Pub Date : 2023-01-19DOI: 10.1109/ICCT56969.2023.10075789
Shiveswarran Ratneswaran, Uthayasanker Thayasivam
The widespread use of location-enabled devices on public transportation vehicles produces a huge amount of geospatial data. The primary objective of this research study is to build a solution framework that can process a large amount of geospatial data obtained from GPS (Global Positioning System) receivers fixed on different buses on different routes, preprocess, clean, and transform that data for analysis. There are various challenges associated with the processing of GPS data, like discontinuities, non-uniformities, poor network coverage, and human errors. This study proposes two novel, simple algorithms to extract bus trip and bus stop sequences, from the crude raw data, incorporating those challenges. Moreover, the dwell times at the bus stops are estimated solely using this GPS data in three different possible scenarios in the data filtering process. When considering the previous related studies in this area, the proposed approaches are applied to GPS data obtained at a medium sample rate (for example, 15 seconds) for heterogeneous traffic conditions, and also with a unique dwell time estimation process. In addition, statistical methods are implemented to analyse a variety of novel public transit-system performance metrics, such as (i) excess journey time (EJT); (ii) excess dwelling time (EDT); (ii) excess running time (ERT); and (iv) segment idle time ratio (SITR), at different time horizons, where these metrics are developed in the absence of schedule data. These metrics facilitate the transport authorities in real-time bus monitoring, evaluating their performance, and identifying inappropriate driving behaviours. A detailed explanation is provided through a case study of two main routes in the Kandy district of Sri Lanka.
{"title":"Extracting potential Travel time information from raw GPS data and Evaluating the Performance of Public transit - a case study in Kandy, Sri Lanka","authors":"Shiveswarran Ratneswaran, Uthayasanker Thayasivam","doi":"10.1109/ICCT56969.2023.10075789","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10075789","url":null,"abstract":"The widespread use of location-enabled devices on public transportation vehicles produces a huge amount of geospatial data. The primary objective of this research study is to build a solution framework that can process a large amount of geospatial data obtained from GPS (Global Positioning System) receivers fixed on different buses on different routes, preprocess, clean, and transform that data for analysis. There are various challenges associated with the processing of GPS data, like discontinuities, non-uniformities, poor network coverage, and human errors. This study proposes two novel, simple algorithms to extract bus trip and bus stop sequences, from the crude raw data, incorporating those challenges. Moreover, the dwell times at the bus stops are estimated solely using this GPS data in three different possible scenarios in the data filtering process. When considering the previous related studies in this area, the proposed approaches are applied to GPS data obtained at a medium sample rate (for example, 15 seconds) for heterogeneous traffic conditions, and also with a unique dwell time estimation process. In addition, statistical methods are implemented to analyse a variety of novel public transit-system performance metrics, such as (i) excess journey time (EJT); (ii) excess dwelling time (EDT); (ii) excess running time (ERT); and (iv) segment idle time ratio (SITR), at different time horizons, where these metrics are developed in the absence of schedule data. These metrics facilitate the transport authorities in real-time bus monitoring, evaluating their performance, and identifying inappropriate driving behaviours. A detailed explanation is provided through a case study of two main routes in the Kandy district of Sri Lanka.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131233156","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10075941
Murali Mohan Mishra, Pravir Kumar
Use of acetylcholinesterase (AChE) inhibitor in treating the neurological disorders has long been studied due to its potential to cross the endothelial tight junctions, longer bioavailability, and better ability to penetrate skin. Alzheimer's disease is found to have closely related with the decline in the level of neurotransmitters which leads to deterioration of the cholinergic neurons of the neocortex and the hippocampus of the rat's brain. Impairment in the transmission of cholinergic nerve signals results in the formation of senile plaque and neurofibrillary tangles (NFT). As a result, one of the main goals for the development of therapeutic approaches for Alzheimer's disease has been to improve the cholinergic activities of the brain. The discovery of one of the most efficient acetylcholinesterase inhibitors called Donepezil was proved to be a much better approach as compared to other drugs such as physostigmine and Tacrine. In the present study we have focused on the role of 5,6-dimethoxy-2-(piperidin-4-ylmethyl)-2,3-dihydroinden-l-one as an important acetylcholinesterase in the treatment of Alzheimer's disease. We have performed molecular docking to see the interaction of ACE target protein and the inhibitory ligands and further validated the pharmacokinetic properties of the drug via ADME analysis of the drug.
{"title":"Identification and Screening of Novel ACE Inhibitors using Computational Approach","authors":"Murali Mohan Mishra, Pravir Kumar","doi":"10.1109/ICCT56969.2023.10075941","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10075941","url":null,"abstract":"Use of acetylcholinesterase (AChE) inhibitor in treating the neurological disorders has long been studied due to its potential to cross the endothelial tight junctions, longer bioavailability, and better ability to penetrate skin. Alzheimer's disease is found to have closely related with the decline in the level of neurotransmitters which leads to deterioration of the cholinergic neurons of the neocortex and the hippocampus of the rat's brain. Impairment in the transmission of cholinergic nerve signals results in the formation of senile plaque and neurofibrillary tangles (NFT). As a result, one of the main goals for the development of therapeutic approaches for Alzheimer's disease has been to improve the cholinergic activities of the brain. The discovery of one of the most efficient acetylcholinesterase inhibitors called Donepezil was proved to be a much better approach as compared to other drugs such as physostigmine and Tacrine. In the present study we have focused on the role of 5,6-dimethoxy-2-(piperidin-4-ylmethyl)-2,3-dihydroinden-l-one as an important acetylcholinesterase in the treatment of Alzheimer's disease. We have performed molecular docking to see the interaction of ACE target protein and the inhibitory ligands and further validated the pharmacokinetic properties of the drug via ADME analysis of the drug.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132980329","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}
The Internet of Things (IoT) is a new standard that has transformed the traditional way of life into a high-tech lifestyle. Smart cities, smart homes, pollution control, energy saving, smart transportation, and smart industries are such transformations due to IoT. The IoT system tries to associate with almost all devices at any place. A broad variety of industries is deploying IoT solutions to make the next level of visibility and improved efficiencies. Attackers are forever on the lookout for brand new ways to compromise systems and gain access to information stores and systems. Mostly, gadgets are inclined to vulnerable attacks because of the straightforward and open nature of their networks. This paper gives an overview of the ongoing status and worries of Internet of things (IoT) security and we have focused on mitigating the brute-force attack and performed real-time cases to secure the readings of the sensors stored. This research presents an outline of safety security challenges, proposed countermeasures, and the future bearings for getting the IoT.
{"title":"Secured Environmental Monitoring System","authors":"Laasya Sree Talluru, Saketh Kapuganti, Yoga Bhavagna Jonnala, Jetendra Joshi","doi":"10.1109/ICCT56969.2023.10075967","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10075967","url":null,"abstract":"The Internet of Things (IoT) is a new standard that has transformed the traditional way of life into a high-tech lifestyle. Smart cities, smart homes, pollution control, energy saving, smart transportation, and smart industries are such transformations due to IoT. The IoT system tries to associate with almost all devices at any place. A broad variety of industries is deploying IoT solutions to make the next level of visibility and improved efficiencies. Attackers are forever on the lookout for brand new ways to compromise systems and gain access to information stores and systems. Mostly, gadgets are inclined to vulnerable attacks because of the straightforward and open nature of their networks. This paper gives an overview of the ongoing status and worries of Internet of things (IoT) security and we have focused on mitigating the brute-force attack and performed real-time cases to secure the readings of the sensors stored. This research presents an outline of safety security challenges, proposed countermeasures, and the future bearings for getting the IoT.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126681083","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076140
V. Juneja, Shail Kumar Dinkar
In wireless sensor network, various factors of sensor node are used for ensured delivery of packets like battery or energy, node's status, neighboring nodes etc. which are essential for successful transmission between source and destination as well as among the intermediate nodes. Open communication and lack of energy make networks vulnerable to several security attacks. During data transmission, data packets move from source to destination through many intermediate nodes that may not be trusted. In this paper, a probabilistic approach is proposed to calculate the trust of the nodes. A constant factor of energy is needed to transfer the packet from one node to another. Trust value and estimated energy consumption at every node is determined. If the calculated energy consumption of a node when compared with divided constant factor of energy using fuzzy logic is said to be the trusted node. If energy consumption matches with the estimated energy value approximately then delivery of data packet is assumed successful otherwise it is considered as Vampire Node. In this paper, an algorithm is proposed to detect Vampire Attack to save the network from extra consumption of energy consumed by a particular node. The performance of the proposed algorithm is measured and compared using various parameters such as energy and traffic load.
{"title":"An Approach against Vampire Attack for Successful Transmission in Wireless Sensor Network","authors":"V. Juneja, Shail Kumar Dinkar","doi":"10.1109/ICCT56969.2023.10076140","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076140","url":null,"abstract":"In wireless sensor network, various factors of sensor node are used for ensured delivery of packets like battery or energy, node's status, neighboring nodes etc. which are essential for successful transmission between source and destination as well as among the intermediate nodes. Open communication and lack of energy make networks vulnerable to several security attacks. During data transmission, data packets move from source to destination through many intermediate nodes that may not be trusted. In this paper, a probabilistic approach is proposed to calculate the trust of the nodes. A constant factor of energy is needed to transfer the packet from one node to another. Trust value and estimated energy consumption at every node is determined. If the calculated energy consumption of a node when compared with divided constant factor of energy using fuzzy logic is said to be the trusted node. If energy consumption matches with the estimated energy value approximately then delivery of data packet is assumed successful otherwise it is considered as Vampire Node. In this paper, an algorithm is proposed to detect Vampire Attack to save the network from extra consumption of energy consumed by a particular node. The performance of the proposed algorithm is measured and compared using various parameters such as energy and traffic load.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126956626","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076119
Pranav Shirgur, Sandeep Chaurasia
The Internet of Things (IoT) is a rapidly developing field of technology which entails a network of smart devices connected to each other and the internet. The TATCRB2industry is anticipated to increase by 18% to 14.4 billion active connections in 2022. There will likely be about 27 billion linked IoT devices by 2025 as supply limitations, brought about by the current global semiconductor and chip shortage - loosen and demand quickens. IoT has quickly penetrated the healthcare industry, this paper defines a framework that enables the development of secure and scalable IoT healthcare platforms/applications. These platforms will also allow for secure cloud storage and analysis of patient data, helping professionals recognize latent parameters such as patient behavioral patterns that contribute to an ailment. This ultimately will enable the study of social and economic impact of a particular disease. This will greatly cull the survivorship bias in the health care industry - especially in testing times like a pandemic.
{"title":"Development of Secure IoT Ecosystems for Healthcare","authors":"Pranav Shirgur, Sandeep Chaurasia","doi":"10.1109/ICCT56969.2023.10076119","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076119","url":null,"abstract":"The Internet of Things (IoT) is a rapidly developing field of technology which entails a network of smart devices connected to each other and the internet. The TATCRB2industry is anticipated to increase by 18% to 14.4 billion active connections in 2022. There will likely be about 27 billion linked IoT devices by 2025 as supply limitations, brought about by the current global semiconductor and chip shortage - loosen and demand quickens. IoT has quickly penetrated the healthcare industry, this paper defines a framework that enables the development of secure and scalable IoT healthcare platforms/applications. These platforms will also allow for secure cloud storage and analysis of patient data, helping professionals recognize latent parameters such as patient behavioral patterns that contribute to an ailment. This ultimately will enable the study of social and economic impact of a particular disease. This will greatly cull the survivorship bias in the health care industry - especially in testing times like a pandemic.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115613688","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076122
Asifuddin Nasiruddin Ahmed, Ravinder Saini
Fraudulent transaction in credit cards has frequently rise in couple of years. Credit card fraud is a major issue for financial organizations, and accurate fraud detection is often difficult. Over Fifty percent of Americans have encountered a fraudulent transaction on their debit or credit card, and more than 1/3 of those who use these cards have done so repeatedly, according to 2021 yearly research. This translates to one hundred and twenty-seven million Americans who have at least once experienced credit card theft. Detection of such fraud happening over huge database is very difficult and time consuming using conventional method. By taking help of AI technology and developing an automated fraud detection system to detect and classify such mishappening using machine learning is an efficient way to deal with this kind of problem. This paper reviews various researchers work on detection of credit card frauds on highly imbalance dataset and discusses some machine learning techniques as Random Forest, Logistic Regression, SVM, Naive Bayes, XGBoost and KNN which are generally used by various researchers to build a model. The findings obtained from various researchers work showed that ensemble machine learning technique such as XGBoost and Random Forest are more capable of providing all over good performance in classifying such fraudulent and non-fraudulent transactions in credit cards.
{"title":"A Survey on Detection of Fraudulent Credit Card Transactions Using Machine Learning Algorithms","authors":"Asifuddin Nasiruddin Ahmed, Ravinder Saini","doi":"10.1109/ICCT56969.2023.10076122","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076122","url":null,"abstract":"Fraudulent transaction in credit cards has frequently rise in couple of years. Credit card fraud is a major issue for financial organizations, and accurate fraud detection is often difficult. Over Fifty percent of Americans have encountered a fraudulent transaction on their debit or credit card, and more than 1/3 of those who use these cards have done so repeatedly, according to 2021 yearly research. This translates to one hundred and twenty-seven million Americans who have at least once experienced credit card theft. Detection of such fraud happening over huge database is very difficult and time consuming using conventional method. By taking help of AI technology and developing an automated fraud detection system to detect and classify such mishappening using machine learning is an efficient way to deal with this kind of problem. This paper reviews various researchers work on detection of credit card frauds on highly imbalance dataset and discusses some machine learning techniques as Random Forest, Logistic Regression, SVM, Naive Bayes, XGBoost and KNN which are generally used by various researchers to build a model. The findings obtained from various researchers work showed that ensemble machine learning technique such as XGBoost and Random Forest are more capable of providing all over good performance in classifying such fraudulent and non-fraudulent transactions in credit cards.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116522144","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076157
Taoufik Ouleddroun, Ayoub Ellahyani, M. El Ansari
Pneumonia is swelling of the lungs that is usually caused by an infection. This disease is considered as one of the most common reasons for US children to be hospitalized. According to American Thoracic Society (ATS), the cost of treating pneumonia cases in hospitals reached 9.5 billion dollar. The appropriate treatment and recovery process for this disease are linked to early diagnosis. In this work a novel method is proposed for detecting the pneumonia and help the radiologists in their decision making process. First, histogram equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are calculated for chest X-ray images. Then, the images extracted are fed to a model consisting of two stream of Convolutional Neural Networks (CNN) that was trained on the Pneumonia Kermany dataset. Finally, several machine learning classifiers are employed to perform the detection process based on the deep features extracted. The proposed system achieves 97.86% in terms of accuracy on the Kermany dataset, which is satisfactory when compared to recently published works.
{"title":"Automated Pneumonia Detection using deep features in chest X-ray images","authors":"Taoufik Ouleddroun, Ayoub Ellahyani, M. El Ansari","doi":"10.1109/ICCT56969.2023.10076157","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076157","url":null,"abstract":"Pneumonia is swelling of the lungs that is usually caused by an infection. This disease is considered as one of the most common reasons for US children to be hospitalized. According to American Thoracic Society (ATS), the cost of treating pneumonia cases in hospitals reached 9.5 billion dollar. The appropriate treatment and recovery process for this disease are linked to early diagnosis. In this work a novel method is proposed for detecting the pneumonia and help the radiologists in their decision making process. First, histogram equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are calculated for chest X-ray images. Then, the images extracted are fed to a model consisting of two stream of Convolutional Neural Networks (CNN) that was trained on the Pneumonia Kermany dataset. Finally, several machine learning classifiers are employed to perform the detection process based on the deep features extracted. The proposed system achieves 97.86% in terms of accuracy on the Kermany dataset, which is satisfactory when compared to recently published works.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122078734","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076212
Madhavendra Singh
Most object detection algorithms attempt to detect all objects present in an image and accordingly classify them. While that approach is useful for various domains and applications, there are also many cases where we would only want to search for a particular object in a given image. For such cases, there is potential to optimize the search by focusing on the object we are looking for and ignoring the rest of the information in the image to the maximum possible extent, thereby greatly improving the computation speed. In this light, I have developed a model which can search for an object given in an image (the object image) in another image where the object mayor may not be present (the target image). The design takes inspiration from Siamese Neural Networks and techniques applied in other object detection algorithms and combines them with a novel technique and loss. I have trained and tested the model using images from the COCO dataset. It has shown improvement in computation speed compared to other state-of-the-art models for the desired task, along with appreciable accuracy.
{"title":"A Novel Approach to Object Detection: Object Search","authors":"Madhavendra Singh","doi":"10.1109/ICCT56969.2023.10076212","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076212","url":null,"abstract":"Most object detection algorithms attempt to detect all objects present in an image and accordingly classify them. While that approach is useful for various domains and applications, there are also many cases where we would only want to search for a particular object in a given image. For such cases, there is potential to optimize the search by focusing on the object we are looking for and ignoring the rest of the information in the image to the maximum possible extent, thereby greatly improving the computation speed. In this light, I have developed a model which can search for an object given in an image (the object image) in another image where the object mayor may not be present (the target image). The design takes inspiration from Siamese Neural Networks and techniques applied in other object detection algorithms and combines them with a novel technique and loss. I have trained and tested the model using images from the COCO dataset. It has shown improvement in computation speed compared to other state-of-the-art models for the desired task, along with appreciable accuracy.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123015409","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10075993
Anany Pandey, Manish Pandey
Price prediction and load forecasting is a difficult task for industries. Electricity price are varied according to load or demand of energy. In this article suggested a novel approach for load and price forecasting based on neural network with improved Polak-Rlbière-Polyak(PRP) learning approach. For training and testing purpose use Russian wholesale market. For the implementation and simulation of proposed approach use matrix laboratory (MATLAB) R2020a and high performance computing (HPC) lab. For the evaluation of proposed method use different result parameter mean absolute percentage error, mean square error and root mean square error. The proposed approach shows lower error rate as compare to different techniques proposed by different researchers in terms of MSE, RMSE and MAPE. For the proposed method MAPE value is 1.2069%.
{"title":"A Robust Neural Network Based Short Time Electricity Price Prediction","authors":"Anany Pandey, Manish Pandey","doi":"10.1109/ICCT56969.2023.10075993","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10075993","url":null,"abstract":"Price prediction and load forecasting is a difficult task for industries. Electricity price are varied according to load or demand of energy. In this article suggested a novel approach for load and price forecasting based on neural network with improved Polak-Rlbière-Polyak(PRP) learning approach. For training and testing purpose use Russian wholesale market. For the implementation and simulation of proposed approach use matrix laboratory (MATLAB) R2020a and high performance computing (HPC) lab. For the evaluation of proposed method use different result parameter mean absolute percentage error, mean square error and root mean square error. The proposed approach shows lower error rate as compare to different techniques proposed by different researchers in terms of MSE, RMSE and MAPE. For the proposed method MAPE value is 1.2069%.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116956358","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 : 2023-01-19DOI: 10.1109/ICCT56969.2023.10076120
Gautam Chettiar, A. Shukla, Preet Nalwaya, K. Sethi, Surya Prakash
Recent trends in artificial intelligence and natural language processing models have led to the generation of highly efficient and versatile intelligent chatbot models., which have the potential to supplant human speech to the level of conversational proficiency. The proposed method creates a chatbot model that trains itself on open conversation datasets and aims to impersonate without compromising the emotional sentiments in the voice. These datasets extract from the applications such as WhatsApp., Telegram., Messenger., or any other chatting platform. Datasets convert to a machine-readable format., which is dynamically updated in real-time during the conversation., and then using speech conversion algorithms convert the reply into the desired individual's voice. The proposed model's conversational ability depends on the amount of conversation data., which gives the output in the person's voice frequency. By using an NLP-based chatbot trained on personalized data using KNN., and handling misses by pipelining the chatbot inputs to the GPT-2 model., the model can generate human-like replies even if there is data insufficiency. The natural replies are complemented with matching human voice and tone characteristics by using the vocoder model., which matches the spectral characteristics of the target voice onto the required voice. This opens a plethora of commercial and therapeutic applications that provide excellent insights into implementing natural communication models for humanoid and robotics innovations.
{"title":"Impersonated Human Speech Chatbot with Adaptive Frequency Spectrum","authors":"Gautam Chettiar, A. Shukla, Preet Nalwaya, K. Sethi, Surya Prakash","doi":"10.1109/ICCT56969.2023.10076120","DOIUrl":"https://doi.org/10.1109/ICCT56969.2023.10076120","url":null,"abstract":"Recent trends in artificial intelligence and natural language processing models have led to the generation of highly efficient and versatile intelligent chatbot models., which have the potential to supplant human speech to the level of conversational proficiency. The proposed method creates a chatbot model that trains itself on open conversation datasets and aims to impersonate without compromising the emotional sentiments in the voice. These datasets extract from the applications such as WhatsApp., Telegram., Messenger., or any other chatting platform. Datasets convert to a machine-readable format., which is dynamically updated in real-time during the conversation., and then using speech conversion algorithms convert the reply into the desired individual's voice. The proposed model's conversational ability depends on the amount of conversation data., which gives the output in the person's voice frequency. By using an NLP-based chatbot trained on personalized data using KNN., and handling misses by pipelining the chatbot inputs to the GPT-2 model., the model can generate human-like replies even if there is data insufficiency. The natural replies are complemented with matching human voice and tone characteristics by using the vocoder model., which matches the spectral characteristics of the target voice onto the required voice. This opens a plethora of commercial and therapeutic applications that provide excellent insights into implementing natural communication models for humanoid and robotics innovations.","PeriodicalId":128100,"journal":{"name":"2023 3rd International Conference on Intelligent Communication and Computational Techniques (ICCT)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131605715","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：