Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212302
Deepa Devasenapathy, M. Raja, R. K. Dwibedi, N. Vinoth, T. Jayasudha, V. D. Ganesh
Digital forensics science places a significant emphasis on the detection of objects as one of the most vital areas of study. Several industries and institutions may benefit from the object detection method, including those concerned with medical diagnostic scanning, traffic monitoring, airport security, law enforcement, and data rescue on a local and global scale. This study aims to detect weapons in video surveillance images by using various enhancement, segmentation, feature extraction, and classification methods by Artificial Neural Network to improve the detection accuracy. Yet, several mathematical and algorithmic models are computed to provide the appropriate approaches.
{"title":"Artificial Neural Network using Image Processing for Digital Forensics Crime Scene Object Detection","authors":"Deepa Devasenapathy, M. Raja, R. K. Dwibedi, N. Vinoth, T. Jayasudha, V. D. Ganesh","doi":"10.1109/ICECAA58104.2023.10212302","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212302","url":null,"abstract":"Digital forensics science places a significant emphasis on the detection of objects as one of the most vital areas of study. Several industries and institutions may benefit from the object detection method, including those concerned with medical diagnostic scanning, traffic monitoring, airport security, law enforcement, and data rescue on a local and global scale. This study aims to detect weapons in video surveillance images by using various enhancement, segmentation, feature extraction, and classification methods by Artificial Neural Network to improve the detection accuracy. Yet, several mathematical and algorithmic models are computed to provide the appropriate approaches.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129781252","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212279
B. Ramar, R. Ramalakshmi, Vaibhav Gandhi, P. Pandiselvam
The proposed research introduces an Improved Convolutional Neural Network (ICNN) to construct EEG-based emotion detection models. This study has utilized an EEG dataset of 15 subjects available from a BCMI laboratory. In our work, differential entropy characteristics obtained from multichannel EEG data are used to train the Improved CNN. The best classification accuracy is 95.67% which is significantly higher than that of the original 62 channels. The most important channels and frequency bands are identified by Improved CNN. The outcomes of our study also demonstrate the existence of neuronal signatures linked to various emotions, which are consistent between sessions and people. Finally, the effectiveness of deep and shallow models are compared and also the performance of improved CNN is compared with benchmark algorithms.
{"title":"Classification of EEG Signals on SEED Dataset Using Improved CNN","authors":"B. Ramar, R. Ramalakshmi, Vaibhav Gandhi, P. Pandiselvam","doi":"10.1109/ICECAA58104.2023.10212279","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212279","url":null,"abstract":"The proposed research introduces an Improved Convolutional Neural Network (ICNN) to construct EEG-based emotion detection models. This study has utilized an EEG dataset of 15 subjects available from a BCMI laboratory. In our work, differential entropy characteristics obtained from multichannel EEG data are used to train the Improved CNN. The best classification accuracy is 95.67% which is significantly higher than that of the original 62 channels. The most important channels and frequency bands are identified by Improved CNN. The outcomes of our study also demonstrate the existence of neuronal signatures linked to various emotions, which are consistent between sessions and people. Finally, the effectiveness of deep and shallow models are compared and also the performance of improved CNN is compared with benchmark algorithms.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128564594","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212239
S. C. Agrawal, R. Tripathi, Neeraj Bhardwaj, Prashun Parashar
Air paint application is a technology that has gained popularity due to its ability to simulate real-life painting tasks in a virtual environment. This technology allows users to experiment with different colors, textures, and finishes without the need for physical paint or equipment. In this study, a solution is proposed that allows to draw anything virtually using a camera and a colored marker. The marker is usually placed on the tip of the finger and its movement is recorded by the camera. Computer vision techniques are used for the solution to this problem with the help of its extensive libraries, simple syntax, and ease of use. However, this problem can also be implemented in other similar open cv supported languages with some basic understanding. This is achieved by tracking and detecting the color of the marker. Once the color is recognized, a mask is created. Morphological operations is performed such as erosion and dilation on the mask. Erosion reduces the impurities in the mask while dilation restores the main mask that has been eroded. The aim of this study is to allow us to draw virtually without the need for physical drawing tools. One of the major applications of this study is to improve the teaching learning process. An instructor with the help of virtual drawing can create effective contents for his/her class like can draw different shapes, tables and write text, can create flowchart, diagram, etc.
{"title":"Virtual Drawing: An Air Paint Application","authors":"S. C. Agrawal, R. Tripathi, Neeraj Bhardwaj, Prashun Parashar","doi":"10.1109/ICECAA58104.2023.10212239","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212239","url":null,"abstract":"Air paint application is a technology that has gained popularity due to its ability to simulate real-life painting tasks in a virtual environment. This technology allows users to experiment with different colors, textures, and finishes without the need for physical paint or equipment. In this study, a solution is proposed that allows to draw anything virtually using a camera and a colored marker. The marker is usually placed on the tip of the finger and its movement is recorded by the camera. Computer vision techniques are used for the solution to this problem with the help of its extensive libraries, simple syntax, and ease of use. However, this problem can also be implemented in other similar open cv supported languages with some basic understanding. This is achieved by tracking and detecting the color of the marker. Once the color is recognized, a mask is created. Morphological operations is performed such as erosion and dilation on the mask. Erosion reduces the impurities in the mask while dilation restores the main mask that has been eroded. The aim of this study is to allow us to draw virtually without the need for physical drawing tools. One of the major applications of this study is to improve the teaching learning process. An instructor with the help of virtual drawing can create effective contents for his/her class like can draw different shapes, tables and write text, can create flowchart, diagram, etc.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129226650","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212403
J. K. A. Roghaan
The purpose of this study is to evaluate how Orthogonal Frequency Division Multiplexing (OFDM) systems function when their carrier frequency offset is fixed or random. The effect of carrier frequency offset on subcarrier orthogonality and the ensuing inter-carrier interference (ICI) are investigated through simulation using MATLAB. The results show that, even in the presence of a high signal-to-noise ratio (SNR), a small frequency offset can cause a significant decline in bit error rate (BER). The BER vs SNR plot demonstrates that even a slight increase in the carrier frequency offset, such as 0.25, negatively affects the BER vs SNR curve. Moreover, for a frequency offset of 0.5, the BER vs SNR curve becomes a flat line, indicating no improvement in SNR. These findings emphasize the critical role of managing carrier frequency offset in OFDM systems to maintain performance and mitigate interference.
{"title":"Evaluating OFDM Performance under Carrier Frequency Offset Effects","authors":"J. K. A. Roghaan","doi":"10.1109/ICECAA58104.2023.10212403","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212403","url":null,"abstract":"The purpose of this study is to evaluate how Orthogonal Frequency Division Multiplexing (OFDM) systems function when their carrier frequency offset is fixed or random. The effect of carrier frequency offset on subcarrier orthogonality and the ensuing inter-carrier interference (ICI) are investigated through simulation using MATLAB. The results show that, even in the presence of a high signal-to-noise ratio (SNR), a small frequency offset can cause a significant decline in bit error rate (BER). The BER vs SNR plot demonstrates that even a slight increase in the carrier frequency offset, such as 0.25, negatively affects the BER vs SNR curve. Moreover, for a frequency offset of 0.5, the BER vs SNR curve becomes a flat line, indicating no improvement in SNR. These findings emphasize the critical role of managing carrier frequency offset in OFDM systems to maintain performance and mitigate interference.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124028130","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212282
Gnanasekaran T, S. R, Bharath Singh Jebaraj
Accidents are termed as unplanned event which causes serious damage to life and property. The reason for road traffic accidents may vary but the major reason is due to driver's ill-health and inattention. A prototype is designed for continuously monitoring the driver's current health condition and automatic headlight intensity control. For adaptive light intensity control, the system will continuously monitor the opposite vehicle's headlight intensity. If the opposite vehicle intensity is high, the headlight beam will be lowered and vice versa. Depending upon the approaching vehicle headlight intensity, the vehicle headlight beam will be either lowered or raised. This avoids glare for the approaching vehicle driver and ensures a safe drive. This anti-glare system will avoid accidents due to unclear vision or temporary blindness due to headlamp light intensity. Another main reason for accidents is the driver's health abnormality. It causes threats to the people traveling in the vehicle and to the people in the approaching vehicle. This system will continuously monitor the main health parameters of the driver like heart rate and temperature. The alcohol is also sensed by the gas sensor. These sensors are interfaced with a microcontroller and the values are compared with the predefined values. The status is displayed in the LCD and information will be provided to the owner through SMS.
{"title":"Flexible Light Intensity Control of Headlamp and Health Monitoring System","authors":"Gnanasekaran T, S. R, Bharath Singh Jebaraj","doi":"10.1109/ICECAA58104.2023.10212282","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212282","url":null,"abstract":"Accidents are termed as unplanned event which causes serious damage to life and property. The reason for road traffic accidents may vary but the major reason is due to driver's ill-health and inattention. A prototype is designed for continuously monitoring the driver's current health condition and automatic headlight intensity control. For adaptive light intensity control, the system will continuously monitor the opposite vehicle's headlight intensity. If the opposite vehicle intensity is high, the headlight beam will be lowered and vice versa. Depending upon the approaching vehicle headlight intensity, the vehicle headlight beam will be either lowered or raised. This avoids glare for the approaching vehicle driver and ensures a safe drive. This anti-glare system will avoid accidents due to unclear vision or temporary blindness due to headlamp light intensity. Another main reason for accidents is the driver's health abnormality. It causes threats to the people traveling in the vehicle and to the people in the approaching vehicle. This system will continuously monitor the main health parameters of the driver like heart rate and temperature. The alcohol is also sensed by the gas sensor. These sensors are interfaced with a microcontroller and the values are compared with the predefined values. The status is displayed in the LCD and information will be provided to the owner through SMS.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116315010","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212147
Srinuvasarao Sanapala, D. D. Reddy, G. L. Chowdary, K.Sai Vikyath
DDoS attacks remain a serious threat to the performance and availability of computer networks. This study provides a machine learning-based method for identifying DDoS attacks in SDN (software-defined networks). The proposed method employs support vector machine (SVM) and decision tree (DT) classifiers to monitor and analyze network traffic in real-time, spotting prospective attacks and thwarting them before they can do any harm. The testing findings show the efficiency of the proposed methodology, detecting and mitigating DDoS attacks with high accuracy while minimizing false positives. The proposed method offers a scalable and effective method for boosting the security of SDN-based networks against DDoS attacks by utilizing the centralized control plane of SDN.
{"title":"Machine Learning Based DDoS Attack Detection in Software Defined Networks (SDN)","authors":"Srinuvasarao Sanapala, D. D. Reddy, G. L. Chowdary, K.Sai Vikyath","doi":"10.1109/ICECAA58104.2023.10212147","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212147","url":null,"abstract":"DDoS attacks remain a serious threat to the performance and availability of computer networks. This study provides a machine learning-based method for identifying DDoS attacks in SDN (software-defined networks). The proposed method employs support vector machine (SVM) and decision tree (DT) classifiers to monitor and analyze network traffic in real-time, spotting prospective attacks and thwarting them before they can do any harm. The testing findings show the efficiency of the proposed methodology, detecting and mitigating DDoS attacks with high accuracy while minimizing false positives. The proposed method offers a scalable and effective method for boosting the security of SDN-based networks against DDoS attacks by utilizing the centralized control plane of SDN.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114819124","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212210
L. D, B. M, M. M, H. Praveena, P. Geetha
The Elderly people practice Polypharmacy by receiving many medications for acute and chronic conditions due to their effectiveness in preventing diseases or slowing disease progression. Elderly people are encouraged to manage medicines by themselves, in spite of their difficulties like poor vision, forgetfulness, non-availability of caretakers, busy schedules of their children etc. A smart Medication box is implemented for elderly people which enables them to take medicines in time, even in the absence of caretakers and sends the status of medication to the family members. The Smart medication box designed initially alerts elderly people to take medicines in the stipulated time by utilizing LED display, sound and light. It also sends the same message in the LED display simultaneously to the family member. After the medicine is consumed, with the help of the GSM module, the message of MEDICINE TAKEN is sent to the family member. The smart Medication box also monitors the stock of medicines continuously and automatically refills it by sending a request to the authenticated pharmacist nearby for supplying the necessary medicines in advance.
{"title":"A Smart Medication Box with Regular Medications and In-Time Refilling","authors":"L. D, B. M, M. M, H. Praveena, P. Geetha","doi":"10.1109/ICECAA58104.2023.10212210","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212210","url":null,"abstract":"The Elderly people practice Polypharmacy by receiving many medications for acute and chronic conditions due to their effectiveness in preventing diseases or slowing disease progression. Elderly people are encouraged to manage medicines by themselves, in spite of their difficulties like poor vision, forgetfulness, non-availability of caretakers, busy schedules of their children etc. A smart Medication box is implemented for elderly people which enables them to take medicines in time, even in the absence of caretakers and sends the status of medication to the family members. The Smart medication box designed initially alerts elderly people to take medicines in the stipulated time by utilizing LED display, sound and light. It also sends the same message in the LED display simultaneously to the family member. After the medicine is consumed, with the help of the GSM module, the message of MEDICINE TAKEN is sent to the family member. The smart Medication box also monitors the stock of medicines continuously and automatically refills it by sending a request to the authenticated pharmacist nearby for supplying the necessary medicines in advance.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114843015","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212249
Abhishek G, A. Prabhu, N. Rani
Dragon fruit is a popular fruit with a unique appearance and taste. It is an important fruit in export and domestic markets. However, its maturity detection is still a challenging task due to the complexity of its physical properties. This research study introduces a new approach by utilizing the VGG16 model and SVM to detect the maturity of dragon fruit. For the purpose of increasing the datasets, the data augmentation techniques were applied that was followed by preprocessing, thresholding, edge detection and contour detection, and extracting the ROI. The segmented images were then sent to the VGG-16 model that provided accuracy of 95.93%, 95.31% and 96.54 % for unripe, partially ripe and ripe stages. The features extracted for the fruit region are mean, standard deviation, entropy, contrast, correlation, Inverse difference moments. These are fed to the SVM classifier that generated accuracy of 91.93%, 91.93 % and 92.54% accuracy for unripe, partially ripe and ripe stage −16 performed better than SVM classifier.
{"title":"Identification of Stages of Ripening of Dragon Fruit Using Neural Networks for Smart Agriculture","authors":"Abhishek G, A. Prabhu, N. Rani","doi":"10.1109/ICECAA58104.2023.10212249","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212249","url":null,"abstract":"Dragon fruit is a popular fruit with a unique appearance and taste. It is an important fruit in export and domestic markets. However, its maturity detection is still a challenging task due to the complexity of its physical properties. This research study introduces a new approach by utilizing the VGG16 model and SVM to detect the maturity of dragon fruit. For the purpose of increasing the datasets, the data augmentation techniques were applied that was followed by preprocessing, thresholding, edge detection and contour detection, and extracting the ROI. The segmented images were then sent to the VGG-16 model that provided accuracy of 95.93%, 95.31% and 96.54 % for unripe, partially ripe and ripe stages. The features extracted for the fruit region are mean, standard deviation, entropy, contrast, correlation, Inverse difference moments. These are fed to the SVM classifier that generated accuracy of 91.93%, 91.93 % and 92.54% accuracy for unripe, partially ripe and ripe stage −16 performed better than SVM classifier.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126220549","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212189
M. N, S. S, E. S, H. S, Megha A, V. M
The reuse of water in process industries is used to increase the quantity of the water level. In process industries, the quality of water plays an important role and it also shows effects during the process. Continuous reuse of water in industries reduces the quality of water parameters. Some water parameters like pH and TDS are affected. Due to the reuse of water, the base level in the water gets increased and also the TDS level gets increased. This affects the quality of water, which leads to formation of mosses. Water parameters should be monitored and controlled. So, the buffer solution is added to the water which helps in reducing the base level of the water. If the buffer solution is added manually the acid level gets increased and leads to scale formation. So these water parameters should be monitored and controlled. The TDS level and pH level are monitored using TDS sensor and pH meter respectively. NodeMCU controls the solenoid valve which is connected with the sodium chloride buffer solution and controls the pH meter. Thus the quality of recycled water is controlled and monitored in the process industry and IOT is used to monitor the pH meter and TDS sensor from any location
{"title":"Implementation of Monitoring and Controlling of pH and TDS in Process Industry","authors":"M. N, S. S, E. S, H. S, Megha A, V. M","doi":"10.1109/ICECAA58104.2023.10212189","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212189","url":null,"abstract":"The reuse of water in process industries is used to increase the quantity of the water level. In process industries, the quality of water plays an important role and it also shows effects during the process. Continuous reuse of water in industries reduces the quality of water parameters. Some water parameters like pH and TDS are affected. Due to the reuse of water, the base level in the water gets increased and also the TDS level gets increased. This affects the quality of water, which leads to formation of mosses. Water parameters should be monitored and controlled. So, the buffer solution is added to the water which helps in reducing the base level of the water. If the buffer solution is added manually the acid level gets increased and leads to scale formation. So these water parameters should be monitored and controlled. The TDS level and pH level are monitored using TDS sensor and pH meter respectively. NodeMCU controls the solenoid valve which is connected with the sodium chloride buffer solution and controls the pH meter. Thus the quality of recycled water is controlled and monitored in the process industry and IOT is used to monitor the pH meter and TDS sensor from any location","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126397528","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212292
M. A. Gandhi, Vusal Karimli Maharram, G. Raja, S.P. Sellapaandi, Ketan Rathor, Kamlesh Singh
Intelligent robots, intelligent mobiles, intelligent stores, and so on are just a few of the areas where computer-aided ergonomics is being put to use. Convenience stores (CVS) are adapting to a new era of competition by offering a wider variety of products and services than ever before, such as daily fresh meals, a cafe, ticketing, and a grocery. Therefore, it is becoming increasingly difficult to estimate daily sales of’ fresh commodities due to the impact of both internal and external factors. In the long run, a trustworthy sales-forecasting system is going to be critical for enhancing corporate plans and gaining an edge over the competition. In today's internet age, data production has reached unprecedented levels, well beyond what any single human being can comprehend. This has led to the development of a plethora of machine learning methods. In this proposed approach various machine learning methods are explored for predicting store's sales and evaluate them to find the one that works best for the specific scenario. Training times are reduced and data quality is enhanced with the help of Normalization in the proposed approach. K-Means is a popular feature selection clustering algorithm. Fuzzy Pruning LS-SVM is used in the suggested method for training the model. The proposed model has superior performance on SVM and CNN.
{"title":"A Novel Method for Exploring the Store Sales Forecasting using Fuzzy Pruning LS-SVM Approach","authors":"M. A. Gandhi, Vusal Karimli Maharram, G. Raja, S.P. Sellapaandi, Ketan Rathor, Kamlesh Singh","doi":"10.1109/ICECAA58104.2023.10212292","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212292","url":null,"abstract":"Intelligent robots, intelligent mobiles, intelligent stores, and so on are just a few of the areas where computer-aided ergonomics is being put to use. Convenience stores (CVS) are adapting to a new era of competition by offering a wider variety of products and services than ever before, such as daily fresh meals, a cafe, ticketing, and a grocery. Therefore, it is becoming increasingly difficult to estimate daily sales of’ fresh commodities due to the impact of both internal and external factors. In the long run, a trustworthy sales-forecasting system is going to be critical for enhancing corporate plans and gaining an edge over the competition. In today's internet age, data production has reached unprecedented levels, well beyond what any single human being can comprehend. This has led to the development of a plethora of machine learning methods. In this proposed approach various machine learning methods are explored for predicting store's sales and evaluate them to find the one that works best for the specific scenario. Training times are reduced and data quality is enhanced with the help of Normalization in the proposed approach. K-Means is a popular feature selection clustering algorithm. Fuzzy Pruning LS-SVM is used in the suggested method for training the model. The proposed model has superior performance on SVM and CNN.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122268166","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：