CNR Author
operator:
and / or
Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2023
Conference article
Restricted
Feature enhancement-based stock prediction strategy to forecast the fiscal market
Padhi D. K., Padhy N., Bhoi A. K.
According to consensus, the stock market can be viewed as a complex nonlinear dynamic system influenced by numerous factors. Traditional stock market research and forecasting techniques do not correctly disclose the fundamental pattern of the stock market. Researchers have lately applied a range of machine learning techniques to estimate future stock market values with greater accuracy and precision. The literature indicates that researchers have not been interested in feature engineering for stock price prediction. Consequently, the purpose of this work is to present a unique technique to feature engineering for predicting stock values using historical data. So far we have used the ITC stock for our practical experiment purposes. More importantly, the addition of feature engineering techniques to identify the potential features may improve the accuracy of the forecasted model. We have developed eight forecasted models for comparison purposes and found a simple machine learning algorithm even works well when we provide appropriate features for training the model.Source: IC3T 2022 - Fourth International Conference on Computer and Communication Technologies, pp. 551–559, Warangal, India, 29-30/07/2022
DOI: 10.1007/978-981-19-8563-8_53
Metrics:
Padhi D. K., Padhy N., Bhoi A. K.
According to consensus, the stock market can be viewed as a complex nonlinear dynamic system influenced by numerous factors. Traditional stock market research and forecasting techniques do not correctly disclose the fundamental pattern of the stock market. Researchers have lately applied a range of machine learning techniques to estimate future stock market values with greater accuracy and precision. The literature indicates that researchers have not been interested in feature engineering for stock price prediction. Consequently, the purpose of this work is to present a unique technique to feature engineering for predicting stock values using historical data. So far we have used the ITC stock for our practical experiment purposes. More importantly, the addition of feature engineering techniques to identify the potential features may improve the accuracy of the forecasted model. We have developed eight forecasted models for comparison purposes and found a simple machine learning algorithm even works well when we provide appropriate features for training the model.Source: IC3T 2022 - Fourth International Conference on Computer and Communication Technologies, pp. 551–559, Warangal, India, 29-30/07/2022
DOI: 10.1007/978-981-19-8563-8_53
Metrics:
See at:
doi.org 
| link.springer.com | CNR ExploRA
2022
Journal article
Open Access
Intrusion detection in cyber-physical environment using hybrid naïve Bayes-decision table and multi-objective evolutionary feature selection
Panigrahi R., Borah S., Pramanik M., Bhoi A. K., Barsocchi P., Nayak S. R., Alnumay W.
Researchers are motivated to build effective Intrusion Detection Systems because of the implications of malicious actions in computing, communication, and cyber-physical systems (IDSs). In order to develop signature-based intrusion detection techniques that are suitable for use in cyber-physical environments, state-of-the-art supervised learning algorithms are devised. The main contribution of this research is the introduction of a signature-based intrusion detection model that is based on a hybrid Decision Table and Naive Bayes technique. In addition, the contribution of the suggested method is evaluated by comparing it to the existing literature in the field. In the preprocessing stage, Multi-Objective Evolutionary Feature Selection (MOEFS) feature selection has been used to select only five attack features from the recent CICIDS017 dataset. Keeping in view the class imbalance nature of CICIDS2017 dataset, adequate attack samples has been selected with more weightage to the attack classes having a smaller number of instances in the dataset. A hybrid of Decision Table and Naive Bayes models were combined to train and detect intrusions. Detection of botnets, port scans, Denial of Service (DoS)/Distributed Denial of Service (DDoS) attacks, such as Golden-Eye, Hulk, Slow httptest, slowloris, Heartbleed, Brute Force attacks, such as Patator (FTP), Patator (SSH), and Web attacks such as Infiltration, Web Brute Force, SQL Injection, and XSS, are all successfully detected by the proposed hybrid detection model. The proposed approach shows an accuracy of 96.8% using five features of CICIDS2017, which is higher than the accuracy of methods discussed in the literatures.Source: Computer communications 188 (2022): 133–144. doi:10.1016/j.comcom.2022.03.009
DOI: 10.1016/j.comcom.2022.03.009
Metrics:
Panigrahi R., Borah S., Pramanik M., Bhoi A. K., Barsocchi P., Nayak S. R., Alnumay W.
Researchers are motivated to build effective Intrusion Detection Systems because of the implications of malicious actions in computing, communication, and cyber-physical systems (IDSs). In order to develop signature-based intrusion detection techniques that are suitable for use in cyber-physical environments, state-of-the-art supervised learning algorithms are devised. The main contribution of this research is the introduction of a signature-based intrusion detection model that is based on a hybrid Decision Table and Naive Bayes technique. In addition, the contribution of the suggested method is evaluated by comparing it to the existing literature in the field. In the preprocessing stage, Multi-Objective Evolutionary Feature Selection (MOEFS) feature selection has been used to select only five attack features from the recent CICIDS017 dataset. Keeping in view the class imbalance nature of CICIDS2017 dataset, adequate attack samples has been selected with more weightage to the attack classes having a smaller number of instances in the dataset. A hybrid of Decision Table and Naive Bayes models were combined to train and detect intrusions. Detection of botnets, port scans, Denial of Service (DoS)/Distributed Denial of Service (DDoS) attacks, such as Golden-Eye, Hulk, Slow httptest, slowloris, Heartbleed, Brute Force attacks, such as Patator (FTP), Patator (SSH), and Web attacks such as Infiltration, Web Brute Force, SQL Injection, and XSS, are all successfully detected by the proposed hybrid detection model. The proposed approach shows an accuracy of 96.8% using five features of CICIDS2017, which is higher than the accuracy of methods discussed in the literatures.Source: Computer communications 188 (2022): 133–144. doi:10.1016/j.comcom.2022.03.009
DOI: 10.1016/j.comcom.2022.03.009
Metrics:
See at:
ISTI Repository 
| www.sciencedirect.com | CNR ExploRA
2022
Journal article
Open Access
The ForEx++ based decision tree ensemble approach for robust detection of Parkinson's disease
Pramanik M., Pradhan R., Nandy P., Bhoi A. K., Barsocchi P.
The progressive reduction of dopaminergic neurons in the human brain, especially at the substantia nigra is one of the principal causes of Parkinson's Disease (PD). Voice alteration is one of the earliest symptoms found in PD patients. Therefore, the impaired PD subjects' acoustic voice signal plays a crucial role in detecting the presence of Parkinson's. This manuscript presents four distinct decision tree ensemble methods of PD detection on a trailblazing ForEx++ rule-based framework. The Systematically Developed Forest (SysFor) and a Penalizing Attributes Decision Forest (ForestPA) ensemble approaches has been used for PD detection. The proposed detection schemes efficiently identify positive subjects using primary voice signal features, viz., baseline, vocal fold, and time-frequency. A novel feature selection scheme termed Feature Ranking to Feature Selection (FRFS) has also been proposed to combine filter and wrapper strategies. The proposed FRFS scheme encompasses Gel's normality test to rank and selects outstanding features from baseline, time-frequency, and vocal fold feature groups. The SysFor and ForestPA decision forests underneath the ForEx++ rule-based framework on both FRFS feature ranking and subset selection represents Parkinson's detection approaches, which expedite a better overall impact on segregating PD from control subjects. It has been observed that the ForestPA decision forest in the ForEx++ framework on FRFS ranked features proved to be a robust Parkinson's detection scheme. The proposed models deliver the highest accuracy of 94.12% and a lowest mean absolute error of 0.25, resulting in an Area Under Curve (AUC) value of 0.97.Source: Journal of ambient intelligence & humanized computing (Print) (2022). doi:10.1007/s12652-022-03719-x
DOI: 10.1007/s12652-022-03719-x
Metrics:
Pramanik M., Pradhan R., Nandy P., Bhoi A. K., Barsocchi P.
The progressive reduction of dopaminergic neurons in the human brain, especially at the substantia nigra is one of the principal causes of Parkinson's Disease (PD). Voice alteration is one of the earliest symptoms found in PD patients. Therefore, the impaired PD subjects' acoustic voice signal plays a crucial role in detecting the presence of Parkinson's. This manuscript presents four distinct decision tree ensemble methods of PD detection on a trailblazing ForEx++ rule-based framework. The Systematically Developed Forest (SysFor) and a Penalizing Attributes Decision Forest (ForestPA) ensemble approaches has been used for PD detection. The proposed detection schemes efficiently identify positive subjects using primary voice signal features, viz., baseline, vocal fold, and time-frequency. A novel feature selection scheme termed Feature Ranking to Feature Selection (FRFS) has also been proposed to combine filter and wrapper strategies. The proposed FRFS scheme encompasses Gel's normality test to rank and selects outstanding features from baseline, time-frequency, and vocal fold feature groups. The SysFor and ForestPA decision forests underneath the ForEx++ rule-based framework on both FRFS feature ranking and subset selection represents Parkinson's detection approaches, which expedite a better overall impact on segregating PD from control subjects. It has been observed that the ForestPA decision forest in the ForEx++ framework on FRFS ranked features proved to be a robust Parkinson's detection scheme. The proposed models deliver the highest accuracy of 94.12% and a lowest mean absolute error of 0.25, resulting in an Area Under Curve (AUC) value of 0.97.Source: Journal of ambient intelligence & humanized computing (Print) (2022). doi:10.1007/s12652-022-03719-x
DOI: 10.1007/s12652-022-03719-x
Metrics:
See at:
link.springer.com | ISTI Repository | CNR ExploRA
2022
Contribution to book
Open Access
Cognitive Internet of Things (IoT) and computational intelligence for mental well-being
Thapa S., Ghimire A., Adhikari S., Bhoi A. K., Barsocchi P.
In the current world of competition and constant struggle, taking care of mental well-being is of the upmost importance. With hundreds of millions of people suffering from mental disorders like depression, Alzheimer disease, schizophrenia, etc. each year, intelligent systems are needed that can diagnose, track, and manage the mental well-being of individuals. Computers have been widely used in various clinical applications such as clinical text analysis and medical image analysis. Computers have found uses in various medical domains such as cancer diagnosis, tumor analysis, etc. Computational intelligence has been used in building smart predictive models that can be of huge significance for diseases that require early clinical intervention. Depression, Alzheimer disease, etc. are mental disorders that worsen with time when not treated appropriately. Thus, there should be systems to identify mental disorders at an early stage. In this chapter, various methods in which mental well-being can be taken care of using computational intelligence are discussed.Source: Cognitive and Soft Computing Techniques for the Analysis of Healthcare Data, edited by Bhoi A.K., de Albuquerque V.H.C., Srinivasu P.N., Marques G., pp. 59–77, 2022
DOI: 10.1016/b978-0-323-85751-2.00004-9
Metrics:
Thapa S., Ghimire A., Adhikari S., Bhoi A. K., Barsocchi P.
In the current world of competition and constant struggle, taking care of mental well-being is of the upmost importance. With hundreds of millions of people suffering from mental disorders like depression, Alzheimer disease, schizophrenia, etc. each year, intelligent systems are needed that can diagnose, track, and manage the mental well-being of individuals. Computers have been widely used in various clinical applications such as clinical text analysis and medical image analysis. Computers have found uses in various medical domains such as cancer diagnosis, tumor analysis, etc. Computational intelligence has been used in building smart predictive models that can be of huge significance for diseases that require early clinical intervention. Depression, Alzheimer disease, etc. are mental disorders that worsen with time when not treated appropriately. Thus, there should be systems to identify mental disorders at an early stage. In this chapter, various methods in which mental well-being can be taken care of using computational intelligence are discussed.Source: Cognitive and Soft Computing Techniques for the Analysis of Healthcare Data, edited by Bhoi A.K., de Albuquerque V.H.C., Srinivasu P.N., Marques G., pp. 59–77, 2022
DOI: 10.1016/b978-0-323-85751-2.00004-9
Metrics:
See at:
ISTI Repository | www.sciencedirect.com | CNR ExploRA
2022
Contribution to book
Open Access
Effects of EEG-sleep irregularities and its behavioral aspects: review and analysis
Satapathy S., Loganathan D., Bhoi A. K., Barsocchi P.
Sleep is one of the most important areas for humans for maintaining daily activities with full concentration and attention. Maintaining the proper sleep patterns is strongly related to physical, mental, cognitive, and physiological well-being. On the other hand, poor sleep patterns may lead to several diseases, affecting both physiological and cognitive functions, which causes worsened general health conditions. For that reason, it is important to understand subjects' sleep behavior and analyzing changes in sleep characteristics has become one a research area, where the different major reasons and causes, which are directly or indirectly responsible for sleep deprivation, need to be identified. All these reasons increase the demands for a brief comparative analysis of the sleep monitoring system. This chapter mainly focuses on the different methods and procedures for analyzing sleep behavior changes in the different stages of sleep. The authors also briefly focus on how the age and gender of subjects may affect their sleep quality. The chapter also offers a systematic review of how artificial intelligence techniques make sleep stage classifications easier. Another important aspect of this chapter is a brief analysis of the different biosignals and their clinical characteristics to measure sleep irregularities.Source: Cognitive and Soft Computing Techniques for the Analysis of Healthcare Data, edited by Bhoi A.K., de Albuquerque V.H.C., Srinivasu P.N., Marques G., pp. 239–267, 2022
DOI: 10.1016/b978-0-323-85751-2.00009-8
Metrics:
Satapathy S., Loganathan D., Bhoi A. K., Barsocchi P.
Sleep is one of the most important areas for humans for maintaining daily activities with full concentration and attention. Maintaining the proper sleep patterns is strongly related to physical, mental, cognitive, and physiological well-being. On the other hand, poor sleep patterns may lead to several diseases, affecting both physiological and cognitive functions, which causes worsened general health conditions. For that reason, it is important to understand subjects' sleep behavior and analyzing changes in sleep characteristics has become one a research area, where the different major reasons and causes, which are directly or indirectly responsible for sleep deprivation, need to be identified. All these reasons increase the demands for a brief comparative analysis of the sleep monitoring system. This chapter mainly focuses on the different methods and procedures for analyzing sleep behavior changes in the different stages of sleep. The authors also briefly focus on how the age and gender of subjects may affect their sleep quality. The chapter also offers a systematic review of how artificial intelligence techniques make sleep stage classifications easier. Another important aspect of this chapter is a brief analysis of the different biosignals and their clinical characteristics to measure sleep irregularities.Source: Cognitive and Soft Computing Techniques for the Analysis of Healthcare Data, edited by Bhoi A.K., de Albuquerque V.H.C., Srinivasu P.N., Marques G., pp. 239–267, 2022
DOI: 10.1016/b978-0-323-85751-2.00009-8
Metrics:
See at:
ISTI Repository | www.sciencedirect.com | CNR ExploRA
2022
Journal article
Open Access
Modified U-NET architecture for segmentation of skin lesion
Anand V., Gupta S., Koundal D., Nayak S. R., Barsocchi P., Bhoi A. K.
Dermoscopy images can be classified more accurately if skin lesions or nodules are segmented. Because of their fuzzy borders, irregular boundaries, inter-and intra-class variances, and so on, nodule segmentation is a difficult task. For the segmentation of skin lesions from dermoscopic pictures, several algorithms have been developed. However, their accuracy lags well behind the industry standard. In this paper, a modified U-Net architecture is proposed by modifying the feature map's dimension for an accurate and automatic segmentation of dermoscopic images. Apart from this, more kernels to the feature map allowed for a more precise extraction of the nodule. We evaluated the effectiveness of the proposed model by considering several hyper parameters such as epochs, batch size, and the types of optimizers, testing it with augmentation techniques implemented to enhance the amount of photos available in the PH2 dataset. The best performance achieved by the proposed model is with an Adam optimizer using a batch size of 8 and 75 epochs.Source: Sensors (Basel) 22 (2022). doi:10.3390/s22030867
DOI: 10.3390/s22030867
Metrics:
Anand V., Gupta S., Koundal D., Nayak S. R., Barsocchi P., Bhoi A. K.
Dermoscopy images can be classified more accurately if skin lesions or nodules are segmented. Because of their fuzzy borders, irregular boundaries, inter-and intra-class variances, and so on, nodule segmentation is a difficult task. For the segmentation of skin lesions from dermoscopic pictures, several algorithms have been developed. However, their accuracy lags well behind the industry standard. In this paper, a modified U-Net architecture is proposed by modifying the feature map's dimension for an accurate and automatic segmentation of dermoscopic images. Apart from this, more kernels to the feature map allowed for a more precise extraction of the nodule. We evaluated the effectiveness of the proposed model by considering several hyper parameters such as epochs, batch size, and the types of optimizers, testing it with augmentation techniques implemented to enhance the amount of photos available in the PH2 dataset. The best performance achieved by the proposed model is with an Adam optimizer using a batch size of 8 and 75 epochs.Source: Sensors (Basel) 22 (2022). doi:10.3390/s22030867
DOI: 10.3390/s22030867
Metrics:
See at:
ISTI Repository | www.mdpi.com | CNR ExploRA
2022
Journal article
Open Access
Crop diversification in South Asia: a panel regression approach
Singh P., Adhale P., Guleria A., Bhoi P. B., Bhoi A. K., Bacco M., Barsocchi P.
South Asia's agricultural sector has experienced vigorous growth and structural transformation over the last few decades, albeit differently across the region. This study examines the crop diversification status and various determinants such as socioeconomic (per capita gross domestic product, population, arable land, and cropland), soil/agronomic (root zone moisture), agricultural inputs (fertilizer and pesticide consumption), the productivity of food and non-food crops, international trade, and climate (maximum and minimum temperature and rainfall) factors. The share of cereals has decreased in most countries, but they continue to dominate South Asian agriculture. The area under high-value crops in India has increased significantly, replaced the area under cereal cultivation during the study period. Similar results were seen in the Maldives, where vegetables replaced oilseeds. The Hausman model test suggested a random-effects model for the analysis of the determinants. All the determinants considered in the study explain 69 percent of the variation in the crop diversification index. The crop diversification in south Asia was influenced by per capita GDP, minimum temperature, pesticide consumption, food crop yield index, and non-food crop yield index during the study period. Cropland percentage and population, on the other hand, reduce the crop diversification. The price factor contributed more than half to agricultural growth. It remained the primary source of growth in all South Asian countries, followed by yield, which is identified as the second most crucial factor. The contribution of crop diversification to agricultural growth has been declining over time.Source: Sustainability (Basel) 14 (2022). doi:10.3390/su14159363
DOI: 10.3390/su14159363
Metrics:
Singh P., Adhale P., Guleria A., Bhoi P. B., Bhoi A. K., Bacco M., Barsocchi P.
South Asia's agricultural sector has experienced vigorous growth and structural transformation over the last few decades, albeit differently across the region. This study examines the crop diversification status and various determinants such as socioeconomic (per capita gross domestic product, population, arable land, and cropland), soil/agronomic (root zone moisture), agricultural inputs (fertilizer and pesticide consumption), the productivity of food and non-food crops, international trade, and climate (maximum and minimum temperature and rainfall) factors. The share of cereals has decreased in most countries, but they continue to dominate South Asian agriculture. The area under high-value crops in India has increased significantly, replaced the area under cereal cultivation during the study period. Similar results were seen in the Maldives, where vegetables replaced oilseeds. The Hausman model test suggested a random-effects model for the analysis of the determinants. All the determinants considered in the study explain 69 percent of the variation in the crop diversification index. The crop diversification in south Asia was influenced by per capita GDP, minimum temperature, pesticide consumption, food crop yield index, and non-food crop yield index during the study period. Cropland percentage and population, on the other hand, reduce the crop diversification. The price factor contributed more than half to agricultural growth. It remained the primary source of growth in all South Asian countries, followed by yield, which is identified as the second most crucial factor. The contribution of crop diversification to agricultural growth has been declining over time.Source: Sustainability (Basel) 14 (2022). doi:10.3390/su14159363
DOI: 10.3390/su14159363
Metrics:
See at:
ISTI Repository | ISTI Repository | www.mdpi.com | CNR ExploRA
2021
Journal article
Open Access
Input use efficiency management for Paddy Production Systems in India: a machine learning approach
Bhoi P. B., Wali V. S., Swain D. K., Sharma K., Bhoi A. K., Bacco M., Barsocchi P.
This research illustrates the technical efficiency of the pan-India paddy cultivation status obtained through a stochastic frontier approach. The results suggest that the mean technical efficiency varies from 0.64 in Gujarat to 0.95 in Odisha. Inputs like human labor, mechanical labor, fertilizer, irrigation and insecticide were found to determine the yield in paddy cultivation across India (except for Chhattisgarh). Inefficiency in the paddy production in Punjab, Bihar, West Bengal, Andhra Pradesh, Tamil Nadu, Kerala, Assam, Gujarat and Odisha in 2016-2017 was caused by technical inefficiency due to poor input management, as suggested by the significant ?2U and ?2v values of the stochastic frontier model. In addition, most of the farm groups in the study operated in the high-efficiency group (80-90% technical efficiency). No specific pattern of input use can be visualized through descriptive measures to give any specific policy implication. Thus, machine learning algorithms based on the input parameters were tested on the data in order to predict the farmers' efficiency class for individual states. The highest mean accuracy of 0.80 for the models of all of the states was achieved in random forest models. Among the various states of India, the best random forest prediction model based on accuracy was fitted to the input data of Bihar (0.91), followed by Uttar Pradesh (0.89), Andhra Pradesh (0.88), Assam (0.88) and West Bengal (0.86). Thus, the study provides a technique for the classification and prediction of a farmer's efficiency group from the levels of input use in paddy cultivation for each state in the study. The study uses the DES input dataset to classify and predict the efficiency group of the farmer, as other machine learning models in agriculture have used mostly satellite, spectral imaging and soil property data to detect disease, weeds and crops.Source: Agriculture (Basel) 11 (2021). doi:10.3390/agriculture11090837
DOI: 10.3390/agriculture11090837
Metrics:
Bhoi P. B., Wali V. S., Swain D. K., Sharma K., Bhoi A. K., Bacco M., Barsocchi P.
This research illustrates the technical efficiency of the pan-India paddy cultivation status obtained through a stochastic frontier approach. The results suggest that the mean technical efficiency varies from 0.64 in Gujarat to 0.95 in Odisha. Inputs like human labor, mechanical labor, fertilizer, irrigation and insecticide were found to determine the yield in paddy cultivation across India (except for Chhattisgarh). Inefficiency in the paddy production in Punjab, Bihar, West Bengal, Andhra Pradesh, Tamil Nadu, Kerala, Assam, Gujarat and Odisha in 2016-2017 was caused by technical inefficiency due to poor input management, as suggested by the significant ?2U and ?2v values of the stochastic frontier model. In addition, most of the farm groups in the study operated in the high-efficiency group (80-90% technical efficiency). No specific pattern of input use can be visualized through descriptive measures to give any specific policy implication. Thus, machine learning algorithms based on the input parameters were tested on the data in order to predict the farmers' efficiency class for individual states. The highest mean accuracy of 0.80 for the models of all of the states was achieved in random forest models. Among the various states of India, the best random forest prediction model based on accuracy was fitted to the input data of Bihar (0.91), followed by Uttar Pradesh (0.89), Andhra Pradesh (0.88), Assam (0.88) and West Bengal (0.86). Thus, the study provides a technique for the classification and prediction of a farmer's efficiency group from the levels of input use in paddy cultivation for each state in the study. The study uses the DES input dataset to classify and predict the efficiency group of the farmer, as other machine learning models in agriculture have used mostly satellite, spectral imaging and soil property data to detect disease, weeds and crops.Source: Agriculture (Basel) 11 (2021). doi:10.3390/agriculture11090837
DOI: 10.3390/agriculture11090837
Metrics:
See at:
ISTI Repository | www.mdpi.com | CNR ExploRA
2021
Journal article
Open Access
Amalgamation of customer relationship management and data analytics in different business sectors - a systematic literature review
Saha L., Tripathy H. K., Nayak S. R., Bhoi A. K., Barsocchi P.
Customization of products or services is a strategy that the business sector has embraced to build a better relationship with the customers to cater to their individual needs and thus providing them a fulfilling experience. This whole process is known as customer relationship management (CRM). In this context, we extensively surveyed 138 papers published between 1996 and 2021 in the area of analytical CRM. Although this study consisted of papers from different business sectors, a fair share of focus was directed to the telecommunication industry and generalized CRM techniques usages. Different science and engineering-based data repositories were studied to ascertain significant studies published in scientific journals, conferences, and articles. The research works on CRM were considered and separated into IT and non-IT-based techniques to study the methods used in different business sectors. The main target behind implementing CRM is for the better revenue growth of the company. Different IT and non-IT-based techniques are used in the analytical CRM area to achieve this target, and researchers have been actively involved in this domain. The purpose of the research was to show the impact of IT-based techniques in the business world. A detailed future course of research in this area was discussed.Source: Sustainability (Basel) 13 (2021). doi:10.3390/su13095279
DOI: 10.3390/su13095279
Metrics:
Saha L., Tripathy H. K., Nayak S. R., Bhoi A. K., Barsocchi P.
Customization of products or services is a strategy that the business sector has embraced to build a better relationship with the customers to cater to their individual needs and thus providing them a fulfilling experience. This whole process is known as customer relationship management (CRM). In this context, we extensively surveyed 138 papers published between 1996 and 2021 in the area of analytical CRM. Although this study consisted of papers from different business sectors, a fair share of focus was directed to the telecommunication industry and generalized CRM techniques usages. Different science and engineering-based data repositories were studied to ascertain significant studies published in scientific journals, conferences, and articles. The research works on CRM were considered and separated into IT and non-IT-based techniques to study the methods used in different business sectors. The main target behind implementing CRM is for the better revenue growth of the company. Different IT and non-IT-based techniques are used in the analytical CRM area to achieve this target, and researchers have been actively involved in this domain. The purpose of the research was to show the impact of IT-based techniques in the business world. A detailed future course of research in this area was discussed.Source: Sustainability (Basel) 13 (2021). doi:10.3390/su13095279
DOI: 10.3390/su13095279
Metrics:
See at:
Sustainability | ISTI Repository | Sustainability | Sustainability | CNR ExploRA
2021
Contribution to book
Open Access
Impact of Artificial Intelligence in health care: a study
Bairagya D., Tripathy H. K., Bhoi A. K., Barsocchi P.
The acceptance of AI in health care relates to the analysis of the huge amount of information that is generated each day and the limitation of physicians to address these needs. The growth of data complexity in the medical domain refers to the increasing usage of artificial intelligence in that sector. Some vital functionaries include care providers, diagnostic recommendation systems, and adherence of patients among others. Likewise, there exist several applications where AI can be successfully deployed in clinical applications. In this study, the role of AI in this critical healthcare sector is highlighted. Some popular existing research works in the healthcare domain are discussed. Software projects involving AI in this sector are summarized. Finally, a real-time implementation of medical imaging using different computational methods is demonstrated. Maximum accuracy of 94.2% was noted for prostate cancer. It is also found that it takes maximum time for the analysis of lung cancer (2.43 s) and minimum for brain cancer (1.12 s).Source: Hybrid Artificial Intelligence and IoT in Healthcare, edited by Bhoi A.K., Mallick P.K., Mohanty M.N., de Albuquerque V.H.C., pp. 311–328, 2021
DOI: 10.1007/978-981-16-2972-3_15
Metrics:
Bairagya D., Tripathy H. K., Bhoi A. K., Barsocchi P.
The acceptance of AI in health care relates to the analysis of the huge amount of information that is generated each day and the limitation of physicians to address these needs. The growth of data complexity in the medical domain refers to the increasing usage of artificial intelligence in that sector. Some vital functionaries include care providers, diagnostic recommendation systems, and adherence of patients among others. Likewise, there exist several applications where AI can be successfully deployed in clinical applications. In this study, the role of AI in this critical healthcare sector is highlighted. Some popular existing research works in the healthcare domain are discussed. Software projects involving AI in this sector are summarized. Finally, a real-time implementation of medical imaging using different computational methods is demonstrated. Maximum accuracy of 94.2% was noted for prostate cancer. It is also found that it takes maximum time for the analysis of lung cancer (2.43 s) and minimum for brain cancer (1.12 s).Source: Hybrid Artificial Intelligence and IoT in Healthcare, edited by Bhoi A.K., Mallick P.K., Mohanty M.N., de Albuquerque V.H.C., pp. 311–328, 2021
DOI: 10.1007/978-981-16-2972-3_15
Metrics:
See at:
ISTI Repository | doi.org | link.springer.com | CNR ExploRA
2021
Contribution to book
Open Access
Hybrid cloud/fog environment for healthcare: an exploratory study, opportunities, challenges, and future prospects
Awotunde J. B., Bhoi A. K., Barsocchi P.
The healthcare system has been on the frontline in recent years, and new technologies have greatly benefited healthcare. Researchers have tried to find solutions to different problems associated with the healthcare system by applied various modern technologies approaches. Among the various technologies, are fog and computing used in smart healthcare systems. These applications with the Internet of things (IoT) recently have help in dispersed patient data globally and have advanced healthcare systems. Hence, various applications and solutions using cloud computing have been proposed by researchers to manage healthcare statistics. However, the issues of latency, context-awareness, and a huge volume of data are remaining challenges in cloud computing. Hence, the possibility of transmission errors and the probability of delay in data processing remain a problem as healthcare datasets become more complex and larger. The most alternative solution to those challenges is fog computing in reducing data management complexity in the healthcare system, thus increasing reliability. But, before using fog computing, it is very essential to look into its associated challenges in other to manage healthcare data effectively. Therefore, this chapter discusses the areas of applicability in healthcare systems of hybrid cloud/fog computing. The several extraordinary opportunities brought by the technologies in the healthcare system with research challenges in deployment are discussed. The applications of fog in IoT-based devices bring healthcare components in a distant cloud operating nearer to data sources and the end-users, thus, resulting in context-awareness and lower latency.Source: Hybrid Artificial Intelligence and IoT in Healthcare, edited by Bhoi A.K., Mallick P.K., Mohanty M.N., de Albuquerque V.H.C., pp. 1–20, 2021
DOI: 10.1007/978-981-16-2972-3_1
Metrics:
Awotunde J. B., Bhoi A. K., Barsocchi P.
The healthcare system has been on the frontline in recent years, and new technologies have greatly benefited healthcare. Researchers have tried to find solutions to different problems associated with the healthcare system by applied various modern technologies approaches. Among the various technologies, are fog and computing used in smart healthcare systems. These applications with the Internet of things (IoT) recently have help in dispersed patient data globally and have advanced healthcare systems. Hence, various applications and solutions using cloud computing have been proposed by researchers to manage healthcare statistics. However, the issues of latency, context-awareness, and a huge volume of data are remaining challenges in cloud computing. Hence, the possibility of transmission errors and the probability of delay in data processing remain a problem as healthcare datasets become more complex and larger. The most alternative solution to those challenges is fog computing in reducing data management complexity in the healthcare system, thus increasing reliability. But, before using fog computing, it is very essential to look into its associated challenges in other to manage healthcare data effectively. Therefore, this chapter discusses the areas of applicability in healthcare systems of hybrid cloud/fog computing. The several extraordinary opportunities brought by the technologies in the healthcare system with research challenges in deployment are discussed. The applications of fog in IoT-based devices bring healthcare components in a distant cloud operating nearer to data sources and the end-users, thus, resulting in context-awareness and lower latency.Source: Hybrid Artificial Intelligence and IoT in Healthcare, edited by Bhoi A.K., Mallick P.K., Mohanty M.N., de Albuquerque V.H.C., pp. 1–20, 2021
DOI: 10.1007/978-981-16-2972-3_1
Metrics:
See at:
ISTI Repository | doi.org | link.springer.com | CNR ExploRA
2021
Journal article
Open Access
Machine learning with ensemble stacking model for automated sleep staging using dual-channel EEG signal
Satapathy S. K., Bhoi A. K., Loganathan D., Khandelwal B., Barsocchi P.
Sleep staging is an important part of diagnosing the different types of sleep-related disorders because any discrepancies in the sleep scoring process may cause serious health problems such as misinterpretations of sleep patterns, medication errors, and improper diagnosis. The best way of analyzing sleep staging is visual interpretations of the polysomnography (PSG) signals recordings from the patients, which is a quite tedious task, requires more domain experts, and time-consuming process. This proposed study aims to develop a new automated sleep staging system using the brain EEG signals. Based on a new automated sleep staging system based on an ensemble learning stacking model that integrates Random Forest (RF) and eXtreme Gradient Boosting (XGBoosting). Additionally, this proposed methodology considers the subjects' age, which helps analyze the S1 sleep stage properly. In this study, both linear (time and frequency) and non-linear features are extracted from the pre-processed signals. The most relevant features are selected using the ReliefF weight algorithm. Finally, the selected features are classified through the proposed two-layer stacking model. The proposed methodology performance is evaluated using the two most popular datasets, such as the Sleep-EDF dataset (S-EDF) and Sleep Expanded-EDF database (SE-EDF) under the Rechtschaffen & Kales (R&K) sleep scoring rules. The performance of the proposed method is also compared with the existing published sleep staging methods. The comparison results signify that the proposed sleep staging system has an excellent improvement in classification accuracy for the six-two sleep states classification. In the S-EDF dataset, the overall accuracy and Cohen's kappa coefficient score obtained by the proposed model is (91.10%, 0.87) and (90.68%, 0.86) with inclusion and exclusion of age feature using the Fpz-Cz channel, respectively. Similarly, the Pz-Oz channel's performance is (90.56%, 0.86) with age feature and (90.11%, 0.86) without age feature. The performed results with the SE-EDF dataset using Fpz-Cz channel is (81.32%, 0.77) and (81.06%, 0.76), using Pz-Oz channel with the inclusion and exclusion of the age feature, respectively. Similarly the model achieved an overall accuracy of 96.67% (CT-6), 96.60% (CT-5), 96.28% (CT-4),96.30% (CT-3) and 97.30% (CT-2) for with 16 selected features using S-EDF database. Similarly the model reported an overall accuracy of 85.85%, 84.98%, 85.51%, 85.37% and 87.40% for CT-6 to CT-2 with 18 selected features using SE-EDF database.Source: Biomedical signal processing and control (Print) 69 (2021). doi:10.1016/j.bspc.2021.102898
DOI: 10.1016/j.bspc.2021.102898
Metrics:
Satapathy S. K., Bhoi A. K., Loganathan D., Khandelwal B., Barsocchi P.
Sleep staging is an important part of diagnosing the different types of sleep-related disorders because any discrepancies in the sleep scoring process may cause serious health problems such as misinterpretations of sleep patterns, medication errors, and improper diagnosis. The best way of analyzing sleep staging is visual interpretations of the polysomnography (PSG) signals recordings from the patients, which is a quite tedious task, requires more domain experts, and time-consuming process. This proposed study aims to develop a new automated sleep staging system using the brain EEG signals. Based on a new automated sleep staging system based on an ensemble learning stacking model that integrates Random Forest (RF) and eXtreme Gradient Boosting (XGBoosting). Additionally, this proposed methodology considers the subjects' age, which helps analyze the S1 sleep stage properly. In this study, both linear (time and frequency) and non-linear features are extracted from the pre-processed signals. The most relevant features are selected using the ReliefF weight algorithm. Finally, the selected features are classified through the proposed two-layer stacking model. The proposed methodology performance is evaluated using the two most popular datasets, such as the Sleep-EDF dataset (S-EDF) and Sleep Expanded-EDF database (SE-EDF) under the Rechtschaffen & Kales (R&K) sleep scoring rules. The performance of the proposed method is also compared with the existing published sleep staging methods. The comparison results signify that the proposed sleep staging system has an excellent improvement in classification accuracy for the six-two sleep states classification. In the S-EDF dataset, the overall accuracy and Cohen's kappa coefficient score obtained by the proposed model is (91.10%, 0.87) and (90.68%, 0.86) with inclusion and exclusion of age feature using the Fpz-Cz channel, respectively. Similarly, the Pz-Oz channel's performance is (90.56%, 0.86) with age feature and (90.11%, 0.86) without age feature. The performed results with the SE-EDF dataset using Fpz-Cz channel is (81.32%, 0.77) and (81.06%, 0.76), using Pz-Oz channel with the inclusion and exclusion of the age feature, respectively. Similarly the model achieved an overall accuracy of 96.67% (CT-6), 96.60% (CT-5), 96.28% (CT-4),96.30% (CT-3) and 97.30% (CT-2) for with 16 selected features using S-EDF database. Similarly the model reported an overall accuracy of 85.85%, 84.98%, 85.51%, 85.37% and 87.40% for CT-6 to CT-2 with 18 selected features using SE-EDF database.Source: Biomedical signal processing and control (Print) 69 (2021). doi:10.1016/j.bspc.2021.102898
DOI: 10.1016/j.bspc.2021.102898
Metrics:
See at:
Biomedical Signal Processing and Control | ISTI Repository | www.sciencedirect.com | CNR ExploRA
2021
Journal article
Open Access
A pragmatic investigation of energy consumption and utilization models in the urban sector using predictive intelligence approaches
Mohapatra S. K., Mishra S., Tripathy H. K., Bhoi A. K., Barsocchi P.
Energy consumption is a crucial domain in energy system management. Recently, it was observed that there has been a rapid rise in the consumption of energy throughout the world. Thus, almost every nation devises its strategies and models to limit energy usage in various areas, ranging from large buildings to industrial firms and vehicles. With technological advancements, computational intelligence models have been successfully contributing to the prediction of the consumption of energy. Machine learning and deep learning-based models enhance the precision and robustness compared to traditional approaches, making it more reliable. This article performs a review analysis of the various computational intelligence approaches currently being utilized to predict energy consumption. An extensive survey procedure is conducted and presented in this study, and relevant works are discussed. Different criteria are considered during the aggregation of the relevant studies relating to the work. The author's perspective, future trends and various novel approaches are also presented as a part of the discussion. This article thereby lays a foundation stone for further research works to be undertaken for energy prediction.Source: Energies (Basel) 14 (2021). doi:10.3390/en14133900
DOI: 10.3390/en14133900
Metrics:
Mohapatra S. K., Mishra S., Tripathy H. K., Bhoi A. K., Barsocchi P.
Energy consumption is a crucial domain in energy system management. Recently, it was observed that there has been a rapid rise in the consumption of energy throughout the world. Thus, almost every nation devises its strategies and models to limit energy usage in various areas, ranging from large buildings to industrial firms and vehicles. With technological advancements, computational intelligence models have been successfully contributing to the prediction of the consumption of energy. Machine learning and deep learning-based models enhance the precision and robustness compared to traditional approaches, making it more reliable. This article performs a review analysis of the various computational intelligence approaches currently being utilized to predict energy consumption. An extensive survey procedure is conducted and presented in this study, and relevant works are discussed. Different criteria are considered during the aggregation of the relevant studies relating to the work. The author's perspective, future trends and various novel approaches are also presented as a part of the discussion. This article thereby lays a foundation stone for further research works to be undertaken for energy prediction.Source: Energies (Basel) 14 (2021). doi:10.3390/en14133900
DOI: 10.3390/en14133900
Metrics:
See at:
Energies | ISTI Repository | Energies | Energies | CNR ExploRA