) in ppm (Parts Per Million). It was found that the excess ripening after which the fruit starts decomposing has a concentration of 300ppm (Ethylene) for all fruits and vegetables. The decomposition results in producing trace amounts of Methane gas, which is also detected using the MQ4 sensor. With all these constraints, the result is calculated by the microprocessor and is displayed in a 16x2 LCD display. The testing process of the device involved many fruits and vegetables. In this work two common fruits (Mango, Banana) and a common vegetable (Tomato) was deeply analyzed and found that the concentration of Ethylene is very much higher than 300 ppm in the fruits or vegetables which are highly decayed and are considered as unfit for the human consumption. It was also found that the ppm curve with respect to time axis derived from the sensor shows a very less deviation for the highly fresh fruits or vegetables. This device can be implemented in all food-based industries where there is a necessity to compute the freshness of fruits and vegetables. The simplicity and cost-efficiency of the device makes it a perfect product that can be used by everyone.
为了了解水果和蔬菜的新鲜度，总是有必要建立一个可以自动检测新鲜度的设备。本文的目的是建立一种测量水果和蔬菜质量的装置，并根据其可食性提供输出。Arduino UNO(微处理器)以及MQ2, MQ4(气体传感器Mĭngăn q / lai 2,4)和IR(红外)传感器用于检测以ppm(百万分之一)为单位的甲烷(CH4)和乙烯(C2H4)的浓度。结果发现，水果在过度成熟后开始分解，所有水果和蔬菜的乙烯浓度为300ppm(乙烯)。分解会产生微量的甲烷气体，MQ4传感器也可以检测到这种气体。在所有这些约束条件下，结果由微处理器计算并显示在16x2 LCD显示器上。该设备的测试过程涉及许多水果和蔬菜。本研究对两种常见的水果(芒果、香蕉)和一种常见的蔬菜(番茄)进行了深入分析，发现乙烯在高度腐烂的水果或蔬菜中的浓度远远高于300ppm，被认为不适合人类食用。还发现，从传感器得出的ppm曲线相对于时间轴的偏差对高度新鲜的水果或蔬菜来说非常小。该设备可用于所有需要计算水果和蔬菜新鲜度的食品行业。该设备的简单性和成本效益使其成为每个人都可以使用的完美产品。
{"title":"Freshness Estimator for Fruits and Vegetables Using MQ Sensors","authors":"S. Bala Naga Pranav, T. R. Kaushek Kumar, J. Hari Prakash, S. Sharan, M. Ganesan","doi":"10.1109/ICACC-202152719.2021.9708369","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708369","url":null,"abstract":"To understand the freshness of fruits and vegetables, there is always a necessity to build a device that can automate the process of detecting the freshness. The objective of this paper is to build a device that measures the quality of fruit and vegetables and provides an output based on its edibility. Arduino UNO (microprocessor) along with MQ2, MQ4 (gas sensors Mĭngăn Qǐ lai 2, 4) and IR (Infra-Red) sensors are used to detect the concentration of Methane (CH4) and Ethylene (C2H4) in ppm (Parts Per Million). It was found that the excess ripening after which the fruit starts decomposing has a concentration of 300ppm (Ethylene) for all fruits and vegetables. The decomposition results in producing trace amounts of Methane gas, which is also detected using the MQ4 sensor. With all these constraints, the result is calculated by the microprocessor and is displayed in a 16x2 LCD display. The testing process of the device involved many fruits and vegetables. In this work two common fruits (Mango, Banana) and a common vegetable (Tomato) was deeply analyzed and found that the concentration of Ethylene is very much higher than 300 ppm in the fruits or vegetables which are highly decayed and are considered as unfit for the human consumption. It was also found that the ppm curve with respect to time axis derived from the sensor shows a very less deviation for the highly fresh fruits or vegetables. This device can be implemented in all food-based industries where there is a necessity to compute the freshness of fruits and vegetables. The simplicity and cost-efficiency of the device makes it a perfect product that can be used by everyone.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132324045","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708197
Mariya Raphel, P. J. Parvathi, Rizwana Yasmin Hashim, Rohan J Thevara, P. Deepasree Varma
In this paper, we focus at tracking down cyberbullies and categorize them based on their age and gender. The dataset that we use to analyze this information is provided by the MySpace group data labeled for cyberbullying. Machine learning classifiers are trained using this data to detect cyberbullies and later we analyze the age and gender patterns of those cyberbullies. We look for features that are simple to extract as well as yield good outcomes. As appropriate training data is often tough to obtain in machine learning-specially in the domain of cyberbullying detection - we also examine to what extend does lesser amounts of training data would contribute to better outcomes by performing cross-validation. Our findings show that employing a few yet expressive features has a significant benefit in detecting cyberbullies, particularly when size of training data is small.
{"title":"Analysing Gender and Age Aspects of Cyberbullying through Online Social Media","authors":"Mariya Raphel, P. J. Parvathi, Rizwana Yasmin Hashim, Rohan J Thevara, P. Deepasree Varma","doi":"10.1109/ICACC-202152719.2021.9708197","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708197","url":null,"abstract":"In this paper, we focus at tracking down cyberbullies and categorize them based on their age and gender. The dataset that we use to analyze this information is provided by the MySpace group data labeled for cyberbullying. Machine learning classifiers are trained using this data to detect cyberbullies and later we analyze the age and gender patterns of those cyberbullies. We look for features that are simple to extract as well as yield good outcomes. As appropriate training data is often tough to obtain in machine learning-specially in the domain of cyberbullying detection - we also examine to what extend does lesser amounts of training data would contribute to better outcomes by performing cross-validation. Our findings show that employing a few yet expressive features has a significant benefit in detecting cyberbullies, particularly when size of training data is small.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131043519","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708219
Nallagatla Roopika, M. Moheth, Sure Vinod, P. Sanjana, K. Balamurugan
Recent advancements in semiconductor technologies supports high data rate communications in V-band. Particularly 60 GHz encourages short range multi Gbps transmission suitable for multimedia applications. The first block of the receiver, Low Noise Amplifier (LNA) should have high gain requirements simultaneously maintaining low noise Figure (NF). This work consists of designing Variable Gain (VG) LNAs over the desired bandwidth (57–64) GHz in the V – Band. Variable loads formed by active devices are used to change body transconductance of amplifying transistor. It is found that better tuning range of 19.23 dB/V is achieved with lower noise Figure of 1. 4SSdB for PMOS variable load LNA. Almost 3.57 GHz bandwidth is achieved with figure-of-the-merit (FOM) of >S in all LNAs.
{"title":"CMOS based variable gain LNA at V-Band","authors":"Nallagatla Roopika, M. Moheth, Sure Vinod, P. Sanjana, K. Balamurugan","doi":"10.1109/ICACC-202152719.2021.9708219","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708219","url":null,"abstract":"Recent advancements in semiconductor technologies supports high data rate communications in V-band. Particularly 60 GHz encourages short range multi Gbps transmission suitable for multimedia applications. The first block of the receiver, Low Noise Amplifier (LNA) should have high gain requirements simultaneously maintaining low noise Figure (NF). This work consists of designing Variable Gain (VG) LNAs over the desired bandwidth (57–64) GHz in the V – Band. Variable loads formed by active devices are used to change body transconductance of amplifying transistor. It is found that better tuning range of 19.23 dB/V is achieved with lower noise Figure of 1. 4SSdB for PMOS variable load LNA. Almost 3.57 GHz bandwidth is achieved with figure-of-the-merit (FOM) of >S in all LNAs.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126238896","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708206
Nitin Rajesh, Vysakh Thachileth Poulose, P.L. Umesh, Renu Mary Daniel
The Coronavirus disease is an acute respiratory disease that has been designated as a pandemic by the WHO(World Health Organization).The rapid increase in the number of illnesses and death rates has put enormous strain on public health services. Hence, its critical to recognize the comorbidities in COVID-19 patients that led to ARDS(Acute Respiratory Distress Syndrome). In this paper, we use machine learning and deep learning methods to classify high risk COVID-19 patients with accurate results. This paper might speed up decisions made in public health services for predicting medical resources as well as early classification of high risk COVID-19 patients.
{"title":"Comorbidity Based Risk Prediction System for ARDS in COVID-19 Patients","authors":"Nitin Rajesh, Vysakh Thachileth Poulose, P.L. Umesh, Renu Mary Daniel","doi":"10.1109/ICACC-202152719.2021.9708206","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708206","url":null,"abstract":"The Coronavirus disease is an acute respiratory disease that has been designated as a pandemic by the WHO(World Health Organization).The rapid increase in the number of illnesses and death rates has put enormous strain on public health services. Hence, its critical to recognize the comorbidities in COVID-19 patients that led to ARDS(Acute Respiratory Distress Syndrome). In this paper, we use machine learning and deep learning methods to classify high risk COVID-19 patients with accurate results. This paper might speed up decisions made in public health services for predicting medical resources as well as early classification of high risk COVID-19 patients.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124266522","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708297
Lakshmi Nair, K. Balamurugan, M. Jayakumar
In the past couple of years, 60 GHz communications have encountered a progress to cover industrial, scientific and commercial applications. The focus of this work is to design electrostatic discharge (ESD) for 60 GHz low noise amplifier (LNA) utilizing 65-nm CMOS technology. In order to improve performance, custom designed spiral inductor working around 60 GHz frequency band has been illustrated. The circuit under test consists of a two-stage common source low noise amplifier. The proposed ESD protection circuits consisting of customized inductor offers less parasitic capacitance and renders lower RF degradation. The measured results shows that the proposed design achieves a gain of 37 dB and noise Figure of 2.745 dB at 60 GHz with 20 mW power consumption.
{"title":"Design of ESD Protection Circuits for LNA Using 65-nm CMOS Technology","authors":"Lakshmi Nair, K. Balamurugan, M. Jayakumar","doi":"10.1109/ICACC-202152719.2021.9708297","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708297","url":null,"abstract":"In the past couple of years, 60 GHz communications have encountered a progress to cover industrial, scientific and commercial applications. The focus of this work is to design electrostatic discharge (ESD) for 60 GHz low noise amplifier (LNA) utilizing 65-nm CMOS technology. In order to improve performance, custom designed spiral inductor working around 60 GHz frequency band has been illustrated. The circuit under test consists of a two-stage common source low noise amplifier. The proposed ESD protection circuits consisting of customized inductor offers less parasitic capacitance and renders lower RF degradation. The measured results shows that the proposed design achieves a gain of 37 dB and noise Figure of 2.745 dB at 60 GHz with 20 mW power consumption.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115248402","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708308
Annie Augustine, K. Sherly
Plants and trees are an inevitable part of our life. All these species contribute to biodiversity, provide clean and fresh air, prevent soil erosion, home remedy, and many more. Acquiring knowledge about species is essential for protecting biodiversity. The identification of plants by conventional methods is complex and time-consuming for novices. Also, many species are endangered because of human encroachment and due to diseases affecting plants. These plant diseases cause economic, social, and ecological losses. In this context, diagnosing diseases accurately and timely and doing the necessary control measures is of the utmost importance. There have been many technological advancements in the area of computer vision to identify plant species and diseases automatically. This paper aims to present various approaches in leaf recognition and disease detection using digital images of leaves. Various phases in image classification using conventional machine learning models and deep learning techniques have been discussed. A comparative study on various paper works and their performance have also been analyzed.
{"title":"Various Approaches in Plant Species Identification and Plant Disease Detection Using Digital Images of Leaves","authors":"Annie Augustine, K. Sherly","doi":"10.1109/ICACC-202152719.2021.9708308","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708308","url":null,"abstract":"Plants and trees are an inevitable part of our life. All these species contribute to biodiversity, provide clean and fresh air, prevent soil erosion, home remedy, and many more. Acquiring knowledge about species is essential for protecting biodiversity. The identification of plants by conventional methods is complex and time-consuming for novices. Also, many species are endangered because of human encroachment and due to diseases affecting plants. These plant diseases cause economic, social, and ecological losses. In this context, diagnosing diseases accurately and timely and doing the necessary control measures is of the utmost importance. There have been many technological advancements in the area of computer vision to identify plant species and diseases automatically. This paper aims to present various approaches in leaf recognition and disease detection using digital images of leaves. Various phases in image classification using conventional machine learning models and deep learning techniques have been discussed. A comparative study on various paper works and their performance have also been analyzed.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127532922","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}
Pub Date : 2021-10-21DOI: 10.1109/ICACC-202152719.2021.9708075
Dayana Mariya Tomy, Aleena M. Jaison, Aksa Christopher, Arun Tomy, Jaison Jacob, A. Harsha
Plant leaves are most commonly affected by diseases caused by bacteria, fungi or viruses which results in an immense decrease in the yield from plants. Since most of the people in India are dependent on agriculture there is a need to detect the plant leaf diseases at an early stage. This paper discusses the plant leaf disease detection using two convolutional neural networks that is AlexNet and VGG16. Both the model was trained using dataset of 38 different classes of plant leaves. The role of number of images, learning rate and freezing of layers in the classification accuracy and training time have been analyzed. Further the prediction of noisy images was performed by using both models and remedy for the disease was displayed.
{"title":"Comparison of ALEXNET and VGG16 for Analysis of Plant Leaf Disease","authors":"Dayana Mariya Tomy, Aleena M. Jaison, Aksa Christopher, Arun Tomy, Jaison Jacob, A. Harsha","doi":"10.1109/ICACC-202152719.2021.9708075","DOIUrl":"https://doi.org/10.1109/ICACC-202152719.2021.9708075","url":null,"abstract":"Plant leaves are most commonly affected by diseases caused by bacteria, fungi or viruses which results in an immense decrease in the yield from plants. Since most of the people in India are dependent on agriculture there is a need to detect the plant leaf diseases at an early stage. This paper discusses the plant leaf disease detection using two convolutional neural networks that is AlexNet and VGG16. Both the model was trained using dataset of 38 different classes of plant leaves. The role of number of images, learning rate and freezing of layers in the classification accuracy and training time have been analyzed. Further the prediction of noisy images was performed by using both models and remedy for the disease was displayed.","PeriodicalId":198810,"journal":{"name":"2021 International Conference on Advances in Computing and Communications (ICACC)","volume":"280 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127476977","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：