Pub Date : 2023-05-26DOI: 10.1109/INCET57972.2023.10170276
Yang Hong
With the increasing popularity of piano, the demand for piano tuning is also increasing. Generally, the professional tuner judges the pitch of the piano through listening. It is inevitable that there will be deviation due to the influence of physical, psychological and objective environment. This paper analyzes and demonstrates the basic methods of piano tuning from the physical characteristics and corresponding physical models of piano tone. The method of music signal processing is systematically analyzed in both time domain and frequency domain. Some algorithms in speech recognition technology are applied to music recognition, and then improved according to the characteristics of piano tuning. In the aspect of pitch detection, aiming at the problem that the piano range is wider than the voice, the pitch detection in the whole frequency band using a single algorithm can not meet the requirements of the piano tuning detection accuracy, and the use of computer-assisted piano tuning method to train students to listen to music is a teaching method developed by the author. It is a new teaching method, which is applicable to students in primary and middle schools. Using the computer-assisted piano tuning method to cultivate students' ability to listen to music can cultivate students' ability to listen to music, improve their sense of music, enhance their memory ability, and develop their artistic imagination. This learning process can also help them play keyboard instruments more skillfully at a very young age. It can help students learn the skills of listening to music and improve their piano playing ability. Using computer-assisted piano tuning method to cultivate students' music listening also helps teachers develop their own teaching skills and can be used in teacher training courses.
{"title":"The Cultivation Of Students' Music Listening With Computer-Aided Piano Tuning Method","authors":"Yang Hong","doi":"10.1109/INCET57972.2023.10170276","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170276","url":null,"abstract":"With the increasing popularity of piano, the demand for piano tuning is also increasing. Generally, the professional tuner judges the pitch of the piano through listening. It is inevitable that there will be deviation due to the influence of physical, psychological and objective environment. This paper analyzes and demonstrates the basic methods of piano tuning from the physical characteristics and corresponding physical models of piano tone. The method of music signal processing is systematically analyzed in both time domain and frequency domain. Some algorithms in speech recognition technology are applied to music recognition, and then improved according to the characteristics of piano tuning. In the aspect of pitch detection, aiming at the problem that the piano range is wider than the voice, the pitch detection in the whole frequency band using a single algorithm can not meet the requirements of the piano tuning detection accuracy, and the use of computer-assisted piano tuning method to train students to listen to music is a teaching method developed by the author. It is a new teaching method, which is applicable to students in primary and middle schools. Using the computer-assisted piano tuning method to cultivate students' ability to listen to music can cultivate students' ability to listen to music, improve their sense of music, enhance their memory ability, and develop their artistic imagination. This learning process can also help them play keyboard instruments more skillfully at a very young age. It can help students learn the skills of listening to music and improve their piano playing ability. Using computer-assisted piano tuning method to cultivate students' music listening also helps teachers develop their own teaching skills and can be used in teacher training courses.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124661771","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170164
Pankhuri Kaushik, Manjeet Singh
The automotive sector has shifted towards Electrically Powered Vehicles due to the increase in energy demand, the gradual limiting of fossil fuels, and environmental issues. The Efficiency of traction of battery packs affects the performance and range of EVs. Temperature significantly affects the rate of Lithium-ion battery deterioration as well as the performance of the chemical reaction that takes place inside the battery which impacts the overall performance of the vehicle. The internal temperature of the battery leads to the dropdown of resistance which cause lots of heat generation. In the same way, external temperature i.e., ambient temperature also impacts the performance of the battery. An optimal temperature range is required for the better performance of the vehicles. In battery electric vehicles, there is a sharp decrease in driving range in cold conditions as compared to combustion engines, which is the drawback of battery electric vehicles. This paper includes the analysis of Li-ion battery characteristics under different conditions by using the UDDS drive cycle and an analysis of ambient temperature impacts on EV’s range in automotive vehicle operation.
{"title":"Analysis and Evaluation of Characteristics of Li-ion Battery using Simulink and Impacts of Ambient Temperature on Pure Electric Vehicle","authors":"Pankhuri Kaushik, Manjeet Singh","doi":"10.1109/INCET57972.2023.10170164","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170164","url":null,"abstract":"The automotive sector has shifted towards Electrically Powered Vehicles due to the increase in energy demand, the gradual limiting of fossil fuels, and environmental issues. The Efficiency of traction of battery packs affects the performance and range of EVs. Temperature significantly affects the rate of Lithium-ion battery deterioration as well as the performance of the chemical reaction that takes place inside the battery which impacts the overall performance of the vehicle. The internal temperature of the battery leads to the dropdown of resistance which cause lots of heat generation. In the same way, external temperature i.e., ambient temperature also impacts the performance of the battery. An optimal temperature range is required for the better performance of the vehicles. In battery electric vehicles, there is a sharp decrease in driving range in cold conditions as compared to combustion engines, which is the drawback of battery electric vehicles. This paper includes the analysis of Li-ion battery characteristics under different conditions by using the UDDS drive cycle and an analysis of ambient temperature impacts on EV’s range in automotive vehicle operation.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129430401","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169935
Bashyam. S, Vunnava Pramodini, Ashik Ashik, V. Prasanth
The toxic gases emitted from garbage waste in houses or communities harm the environment and human health. Various health issues, such as respiratory problems and skin cancer, will occur because of these toxic gases. Considering such cases, it aims to develop a sensor-based system to detect the presence of ammonia, hydrogen sulfide, methane, humidity, temperature, and garbage level in the bin. The data acquisition and processing units collect and analyze the sensor data, generating real-time gas concentration readings. Hypertext processors and Arduino programs are used to obtain and monitor the readings of the sensors. Moreover, an exhaust fan is placed, which turns on when the gas levels or the temperature increases above respective threshold values.
{"title":"IoT-Based Garbage Gas Detection System","authors":"Bashyam. S, Vunnava Pramodini, Ashik Ashik, V. Prasanth","doi":"10.1109/INCET57972.2023.10169935","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169935","url":null,"abstract":"The toxic gases emitted from garbage waste in houses or communities harm the environment and human health. Various health issues, such as respiratory problems and skin cancer, will occur because of these toxic gases. Considering such cases, it aims to develop a sensor-based system to detect the presence of ammonia, hydrogen sulfide, methane, humidity, temperature, and garbage level in the bin. The data acquisition and processing units collect and analyze the sensor data, generating real-time gas concentration readings. Hypertext processors and Arduino programs are used to obtain and monitor the readings of the sensors. Moreover, an exhaust fan is placed, which turns on when the gas levels or the temperature increases above respective threshold values.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"122 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129471355","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170350
Aakansha Ramesh, Gauri Thube, Swaranjali Jadhav
Fake news has become a huge issue in present times; it is both a societal and technical issue. It is difficult for companies to identify as the term covers different meanings like satire, false tales, factual errors, misleading headlines, and propaganda. Social media plays a crucial role in spreading fake news. It is propagated over different social networking sites and creates confusion, biases, and induces fear among people. Different approaches have been implemented over the years. Despite all the different trials, fake news remains a crucial challenge. The application will analyze the news and classify it into real/fake and clickbait/non-clickbait. In addition to analyzing the news into different categories, it summarizes and includes a dynamic feature that fetches live news.
{"title":"Realtime News Analysis using Natural Language Processing","authors":"Aakansha Ramesh, Gauri Thube, Swaranjali Jadhav","doi":"10.1109/INCET57972.2023.10170350","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170350","url":null,"abstract":"Fake news has become a huge issue in present times; it is both a societal and technical issue. It is difficult for companies to identify as the term covers different meanings like satire, false tales, factual errors, misleading headlines, and propaganda. Social media plays a crucial role in spreading fake news. It is propagated over different social networking sites and creates confusion, biases, and induces fear among people. Different approaches have been implemented over the years. Despite all the different trials, fake news remains a crucial challenge. The application will analyze the news and classify it into real/fake and clickbait/non-clickbait. In addition to analyzing the news into different categories, it summarizes and includes a dynamic feature that fetches live news.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129703733","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170557
Md. Aminul Islam, Md Khabir Hossain Talukder, Shah Md Ahad
In this paper, methodical parametric analysis and design of vehicle-mounted whip antennas are presented for HF and VHF communication. For VHF whip antennas, the impacts of variation of the ground plane, antenna height and position, and ground material are investigated. Results indicate that the larger the length of the ground plane, the better is the reflection coefficient, and the vehicle rooftop surface can be used effectively as the ground plane. Antenna height variation from the ground plane indicates that the lower height of the antenna from the ground plane provides better results. Next, the effects of various ground materials are investigated and the performances are found quite similar to each other. Finally, the performance of the designed VHF whip antenna is investigated in several mounting locations on the vehicle. In addition, for HF whip antennas, the bending technique is used for antenna miniaturization and bandwidth enhancement. Here, the roof surface of the vehicle is considered as the ground plane and the antenna is found radiating successfully at desired frequency range. All these findings can be utilized to design customized vehicle-mounted antennas in the HF and VHF frequency bands for secure, faster, and effective communication on the move.
{"title":"Design and Analysis of Vehicle Mounted Whip Antennas for HF and VHF Communication","authors":"Md. Aminul Islam, Md Khabir Hossain Talukder, Shah Md Ahad","doi":"10.1109/INCET57972.2023.10170557","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170557","url":null,"abstract":"In this paper, methodical parametric analysis and design of vehicle-mounted whip antennas are presented for HF and VHF communication. For VHF whip antennas, the impacts of variation of the ground plane, antenna height and position, and ground material are investigated. Results indicate that the larger the length of the ground plane, the better is the reflection coefficient, and the vehicle rooftop surface can be used effectively as the ground plane. Antenna height variation from the ground plane indicates that the lower height of the antenna from the ground plane provides better results. Next, the effects of various ground materials are investigated and the performances are found quite similar to each other. Finally, the performance of the designed VHF whip antenna is investigated in several mounting locations on the vehicle. In addition, for HF whip antennas, the bending technique is used for antenna miniaturization and bandwidth enhancement. Here, the roof surface of the vehicle is considered as the ground plane and the antenna is found radiating successfully at desired frequency range. All these findings can be utilized to design customized vehicle-mounted antennas in the HF and VHF frequency bands for secure, faster, and effective communication on the move.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130312418","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170737
Xiaochen Guo, Shihui Du
With the rapid development of music social media, online music resources are rapidly increasing and music types are increasingly diversified. As an effective means to organize massive music data, rich music annotation information has become an important part of online music services. Automatic music tagging algorithm based on tag depth analysis is an automatic music tagging method that uses the concept of tag depth to classify songs. The algorithm starts with a set of songs, where each song is assigned one or more tags. The lengths of these markers are then compared and assigned to different categories. For example, if a song has three tags, it will be classified as pop / rock, dance and country music. If the song uses two tags, it will be classified as rock / pop and pop / rock, respectively. This process will continue until all songs have been classified by their tag depth and classified accordingly.
{"title":"Automatic Music Labeling Algorithm based on Tag Depth Analysis","authors":"Xiaochen Guo, Shihui Du","doi":"10.1109/INCET57972.2023.10170737","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170737","url":null,"abstract":"With the rapid development of music social media, online music resources are rapidly increasing and music types are increasingly diversified. As an effective means to organize massive music data, rich music annotation information has become an important part of online music services. Automatic music tagging algorithm based on tag depth analysis is an automatic music tagging method that uses the concept of tag depth to classify songs. The algorithm starts with a set of songs, where each song is assigned one or more tags. The lengths of these markers are then compared and assigned to different categories. For example, if a song has three tags, it will be classified as pop / rock, dance and country music. If the song uses two tags, it will be classified as rock / pop and pop / rock, respectively. This process will continue until all songs have been classified by their tag depth and classified accordingly.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126991955","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169918
Keertana Nair, Gopikrishna P B, Rubell Marion Lincy G
Brain-Computer Interface (BCI) is a system which is used to interact with the computer system and can be used to control different assistive devices by utilizing the brain signals such as Electroencephalography (EEG). Motor Imagery (MI) is considered one of the prominent fields of BCI systems which are based on EEG signals. These systems have the capability to restore motor ability in humans. Though a good deal of Machine Learning (ML) approaches were investigated in recent years, studies that explore BCI with Deep Learning methods or Wavelet Scattering Transforms have not been extensively used. Also, conventional classification methods show longer computational time and they are incapable of processing non-linear and non-stationary EEG signals. The proposed system aims to explore the area of a calibration-free or a subject-independent model by integrating Deep Convolutional Neural Network (CNN) with Wavelet Scattering Network by utilizing feature maps learned from both CNN and Scattering networks to tackle the non-linearity and non-stationarity of the EEG signals and thereby to improve the classification accuracy of the model to build a more robust and generalized MI-based BCI system. The proposed model outperforms the state-of-the-art techniques, achieving an accuracy of 87% and 93% on BCIC IV 2a and SMR-BCI datasets respectively.
脑机接口(brain - computer Interface, BCI)是一种用于与计算机系统交互的系统，可以利用脑电图(EEG)等脑信号来控制不同的辅助设备。运动想象(MI)是基于脑电信号的脑机接口(BCI)系统的一个重要领域。这些系统有能力恢复人类的运动能力。尽管近年来研究了大量的机器学习(ML)方法，但利用深度学习方法或小波散射变换探索脑机接口的研究尚未得到广泛应用。此外，传统的脑电信号分类方法计算时间较长，无法处理非线性和非平稳的脑电信号。该系统旨在将CNN与小波散射网络相结合，探索无标定或主体无关的模型领域，利用CNN和小波散射网络学习到的特征映射，解决脑电信号的非线性和非平稳性，从而提高模型的分类精度，构建一个更鲁棒和广义的基于mi的BCI系统。该模型优于最先进的技术，在BCIC IV 2a和SMR-BCI数据集上分别达到87%和93%的准确率。
{"title":"Motor Imagery-Based Brain-Computer Interface Using Fusion of Deep Convolutional Neural Network with Wavelet Scattering Network","authors":"Keertana Nair, Gopikrishna P B, Rubell Marion Lincy G","doi":"10.1109/INCET57972.2023.10169918","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169918","url":null,"abstract":"Brain-Computer Interface (BCI) is a system which is used to interact with the computer system and can be used to control different assistive devices by utilizing the brain signals such as Electroencephalography (EEG). Motor Imagery (MI) is considered one of the prominent fields of BCI systems which are based on EEG signals. These systems have the capability to restore motor ability in humans. Though a good deal of Machine Learning (ML) approaches were investigated in recent years, studies that explore BCI with Deep Learning methods or Wavelet Scattering Transforms have not been extensively used. Also, conventional classification methods show longer computational time and they are incapable of processing non-linear and non-stationary EEG signals. The proposed system aims to explore the area of a calibration-free or a subject-independent model by integrating Deep Convolutional Neural Network (CNN) with Wavelet Scattering Network by utilizing feature maps learned from both CNN and Scattering networks to tackle the non-linearity and non-stationarity of the EEG signals and thereby to improve the classification accuracy of the model to build a more robust and generalized MI-based BCI system. The proposed model outperforms the state-of-the-art techniques, achieving an accuracy of 87% and 93% on BCIC IV 2a and SMR-BCI datasets respectively.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123810337","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169902
Sharat Hiremath, B. Yamini, Tejashwini M N, Prabha K
In this paper automation of library management system is achieved by designing an autonomous robot to automate the process of picking the required book and dropping them to the borrower table and also to replace the book back to the shelf and also a webpage is created to access the books in library. Manually searching a book in a library is a labour - intensive procedure and if the book is misplaced either purposefully or accidentally it requires extra time and effort to retrieve it. To address this issue, an attempt is currently being made to automate libraries so that books can be quickly discovered and easily picked up and positioned using a robotic arm equipped with RFID equipment, Zigbee, Colour Sensor and DC Motors. The user will have to enter the book details either to borrow or return the book on the webpage and accordingly the robot will receive command and performs the task. A rack is designed and different coloured tags are placed in each row so the robot can find the desired row in the rack. The experimental results showed that the robot is capable to carry book weighing up to 500 grams.
{"title":"Automation of Library Management System using Autonomous Robot","authors":"Sharat Hiremath, B. Yamini, Tejashwini M N, Prabha K","doi":"10.1109/INCET57972.2023.10169902","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169902","url":null,"abstract":"In this paper automation of library management system is achieved by designing an autonomous robot to automate the process of picking the required book and dropping them to the borrower table and also to replace the book back to the shelf and also a webpage is created to access the books in library. Manually searching a book in a library is a labour - intensive procedure and if the book is misplaced either purposefully or accidentally it requires extra time and effort to retrieve it. To address this issue, an attempt is currently being made to automate libraries so that books can be quickly discovered and easily picked up and positioned using a robotic arm equipped with RFID equipment, Zigbee, Colour Sensor and DC Motors. The user will have to enter the book details either to borrow or return the book on the webpage and accordingly the robot will receive command and performs the task. A rack is designed and different coloured tags are placed in each row so the robot can find the desired row in the rack. The experimental results showed that the robot is capable to carry book weighing up to 500 grams.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123194551","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170637
Talapally Sandeep Kumar, B. Annappa, Shubham Dodia
Skin is the most powerful shield human organ that protects the internal organs of the human body from external attacks. This important organ is attacked by a diverse range of microbes such as viruses, fungi, and bacteria causing a lot of damage to the skin. Apart from these microbes, even dust plays important role in damaging skin. Every year several people in the world are suffering from skin diseases. These skin diseases are contagious and spread very fast. There are varieties of skin diseases. Thus it requires a lot of practice to distinguish the skin disease by the doctor and provide treatment. In order to automate this process several deep learning models are used in recent past years. This paper demonstrates an efficient and lightweight modified SqueezeNet deep learning model on the HAM10000 dataset for skin cancer classification. This model has outperformed state-of-the-art models with fewer parameters. As compared to existing deep learning models, this SqueezeNet variant has achieved 99.7%, 97.7%, and 97.04% as train, validation, and test accuracies respectively using only 0.13 million parameters.
{"title":"Classification of Skin Cancer Images using Lightweight Convolutional Neural Network","authors":"Talapally Sandeep Kumar, B. Annappa, Shubham Dodia","doi":"10.1109/INCET57972.2023.10170637","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170637","url":null,"abstract":"Skin is the most powerful shield human organ that protects the internal organs of the human body from external attacks. This important organ is attacked by a diverse range of microbes such as viruses, fungi, and bacteria causing a lot of damage to the skin. Apart from these microbes, even dust plays important role in damaging skin. Every year several people in the world are suffering from skin diseases. These skin diseases are contagious and spread very fast. There are varieties of skin diseases. Thus it requires a lot of practice to distinguish the skin disease by the doctor and provide treatment. In order to automate this process several deep learning models are used in recent past years. This paper demonstrates an efficient and lightweight modified SqueezeNet deep learning model on the HAM10000 dataset for skin cancer classification. This model has outperformed state-of-the-art models with fewer parameters. As compared to existing deep learning models, this SqueezeNet variant has achieved 99.7%, 97.7%, and 97.04% as train, validation, and test accuracies respectively using only 0.13 million parameters.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123195342","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170610
S. Hariharan, Deveshwaran Sridharan, K. R, M. T A, C. Tamilselvi, Dahlia Sam
Diabetes is an ongoing infection that influences a large number of individuals overall and can prompt serious unexpected issues whenever left untreated. Early identification of diabetes can altogether diminish the risk of intricacies and work on significant results. Lately, the utilization of wearable technology has arisen as a promising device for illness identification and checking. Smartwatches furnished with bioactive sensors can give ceaseless, painless observing of body vitals, making them ideal for diabetes screening. This study proposes a framework that uses patient information for preparing a hybrid AI model to distinguish the presence of diabetes. The framework consolidates body vitals estimated utilizing a smartwatch with a bioactive sensor to get exact and nonstop information on the wearer's wellbeing status. The mixture model coordinates both profound learning and conventional AI calculations to accomplish predominant precision in identifying diabetes. The framework gathers information on different body vitals, for example, pulse, circulatory strain, and skin conductance, which are known to be firmly connected with diabetes. The gathered information is pre-handled and afterward used to prepare the hybrid model. The profound learning calculation is utilized to remove significant level highlights from the crude information, while the conventional AI calculation is utilized to arrange the information into diabetic or non-diabetic classifications. The cross breed model is intended to work on the accuracy of diabetes location by integrating the qualities of both profound learning and conventional AI.
{"title":"Real-time Monitoring and Early Detection of Diabetes with Bioactive and Biological Impedance Sensors using Hybrid Machine Learning Algorithm","authors":"S. Hariharan, Deveshwaran Sridharan, K. R, M. T A, C. Tamilselvi, Dahlia Sam","doi":"10.1109/INCET57972.2023.10170610","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170610","url":null,"abstract":"Diabetes is an ongoing infection that influences a large number of individuals overall and can prompt serious unexpected issues whenever left untreated. Early identification of diabetes can altogether diminish the risk of intricacies and work on significant results. Lately, the utilization of wearable technology has arisen as a promising device for illness identification and checking. Smartwatches furnished with bioactive sensors can give ceaseless, painless observing of body vitals, making them ideal for diabetes screening. This study proposes a framework that uses patient information for preparing a hybrid AI model to distinguish the presence of diabetes. The framework consolidates body vitals estimated utilizing a smartwatch with a bioactive sensor to get exact and nonstop information on the wearer's wellbeing status. The mixture model coordinates both profound learning and conventional AI calculations to accomplish predominant precision in identifying diabetes. The framework gathers information on different body vitals, for example, pulse, circulatory strain, and skin conductance, which are known to be firmly connected with diabetes. The gathered information is pre-handled and afterward used to prepare the hybrid model. The profound learning calculation is utilized to remove significant level highlights from the crude information, while the conventional AI calculation is utilized to arrange the information into diabetic or non-diabetic classifications. The cross breed model is intended to work on the accuracy of diabetes location by integrating the qualities of both profound learning and conventional AI.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114311407","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：