Rhodamine 6G – polymethylmethacrylate/polycarbonate (Rh6G–PMMA/PC) were prepared by a casting method at room temperature with diverse volume ratios of Rh6G dye solution (5, 10, 15, 20 and 25) ml. The as-prepared films were categorised via UV–Vis spectrophotometer, and the optical properties were investigated in the wavelength range of (200-800) nm. The absorption peaks for pure PMMA/PC film were affected by inserting Rh6G dye solution, the wavelength of absorption peak of pure PMMA/PC film is at 300 nm and 340 nm while there are different behaveior at different concentration of RG6 after mixing with PMMA/PC films; there are red shift for concentrations (10 and 25 ml) of RG6 after mixing with PMMA/PC films by appear another peaks at 530 nm and 535 nm respectively. In addition, there is a blue shift for concentrations (15 and 20 ml) of RG6 after mixing with PMMA/PC films, as evidenced by the appearance of new peaks at wavelength 265 nm. Furthermore, new peaks appeared and were absorbed while the energy band gap was influenced, with values ranging from 4.3 eV for pure PMMA/PC film to 4.18 eV for mixtures 10 and 25 ml concentration of Rh6G/ PMMA/PC belonging to the red shift to 4.9 eV and 4.85 eV for mixtures 15 and 20 ml concentration of Rh6G/ PMMA/PC belonging to the blue shift.
{"title":"Investigating The Effects of The Different Rhodamine 6G Laser Dye Volume Ratios on The Optical Properties of PMMA/PC Films","authors":"M. S. Jalil, F. Kadhum, A. Saeed, M. Al-Kadhemy","doi":"10.48129/kjs.19853","DOIUrl":"https://doi.org/10.48129/kjs.19853","url":null,"abstract":"Rhodamine 6G – polymethylmethacrylate/polycarbonate (Rh6G–PMMA/PC) were prepared by a casting method at room temperature with diverse volume ratios of Rh6G dye solution (5, 10, 15, 20 and 25) ml. The as-prepared films were categorised via UV–Vis spectrophotometer, and the optical properties were investigated in the wavelength range of (200-800) nm. The absorption peaks for pure PMMA/PC film were affected by inserting Rh6G dye solution, the wavelength of absorption peak of pure PMMA/PC film is at 300 nm and 340 nm while there are different behaveior at different concentration of RG6 after mixing with PMMA/PC films; there are red shift for concentrations (10 and 25 ml) of RG6 after mixing with PMMA/PC films by appear another peaks at 530 nm and 535 nm respectively. In addition, there is a blue shift for concentrations (15 and 20 ml) of RG6 after mixing with PMMA/PC films, as evidenced by the appearance of new peaks at wavelength 265 nm. Furthermore, new peaks appeared and were absorbed while the energy band gap was influenced, with values ranging from 4.3 eV for pure PMMA/PC film to 4.18 eV for mixtures 10 and 25 ml concentration of Rh6G/ PMMA/PC belonging to the red shift to 4.9 eV and 4.85 eV for mixtures 15 and 20 ml concentration of Rh6G/ PMMA/PC belonging to the blue shift.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89919273","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 frequent occurrence of climate related events and changes in average temperature, are predicted to increase the vulnerability of the coastal population of Sindh. A climate vulnerability index (CVI) was established and applied to the coastal subdistricts of Badin, Sindh, Pakistan. This study aimed to recognize the vulnerabilities of the coastal population of Sindh exposed to climate change. According to the study, the subdistricts of Badin have been exposed to high temperatures and significant climatic tragedies during the last two decades. The highest vulnerability to climate variability was found in Tando Bago (0.72) and Badin (0.70). Matli is better off in adaptive capacity through socio-demographic (0.29). The vulnerability to resource dependency and knowledge and skill was low in the sub-district of Talhar. In terms of sensitivity, Tando Bago is the most sensitive subdistrict in terms of health (0.55) and resource variability (0.80). The study raises concerns related to coastal communities and their aptitude to address present and upcoming challenges connected with climate change and increased insecurity. The CVI calculated (0.59) can be utilized to improve adaptive capacity, minimize sensitivity, and mitigate exposure to climatic extremes in adaptation planning.
{"title":"Climate Vulnerability Index of the Coastal Subdistricts of Badin, Sindh, Pakistan","authors":"Noor Fatima, Aamir Alamgir, M. Khan, M. Owais","doi":"10.48129/kjs.17873","DOIUrl":"https://doi.org/10.48129/kjs.17873","url":null,"abstract":"The frequent occurrence of climate related events and changes in average temperature, are predicted to increase the vulnerability of the coastal population of Sindh. A climate vulnerability index (CVI) was established and applied to the coastal subdistricts of Badin, Sindh, Pakistan. This study aimed to recognize the vulnerabilities of the coastal population of Sindh exposed to climate change. According to the study, the subdistricts of Badin have been exposed to high temperatures and significant climatic tragedies during the last two decades. The highest vulnerability to climate variability was found in Tando Bago (0.72) and Badin (0.70). Matli is better off in adaptive capacity through socio-demographic (0.29). The vulnerability to resource dependency and knowledge and skill was low in the sub-district of Talhar. In terms of sensitivity, Tando Bago is the most sensitive subdistrict in terms of health (0.55) and resource variability (0.80). The study raises concerns related to coastal communities and their aptitude to address present and upcoming challenges connected with climate change and increased insecurity. The CVI calculated (0.59) can be utilized to improve adaptive capacity, minimize sensitivity, and mitigate exposure to climatic extremes in adaptation planning.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78915118","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}
F. Al-Horani, Sewar T. Al-Talafhah, Maysoon Kteifan, Emad Ibraheim Hussein
Coral deterioration is often linked with coastal pollution. This aimed to study biochemical stress responses in the common coral Stylophora pistillata collected and/or planted in coastal sites subject to pollution and sites without pollution in the Gulf of Aqaba. DNA damage and lipid peroxidation were analyzed to measure stress in corals. High DNA damage was found in natural corals from polluted sites, while higher lipid peroxidation was found in control site compared with polluted sites. Lipid peroxidation was higher in polluted sites after one-year of deployment. Corals’ incubations with copper and lead produced high levels of DNA damage and lipid peroxidation compared with control samples. The results suggested that although corals are visually looking healthy, but they are suffering at subcellular levels. The consequences of such stress might affect the fecundity and growth rates of corals. The results suggest that biomarkers used are efficient tools for early stress detection in corals, though the cost of assessing DNA damage is relatively expensive compared with lipid peroxidation.
{"title":"Stress response of the coral Stylophora pistillata towards possible anthropogenic impacts in the Gulf of Aqaba, Red Sea","authors":"F. Al-Horani, Sewar T. Al-Talafhah, Maysoon Kteifan, Emad Ibraheim Hussein","doi":"10.48129/kjs.16207","DOIUrl":"https://doi.org/10.48129/kjs.16207","url":null,"abstract":"Coral deterioration is often linked with coastal pollution. This aimed to study biochemical stress responses in the common coral Stylophora pistillata collected and/or planted in coastal sites subject to pollution and sites without pollution in the Gulf of Aqaba. DNA damage and lipid peroxidation were analyzed to measure stress in corals. High DNA damage was found in natural corals from polluted sites, while higher lipid peroxidation was found in control site compared with polluted sites. Lipid peroxidation was higher in polluted sites after one-year of deployment. Corals’ incubations with copper and lead produced high levels of DNA damage and lipid peroxidation compared with control samples. The results suggested that although corals are visually looking healthy, but they are suffering at subcellular levels. The consequences of such stress might affect the fecundity and growth rates of corals. The results suggest that biomarkers used are efficient tools for early stress detection in corals, though the cost of assessing DNA damage is relatively expensive compared with lipid peroxidation.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89980380","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}
As Lab-on-Chip platforms with micro-and nano-dimensions evolve biosensors using miniaturized and high-sensitivity cantilevers are becoming more attractive. Although these sensors function in non-isothermal situations, computational mathematics generally ignores the temperature. Conversely, biosensor cannot be designed with a single-layered cantilever. Yet, in Nano-Electro- Mechanical-Systems, the influence of temperature is more likely to be dominant since the surfaceto- volume ratio is higher. In the context of this conclusion, the mathematical modelling comprises temperature and the associated material attributes. This work presents a simple and direct analytical technique for analysing the control of bimetallic cantilevers with NEMS-based sensing and actuation mechanisms. Methodological techniques were used to develop and solve some wellknown models of mathematical equations. Parametric analysis data is a major factor in the functioning of all of the other works studied. The findings of FEA comparisons and experiments reveal that the mathematical model's predictions are more than 20% correct.
{"title":"Mathematical Modelling and Analysis of Temperature Effects in NEMS Based Bi-Metallic Cantilever for Molecular Biosensing Applications","authors":"Miranji Katta, S. R.","doi":"10.48129/kjs.20495","DOIUrl":"https://doi.org/10.48129/kjs.20495","url":null,"abstract":"As Lab-on-Chip platforms with micro-and nano-dimensions evolve biosensors using miniaturized and high-sensitivity cantilevers are becoming more attractive. Although these sensors function in non-isothermal situations, computational mathematics generally ignores the temperature. Conversely, biosensor cannot be designed with a single-layered cantilever. Yet, in Nano-Electro- Mechanical-Systems, the influence of temperature is more likely to be dominant since the surfaceto- volume ratio is higher. In the context of this conclusion, the mathematical modelling comprises temperature and the associated material attributes. This work presents a simple and direct analytical technique for analysing the control of bimetallic cantilevers with NEMS-based sensing and actuation mechanisms. Methodological techniques were used to develop and solve some wellknown models of mathematical equations. Parametric analysis data is a major factor in the functioning of all of the other works studied. The findings of FEA comparisons and experiments reveal that the mathematical model's predictions are more than 20% correct.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84638397","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 : 2022-06-22DOI: 10.48129/kjs.splml.19477
Sajid Khan, Faiqa Arshad, Maryam Zulfiqar, M. A. Khan, S. Memon
Almost one out of five people, including children, suffers from musculoskeletal disorders. It is the second leading cause of disability worldwide. It affects the musculoskeletal system’s major areas, represented by the shoulder, forearm, and wrist. It causes severe pain, joint noises, and disability. To detect the abnormality, the radiologist analyzes the patient’s anatomy through X-rays of different views and projections. To automatically diagnose the abnormality in the musculoskeletal system is a challenging task. Previously, various researchers detected the abnormality in the musculoskeletal system from radiographic images by using several deep learning techniques. They used a capsule network, 169-layer convolutional neural network, and group normalized convolutional neural network in musculoskeletal abnormality detection. However, to propose methods for improving abnormality detection, further work needs to be done because the accuracy of the conventional methods is far away from 90%. This paper presents an ensemble learning-based classification system for detecting abnormality in wrist radiographs. Tags in radiographs may result in learning noisy features hence reducing the performance. Therefore, tags are segmented and removed using UNet trained on the annotated ground truths. Segmented images are then used for voting-based diagnosis. The simulation results show that the proposed methodology improves testing accuracy by 1.5%-4.5% compared to the available wrist abnormality detection methods. The proposed methodology can be used for any kind of musculoskeletal abnormality detection.
{"title":"Ensemble learning-based abnormality diagnosis in wrist skeleton radiographs using densenet variants voting","authors":"Sajid Khan, Faiqa Arshad, Maryam Zulfiqar, M. A. Khan, S. Memon","doi":"10.48129/kjs.splml.19477","DOIUrl":"https://doi.org/10.48129/kjs.splml.19477","url":null,"abstract":"Almost one out of five people, including children, suffers from musculoskeletal disorders. It is the second leading cause of disability worldwide. It affects the musculoskeletal system’s major areas, represented by the shoulder, forearm, and wrist. It causes severe pain, joint noises, and disability. To detect the abnormality, the radiologist analyzes the patient’s anatomy through X-rays of different views and projections. To automatically diagnose the abnormality in the musculoskeletal system is a challenging task. Previously, various researchers detected the abnormality in the musculoskeletal system from radiographic images by using several deep learning techniques. They used a capsule network, 169-layer convolutional neural network, and group normalized convolutional neural network in musculoskeletal abnormality detection. However, to propose methods for improving abnormality detection, further work needs to be done because the accuracy of the conventional methods is far away from 90%. This paper presents an ensemble learning-based classification system for detecting abnormality in wrist radiographs. Tags in radiographs may result in learning noisy features hence reducing the performance. Therefore, tags are segmented and removed using UNet trained on the annotated ground truths. Segmented images are then used for voting-based diagnosis. The simulation results show that the proposed methodology improves testing accuracy by 1.5%-4.5% compared to the available wrist abnormality detection methods. The proposed methodology can be used for any kind of musculoskeletal abnormality detection.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90394073","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 : 2022-06-22DOI: 10.48129/kjs.splml.19119
Ra Nugraha, H. Pardede, Agus Subekti
Fraud on health insurance impacts cost overruns and a quality decline in health services in the long term. The use of machine learning to detect fraud on health insurance is increasingly popular. However, one challenge in predicting health insurance fraud is the data imbalance. The data imbalance can cause a bias towards the majority class in many machine learning methods. Oversampling is a solution for data imbalance by augmenting new data based on the existing minority class data. Recently, there has been growing interest in employing deep learning for data augmentation. One of them is using Generative Adversarial Networks (GAN). This paper proposes using GAN as an oversampling method to generate additional data for minority classes. Since data for detecting health insurance fraud are tabular, we adopt Conditional Tabular GAN (CTGAN) architecture where the generator is conditioned to adjust the tabular data input and receive additional information to produce samples according to the specified class conditions. The new balanced data are used to train 17 classification algorithms. Our experiments showed that the proposed method performs better than other oversampling methods on several evaluation metrics, i.e., accuracy, precision score, F1-score, and ROC.
{"title":"Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim","authors":"Ra Nugraha, H. Pardede, Agus Subekti","doi":"10.48129/kjs.splml.19119","DOIUrl":"https://doi.org/10.48129/kjs.splml.19119","url":null,"abstract":"Fraud on health insurance impacts cost overruns and a quality decline in health services in the long term. The use of machine learning to detect fraud on health insurance is increasingly popular. However, one challenge in predicting health insurance fraud is the data imbalance. The data imbalance can cause a bias towards the majority class in many machine learning methods. Oversampling is a solution for data imbalance by augmenting new data based on the existing minority class data. Recently, there has been growing interest in employing deep learning for data augmentation. One of them is using Generative Adversarial Networks (GAN). This paper proposes using GAN as an oversampling method to generate additional data for minority classes. Since data for detecting health insurance fraud are tabular, we adopt Conditional Tabular GAN (CTGAN) architecture where the generator is conditioned to adjust the tabular data input and receive additional information to produce samples according to the specified class conditions. The new balanced data are used to train 17 classification algorithms. Our experiments showed that the proposed method performs better than other oversampling methods on several evaluation metrics, i.e., accuracy, precision score, F1-score, and ROC.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77275258","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 : 2022-06-22DOI: 10.48129/kjs.splml.19407
Chen Liu, Yu-heng Zhao
Egg prices are linked to people’s livelihoods, and layer farmers face the risk of large fluctuations. The “Insurance + Futures” mode, as one of new price risk management modes, suffers from the problems of inaccurately determining insurance price and premium rate: an approach that overcomes these problems by proposing a mode based on the autoregressive neural network(AR-Net) model is proposed. This study uses the data pertaining to China’s egg futures closing prices from November 2013 to March 2021 for analysis, a dataset of 1756 samples can be obtained from theWind database. The improved egg price risk management mode presented herein comprises three stages. Firstly, compared with the statistical models (Autoregressive model, ARIMA model, Monte Carlo simulation) and neural network model (Back propagation (BP) model, convolutional neural network (CNN) model), the AR-Net model improves the accuracy of insurance price forecast by its seasonal trend coefficients. Secondly, the AR-Net model is used for rolling forecasts of insurance price and premium rate during the insurance period. Scenario simulations predict that the new mode offers better risk management. Thirdly, the result of robustness analysis by value at risk-generalized autoregressive conditional heteroskedasticity(VaR-GARCH) model implies that the AR-Net model can improve the management of risk.
{"title":"Price risk management effect on the China’s egg “Insurance + Futures” mode: an empirical analysis based on the AR-Net model","authors":"Chen Liu, Yu-heng Zhao","doi":"10.48129/kjs.splml.19407","DOIUrl":"https://doi.org/10.48129/kjs.splml.19407","url":null,"abstract":"Egg prices are linked to people’s livelihoods, and layer farmers face the risk of large fluctuations. The “Insurance + Futures” mode, as one of new price risk management modes, suffers from the problems of inaccurately determining insurance price and premium rate: an approach that overcomes these problems by proposing a mode based on the autoregressive neural network(AR-Net) model is proposed. This study uses the data pertaining to China’s egg futures closing prices from November 2013 to March 2021 for analysis, a dataset of 1756 samples can be obtained from theWind database. The improved egg price risk management mode presented herein comprises three stages. Firstly, compared with the statistical models (Autoregressive model, ARIMA model, Monte Carlo simulation) and neural network model (Back propagation (BP) model, convolutional neural network (CNN) model), the AR-Net model improves the accuracy of insurance price forecast by its seasonal trend coefficients. Secondly, the AR-Net model is used for rolling forecasts of insurance price and premium rate during the insurance period. Scenario simulations predict that the new mode offers better risk management. Thirdly, the result of robustness analysis by value at risk-generalized autoregressive conditional heteroskedasticity(VaR-GARCH) model implies that the AR-Net model can improve the management of risk.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87292667","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 : 2022-06-22DOI: 10.48129/kjs.splml.19189
Sonika Jindal, Monika Sachdeva, A. Kushwaha
In the last few decades, Human Activity Recognition (HAR) has been a centre of attraction in many research domains, and it is referred to as the potential of interpreting human body gestures through sensors and ascertaining the activity of a human being. The present work has proposed the voting classifier system for human activity recognition. For the voting classifier system, five machine learning classifiers are considered: Logistic Regression (LR), K-Nearest Neighbour (KNN), Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM). These machine learning classifiers are ensembled by analyzing the best performers among them. The ensemble voting classifiers are proposed under two variations, i.e., hard voting and soft voting. The various combinations of voting classifiers are compared and evaluated. For experiments, the benchmark dataset of the UCI-HAR dataset is considered, and all the data files are combined into a single file to avoid bias. The dimensionality of the dataset is reduced by using Principal Component Analysis (PCA) from 561 features to 200 components. The results reveal that Voting Classifier-II (a combination of SVM, KNN, and LR) using soft voting outperformed other machine learning classifiers.
{"title":"Performance evaluation of machine learning based voting classifier system for human activity recognition","authors":"Sonika Jindal, Monika Sachdeva, A. Kushwaha","doi":"10.48129/kjs.splml.19189","DOIUrl":"https://doi.org/10.48129/kjs.splml.19189","url":null,"abstract":"In the last few decades, Human Activity Recognition (HAR) has been a centre of attraction in many research domains, and it is referred to as the potential of interpreting human body gestures through sensors and ascertaining the activity of a human being. The present work has proposed the voting classifier system for human activity recognition. For the voting classifier system, five machine learning classifiers are considered: Logistic Regression (LR), K-Nearest Neighbour (KNN), Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM). These machine learning classifiers are ensembled by analyzing the best performers among them. The ensemble voting classifiers are proposed under two variations, i.e., hard voting and soft voting. The various combinations of voting classifiers are compared and evaluated. For experiments, the benchmark dataset of the UCI-HAR dataset is considered, and all the data files are combined into a single file to avoid bias. The dimensionality of the dataset is reduced by using Principal Component Analysis (PCA) from 561 features to 200 components. The results reveal that Voting Classifier-II (a combination of SVM, KNN, and LR) using soft voting outperformed other machine learning classifiers.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81284627","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 : 2022-06-22DOI: 10.48129/kjs.splml.18993
S. Mittal, C. K. Nagpal
Large volume, random fluctuations and distractive patterns in raw price data lead to overfitting in stock price prediction. Thus research papers in this area suffer from multiple limitations: Very short prediction period from one day to one week, consideration of few stocks only instead of whole of stock market spectrum, exploration of more suitable machine learning algorithms. By overcoming the problems of raw data these limitations can be conquered. Proposed work uses a supervised machine learning approach on statistically learned macro features obtained from gist of input data, free from raw data drawbacks, to predict the price band for the upcoming month and a half for almost all NIFTY50 stocks. The predicted bands are tested for precision in comparison with actual stock price bands. Motivating outcomes so obtained were used for automated sensing of opportunity to make buy / sell / wait decision using fuzzy logic. The results show that the price bands are quite accurate with reasonable tolerance. Monetization capability of the predicted bands has also been enhanced by using an opportunity controller k.
{"title":"A predictive analytics framework for opportunity sensing in stock market","authors":"S. Mittal, C. K. Nagpal","doi":"10.48129/kjs.splml.18993","DOIUrl":"https://doi.org/10.48129/kjs.splml.18993","url":null,"abstract":"Large volume, random fluctuations and distractive patterns in raw price data lead to overfitting in stock price prediction. Thus research papers in this area suffer from multiple limitations: Very short prediction period from one day to one week, consideration of few stocks only instead of whole of stock market spectrum, exploration of more suitable machine learning algorithms. By overcoming the problems of raw data these limitations can be conquered. Proposed work uses a supervised machine learning approach on statistically learned macro features obtained from gist of input data, free from raw data drawbacks, to predict the price band for the upcoming month and a half for almost all NIFTY50 stocks. The predicted bands are tested for precision in comparison with actual stock price bands. Motivating outcomes so obtained were used for automated sensing of opportunity to make buy / sell / wait decision using fuzzy logic. The results show that the price bands are quite accurate with reasonable tolerance. Monetization capability of the predicted bands has also been enhanced by using an opportunity controller k.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75733766","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 : 2022-06-22DOI: 10.48129/kjs.splml.19571
Derya Birant, Emircan Tepe
Using big data-assisted machine learning methods in animal science has received increasing attention in recent years since they extract useful insights from large-scale animal datasets. Especially, animal activity recognition is the task of identifying the actions performed by animals and can provide rich insight into their health, welfare, reproduction, survival, foraging, and interaction with humans/other animals. This paper aims to propose a new solution for this purpose by building a machine learning model that classifies the actions of horses based on big sensor data. Unlike the previous studies, our study is original in that it compares the accuracies of per-subject (personalized) and cross-subject (generalized) models. It is the first study that especially compares different ensemble learning algorithms for horse activity recognition in terms of classification accuracy, including bagging trees, extremely randomized trees, random forest, extreme gradient boosting, light gradient boosting, gradient boosting, and categorical boosting. The purpose of the study is to classify five horse activities: walking, standing, grazing, galloping, and trotting. The experimental results showed that our solution achieved very good performance (94.62%) on average on a real-world dataset. Furthermore, the results also showed that our method outperformed the state-of-the-art methods on the same dataset.
{"title":"Classifying horse activities with big data using machine learning","authors":"Derya Birant, Emircan Tepe","doi":"10.48129/kjs.splml.19571","DOIUrl":"https://doi.org/10.48129/kjs.splml.19571","url":null,"abstract":"Using big data-assisted machine learning methods in animal science has received increasing attention in recent years since they extract useful insights from large-scale animal datasets. Especially, animal activity recognition is the task of identifying the actions performed by animals and can provide rich insight into their health, welfare, reproduction, survival, foraging, and interaction with humans/other animals. This paper aims to propose a new solution for this purpose by building a machine learning model that classifies the actions of horses based on big sensor data. Unlike the previous studies, our study is original in that it compares the accuracies of per-subject (personalized) and cross-subject (generalized) models. It is the first study that especially compares different ensemble learning algorithms for horse activity recognition in terms of classification accuracy, including bagging trees, extremely randomized trees, random forest, extreme gradient boosting, light gradient boosting, gradient boosting, and categorical boosting. The purpose of the study is to classify five horse activities: walking, standing, grazing, galloping, and trotting. The experimental results showed that our solution achieved very good performance (94.62%) on average on a real-world dataset. Furthermore, the results also showed that our method outperformed the state-of-the-art methods on the same dataset.","PeriodicalId":49933,"journal":{"name":"Kuwait Journal of Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80621742","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：