Lilia Muñoz, M. Alonso-García, Vladimir Villarreal, Guillermo Hernández, Mel Nielsen, Francisco Pinto-Santos, Amilkar Saavedra, Mariana Areiza, Juan Montenegro, Inés Sittón-Candanedo, Yen-Air Caballero-González, S. Trabelsi, J. Corchado
The areas of data science and data engineering have experienced strong advances in recent years. This has had a particular impact in areas such as healthcare, where, as a result of the pandemic caused by the COVID-19 virus, technological development has accelerated. This has led to a need to produce solutions that enable the collection, integration and efficient use of information for decision making scenarios. This is evidenced by the proliferation of monitoring, data collection, analysis, and prediction systems aimed at controlling the pandemic. This article proposes a hybrid model that combines the dynamics of epidemiological processes with the predictive capabilities of artificial neural networks to go beyond the prediction of the first ones. In addition, the system allows for the introduction of additional information through an expert system, thus allowing the incorporation of additional hypotheses on the adoption of containment measures.
{"title":"A Hybrid System For Pandemic Evolution Prediction","authors":"Lilia Muñoz, M. Alonso-García, Vladimir Villarreal, Guillermo Hernández, Mel Nielsen, Francisco Pinto-Santos, Amilkar Saavedra, Mariana Areiza, Juan Montenegro, Inés Sittón-Candanedo, Yen-Air Caballero-González, S. Trabelsi, J. Corchado","doi":"10.14201/adcaij.28093","DOIUrl":"https://doi.org/10.14201/adcaij.28093","url":null,"abstract":"The areas of data science and data engineering have experienced strong advances in recent years. This has had a particular impact in areas such as healthcare, where, as a result of the pandemic caused by the COVID-19 virus, technological development has accelerated. This has led to a need to produce solutions that enable the collection, integration and efficient use of information for decision making scenarios. This is evidenced by the proliferation of monitoring, data collection, analysis, and prediction systems aimed at controlling the pandemic. This article proposes a hybrid model that combines the dynamics of epidemiological processes with the predictive capabilities of artificial neural networks to go beyond the prediction of the first ones. In addition, the system allows for the introduction of additional information through an expert system, thus allowing the incorporation of additional hypotheses on the adoption of containment measures. \u0000 \u0000 \u0000 \u0000 ","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"68 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84093410","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 financial risk of investing in Bitcoin is increasing, and everyone partic-ipating in the transaction is aware of it. The rise and fall of bitcoin’s value is difficult to predict, and the system is fraught with uncertainty. As a result, this study proposed to use the «Deep learning» technique for predicting fi-nancial risk associated with bitcoin investment, that is linked to its «weighted price» on the bitcoin market’s volatility. The dataset used included Bitcoin historical data, which was acquired «at one-minute intervals» from selected exchanges of January 2012 through December 2020. The deep learning lin-ear-SVM-based technique was used to obtain an advantage in handling the high-dimensional challenges related with bitcoin-based transaction transac-tions large data volume. Four variables («High», «Low», «Close», and «Volume (BTC)».) are conceptualized to predict weighted price, in order to indi-cate if there is a propensity of financial risk over the effect of their interaction. The results of the experimental investigation show that the fi-nancial risk associated with bitcoin investing is accurately predicted. This has helped to discover engagements and disengagements with doubts linked with bitcoin investment transactions, resulting in increased confidence and trust in the system as well as the elimination of financial risk. Our model had a significantly greater prediction accuracy, demonstrating the utility of deep learning systems in detecting financial problems related to digital currency.
{"title":"Predicting Financial Risk Associated to Bitcoin Investment by Deep Learning","authors":"N. Aljojo","doi":"10.14201/adcaij.27269","DOIUrl":"https://doi.org/10.14201/adcaij.27269","url":null,"abstract":"The financial risk of investing in Bitcoin is increasing, and everyone partic-ipating in the transaction is aware of it. The rise and fall of bitcoin’s value is difficult to predict, and the system is fraught with uncertainty. As a result, this study proposed to use the «Deep learning» technique for predicting fi-nancial risk associated with bitcoin investment, that is linked to its «weighted price» on the bitcoin market’s volatility. The dataset used included Bitcoin historical data, which was acquired «at one-minute intervals» from selected exchanges of January 2012 through December 2020. The deep learning lin-ear-SVM-based technique was used to obtain an advantage in handling the high-dimensional challenges related with bitcoin-based transaction transac-tions large data volume. Four variables («High», «Low», «Close», and «Volume (BTC)».) are conceptualized to predict weighted price, in order to indi-cate if there is a propensity of financial risk over the effect of their interaction. The results of the experimental investigation show that the fi-nancial risk associated with bitcoin investing is accurately predicted. This has helped to discover engagements and disengagements with doubts linked with bitcoin investment transactions, resulting in increased confidence and trust in the system as well as the elimination of financial risk. Our model had a significantly greater prediction accuracy, demonstrating the utility of deep learning systems in detecting financial problems related to digital currency.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"93 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88933799","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 population size of DE plays a significant role in the way the algorithm performs as it influences whether good solutions can be found. Generally, the population size of DE algorithm is a user-defined input that remains fixed during the optimization process. Therefore, inadequate selection of DE population size may seriously hinder the performance of the algorithm. This paper investigates the impact of DE population size on (i) the performance of DE when applied to the optimal tuning of power system stabilizers (PSSs); and (ii) the ability of the tuned PSSs to perform efficiently to damp low-frequency oscillations. The effectiveness of these controllers is evaluated based on frequency domain analysis and validated using time-domain simulations. Simulation results show that a small population size may lead the algorithm to converge prematurely, and thus resulting in a poor controller performance. On the other hand, a large population size requires more computational effort, whilst no noticeable improvement in the performance of the controller is observed.
{"title":"A Study on the Impact of DE Population Size on the Performance Power System Stabilizers","authors":"Komla Agbenyo Folly, Tshina Fa Mulumba","doi":"10.14201/adcaij.27955","DOIUrl":"https://doi.org/10.14201/adcaij.27955","url":null,"abstract":"The population size of DE plays a significant role in the way the algorithm performs as it influences whether good solutions can be found. Generally, the population size of DE algorithm is a user-defined input that remains fixed during the optimization process. Therefore, inadequate selection of DE population size may seriously hinder the performance of the algorithm. This paper investigates the impact of DE population size on (i) the performance of DE when applied to the optimal tuning of power system stabilizers (PSSs); and (ii) the ability of the tuned PSSs to perform efficiently to damp low-frequency oscillations. The effectiveness of these controllers is evaluated based on frequency domain analysis and validated using time-domain simulations. Simulation results show that a small population size may lead the algorithm to converge prematurely, and thus resulting in a poor controller performance. On the other hand, a large population size requires more computational effort, whilst no noticeable improvement in the performance of the controller is observed.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"41 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91357431","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}
Vishakha Arya, A. Mishra, Alfonso González-Briones
The novel coronavirus (Covid-19) pandemic has struck the whole world and is one of the most striking topics on social media platforms. Sentiment outbreak on social media enduring various thoughts, opinions, and emotions about the Covid-19 disease, expressing views they are feeling presently. Analyzing sentiments helps to yield better results. Gathering data from different blogging sites like Facebook, Twitter, Weibo, YouTube, Instagram, etc., and Twitter is the largest repository. Videos, text, and audio were also collected from repositories. Sentiment analysis uses opinion mining to acquire the sentiments of its users and categorizes them accordingly as positive, negative, and neutral. Analytical and machine learning classification is implemented to 3586 tweets collected in different time frames. In this paper, sentiment analysis was performed on tweets accumulated during the Covid-19 pandemic, Coronavirus disease. Tweets are collected from the Twitter database using Hydrator a web-based application. Data-preprocessing removes all the noise, outliers from the raw data. With Natural Language Toolkit (NLTK), text classification for sentiment analysis and calculate the score subjective polarity, counts, and sentiment distribution. N-gram is used in textual mining -and Natural Language Processing for a continuous sequence of words in a text or document applying uni-gram, bi-gram, and tri-gram for statistical computation. Term frequency and Inverse document frequency (TF-IDF) is a feature extraction technique that converts textual data into numeric form. Vectorize data feed to our model to obtain insights from linguistic data. Linear SVC, MultinomialNB, GBM, and Random Forest classifier with Tfidf classification model applied to our proposed model. Linear Support Vector classification performs better than the other two classifiers. Results depict that RF performs better.
{"title":"Analysis of sentiments on the onset of Covid-19 using Machine Learning Techniques","authors":"Vishakha Arya, A. Mishra, Alfonso González-Briones","doi":"10.14201/adcaij.27348","DOIUrl":"https://doi.org/10.14201/adcaij.27348","url":null,"abstract":"The novel coronavirus (Covid-19) pandemic has struck the whole world and is one of the most striking topics on social media platforms. Sentiment outbreak on social media enduring various thoughts, opinions, and emotions about the Covid-19 disease, expressing views they are feeling presently. Analyzing sentiments helps to yield better results. Gathering data from different blogging sites like Facebook, Twitter, Weibo, YouTube, Instagram, etc., and Twitter is the largest repository. Videos, text, and audio were also collected from repositories. Sentiment analysis uses opinion mining to acquire the sentiments of its users and categorizes them accordingly as positive, negative, and neutral. Analytical and machine learning classification is implemented to 3586 tweets collected in different time frames. In this paper, sentiment analysis was performed on tweets accumulated during the Covid-19 pandemic, Coronavirus disease. Tweets are collected from the Twitter database using Hydrator a web-based application. Data-preprocessing removes all the noise, outliers from the raw data. With Natural Language Toolkit (NLTK), text classification for sentiment analysis and calculate the score subjective polarity, counts, and sentiment distribution. N-gram is used in textual mining -and Natural Language Processing for a continuous sequence of words in a text or document applying uni-gram, bi-gram, and tri-gram for statistical computation. Term frequency and Inverse document frequency (TF-IDF) is a feature extraction technique that converts textual data into numeric form. Vectorize data feed to our model to obtain insights from linguistic data. Linear SVC, MultinomialNB, GBM, and Random Forest classifier with Tfidf classification model applied to our proposed model. Linear Support Vector classification performs better than the other two classifiers. Results depict that RF performs better.\u0000 ","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"190 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79231399","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}
Zahra Foroozandeha, S. Ramos, J. Soares, Vale Zita, António Gomes
Nowadays, the buildings have an important role on high demand of electricity energy. Therefore, the energy management of the buildings may have significant influence on reducing the electricity consumption. Moreover, Electric Vehicles (EVs) have been considering as a power storage devices in Smart Buildings (SBs) aiming to reduce the cost and consuming energy. Here, an energy management framework is proposed in which by considering the flexibility of the contracted power of each apartment, an optimal charging-discharging scheduled for EVs and Battery Energy Storage System (BESS) is defined over long time period to minimize the electricity cost of the building. The proposed model is design by a Mixed Binary Linear rogramming formulation (MBLP) that the charging and discharging of EVs as well as BESS in each period is treated as binary decision variables. In order to validate the model, a case study involving three scenarios are considered. The obtained results indicate a 15% reduction in total electricity consumption cost and consumption energy by the grid over a one year. Finally, the impact of capacity and charge/discharge rate of BESS on the power cost is analyzed and the optimal size of the BESS for assumed SB in the case study is also reported.
{"title":"Charge/Discharge Scheduling of Electric Vehicles and Battery Energy Storage in Smart Building: a Mix Binary Linear Programming model","authors":"Zahra Foroozandeha, S. Ramos, J. Soares, Vale Zita, António Gomes","doi":"10.14201/adcaij.27904","DOIUrl":"https://doi.org/10.14201/adcaij.27904","url":null,"abstract":"Nowadays, the buildings have an important role on high demand of electricity energy. Therefore, the energy management of the buildings may have significant influence on reducing the electricity consumption. Moreover, Electric Vehicles (EVs) have been considering as a power storage devices in Smart Buildings (SBs) aiming to reduce the cost and consuming energy. Here, an energy management framework is proposed in which by considering the flexibility of the contracted power of each apartment, an optimal charging-discharging scheduled for EVs and Battery Energy Storage System (BESS) is defined over long time period to minimize the electricity cost of the building. The proposed model is design by a Mixed Binary Linear rogramming formulation (MBLP) that the charging and discharging of EVs as well as BESS in each period is treated as binary decision variables. In order to validate the model, a case study involving three scenarios are considered. The obtained results indicate a 15% reduction in total electricity consumption cost and consumption energy by the grid over a one year. Finally, the impact of capacity and charge/discharge rate of BESS on the power cost is analyzed and the optimal size of the BESS for assumed SB in the case study is also reported.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"91 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90971480","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}
Ricardo Faia, T. Pinto, F. Lezama, Z. Vale, J. Corchado, Alfonso González-Briones
The prosumers flexibility procurement has increased due to the current penetration of distributed and variable renewable energy sources. The prosumers flexibility is often able to quickly adjust the power consumption, making it well suited as a primary and secondary reserve for ancillary services. In the era of smart grids, the role of the aggregator has been increasingly exploited and considered as a player that can facilitate small prosumers' participation in electricity markets. This paper proposes an approach based on the use of prosumers flexibility by an aggregator to support ancillary services at a low voltage level. An asymmetric pool market approach is considered for flexibility negotiation between prosumers and the local marker operator (aggregator). From the achieved results it is possible to conclude that the use of flexibility can bring technical and economic benefits for network operators.
{"title":"Prosumers Flexibility as Support for Ancillary Services in Low Voltage Level","authors":"Ricardo Faia, T. Pinto, F. Lezama, Z. Vale, J. Corchado, Alfonso González-Briones","doi":"10.14201/adcaij.27896","DOIUrl":"https://doi.org/10.14201/adcaij.27896","url":null,"abstract":"The prosumers flexibility procurement has increased due to the current penetration of distributed and variable renewable energy sources. The prosumers flexibility is often able to quickly adjust the power consumption, making it well suited as a primary and secondary reserve for ancillary services. In the era of smart grids, the role of the aggregator has been increasingly exploited and considered as a player that can facilitate small prosumers' participation in electricity markets. This paper proposes an approach based on the use of prosumers flexibility by an aggregator to support ancillary services at a low voltage level. An asymmetric pool market approach is considered for flexibility negotiation between prosumers and the local marker operator (aggregator). From the achieved results it is possible to conclude that the use of flexibility can bring technical and economic benefits for network operators.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"28 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83633389","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 k-Nearest Neighbor method is one of the most popular techniques for both classification and regression purposes. Because of its operation, the application of this classification may be limited to problems with a certain number of instances, particularly, when run time is a consideration. However, the classification of large amounts of data has become a fundamental task in many real-world applications. It is logical to scale the k-Nearest Neighbor method to large scale datasets. This paper proposes a new k-Nearest Neighbor classification method (KNN-CCL) which uses a parallel centroid-based and hierarchical clustering algorithm to separate the sample of training dataset into multiple parts. The introduced clustering algorithm uses four stages of successive refinements and generates high quality clusters. The k-Nearest Neighbor approach subsequently makes use of them to predict the test datasets. Finally, sets of experiments are conducted on the UCI datasets. The experimental results confirm that the proposed k-Nearest Neighbor classification method performs well with regard to classification accuracy and performance.
{"title":"Efficient Parallel Processing of k-Nearest Neighbor Queries by Using a Centroid-based and Hierarchical Clustering Algorithm","authors":"Elaheh Gavagsaz","doi":"10.30564/aia.v4i1.4668","DOIUrl":"https://doi.org/10.30564/aia.v4i1.4668","url":null,"abstract":"The k-Nearest Neighbor method is one of the most popular techniques for both classification and regression purposes. Because of its operation, the application of this classification may be limited to problems with a certain number of instances, particularly, when run time is a consideration. However, the classification of large amounts of data has become a fundamental task in many real-world applications. It is logical to scale the k-Nearest Neighbor method to large scale datasets. This paper proposes a new k-Nearest Neighbor classification method (KNN-CCL) which uses a parallel centroid-based and hierarchical clustering algorithm to separate the sample of training dataset into multiple parts. The introduced clustering algorithm uses four stages of successive refinements and generates high quality clusters. The k-Nearest Neighbor approach subsequently makes use of them to predict the test datasets. Finally, sets of experiments are conducted on the UCI datasets. The experimental results confirm that the proposed k-Nearest Neighbor classification method performs well with regard to classification accuracy and performance.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"43 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82546097","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}
Navid Moshtaghi Yazdani, R. Kardehi Moghaddam, Mohammad Hasan Olyaei
Safety is an important aim in designing safe-critical systems. To design such systems, many policy iterative algorithms are introduced to find safe optimal controllers. Due to the fact that in most practical systems, finding accurate information from the system is rather impossible, a new online training method is presented in this paper to perform an iterative reinforcement learning based algorithm using real data instead of identifying system dynamics. Also, in this paper the impact of model uncertainty is examined on control Lyapunov functions (CLF) and control barrier functions (CBF) dynamic limitations. The Sum of Square program is used to iteratively find an optimal safe control solution. The simulation results which are applied on a quarter car model show the efficiency of the proposed method in the fields of optimality and robustness.
{"title":"Safety-critical Policy Iteration Algorithm for Control under Model Uncertainty","authors":"Navid Moshtaghi Yazdani, R. Kardehi Moghaddam, Mohammad Hasan Olyaei","doi":"10.30564/aia.v4i1.4361","DOIUrl":"https://doi.org/10.30564/aia.v4i1.4361","url":null,"abstract":"Safety is an important aim in designing safe-critical systems. To design such systems, many policy iterative algorithms are introduced to find safe optimal controllers. Due to the fact that in most practical systems, finding accurate information from the system is rather impossible, a new online training method is presented in this paper to perform an iterative reinforcement learning based algorithm using real data instead of identifying system dynamics. Also, in this paper the impact of model uncertainty is examined on control Lyapunov functions (CLF) and control barrier functions (CBF) dynamic limitations. The Sum of Square program is used to iteratively find an optimal safe control solution. The simulation results which are applied on a quarter car model show the efficiency of the proposed method in the fields of optimality and robustness.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"64 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76517798","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 world’s elderly population is growing every year. It is easy to say that the fall is one of the major dangers that threaten them. This paper offers a Trained Model for fall detection to help the older people live comfortably and alone at home. The purpose of this paper is to investigate appropriate methods for diagnosing falls by analyzing the motion and shape characteristics of the human body. Several machine learning technologies have been proposed for automatic fall detection. The proposed research reported in this paper detects a moving object by using a background subtraction algorithm with a single camera. The next step is to extract the features that are very important and generally describe the human shape and show the difference between the human falls from the daily activities. These features are based on motion, changes in human shape, and oval diameters around the human and temporal head position. The features extracted from the human mask are eventually fed in to various machine learning classifiers for fall detection. Experimental results showed the efficiency and reliability of the proposed method with a fall detection rate of 81% that have been tested with UR Fall Detection dataset.
{"title":"Elderly Fall Detection by Sensitive Features Based on Image Processing and Machine Learning","authors":"Mohammad Hasan Olyaei, A. Olyaei, Sumaya Hamidi","doi":"10.30564/aia.v4i1.4419","DOIUrl":"https://doi.org/10.30564/aia.v4i1.4419","url":null,"abstract":"The world’s elderly population is growing every year. It is easy to say that the fall is one of the major dangers that threaten them. This paper offers a Trained Model for fall detection to help the older people live comfortably and alone at home. The purpose of this paper is to investigate appropriate methods for diagnosing falls by analyzing the motion and shape characteristics of the human body. Several machine learning technologies have been proposed for automatic fall detection. The proposed research reported in this paper detects a moving object by using a background subtraction algorithm with a single camera. The next step is to extract the features that are very important and generally describe the human shape and show the difference between the human falls from the daily activities. These features are based on motion, changes in human shape, and oval diameters around the human and temporal head position. The features extracted from the human mask are eventually fed in to various machine learning classifiers for fall detection. Experimental results showed the efficiency and reliability of the proposed method with a fall detection rate of 81% that have been tested with UR Fall Detection dataset.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"194 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77764001","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}
Mengyue Zhang, Jinyong Chen, Gang Wang, Min Wang, Kang Sun
Target recognition based on deep learning relies on a large quantity of samples, but in some specific remote sensing scenes, the samples are very rare. Currently, few-shot learning can obtain high-performance target classification models using only a few samples, but most researches are based on the natural scene. Therefore, this paper proposes a metric-based few-shot classification technology in remote sensing. First, we constructed a dataset (RSD-FSC) for few-shot classification in remote sensing, which contained 21 classes typical target sample slices of remote sensing images. Second, based on metric learning, a k-nearest neighbor classification network is proposed, to find multiple training samples similar to the testing target, and then the similarity between the testing target and multiple similar samples is calculated to classify the testing target. Finally, the 5-way 1-shot, 5-way 5-shot and 5-way 10-shot experiments are conducted to improve the generalization of the model on few-shot classification tasks. The experimental results show that for the newly emerged classes few-shot samples, when the number of training samples is 1, 5 and 10, the average accuracy of target recognition can reach 59.134%, 82.553% and 87.796%, respectively. It demonstrates that our proposed method can resolve fewshot classification in remote sensing image and perform better than other few-shot classification methods.
{"title":"Metric-based Few-shot Classification in Remote Sensing Image","authors":"Mengyue Zhang, Jinyong Chen, Gang Wang, Min Wang, Kang Sun","doi":"10.30564/aia.v4i1.4124","DOIUrl":"https://doi.org/10.30564/aia.v4i1.4124","url":null,"abstract":"Target recognition based on deep learning relies on a large quantity of samples, but in some specific remote sensing scenes, the samples are very rare. Currently, few-shot learning can obtain high-performance target classification models using only a few samples, but most researches are based on the natural scene. Therefore, this paper proposes a metric-based few-shot classification technology in remote sensing. First, we constructed a dataset (RSD-FSC) for few-shot classification in remote sensing, which contained 21 classes typical target sample slices of remote sensing images. Second, based on metric learning, a k-nearest neighbor classification network is proposed, to find multiple training samples similar to the testing target, and then the similarity between the testing target and multiple similar samples is calculated to classify the testing target. Finally, the 5-way 1-shot, 5-way 5-shot and 5-way 10-shot experiments are conducted to improve the generalization of the model on few-shot classification tasks. The experimental results show that for the newly emerged classes few-shot samples, when the number of training samples is 1, 5 and 10, the average accuracy of target recognition can reach 59.134%, 82.553% and 87.796%, respectively. It demonstrates that our proposed method can resolve fewshot classification in remote sensing image and perform better than other few-shot classification methods.","PeriodicalId":42597,"journal":{"name":"ADCAIJ-Advances in Distributed Computing and Artificial Intelligence Journal","volume":"166 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2022-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76177358","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：