Mukesh Kondala, S. Nudurupati, Eko Riwayadi, Abhijeet Chavan, Shaik Rajah Asif, N. Gupta
The Circular Economy (CE) is getting its attention these days, which has a massive impact on the industries, particularly in the manufacturing segment. The countries worldwide started believing in CE, and its practices got the benefits after thoroughly implementing it to their current practices. The concept is not new, but it came up with a new ideology and new techniques already proven by countries like China and the UK. Different industries show their innovativeness by adapting to the change for the future. We found that the Ice Cream Industry is one of them that adopt change quickly. The paper discusses the introduction of the CE, the current trends, the comparison of the olden style with new style after implementing CE practices, the challenges and barriers in implementing, and the benefits of implementing CE Practices in Visakhapatnam’s dairy industry. We followed a personal interview method for getting first-hand and rich information from the CEOs and operational managers of the company. Also, we followed the case study method to extract how they shifted from traditional manufacturing practices to the current and latest trends in manufacturing. In their manufacturing practices, we aimed to get factual information on the changeover from linear to circular.
{"title":"Moving towards a sustainable world with the circular economy practices concerning the SMEs in Visakhapatnam’s ice-cream industry","authors":"Mukesh Kondala, S. Nudurupati, Eko Riwayadi, Abhijeet Chavan, Shaik Rajah Asif, N. Gupta","doi":"10.32629/jai.v6i1.676","DOIUrl":"https://doi.org/10.32629/jai.v6i1.676","url":null,"abstract":"The Circular Economy (CE) is getting its attention these days, which has a massive impact on the industries, particularly in the manufacturing segment. The countries worldwide started believing in CE, and its practices got the benefits after thoroughly implementing it to their current practices. The concept is not new, but it came up with a new ideology and new techniques already proven by countries like China and the UK. Different industries show their innovativeness by adapting to the change for the future. We found that the Ice Cream Industry is one of them that adopt change quickly. The paper discusses the introduction of the CE, the current trends, the comparison of the olden style with new style after implementing CE practices, the challenges and barriers in implementing, and the benefits of implementing CE Practices in Visakhapatnam’s dairy industry. We followed a personal interview method for getting first-hand and rich information from the CEOs and operational managers of the company. Also, we followed the case study method to extract how they shifted from traditional manufacturing practices to the current and latest trends in manufacturing. In their manufacturing practices, we aimed to get factual information on the changeover from linear to circular.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42179163","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 diagnosis of diabetic retinopathy depends on the evaluation of retinal fundus pictures. The current methods have been successful in extracting features from fundus images, but due to the complex blood vessel distribution in these images and the presence of a great deal of noise, simple methods based on threshold segmentation and clustering are vulnerable to feature loss during the extraction process. For example, the small blood vessels in the fundus are lost, and the branches of blood vessels are blurred. In addition, the noise in medical images is mainly distributed in the high-frequency area of the image. The proposed method to segment the retinal fundus vessels in the DRIVE and STARE datasets, the average accuracy of this method is 95.45% and 94.81%, respectively, and the sensitivity and specificity are 73.35%, 75.39% and 97.34%, 95.75%. In addition, compared with related methods, the proposed method has higher segmentation accuracy, and after segmentation, the fundus blood vessels have higher integrity, clear structure, and less loss of small blood vessels.
{"title":"Diabetic retinopathy feature extraction images based on confusion neural network","authors":"M. Ghet, Omar Ismael Al-Sanjary, A. Khatibi","doi":"10.32629/jai.v6i1.636","DOIUrl":"https://doi.org/10.32629/jai.v6i1.636","url":null,"abstract":"The diagnosis of diabetic retinopathy depends on the evaluation of retinal fundus pictures. The current methods have been successful in extracting features from fundus images, but due to the complex blood vessel distribution in these images and the presence of a great deal of noise, simple methods based on threshold segmentation and clustering are vulnerable to feature loss during the extraction process. For example, the small blood vessels in the fundus are lost, and the branches of blood vessels are blurred. In addition, the noise in medical images is mainly distributed in the high-frequency area of the image. The proposed method to segment the retinal fundus vessels in the DRIVE and STARE datasets, the average accuracy of this method is 95.45% and 94.81%, respectively, and the sensitivity and specificity are 73.35%, 75.39% and 97.34%, 95.75%. In addition, compared with related methods, the proposed method has higher segmentation accuracy, and after segmentation, the fundus blood vessels have higher integrity, clear structure, and less loss of small blood vessels.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48136952","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}
Somayah Karsoum, Clark Barrus, L. Gruenwald, Eleazar Leal
Sequential pattern mining is one of the data mining tasks used to find the subsequences in a sequence dataset that appear together in order based on time. Sequence data can be collected from devices, such as sensors, GPS, or satellites, and ordered based on timestamps, which are the times when they are generated/collected. Mining patterns in such data can be used to support many applications, including transportation recommendation systems, transportation safety, weather forecasting, and disease symptom analysis. Numerous techniques have been proposed to address the problem of how to mine subsequences in a sequence dataset; however, current traditional algorithms ignore the temporal information between the itemset in a sequential pattern. This information is essential in many situations. Though knowing that measurement Y occurs after measurement X is valuable, it is more valuable to know the estimated time before the appearance of measurement Y, for example, to schedule maintenance at the right time to prevent railway damage. Considering temporal relationship information for sequential patterns raises new issues to be solved, such as designing a new data structure to save this information and traversing this structure efficiently to discover patterns without re-scanning the database. In this paper, we propose an algorithm called Minits-AllOcc (MINIng Timed Sequential Pattern for All-time Occurrences) to find sequential patterns and the transition time between itemsets based on all occurrences of a pattern in the database. We also propose a parallel multi-core CPU version of this algorithm, called MMinits-AllOcc (Multi-core for MINIng Timed Sequential Pattern for All-time Occurrences), to deal with Big Data. Extensive experiments on real and synthetic datasets show the advantages of this approach over the brute-force method. Also, the multi-core CPU version of the algorithm is shown to outperform the single-core version on Big Data by 2.5X.
序列模式挖掘是一种数据挖掘任务，用于查找序列数据集中根据时间按顺序出现在一起的子序列。序列数据可以从传感器、GPS或卫星等设备收集，并根据时间戳进行排序，时间戳是生成/收集序列数据的时间。此类数据中的挖掘模式可用于支持许多应用程序，包括交通推荐系统、交通安全、天气预报和疾病症状分析。已经提出了许多技术来解决如何在序列数据集中挖掘子序列的问题；然而，目前的传统算法忽略了序列模式中项目集之间的时间信息。这些信息在许多情况下都是必不可少的。虽然知道测量Y发生在测量X之后是有价值的，但知道测量Y出现之前的估计时间更为有价值，例如，在正确的时间安排维护以防止铁路损坏。考虑顺序模式的时间关系信息提出了需要解决的新问题，例如设计一个新的数据结构来保存这些信息，并在不重新扫描数据库的情况下高效地遍历这个结构来发现模式。在本文中，我们提出了一种称为Minits-AllOcc（所有时间出现的MINIng Timed Sequential Pattern for All time Occurrences）的算法，以基于数据库中模式的所有出现来查找序列模式和项目集之间的转换时间。我们还提出了该算法的并行多核CPU版本，称为MMinits-AllOcc（用于最小化所有时间发生的定时序列模式的多核），以处理大数据。在真实数据集和合成数据集上进行的大量实验表明，与暴力方法相比，这种方法具有优势。此外，该算法的多核CPU版本在大数据上的表现比单核版本好2.5倍。
{"title":"Mining timed sequential patterns: The Minits-AllOcc technique","authors":"Somayah Karsoum, Clark Barrus, L. Gruenwald, Eleazar Leal","doi":"10.32629/jai.v6i1.593","DOIUrl":"https://doi.org/10.32629/jai.v6i1.593","url":null,"abstract":"Sequential pattern mining is one of the data mining tasks used to find the subsequences in a sequence dataset that appear together in order based on time. Sequence data can be collected from devices, such as sensors, GPS, or satellites, and ordered based on timestamps, which are the times when they are generated/collected. Mining patterns in such data can be used to support many applications, including transportation recommendation systems, transportation safety, weather forecasting, and disease symptom analysis. Numerous techniques have been proposed to address the problem of how to mine subsequences in a sequence dataset; however, current traditional algorithms ignore the temporal information between the itemset in a sequential pattern. This information is essential in many situations. Though knowing that measurement Y occurs after measurement X is valuable, it is more valuable to know the estimated time before the appearance of measurement Y, for example, to schedule maintenance at the right time to prevent railway damage. Considering temporal relationship information for sequential patterns raises new issues to be solved, such as designing a new data structure to save this information and traversing this structure efficiently to discover patterns without re-scanning the database. In this paper, we propose an algorithm called Minits-AllOcc (MINIng Timed Sequential Pattern for All-time Occurrences) to find sequential patterns and the transition time between itemsets based on all occurrences of a pattern in the database. We also propose a parallel multi-core CPU version of this algorithm, called MMinits-AllOcc (Multi-core for MINIng Timed Sequential Pattern for All-time Occurrences), to deal with Big Data. Extensive experiments on real and synthetic datasets show the advantages of this approach over the brute-force method. Also, the multi-core CPU version of the algorithm is shown to outperform the single-core version on Big Data by 2.5X.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46544838","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}
Software defect prediction (SDP) is an essential task for developing quality software, and various models have been developed for this purpose. However, the imbalanced nature of software defect datasets has challenged these models, resulting in decreased performance. To address this challenge, the author has proposed a hybrid machine learning model that combines Synthetic Minority Oversampling Technique (SMOTE) with Support Vector Machine (SVM)—SMOTE-SVM (S-SVM) model. The author has empirically examined SDP using multiple datasets (CM1, PC1, JM1, PC3, KC1, EQ and JDT) from the PROMISE and AEEEM repositories. The experimental study indicates that the S-SVM model involved training and compared with previously developed balanced and imbalanced test datasets using four evaluation metrics: Precision, Recall, F1 score, and Accuracy. For the balanced dataset, the S-SVM model achieved precision values ranging from 70 to 96, recall values ranging from 52 to 94, F1-score values ranging from 67 to 90, and accuracy values ranging from 69 to 98. For the imbalanced dataset, the S-SVM model achieved precision values ranging from 60 to 93, recall values ranging from 64 to 97, F1-score values ranging from 69 to 91, and accuracy values ranging from 67 to 87. The proposed S-SVM model outperforms other models’ ability to classify and predict software defects. Therefore, the hybridisation of SMOTE and SVM improved the model’s ability to categories and predict balanced and imbalanced datasets when sufficient defective and non-defective data is provided.
{"title":"A Hybrid Software Defects Prediction Model for Imbalance Datasets Using Machine Learning Techniques: (S-SVM Model)","authors":"Mohd. Mustaqeem, Tamanna Siddiqui","doi":"10.32629/jai.v6i1.559","DOIUrl":"https://doi.org/10.32629/jai.v6i1.559","url":null,"abstract":"Software defect prediction (SDP) is an essential task for developing quality software, and various models have been developed for this purpose. However, the imbalanced nature of software defect datasets has challenged these models, resulting in decreased performance. To address this challenge, the author has proposed a hybrid machine learning model that combines Synthetic Minority Oversampling Technique (SMOTE) with Support Vector Machine (SVM)—SMOTE-SVM (S-SVM) model. The author has empirically examined SDP using multiple datasets (CM1, PC1, JM1, PC3, KC1, EQ and JDT) from the PROMISE and AEEEM repositories. The experimental study indicates that the S-SVM model involved training and compared with previously developed balanced and imbalanced test datasets using four evaluation metrics: Precision, Recall, F1 score, and Accuracy. For the balanced dataset, the S-SVM model achieved precision values ranging from 70 to 96, recall values ranging from 52 to 94, F1-score values ranging from 67 to 90, and accuracy values ranging from 69 to 98. For the imbalanced dataset, the S-SVM model achieved precision values ranging from 60 to 93, recall values ranging from 64 to 97, F1-score values ranging from 69 to 91, and accuracy values ranging from 67 to 87. The proposed S-SVM model outperforms other models’ ability to classify and predict software defects. Therefore, the hybridisation of SMOTE and SVM improved the model’s ability to categories and predict balanced and imbalanced datasets when sufficient defective and non-defective data is provided.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49055736","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}
Recognizing and analyzing moving targets is an important research subject since computer vision is employed in so many facets of our daily lives, including intelligent robotics, video surveillance, medical education, sporting events, and the maintenance of our national defense. This is because it may be difficult to properly analyse and keep up with moving materials. The various training postures of an athlete are explored in this study through the examination of a weightlifting video. This article was written to assist coaches in their efforts to improve the performance of their athletes in their respective sports. A technique for extracting essential poses from sports films has been proposed. The classification of different subjects of interest serves as the foundation for this technique. Because of its inadequate edge detection method, the current motion identification system does a bad job of detecting athletes, which is one of the reasons why it does a poor job of identifying motion in general. This flaw is one of the reasons why the system isn’t very strong at detecting athletes. The following was one of the factors that contributed to this outcome: in truth, the situation is currently in this state. The result of the newly developed system outperforms the prior system in terms of tracking recognition accuracy and convergence speed. The system was put to the test. The findings of the system’s study served as the foundation for this decision. Finally, the findings of the categorization reveal that the selection approach tries to separate fundamental postures.
{"title":"Transfer learning model for the motion detection of sports players","authors":"Wael Alghamdi","doi":"10.32629/jai.v6i1.577","DOIUrl":"https://doi.org/10.32629/jai.v6i1.577","url":null,"abstract":"Recognizing and analyzing moving targets is an important research subject since computer vision is employed in so many facets of our daily lives, including intelligent robotics, video surveillance, medical education, sporting events, and the maintenance of our national defense. This is because it may be difficult to properly analyse and keep up with moving materials. The various training postures of an athlete are explored in this study through the examination of a weightlifting video. This article was written to assist coaches in their efforts to improve the performance of their athletes in their respective sports. A technique for extracting essential poses from sports films has been proposed. The classification of different subjects of interest serves as the foundation for this technique. Because of its inadequate edge detection method, the current motion identification system does a bad job of detecting athletes, which is one of the reasons why it does a poor job of identifying motion in general. This flaw is one of the reasons why the system isn’t very strong at detecting athletes. The following was one of the factors that contributed to this outcome: in truth, the situation is currently in this state. The result of the newly developed system outperforms the prior system in terms of tracking recognition accuracy and convergence speed. The system was put to the test. The findings of the system’s study served as the foundation for this decision. Finally, the findings of the categorization reveal that the selection approach tries to separate fundamental postures.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42852200","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}
Academic success for students in any educational institute is the primary requirement for all stakeholders, i.e., students, teachers, parents, administrators and management, industry, and the environment. Regular feedback from all stakeholders helps higher education institutions (HEIs) rise professionally and academically, yet they must use emerging technologies that can help institutions to grow at a faster pace. Early prediction of students’ success using trending artificial intelligence technologies like machine learning, early finding of at-risk students, and predicting a suitable branch or course can help both management and students improve their academics. In our work, we have proposed a new student performance prediction model in which we have used ensemble machine learning with stacking of four multi-class classifiers, decision tree, k-nearest neighbor, Naïve Bayes, and One vs. Rest support vector machine classifiers. The proposed model predicts the final grade of a student at the earliest possible time and the suitable stream for a new student. A student dataset of over a thousand students from five different branches of an engineering institute has been taken to test the results. The proposed model compares the four-machine learning (ML) techniques being used and predicts the final grade with an accuracy of 93%.
{"title":"Designing new student performance prediction model using ensemble machine learning","authors":"Rajan Saluja, Munishwar Rai, R. Saluja","doi":"10.32629/jai.v6i1.583","DOIUrl":"https://doi.org/10.32629/jai.v6i1.583","url":null,"abstract":"Academic success for students in any educational institute is the primary requirement for all stakeholders, i.e., students, teachers, parents, administrators and management, industry, and the environment. Regular feedback from all stakeholders helps higher education institutions (HEIs) rise professionally and academically, yet they must use emerging technologies that can help institutions to grow at a faster pace. Early prediction of students’ success using trending artificial intelligence technologies like machine learning, early finding of at-risk students, and predicting a suitable branch or course can help both management and students improve their academics. In our work, we have proposed a new student performance prediction model in which we have used ensemble machine learning with stacking of four multi-class classifiers, decision tree, k-nearest neighbor, Naïve Bayes, and One vs. Rest support vector machine classifiers. The proposed model predicts the final grade of a student at the earliest possible time and the suitable stream for a new student. A student dataset of over a thousand students from five different branches of an engineering institute has been taken to test the results. The proposed model compares the four-machine learning (ML) techniques being used and predicts the final grade with an accuracy of 93%.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41795096","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}
Shaikh Abdul Waheed, Mohammed Abdul Matheen, Syed Hussain Hussain, A. K. Lodhi, G.S. Maboobatcha
This study aims at analyzing the impact of gender and race on the linguistic abilities and stuttering of children. The current article also seeks to check whether children with stuttering disorder and normal children differ in linguistic skills. Parametric methods like t-tests and Analysis of Variance (ANOVA) have been applied to test hypotheses. The p-values that were generated in the parametric tests signify that the gender of the child has an impact on the onset of stuttering. However, the race of children did not affect the onset of stuttering. The regression results of the machine learning part have indicated many findings. The results indicated that a child’s race does not impact the onset of stuttering. Hence, the null hypothesis about race was accepted by signifying that children of any race can adopt stuttering. This finding also suggests that children can face linguistic difficulties irrespective of their race. Another finding is that children with stuttering (CWS) repeat more words than children with not stuttering (CWNS). In addition, CWS repeat more syllables than CWNS. It indicates that the null hypothesis can be accepted by stating that children can suffer from linguistic difficulties irrespective of their race. Another key finding is that there can be a significant difference in the linguistic abilities of male and female children. Another inference is that the p-values indicate a significant difference between linguistic skills among CWS and CWNS. In other words, CWS are more prone to repeat syllables than normal children.
{"title":"Machine learning approach to analyze the impact of demographic and linguistic features of children on their stuttering","authors":"Shaikh Abdul Waheed, Mohammed Abdul Matheen, Syed Hussain Hussain, A. K. Lodhi, G.S. Maboobatcha","doi":"10.32629/jai.v6i1.553","DOIUrl":"https://doi.org/10.32629/jai.v6i1.553","url":null,"abstract":"This study aims at analyzing the impact of gender and race on the linguistic abilities and stuttering of children. The current article also seeks to check whether children with stuttering disorder and normal children differ in linguistic skills. Parametric methods like t-tests and Analysis of Variance (ANOVA) have been applied to test hypotheses. The p-values that were generated in the parametric tests signify that the gender of the child has an impact on the onset of stuttering. However, the race of children did not affect the onset of stuttering. The regression results of the machine learning part have indicated many findings. The results indicated that a child’s race does not impact the onset of stuttering. Hence, the null hypothesis about race was accepted by signifying that children of any race can adopt stuttering. This finding also suggests that children can face linguistic difficulties irrespective of their race. Another finding is that children with stuttering (CWS) repeat more words than children with not stuttering (CWNS). In addition, CWS repeat more syllables than CWNS. It indicates that the null hypothesis can be accepted by stating that children can suffer from linguistic difficulties irrespective of their race. Another key finding is that there can be a significant difference in the linguistic abilities of male and female children. Another inference is that the p-values indicate a significant difference between linguistic skills among CWS and CWNS. In other words, CWS are more prone to repeat syllables than normal children.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42502308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1101/2023.05.23.23290343
D. Bertin, P. Bongrand, N. Bardin
Diagnosis is a key step of patient management. During decades, refined decision algorithms and numerical scores based on conventional statistic tools were elaborated to ensure optimal reliability. Recently, a number of machine learning tools were developed and applied to process more and more extensive data sets, including up to million of items and yielding sophisticated classification models. While this approach met with impressive efficiency in some cases, practical limitations stem from the high number of parameters that may be required by a model, resulting in increased cost and delay of decision making. Also, information relative to the specificity of local recruitment may be lost, hampering any simplification of universal models. Here, we explored the capacity of currently available artificial intelligence tools to classify patients found in a single health center on the basis of a limited number of parameters. As a model, the discrimination between systemic lupus erythematosus (SLE) and mixed connective tissue disease (MCTD) on the basis of thirteen biological parameters was studied with eight widely used classifiers. It is concluded that classification performance may be significantly improved by a knowledge-based selection of discriminating parameters.
{"title":"Can artificial intelligence help a clinical laboratory to draw useful information from limited data sets ? Application to Mixed Connective Tissue Disease","authors":"D. Bertin, P. Bongrand, N. Bardin","doi":"10.1101/2023.05.23.23290343","DOIUrl":"https://doi.org/10.1101/2023.05.23.23290343","url":null,"abstract":"Diagnosis is a key step of patient management. During decades, refined decision algorithms and numerical scores based on conventional statistic tools were elaborated to ensure optimal reliability. Recently, a number of machine learning tools were developed and applied to process more and more extensive data sets, including up to million of items and yielding sophisticated classification models. While this approach met with impressive efficiency in some cases, practical limitations stem from the high number of parameters that may be required by a model, resulting in increased cost and delay of decision making. Also, information relative to the specificity of local recruitment may be lost, hampering any simplification of universal models. Here, we explored the capacity of currently available artificial intelligence tools to classify patients found in a single health center on the basis of a limited number of parameters. As a model, the discrimination between systemic lupus erythematosus (SLE) and mixed connective tissue disease (MCTD) on the basis of thirteen biological parameters was studied with eight widely used classifiers. It is concluded that classification performance may be significantly improved by a knowledge-based selection of discriminating parameters.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48268369","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}
A financial time series is chaotic and non-stationary in nature, and predicting it outcomes is a very complex and challenging task. In this research, the theory of chaos, Long Short-Term Memory (LSTM), and Polynomial Regression (PR) are used in tandem to create a novel financial time series prediction hybrid, Chaos+LSTM+PR. The first step in this hybrid will determine whether or not a financial time series contains chaos. Following that, the chaos in the time series is modeled using Chaos Theory. The modeled time series is fed into the LSTM to obtain initial predictions. The error series obtained from LSTM predictions is fitted by PR to obtain error predictions. The error predictions and initial predictions from LSTM are combined to obtain final predictions. The effectiveness of this hybrid is examined by three types of financial time series (Chaos+LSTM+PR), including stock market indices (S&P 500, Nifty 50, Shanghai Composite), commodity prices (gold, crude oil, soya beans), and foreign exchange rates (INR/USD, JPY/USD, SGD/USD). The results show that the proposed hybrid outperforms ARIMA (autoregressive integrated moving average), Prophet, CART (Classification and Regression Tree), RF (Random Forest), LSTM, Chaos+CART, Chaos+CART, and Chaos+LSTM. The results are also checked for statistical significance.
{"title":"Financial time series prediction using deep computing approaches","authors":"M. Durairaj, C. Suneetha, B. Mohan","doi":"10.32629/jai.v6i1.558","DOIUrl":"https://doi.org/10.32629/jai.v6i1.558","url":null,"abstract":"A financial time series is chaotic and non-stationary in nature, and predicting it outcomes is a very complex and challenging task. In this research, the theory of chaos, Long Short-Term Memory (LSTM), and Polynomial Regression (PR) are used in tandem to create a novel financial time series prediction hybrid, Chaos+LSTM+PR. The first step in this hybrid will determine whether or not a financial time series contains chaos. Following that, the chaos in the time series is modeled using Chaos Theory. The modeled time series is fed into the LSTM to obtain initial predictions. The error series obtained from LSTM predictions is fitted by PR to obtain error predictions. The error predictions and initial predictions from LSTM are combined to obtain final predictions. The effectiveness of this hybrid is examined by three types of financial time series (Chaos+LSTM+PR), including stock market indices (S&P 500, Nifty 50, Shanghai Composite), commodity prices (gold, crude oil, soya beans), and foreign exchange rates (INR/USD, JPY/USD, SGD/USD). The results show that the proposed hybrid outperforms ARIMA (autoregressive integrated moving average), Prophet, CART (Classification and Regression Tree), RF (Random Forest), LSTM, Chaos+CART, Chaos+CART, and Chaos+LSTM. The results are also checked for statistical significance.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43410537","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}
Arindam Chakrabarty, U. Das, S. Kushwaha, Prathamesh P. Churi
The human civilization has witnessed myriads of road-block and crossroads at every facet of its journey. Many a time, it becomes untenable to sustain its existence. The series of health hazards, critical epidemics and even the catastrophic pandemic diseases have been challenging our vivid foundation and perpetuity. The disasters both natural and man-made have attempted massively to destroy, devastate, and ruin our glorious leadership on earth. In all such cases, the society has responded through rendering relief and rescue operations and offering emergency health services to mitigate these humanitarian crises. It is imperative to understand, the response time for such emergencies varies with the nature and intensity of the hazards. It is still difficult to reach the epicenter or the point of occurrence even though services have begun to function towards the outer periphery region. The deployment of medical and non-medical personnel at the critical point in the early hours becomes unsuitable and unwise decision. There are issues of the inadequacy of resources for deployment strategy. In the era of 4IR (4th Industrial Revolution or Industry 4.0), it is emergent to improvise AI induced guided or auto guided devices that can perform various tasks at such unprecedented humanitarian crisis. The introduction of the Internet of Robotic Things (IoRT) protocol embedded with medical based AI i.e. Internet of Medical Robotic Things (IoMRT) would be able to deliver superior performance to minimize loss of life and property. This paper has attempted to explore how the IoMRT system can contribute to society with excellence.
{"title":"Managing Humanitarian Challenges of Disaster Responses and Pandemic Crises: Interface of 4IR Ecosystem","authors":"Arindam Chakrabarty, U. Das, S. Kushwaha, Prathamesh P. Churi","doi":"10.32629/jai.v5i2.550","DOIUrl":"https://doi.org/10.32629/jai.v5i2.550","url":null,"abstract":"The human civilization has witnessed myriads of road-block and crossroads at every facet of its journey. Many a time, it becomes untenable to sustain its existence. The series of health hazards, critical epidemics and even the catastrophic pandemic diseases have been challenging our vivid foundation and perpetuity. The disasters both natural and man-made have attempted massively to destroy, devastate, and ruin our glorious leadership on earth. In all such cases, the society has responded through rendering relief and rescue operations and offering emergency health services to mitigate these humanitarian crises. It is imperative to understand, the response time for such emergencies varies with the nature and intensity of the hazards. It is still difficult to reach the epicenter or the point of occurrence even though services have begun to function towards the outer periphery region. The deployment of medical and non-medical personnel at the critical point in the early hours becomes unsuitable and unwise decision. There are issues of the inadequacy of resources for deployment strategy. In the era of 4IR (4th Industrial Revolution or Industry 4.0), it is emergent to improvise AI induced guided or auto guided devices that can perform various tasks at such unprecedented humanitarian crisis. The introduction of the Internet of Robotic Things (IoRT) protocol embedded with medical based AI i.e. Internet of Medical Robotic Things (IoMRT) would be able to deliver superior performance to minimize loss of life and property. This paper has attempted to explore how the IoMRT system can contribute to society with excellence.","PeriodicalId":70721,"journal":{"name":"自主智能(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47427755","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：