Pub Date : 2023-06-27DOI: 10.3991/ijoe.v19i08.39661
Genc Hamzaj, Artan Mazrekaj, Isak Shabani
The quality of the data in core electronic registers has constantly decreased as a result of numerous errors that were made and inconsistencies in the data in these databases due to the growing number of databases created with the intention of providing electronic services for public administration and the lack of the data harmonization or interoperability between these databases.Evaluating and improving the quality of data by matching and linking records from multiple data sources becomes exceedingly difficult due to the incredibly large volume of data in these numerous data sources with different data architectures and no unique field to create interconnection among them.Different algorithms are developed to treat these issues and our focus will be on algorithms that handle large amounts of data, such as Levenshtein distance (LV) algorithm and Damerau-Levenshtein distance (DL) algorithm.In order to analyze and evaluate the effectiveness and quality of data using the mentioned algorithms and making improvements to these algorithms, through this paper we will conduct experiments on large data sets with more than 1 million records.
{"title":"Applying Optimized Algorithms and Technology for Interconnecting Big Data Resources in Government Institutions","authors":"Genc Hamzaj, Artan Mazrekaj, Isak Shabani","doi":"10.3991/ijoe.v19i08.39661","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.39661","url":null,"abstract":"The quality of the data in core electronic registers has constantly decreased as a result of numerous errors that were made and inconsistencies in the data in these databases due to the growing number of databases created with the intention of providing electronic services for public administration and the lack of the data harmonization or interoperability between these databases.Evaluating and improving the quality of data by matching and linking records from multiple data sources becomes exceedingly difficult due to the incredibly large volume of data in these numerous data sources with different data architectures and no unique field to create interconnection among them.Different algorithms are developed to treat these issues and our focus will be on algorithms that handle large amounts of data, such as Levenshtein distance (LV) algorithm and Damerau-Levenshtein distance (DL) algorithm.In order to analyze and evaluate the effectiveness and quality of data using the mentioned algorithms and making improvements to these algorithms, through this paper we will conduct experiments on large data sets with more than 1 million records.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47827407","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 : 2023-06-27DOI: 10.3991/ijoe.v19i08.39853
M’barek Iaousse, Youness Jouilil, Mohamed Bouincha, D. Mentagui
This manuscript presents a simulation comparison of statistical classical methods and machine learning algorithms for time series forecasting notably the ARIMA model, K-Nearest Neighbors (KNN), The support Vector Regression (SVR), and Long-Short Term Memory (LSTM). The performance of the models was evaluated using different metrics especially Mean Squared Error (MSE), Mean Absolute Error (MAE), Median Absolute Error (Median AE), and Root Mean Squared Error (RMSE). The results of the simulations approve that KNN algorithm has better accuracy than the others models’ forecasting notably in the middle and long terms. The MAPE for the KNN model was around 4.976843 while SVR and LSTM architectures had a MAPE of 6.810311 and 13.992133 respectively. In the medium and long term, ML models are so powerful on big datasets. Paradoxically, Machine learning architectures outperform ARIMA for shorter-term predictions. Thus, ARIMA is most appropriate in the case of univariate small data sets, where deep learning algorithms are not yet at their best.
{"title":"Comparative Simulation Study of Classical and Machine Learning Techniques for Forecasting Time Series Data","authors":"M’barek Iaousse, Youness Jouilil, Mohamed Bouincha, D. Mentagui","doi":"10.3991/ijoe.v19i08.39853","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.39853","url":null,"abstract":"This manuscript presents a simulation comparison of statistical classical methods and machine learning algorithms for time series forecasting notably the ARIMA model, K-Nearest Neighbors (KNN), The support Vector Regression (SVR), and Long-Short Term Memory (LSTM). The performance of the models was evaluated using different metrics especially Mean Squared Error (MSE), Mean Absolute Error (MAE), Median Absolute Error (Median AE), and Root Mean Squared Error (RMSE). The results of the simulations approve that KNN algorithm has better accuracy than the others models’ forecasting notably in the middle and long terms. The MAPE for the KNN model was around 4.976843 while SVR and LSTM architectures had a MAPE of 6.810311 and 13.992133 respectively. In the medium and long term, ML models are so powerful on big datasets. Paradoxically, Machine learning architectures outperform ARIMA for shorter-term predictions. Thus, ARIMA is most appropriate in the case of univariate small data sets, where deep learning algorithms are not yet at their best.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45542272","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 : 2023-06-27DOI: 10.3991/ijoe.v19i08.39881
Faten Imad Ali, Mais Al-Saffar, Noor Ali Sadek
Anesthesia is critical in medical procedures to ensure the patient's body remains stable and unresponsive during surgery. However, administering the correct dose can be challenging, particularly in prolonged surgeries. An auto-controlled system that incorporates vital sensors and a microprocessor controller has been proposed to address this issue. This system uses an infusion pump to provide the correct amount of anesthetic based on the patient's vital signs. The microprocessor takes control of the system once initiated and signals the motor driver to start injecting the required amount of anesthesia while monitoring vital signs such as temperature, heartbeat, and Spo2. The system alerts the doctor if any abnormality is detected, and the supply of anesthetic is stopped until everything returns to normal. This system ensures accurate anesthetic dosage, minimizing the risk of complications and ensuring a safe surgical procedure.
{"title":"Design of an Adaptive State Anesthesia Feedback Controller","authors":"Faten Imad Ali, Mais Al-Saffar, Noor Ali Sadek","doi":"10.3991/ijoe.v19i08.39881","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.39881","url":null,"abstract":"Anesthesia is critical in medical procedures to ensure the patient's body remains stable and unresponsive during surgery. However, administering the correct dose can be challenging, particularly in prolonged surgeries. An auto-controlled system that incorporates vital sensors and a microprocessor controller has been proposed to address this issue. This system uses an infusion pump to provide the correct amount of anesthetic based on the patient's vital signs. The microprocessor takes control of the system once initiated and signals the motor driver to start injecting the required amount of anesthesia while monitoring vital signs such as temperature, heartbeat, and Spo2. The system alerts the doctor if any abnormality is detected, and the supply of anesthetic is stopped until everything returns to normal. This system ensures accurate anesthetic dosage, minimizing the risk of complications and ensuring a safe surgical procedure.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44938143","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 : 2023-06-27DOI: 10.3991/ijoe.v19i08.39433
Hamza Abu Owida, Bashar Al-haj Moh'd, Nidal M. Turab, J. Al-Nabulsi, Suhaila Abuowaida
It is no secret that the rise of the Internet and other digital technologies has sparked renewed interest in AI-based techniques, especially those that fall under the umbrella of the subset of algorithms known as "Machine Learning" (ML). These advancements in electronics have allowed us to comprehend the world beyond the bounds of human cognition. A high-dimensional dataset's complicated nature. Although these techniques have been regularly employed by the medical sciences, their adoption to enhance patient care has been a bit slow. The availability of curated diverse data sets for model development is all examples of the substantial hurdles that have delayed these efforts. The future clinical acceptance of each of these characteristics may be affected by a number of limiting conditions, such as the time and resources spent on data collection and model development, the cost of integration relative to the time and resources spent on translation, and the potential for patient damage. In order to preserve value and enhance medical care, the goal of this article is to evaluate all facets of the issue in light of the validity of using ML methods in cancer, to serve as a template for further research and the subfield of oncology that serves as a model for other parts of the discipline.
{"title":"The Evolution and Reliability of Machine Learning Techniques for Oncology","authors":"Hamza Abu Owida, Bashar Al-haj Moh'd, Nidal M. Turab, J. Al-Nabulsi, Suhaila Abuowaida","doi":"10.3991/ijoe.v19i08.39433","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.39433","url":null,"abstract":"It is no secret that the rise of the Internet and other digital technologies has sparked renewed interest in AI-based techniques, especially those that fall under the umbrella of the subset of algorithms known as \"Machine Learning\" (ML). \u0000These advancements in electronics have allowed us to comprehend the world beyond the bounds of human cognition. A high-dimensional dataset's complicated nature. Although these techniques have been regularly employed by the medical sciences, their adoption to enhance patient care has been a bit slow. The availability of curated diverse data sets for model development is all examples of the substantial hurdles that have delayed these efforts. The future clinical acceptance of each of these characteristics may be affected by a number of limiting conditions, such as the time and resources spent on data collection and model development, the cost of integration relative to the time and resources spent on translation, and the potential for patient damage. In order to preserve value and enhance medical care, the goal of this article is to evaluate all facets of the issue in light of the validity of using ML methods in cancer, to serve as a template for further research and the subfield of oncology that serves as a model for other parts of the discipline.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44990808","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 : 2023-06-27DOI: 10.3991/ijoe.v19i08.38781
Alejandro Astudillo, Edna Avella-Rodríguez, Gloria Arango-Hoyos, J. Ramirez-Scarpetta, Esteban Rosero
This paper presents a wearable virtual reality system with a wireless network of inertial sensors for lower limb monitoring. The system comprises seven sensor nodes sending data wirelessly to a master node. The information is then collected, organized, and sent to a screening device via a serial interface. An application executed either on a smartphone or a personal computer features an avatar which represents the received data and mimics the sensed movements of the patient, providing online feedback during and after the execution of a therapy. The data resulting from the therapy execution can be uploaded to a web server to facilitate the assessment and decision-making by health professionals. A pendulum featuring a rotary optical encoder is used for sensor functional behavior validation. In addition, the orientation angles measured by the proposed system are compared with respect to measurements from the motion analysis software Kinovea. The delay between the patient's body movement and the avatar is 33 ms, which is acceptable for visual feedback. This system is portable, inexpensive and enables a patient to complete physical therapy sessions at home or anywhere, with the advantage of enabling visual feedback through an avatar during rehabilitation therapy and allowing the reproduction of a therapy session for further analysis.
{"title":"Smartphone-Based Wearable Gait Monitoring System Using Wireless Inertial Sensors","authors":"Alejandro Astudillo, Edna Avella-Rodríguez, Gloria Arango-Hoyos, J. Ramirez-Scarpetta, Esteban Rosero","doi":"10.3991/ijoe.v19i08.38781","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.38781","url":null,"abstract":"This paper presents a wearable virtual reality system with a wireless network of inertial sensors for lower limb monitoring. The system comprises seven sensor nodes sending data wirelessly to a master node. The information is then collected, organized, and sent to a screening device via a serial interface. An application executed either on a smartphone or a personal computer features an avatar which represents the received data and mimics the sensed movements of the patient, providing online feedback during and after the execution of a therapy. The data resulting from the therapy execution can be uploaded to a web server to facilitate the assessment and decision-making by health professionals. A pendulum featuring a rotary optical encoder is used for sensor functional behavior validation. In addition, the orientation angles measured by the proposed system are compared with respect to measurements from the motion analysis software Kinovea. The delay between the patient's body movement and the avatar is 33 ms, which is acceptable for visual feedback. This system is portable, inexpensive and enables a patient to complete physical therapy sessions at home or anywhere, with the advantage of enabling visual feedback through an avatar during rehabilitation therapy and allowing the reproduction of a therapy session for further analysis.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42227247","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 : 2023-06-27DOI: 10.3991/ijoe.v19i08.37417
Anas Domyati, Q. Memon
One of the hardest jobs in medicine is to predict when someone will have a heart attack. Given how challenging it is to anticipate heart attack, there is an urgent need to automate the prediction process using diagnostic data, and at the very least generate an early warning. This research makes a contribution by making it easier to diagnose cardiac problems using machine learning methods applied on the well-known Cleveland heart disease dataset. Several performance indicators are utilized to evaluate each model's strength. It turns out that support vector machine and random forest produced some incredibly promising outcomes. An improved prediction of heart disease for an embedded platform is, thus, proposed, based on the computational complexity of each model and experimental results, where the advantages of several classifiers are accumulated. The approach suggests that, and only if, more than one of these classifiers detect heart disease, the detection of heart illness is possible with increased confidence. In the end, experimental findings are drawn to a conclusion, with potential future options for advancing this effort.
{"title":"Machine Learning Based Improved Heart Disease Detection with Confidence","authors":"Anas Domyati, Q. Memon","doi":"10.3991/ijoe.v19i08.37417","DOIUrl":"https://doi.org/10.3991/ijoe.v19i08.37417","url":null,"abstract":"One of the hardest jobs in medicine is to predict when someone will have a heart attack. Given how challenging it is to anticipate heart attack, there is an urgent need to automate the prediction process using diagnostic data, and at the very least generate an early warning. This research makes a contribution by making it easier to diagnose cardiac problems using machine learning methods applied on the well-known Cleveland heart disease dataset. Several performance indicators are utilized to evaluate each model's strength. It turns out that support vector machine and random forest produced some incredibly promising outcomes. An improved prediction of heart disease for an embedded platform is, thus, proposed, based on the computational complexity of each model and experimental results, where the advantages of several classifiers are accumulated. The approach suggests that, and only if, more than one of these classifiers detect heart disease, the detection of heart illness is possible with increased confidence. In the end, experimental findings are drawn to a conclusion, with potential future options for advancing this effort.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46623336","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 : 2023-06-13DOI: 10.3991/ijoe.v19i07.40161
Saleh Hamad Sajaan Almansour, Rahul Singh, S. M. Alyami, N. Sharma, Mana Saleh Al Reshan, Sheifali Gupta, Mahdi Falah Mahdi Alyami, A. Shaikh
Knee osteoarthritis (OA) is a chronic degenerative joint disease affecting millions worldwide, particularly those over 60. It is a significant cause of disability and can impact an individual's quality of life. The condition occurs when the cartilage in the knee joint wears away over time, leading to bone-on-bone contact, which can result in pain, stiffness, swelling, and decreased range of motion. Deep neural networks, especially convolutional neural networks (CNN), are powerful tools in medical applications such as diagnosis and detection. This research proposes a CNN model to classify knee osteoarthritis into five categories using x-ray images. These classes are labeled: Minimal, Healthy, Moderate, Doubtful, and Severe. Furthermore, the proposed CNN model has been compared with two pre-trained transfer learning models: Xception and InceptionResNet V2. These models were evaluated based on precision, recall, F1 score, and accuracy. The results showed that although all three models performed very well, the proposed model outperformed both transfer learning models with 98% accuracy. It also achieved the highest values for other parameters such as precision, recall, and F1 score. The proposed model has several potential applications in clinical practice, such as assisting doctors in accurately classifying knee osteoarthritis severity levels by analyzing single X-ray images.
{"title":"A Convolution Neural Network Design for Knee Osteoarthritis Diagnosis Using X-ray Images","authors":"Saleh Hamad Sajaan Almansour, Rahul Singh, S. M. Alyami, N. Sharma, Mana Saleh Al Reshan, Sheifali Gupta, Mahdi Falah Mahdi Alyami, A. Shaikh","doi":"10.3991/ijoe.v19i07.40161","DOIUrl":"https://doi.org/10.3991/ijoe.v19i07.40161","url":null,"abstract":"Knee osteoarthritis (OA) is a chronic degenerative joint disease affecting millions worldwide, particularly those over 60. It is a significant cause of disability and can impact an individual's quality of life. The condition occurs when the cartilage in the knee joint wears away over time, leading to bone-on-bone contact, which can result in pain, stiffness, swelling, and decreased range of motion. Deep neural networks, especially convolutional neural networks (CNN), are powerful tools in medical applications such as diagnosis and detection. This research proposes a CNN model to classify knee osteoarthritis into five categories using x-ray images. These classes are labeled: Minimal, Healthy, Moderate, Doubtful, and Severe. Furthermore, the proposed CNN model has been compared with two pre-trained transfer learning models: Xception and InceptionResNet V2. These models were evaluated based on precision, recall, F1 score, and accuracy. The results showed that although all three models performed very well, the proposed model outperformed both transfer learning models with 98% accuracy. It also achieved the highest values for other parameters such as precision, recall, and F1 score. The proposed model has several potential applications in clinical practice, such as assisting doctors in accurately classifying knee osteoarthritis severity levels by analyzing single X-ray images.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48386574","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 : 2023-06-13DOI: 10.3991/ijoe.v19i07.39187
Israa Abdullah, Wrya Monnet
The Tactile Internet (TI) can be regarded as the next evolution in the world of communication. With its envisioned purpose and potential in shaping up the economy, industry and society, this paradigm aims to bring a new dimension to life by enabling humans to interact with machines remotely and in real-time with haptic and kinesthetic feedback. However, to translate this into reality, Tactile Internet will need to meet the stringent requirements of extremely low latency in conjunction with ultra-high reliability, availability, and security. This poses a challenge on the available communication systems to achieve a round-trip delay within 1 to 10 milliseconds time bound that enables the timely delivery of critical tactile and haptic sensations. This paper aims to evaluate the Real-Time Transport Protocol (RTP) through an emulation framework. It integrates containerization using Linux-based Docker Containers with NS-3 Network Simulator to conceptualize a haptic teleoperation system. The framework is then used to test the protocol’s feasibility for delivering texture haptic data between master and slave domains in accordance with the end-to-end delay requirements specified by IEEE 1918.1 standards. The results have shown that the timely provision of haptic data is achievable by obtaining an average round-trip delay of 17.8493 ms from the emulation experiment. As such, the results satisfy the expected IEEE 1918.1 standards constraints for medium-dynamic environment use cases.
{"title":"Emulation Framework for Haptic Data Transmission Using Real-Time Transport Protocol","authors":"Israa Abdullah, Wrya Monnet","doi":"10.3991/ijoe.v19i07.39187","DOIUrl":"https://doi.org/10.3991/ijoe.v19i07.39187","url":null,"abstract":"The Tactile Internet (TI) can be regarded as the next evolution in the world of communication. With its envisioned purpose and potential in shaping up the economy, industry and society, this paradigm aims to bring a new dimension to life by enabling humans to interact with machines remotely and in real-time with haptic and kinesthetic feedback. However, to translate this into reality, Tactile Internet will need to meet the stringent requirements of extremely low latency in conjunction with ultra-high reliability, availability, and security. This poses a challenge on the available communication systems to achieve a round-trip delay within 1 to 10 milliseconds time bound that enables the timely delivery of critical tactile and haptic sensations. \u0000This paper aims to evaluate the Real-Time Transport Protocol (RTP) through an emulation framework. It integrates containerization using Linux-based Docker Containers with NS-3 Network Simulator to conceptualize a haptic teleoperation system. The framework is then used to test the protocol’s feasibility for delivering texture haptic data between master and slave domains in accordance with the end-to-end delay requirements specified by IEEE 1918.1 standards. The results have shown that the timely provision of haptic data is achievable by obtaining an average round-trip delay of 17.8493 ms from the emulation experiment. As such, the results satisfy the expected IEEE 1918.1 standards constraints for medium-dynamic environment use cases.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47036755","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 : 2023-06-13DOI: 10.3991/ijoe.v19i07.38869
Ali Abid Hussan Altalbi, Shaimaa Hameed Shaker, Akbas Ezaldeen Ali
Anomaly detection, which is also referred to as novelty detection or outlier detection, is process of identifying unusual occurrences, observations, or events which considerably differ from the bulk of data and do not fit a predetermined definition of typical behavior. Medicine, cybersecurity, statistics, machine vision, law enforcement, neurology, and financial fraud are just a handful of the industries where anomaly detection is used. In the presented study, an online tool is utilized to identify crowd distortions, which could be brought on by panic. An activity map is produced with the use of numerous frames to show the continuity regarding the flow over time following the global optical flow has been calculated in the quickest time and with the highest precision possible utilizing the Farneback approach to calculate the magnitudes. Utilizing a specific threshold, the oddity in the video will be picked up by the activity map's generation of an entropy. The results indicate that the maximum entropy level for indoor video is <0.16 and the maximum entropy level for outdoor video is >0.45. A threshold of 0.04 is used to determine whether a frame is abnormal or normal.
{"title":"Localization of Strangeness for Real Time Video in Crowd Activity Using Optical Flow and Entropy","authors":"Ali Abid Hussan Altalbi, Shaimaa Hameed Shaker, Akbas Ezaldeen Ali","doi":"10.3991/ijoe.v19i07.38869","DOIUrl":"https://doi.org/10.3991/ijoe.v19i07.38869","url":null,"abstract":"Anomaly detection, which is also referred to as novelty detection or outlier detection, is process of identifying unusual occurrences, observations, or events which considerably differ from the bulk of data and do not fit a predetermined definition of typical behavior. Medicine, cybersecurity, statistics, machine vision, law enforcement, neurology, and financial fraud are just a handful of the industries where anomaly detection is used. In the presented study, an online tool is utilized to identify crowd distortions, which could be brought on by panic. An activity map is produced with the use of numerous frames to show the continuity regarding the flow over time following the global optical flow has been calculated in the quickest time and with the highest precision possible utilizing the Farneback approach to calculate the magnitudes. Utilizing a specific threshold, the oddity in the video will be picked up by the activity map's generation of an entropy. The results indicate that the maximum entropy level for indoor video is <0.16 and the maximum entropy level for outdoor video is >0.45. A threshold of 0.04 is used to determine whether a frame is abnormal or normal.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44852497","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 : 2023-06-13DOI: 10.3991/ijoe.v19i07.39089
K. Rajeswari, Sushma Vispute, Amulya Maitre, Reena Kharat, Amruta Aher, N. Vivekanandan, Renu Kachoria, Swati Jaiswal
Coronavirus 2 virus is responsible for the spread of the infectious disease COVID-19 (also known as Coronavirus disease). People around the globe who got infected with the virus experienced a respiratory illness that could become as serious as leading someone to lose their life. However, the upside of the pandemic is that it has led to numerous types of research and explorations, majorly in the medical science field. Since a systematic survey of previous research activities and bibliometric analysis gives a brief idea about such contributions and acts as a reference to future research, this study aims to cover the research related to COVID-19 in the computer technology domain. It is limited to the works accepted and accessible with the keywords - Covid-19, prediction, and pandemic, in the Scopus search engine to justify the scope of this survey. Further, the paper highlights a few prior works used for predictive analysis and presents a quantitative angle on their algorithms. Earlier works showcase Time Series Analysis using ARIMA/SARIMA models for predicting the vaccination rates, and Extreme Gradient Boosting (XGBoost), Xtremely Boosted Network (XBNet) Regression, and Recurrent Neural Network (RNN) for Confirmed, Cured, and Death cases. Amongst the algorithms used in the latter use case, XBNet regression performed better than XGBoost regressor.
{"title":"Time Series Analysis with Systematic Survey on Covid-19 Based Predictive Studies During Pandemic Period using Enhanced Machine Learning Techniques","authors":"K. Rajeswari, Sushma Vispute, Amulya Maitre, Reena Kharat, Amruta Aher, N. Vivekanandan, Renu Kachoria, Swati Jaiswal","doi":"10.3991/ijoe.v19i07.39089","DOIUrl":"https://doi.org/10.3991/ijoe.v19i07.39089","url":null,"abstract":"Coronavirus 2 virus is responsible for the spread of the infectious disease COVID-19 (also known as Coronavirus disease). People around the globe who got infected with the virus experienced a respiratory illness that could become as serious as leading someone to lose their life. However, the upside of the pandemic is that it has led to numerous types of research and explorations, majorly in the medical science field. Since a systematic survey of previous research activities and bibliometric analysis gives a brief idea about such contributions and acts as a reference to future research, this study aims to cover the research related to COVID-19 in the computer technology domain. It is limited to the works accepted and accessible with the keywords - Covid-19, prediction, and pandemic, in the Scopus search engine to justify the scope of this survey. Further, the paper highlights a few prior works used for predictive analysis and presents a quantitative angle on their algorithms. Earlier works showcase Time Series Analysis using ARIMA/SARIMA models for predicting the vaccination rates, and Extreme Gradient Boosting (XGBoost), Xtremely Boosted Network (XBNet) Regression, and Recurrent Neural Network (RNN) for Confirmed, Cured, and Death cases. Amongst the algorithms used in the latter use case, XBNet regression performed better than XGBoost regressor.","PeriodicalId":36900,"journal":{"name":"International Journal of Online and Biomedical Engineering","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49646148","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：