Pub Date : 2023-07-30DOI: 10.12694/scpe.v24i2.2081
Preksha Pareek, Ruchi Jayaswal, S. Patil, Kishan Vyas
The medical field in itself is a complex term where the diagnosis is of the most importance. If there is a correct diagnosis made on time in the appropriate time duration then the treatment can be started in a timely manner and this treatment will be beneficial in curing the patient. There are many different techniques that are available to find the abnormalities in an image given but we will review some of them which are most recently developed and will compare the results of each of them. A detailed study is done at the end of this paper which gives insights into fractures and their types. The dataset which we would consider is the MURA dataset. Discussion about further research in this area is also done to help researchers in exploring new dimensions in this field.
{"title":"A Bone Fracture Detection using AI-Based Techniques","authors":"Preksha Pareek, Ruchi Jayaswal, S. Patil, Kishan Vyas","doi":"10.12694/scpe.v24i2.2081","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2081","url":null,"abstract":"The medical field in itself is a complex term where the diagnosis is of the most importance. If there is a correct diagnosis made on time in the appropriate time duration then the treatment can be started in a timely manner and this treatment will be beneficial in curing the patient. There are many different techniques that are available to find the abnormalities in an image given but we will review some of them which are most recently developed and will compare the results of each of them. A detailed study is done at the end of this paper which gives insights into fractures and their types. The dataset which we would consider is the MURA dataset. Discussion about further research in this area is also done to help researchers in exploring new dimensions in this field.\u0000 ","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76558913","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 : 2023-07-30DOI: 10.12694/scpe.v24i2.2146
Ling Wang
In order to meet the requirements of computer hardware and network data transmission security, a research based on Internet of Things communication technology is proposed. The main content of this research is the research based on the communication technology of the Internet of Things, through the description of the communication protocol of the Internet of Things, the system hardware design and implementation methods are used, and finally the research method based on the communication technology of the Internet of Things is constructed through experiments and analysis. The core technologies of 5G connectivity are being used to construct the IOT. As a result, the IOT might gain momentum. The experimental findings demonstrate that the delays are all within 200 Ms. When the message size is short (within 1KB), the transmission of diverse hardware is average, and the transmission quality standards of QoS1 are fulfilled. The transmission quality standards of QoS1 can match the communication reliability and security needs of the Internet of Things. This article evaluates the performance of data transfers with lengths of 20 byte, 30 byte, 50 byte, and 70 byte, respectively. This paper evaluates the efficiency of Wi-Fi access configuration by sending data packets of varying sizes i.e., 10 bytes, 30 bytes, 50 bytes, and 70 bytes over a distribution network. The results show that, on average, the network takes 0.6692s, 1.3546s, 2.8600s, and 4.7319s to deliver each packet, with success rates of 100% in each case. The system's increased network distribution efficiency is observed from the experimentation. The research based on the Internet of Things communication technology can meet the needs of computer hardware and network data transmission security.
{"title":"Computer Hardware and Network Data Transmission based on Internet of Things Communication Technology","authors":"Ling Wang","doi":"10.12694/scpe.v24i2.2146","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2146","url":null,"abstract":"In order to meet the requirements of computer hardware and network data transmission security, a research based on Internet of Things communication technology is proposed. The main content of this research is the research based on the communication technology of the Internet of Things, through the description of the communication protocol of the Internet of Things, the system hardware design and implementation methods are used, and finally the research method based on the communication technology of the Internet of Things is constructed through experiments and analysis. The core technologies of 5G connectivity are being used to construct the IOT. As a result, the IOT might gain momentum. The experimental findings demonstrate that the delays are all within 200 Ms. When the message size is short (within 1KB), the transmission of diverse hardware is average, and the transmission quality standards of QoS1 are fulfilled. The transmission quality standards of QoS1 can match the communication reliability and security needs of the Internet of Things. This article evaluates the performance of data transfers with lengths of 20 byte, 30 byte, 50 byte, and 70 byte, respectively. This paper evaluates the efficiency of Wi-Fi access configuration by sending data packets of varying sizes i.e., 10 bytes, 30 bytes, 50 bytes, and 70 bytes over a distribution network. The results show that, on average, the network takes 0.6692s, 1.3546s, 2.8600s, and 4.7319s to deliver each packet, with success rates of 100% in each case. The system's increased network distribution efficiency is observed from the experimentation. The research based on the Internet of Things communication technology can meet the needs of computer hardware and network data transmission security.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79177278","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 : 2023-07-30DOI: 10.12694/scpe.v24i2.2249
S. Ziyad, May S. Altulyan, Liakathunisa, Meshal S Alharbi
Promising technologies such as sensors, networking, and edge have led to many smart healthcare solutions to monitor and track patient health status. The health sector is now experiencing a significant transformation from conventional patient care to a smart healthcare environment. Smart health care allows medical professionals to monitor patients remotely and visualize the disease prognosis effectively. The Internet of medical things connect patients, doctors, and medical equipment via wireless networking technologies to process the data with Artificial Intelligence models. One of the domains of automated health care systems is to alert the caregivers and hospital on emergency conditions. This research study is a novel work that aims to help the caregivers of somnambulism patients attend to them in case of emergency. Sleep quality improves the health and work efficiency of any person. The caregivers of sleepwalking patients suffer from lack of sleep as the patient gets active during the night hours. The model is based on fall detection and sleep detection from wearable sensor data. The fall detection model includes feature selection by LASSO and classification by ensemble classifier. The proposed methodology shows improved performance for the fall detection model for all ensemble machine learning classifiers.
{"title":"Accident Attention System for Somnambulism Patients","authors":"S. Ziyad, May S. Altulyan, Liakathunisa, Meshal S Alharbi","doi":"10.12694/scpe.v24i2.2249","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2249","url":null,"abstract":"Promising technologies such as sensors, networking, and edge have led to many smart healthcare solutions to monitor and track patient health status. The health sector is now experiencing a significant transformation from conventional patient care to a smart healthcare environment. Smart health care allows medical professionals to monitor patients remotely and visualize the disease prognosis effectively. The Internet of medical things connect patients, doctors, and medical equipment via wireless networking technologies to process the data with Artificial Intelligence models. One of the domains of automated health care systems is to alert the caregivers and hospital on emergency conditions. This research study is a novel work that aims to help the caregivers of somnambulism patients attend to them in case of emergency. Sleep quality improves the health and work efficiency of any person. The caregivers of sleepwalking patients suffer from lack of sleep as the patient gets active during the night hours. The model is based on fall detection and sleep detection from wearable sensor data. The fall detection model includes feature selection by LASSO and classification by ensemble classifier. The proposed methodology shows improved performance for the fall detection model for all ensemble machine learning classifiers.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72893486","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 : 2023-07-30DOI: 10.12694/scpe.v24i2.2102
P. Oza, Smita Agrawal, Dhruv Ravaliya, Riya Kakkar
Complex networks are an essential tool in machine learning and data mining. The underlying information can help understand the system and reveal new information. Community is sub-groups in networks that are densely connected. This community can help us reveal a lot of information. The community detection problem is a method to find communities in the network. The igraph library is used by many researchers due to the utilization of various community detection algorithms implemented in both Python and R language. The algorithms are implemented using various methods showing various performance results. We have evaluated the community detection algorithm and ranked it based on its performance in different scenarios and various performance metrics. The results show that the Multi-level, Leiden community detection algorithm, and Walk trap got the highest performance compared to spin glass and leading eigenvector algorithms. The findings based on these algorithms help researchers to choose algorithms from the igraph library according to their requirements.
{"title":"Evaluating the Igraph Community Detection Algorithms on Different Real Networks","authors":"P. Oza, Smita Agrawal, Dhruv Ravaliya, Riya Kakkar","doi":"10.12694/scpe.v24i2.2102","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2102","url":null,"abstract":"Complex networks are an essential tool in machine learning and data mining. The underlying information can help understand the system and reveal new information. Community is sub-groups in networks that are densely connected. This community can help us reveal a lot of information. The community detection problem is a method to find communities in the network. The igraph library is used by many researchers due to the utilization of various community detection algorithms implemented in both Python and R language. The algorithms are implemented using various methods showing various performance results. We have evaluated the community detection algorithm and ranked it based on its performance in different scenarios and various performance metrics. The results show that the Multi-level, Leiden community detection algorithm, and Walk trap got the highest performance compared to spin glass and leading eigenvector algorithms. The findings based on these algorithms help researchers to choose algorithms from the igraph library according to their requirements.\u0000 ","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81837604","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 : 2023-07-30DOI: 10.12694/scpe.v24i2.2078
Garima Vijh, Swati Agrawal, Richa Sharma
The foundation of smart cities is based on an autonomous and decentralized architecture, which consists of sophisticated information and communication technologies (ICT) in convergence with technology enabled solution to improve the business management process in industry 4.0. This study tends to examine the adoption of blockchain technologies (DLT) in the human resource management (HRM) of organizations in building solutions for IOT (Internet of things) smart cities. The current study explores a unique set of factors selected from the extensive literature and acquired information from fifteen experts having significant experience of blockchain technology in their respective organizations. An integrated fuzzy analytic hierarchy process (F-AHP) is applied to prioritize the identified success factors. Further, the modified decision-making trial and evaluation laboratory (M-DEMATEL) method is utilized to represent the complicated causal relationships among different sub-factors on blockchain-HRM integration. The findings show the application of blockchain will foster a paradigm change in IOT based smart communities, where recruiters verify the candidate credentials including education, skills, and work experience. The payroll managers would determine the more effective way to make work less complex and moderate, enabling timelier payments to global employees. Furthermore, DLT would enhance the employee learning records and update the real-time information in HRM database technologies. Thus, providing a detailed guide for future Industry 4.0 developers about how blockchain can improve the next generation of industrial applications. The developed method can help the decision-makers and provide a foundational view to examine the benefits of implementing blockchain technology in the HRM setting of an organization before they choose to integrate in order to enhance Industry 4.0 technologies. This research will be a novel attempt to synthesize the key factors and subfactors about technology enabled solution within the intelligent HRM process, shedding light to rethink HRM strategies to incorporate blockchain technology in organizations.
{"title":"Technology Enabled Intelligent Solution in Human Resource Management for Smart Cities","authors":"Garima Vijh, Swati Agrawal, Richa Sharma","doi":"10.12694/scpe.v24i2.2078","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2078","url":null,"abstract":"The foundation of smart cities is based on an autonomous and decentralized architecture, which consists of sophisticated information and communication technologies (ICT) in convergence with technology enabled solution to improve the business management process in industry 4.0. This study tends to examine the adoption of blockchain technologies (DLT) in the human resource management (HRM) of organizations in building solutions for IOT (Internet of things) smart cities.\u0000The current study explores a unique set of factors selected from the extensive literature and acquired information from fifteen experts having significant experience of blockchain technology in their respective organizations. An integrated fuzzy analytic hierarchy process (F-AHP) is applied to prioritize the identified success factors. Further, the modified decision-making trial and evaluation laboratory (M-DEMATEL) method is utilized to represent the complicated causal relationships among different sub-factors on blockchain-HRM integration.\u0000The findings show the application of blockchain will foster a paradigm change in IOT based smart communities, where recruiters verify the candidate credentials including education, skills, and work experience. The payroll managers would determine the more effective way to make work less complex and moderate, enabling timelier payments to global employees. Furthermore, DLT would enhance the employee learning records and update the real-time information in HRM database technologies. Thus, providing a detailed guide for future Industry 4.0 developers about how blockchain can improve the next generation of industrial applications.\u0000The developed method can help the decision-makers and provide a foundational view to examine the benefits of implementing blockchain technology in the HRM setting of an organization before they choose to integrate in order to enhance Industry 4.0 technologies.\u0000This research will be a novel attempt to synthesize the key factors and subfactors about technology enabled solution within the intelligent HRM process, shedding light to rethink HRM strategies to incorporate blockchain technology in organizations.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90806933","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 : 2023-07-30DOI: 10.12694/scpe.v24i2.2117
Praveen Modi, Y. Kumar
The major reason behind the blindness of the diabetes patients is diabetic retinopathy. It can be characterized as an eye disease that affects the retina of eye due to diabetes mellitus. The detection of diabetic retinopathy in early stage is a challenging task to ophthalmologists. This paper presents a diabetic retinopathy detection system for accurate detection of DR in the patients. The proposed diabetic retinopathy detection system is the combination of several preprocessing technique and deep belief nets. The aim of preprocessing technique is to enhance the images, edge detection, and segmentation. Further, the deep belief nets are adopted for the accurate detection of DR. But, the parameter tuning of weight, bias and learning rate have significant impact on the performance of deep belief nets. This work also addresses these issues of deep belief nets though an adaptive learning strategy for learning rate and updated mechanism for weight and bias issues. The proposed system is implemented in cloud environment. It is utilized to store the information regarding DR and communication between doctors and patients. Further, the efficacy of the proposed diabetic retinopathy detection system is tested over an image dataset and it comprises of three thousand two hundred eye images include with diabetes retinopathy and no diabetes retinopathy. The results are evaluated using accuracy, sensitivity, specificity, F1-Score and AUC parameters. The results of proposed system are compared with KNN, SVM, ANN, InceptionV3, VGG16 and VGG19 techniques. The results showed that proposed diabetic retinopathy detection system obtains 91.28% of accuracy, 93.46% of sensitivity, 94.84 of specificity and 94.14 of F1-Score rates than other techniques using 10-cross fold validation method. Hence, it is stated that proposed system detects diabetes retinopathy more accurate than other techniques.
{"title":"An Effective Diabetic Retinopathy Detection System using Deep Belief Nets and Adaptive Learning in Cloud Environment","authors":"Praveen Modi, Y. Kumar","doi":"10.12694/scpe.v24i2.2117","DOIUrl":"https://doi.org/10.12694/scpe.v24i2.2117","url":null,"abstract":"The major reason behind the blindness of the diabetes patients is diabetic retinopathy. It can be characterized as an eye disease that affects the retina of eye due to diabetes mellitus. The detection of diabetic retinopathy in early stage is a challenging task to ophthalmologists. This paper presents a diabetic retinopathy detection system for accurate detection of DR in the patients. The proposed diabetic retinopathy detection system is the combination of several preprocessing technique and deep belief nets. The aim of preprocessing technique is to enhance the images, edge detection, and segmentation. Further, the deep belief nets are adopted for the accurate detection of DR. But, the parameter tuning of weight, bias and learning rate have significant impact on the performance of deep belief nets. This work also addresses these issues of deep belief nets though an adaptive learning strategy for learning rate and updated mechanism for weight and bias issues. The proposed system is implemented in cloud environment. It is utilized to store the information regarding DR and communication between doctors and patients. Further, the efficacy of the proposed diabetic retinopathy detection system is tested over an image dataset and it comprises of three thousand two hundred eye images include with diabetes retinopathy and no diabetes retinopathy. The results are evaluated using accuracy, sensitivity, specificity, F1-Score and AUC parameters. The results of proposed system are compared with KNN, SVM, ANN, InceptionV3, VGG16 and VGG19 techniques. The results showed that proposed diabetic retinopathy detection system obtains 91.28% of accuracy, 93.46% of sensitivity, 94.84 of specificity and 94.14 of F1-Score rates than other techniques using 10-cross fold validation method. Hence, it is stated that proposed system detects diabetes retinopathy more accurate than other techniques.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83254953","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 : 2022-12-24DOI: 10.12694/scpe.v23i4.2010
Abderrahim Bouchair, Belabbas Yagoubi, Sid Ahmed Makhlouf
Network virtualization (NV) has evolved systematically through the urge to share computing resources and improve service deployment in a large-scale environment. Virtual network embedding (VNE) is a well-established technology applied to reinforce the NV process, providing a devoted implementation for a particular case study. In cloud computing, integration of software-defined networking (SDN) has proved to be a practical support to the principal cloud utilities. In return, the SDN-enabled cloud offers innovative deployment techniques for network-based services, which increase the opportunity to efficiently incorporate new network management policies that solve the VNE problem. In this paper, the authors proposed a transition of modern portfolio theory (MPT) into a VNE approach that optimally addresses the selection and ranking of resources in data center networks (DCNs). Results analysis demonstrates the VNE approach's better performance versus similar methods in terms of acceptance ratio, runtime, and substrate resource utilization.
{"title":"A Driven Modern Portfolio Theory for Virtual Network Embedding in SDN-Enabled Cloud","authors":"Abderrahim Bouchair, Belabbas Yagoubi, Sid Ahmed Makhlouf","doi":"10.12694/scpe.v23i4.2010","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2010","url":null,"abstract":"Network virtualization (NV) has evolved systematically through the urge to share computing resources and improve service deployment in a large-scale environment. Virtual network embedding (VNE) is a well-established technology applied to reinforce the NV process, providing a devoted implementation for a particular case study. In cloud computing, integration of software-defined networking (SDN) has proved to be a practical support to the principal cloud utilities. In return, the SDN-enabled cloud offers innovative deployment techniques for network-based services, which increase the opportunity to efficiently incorporate new network management policies that solve the VNE problem. In this paper, the authors proposed a transition of modern portfolio theory (MPT) into a VNE approach that optimally addresses the selection and ranking of resources in data center networks (DCNs). Results analysis demonstrates the VNE approach's better performance versus similar methods in terms of acceptance ratio, runtime, and substrate resource utilization.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74608538","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 : 2022-12-24DOI: 10.12694/scpe.v23i4.2027
Rupal A. Kapdi, Pimal Khanpara, Rohan Modi, M. Gupta
The detection of seat belts is an essential aspect of vehicle safety. It is crucial in providing protection in the event of an accident. Seat belt detection devices are installed into many automobiles, although they may be easily manipulated or disregarded. As a result, the existing approaches and algorithms for seat belt detection are insufficient. Using various external methods and algorithms, it is required to determine if the seat belt is fastened or not. This paper proposes an approach to identify seat belt fastness using the concepts of image processing and deep learning. Our proposed approach can be deployed in any organizational setup to aid the concerned authorities in identifying whether or not the drivers of the vehicles passing through the entrance have buckled their seat belts up. If a seat belt is not detected in a vehicle, the number plate recognition module records the vehicle number. The concerned authorities might use this record to take further necessary actions. This way, the organization authorities can keep track of all the vehicles entering the premises and ensure that all drivers/shotgun seat passengers are wearing seat belts.
{"title":"Image-based Seat Belt Fastness Detection using Deep Learning","authors":"Rupal A. Kapdi, Pimal Khanpara, Rohan Modi, M. Gupta","doi":"10.12694/scpe.v23i4.2027","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2027","url":null,"abstract":"The detection of seat belts is an essential aspect of vehicle safety. It is crucial in providing protection in the event of an accident. Seat belt detection devices are installed into many automobiles, although they may be easily manipulated or disregarded. As a result, the existing approaches and algorithms for seat belt detection are insufficient. Using various external methods and algorithms, it is required to determine if the seat belt is fastened or not. This paper proposes an approach to identify seat belt fastness using the concepts of image processing and deep learning. Our proposed approach can be deployed in any organizational setup to aid the concerned authorities in identifying whether or not the drivers of the vehicles passing through the entrance have buckled their seat belts up. If a seat belt is not detected in a vehicle, the number plate recognition module records the vehicle number. The concerned authorities might use this record to take further necessary actions. This way, the organization authorities can keep track of all the vehicles entering the premises and ensure that all drivers/shotgun seat passengers are wearing seat belts.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90197744","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 : 2022-12-24DOI: 10.12694/scpe.v23i4.2051
P. Yadlapalli, D. Bhavana
Medical image processing involves using and examining 3D human body images, which are most frequently acquired through a computed tomography scanner, to diagnose disorders. Medical image process- ing helps radiologists, engineers, and clinicians better comprehend the anatomy of specific patients or groups of patients. Due to recent advancements in deep learn ing techniques, the study of medical image analysis is now a quickly expanding area of research. Interstitial Lung Disease is a chronic lung disease that worsens with time. This condition cannot be completely treated when the lungs have been damaged. Early detection, on the other hand, aids in the control of the disease. It causes lung scarring as a result. The first methodology characterizes lung tissue utilizing first order statistics, grey live occurrence, run length matrices, and fractal analysis. It was suggested by Uppaluri et al in one instance. In the pre-processing step, patients' CT scans are presented using various color map models for better understanding of data-set. and also for determining the patients final Force Vital Capacity and Confidence values using a Pytorch model with leaky relu activation function. These variables can be used to determine whether a person has a disease. Segmentation is a crucial stage in employing a computer assisted diagnosis system to estimate interstitial lung disease. Accurate segmentation of aberrant lung is essential for a trustworthy computer-aided illness diagnosis. Using separate training, validation, and test sets, we proposed an efficient deep learning model using Unet architecture and Densenet121 to segment lungs with Interstitial Lung Disease. The proposed segmentation model distinguishes the exact lung region from the ct slice background. To train and evaluate the algo rithm, 176 sparsely annotated Computed Tomography scans were utilized. The training was completed in a supervised and end to end manner. Contrary to current approaches, the suggested method yields accurate segmentation results without the requirement for re-initialization. We were able to achieve an accuracy of 92.59 percent after training the proposed model with Nvidia's CUDA GPU.
{"title":"Segmentation and Pre-processing of Interstitial Lung Disease using Deep Learning Model","authors":"P. Yadlapalli, D. Bhavana","doi":"10.12694/scpe.v23i4.2051","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2051","url":null,"abstract":"Medical image processing involves using and examining 3D human body images, which are most frequently acquired through a computed tomography scanner, to diagnose disorders. Medical image process- ing helps radiologists, engineers, and clinicians better comprehend the anatomy of specific patients or groups of patients. Due to recent advancements in deep learn ing techniques, the study of medical image analysis is now a quickly expanding area of research. Interstitial Lung Disease is a chronic lung disease that worsens with time. This condition cannot be completely treated when the lungs have been damaged. Early detection, on the other hand, aids in the control of the disease. It causes lung scarring as a result. The first methodology characterizes lung tissue utilizing first order statistics, grey live occurrence, run length matrices, and fractal analysis. It was suggested by Uppaluri et al in one instance. In the pre-processing step, patients' CT scans are presented using various color map models for better understanding of data-set. and also for determining the patients final Force Vital Capacity and Confidence values using a Pytorch model with leaky relu activation function. These variables can be used to determine whether a person has a disease. Segmentation is a crucial stage in employing a computer assisted diagnosis system to estimate interstitial lung disease. Accurate segmentation of aberrant lung is essential for a trustworthy computer-aided illness diagnosis. Using separate training, validation, and test sets, we proposed an efficient deep learning model using Unet architecture and Densenet121 to segment lungs with Interstitial Lung Disease. The proposed segmentation model distinguishes the exact lung region from the ct slice background. To train and evaluate the algo rithm, 176 sparsely annotated Computed Tomography scans were utilized. The training was completed in a supervised and end to end manner. Contrary to current approaches, the suggested method yields accurate segmentation results without the requirement for re-initialization. We were able to achieve an accuracy of 92.59 percent after training the proposed model with Nvidia's CUDA GPU.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76790554","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 : 2022-12-24DOI: 10.12694/scpe.v23i4.2049
Kadari Neeraja, G. Narsimha
The most important field of robotics study is path planning. Path planning problem in general is an NP-complete problem. Though several attempts have been made using A*, PRM, RRT, and RRT* these algorithms explore too many nodes in the state space, not completely captured kinematic constraints, and are not optimal in real-time. In this paper, a Multi-Objective Hybrid Collision- free Optimal Path Finder (MOHC-OPF) is proposed which is an attempt to obtain a near-optimal solution by exploring fewer nodes compare to the above existing methods while considering kinematic constraints aiming to generate optimal drivable paths. The empirical study revealed that the proposed algorithm is capable of detecting static obstacles and finding a collision-free nearest-optimal, smooth and safe path to the destination in a static known environment. Multiple criteria, including path length, collision-free, execution time, and smooth path, are used to determine an optimal path.. The proposed algorithm shows efficiency in finding the shortest path length and execution time decreased in 90% of the experiments.
{"title":"A Multi Objective Hybrid Collision-free Optimal Path Finder for Autonomous Robots in Known Static Environments","authors":"Kadari Neeraja, G. Narsimha","doi":"10.12694/scpe.v23i4.2049","DOIUrl":"https://doi.org/10.12694/scpe.v23i4.2049","url":null,"abstract":"The most important field of robotics study is path planning. Path planning problem in general is an NP-complete problem. Though several attempts have been made using A*, PRM, RRT, and RRT* these algorithms explore too many nodes in the state space, not completely captured kinematic constraints, and are not optimal in real-time. In this paper, a Multi-Objective Hybrid Collision- free Optimal Path Finder (MOHC-OPF) is proposed which is an attempt to obtain a near-optimal solution by exploring fewer nodes compare to the above existing methods while considering kinematic constraints aiming to generate optimal drivable paths. The empirical study revealed that the proposed algorithm is capable of detecting static obstacles and finding a collision-free nearest-optimal, smooth and safe path to the destination in a static known environment. Multiple criteria, including path length, collision-free, execution time, and smooth path, are used to determine an optimal path.. The proposed algorithm shows efficiency in finding the shortest path length and execution time decreased in 90% of the experiments.","PeriodicalId":43791,"journal":{"name":"Scalable Computing-Practice and Experience","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82868473","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：