Future mechanical frameworks will be arranged in exceptionally organized conditions in which they speak with modern control frameworks, cloud administrations or various other systems at distant areas. In this pattern of solid digitization of modern frameworks (likewise some of the time alluded to as Industry 4.0), digital assaults are an in-wrinkling danger to the uprightness of the automated frameworks at the center of this unique turn of events. It is normal, that the ROS shall assume a significant function in advanced mechanics outside of unadulterated exploration situated situations. ROS anyway has noteworthy security issues which should be tended to before such items should arrive at mass business sectors. Robot Operating System has emerged promptly as an alluring production method at micro and nano scales, particularly in the area of biomedical applications because of its flexibility and condensed size. As disputed to conventional grippers in the field of biomedical applications where mobility is less and show size restriction threats, ROS based micro-grippers are clear from outside power input and yield better mobility. It also has a significant impact on the field of biomedical surgery, where security is a major threat. With the current improvements in wireless communications, Tactile Internet has endorsed a dominant impact. It is regarded as the future huge development which can give current-time regulation in industrial systems, especially in the field of tele surgery. Even though, in remote-surgery environment the data transfer is subjected to various attack points. Hence, in order to understand the real capacity of safe tele-surgery, it is needed to develop a safe verification and key agreement protocol for tele-surgery. We offer here an effective, secure and common verification method in the field of biomedical application in the field of robotic tele-operation. The developed protocol ensures safe interaction samidst the surgeon, robotic arm, and the devoted jurisdiction; The results obtained express the flexibility of the protocol against offline password assuming attacks, replay attacks, imitation attacks, man-in-the-middle attacks, DoS attacks, etc.
{"title":"Security for the Networked Robot Operating System for Biomedical Applications","authors":"M. Rajakumaran, S. Ramabalan","doi":"10.1166/jmihi.2021.3878","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3878","url":null,"abstract":"Future mechanical frameworks will be arranged in exceptionally organized conditions in which they speak with modern control frameworks, cloud administrations or various other systems at distant areas. In this pattern of solid digitization of modern frameworks (likewise some of the time\u0000 alluded to as Industry 4.0), digital assaults are an in-wrinkling danger to the uprightness of the automated frameworks at the center of this unique turn of events. It is normal, that the ROS shall assume a significant function in advanced mechanics outside of unadulterated exploration situated\u0000 situations. ROS anyway has noteworthy security issues which should be tended to before such items should arrive at mass business sectors. Robot Operating System has emerged promptly as an alluring production method at micro and nano scales, particularly in the area of biomedical applications\u0000 because of its flexibility and condensed size. As disputed to conventional grippers in the field of biomedical applications where mobility is less and show size restriction threats, ROS based micro-grippers are clear from outside power input and yield better mobility. It also has a significant\u0000 impact on the field of biomedical surgery, where security is a major threat. With the current improvements in wireless communications, Tactile Internet has endorsed a dominant impact. It is regarded as the future huge development which can give current-time regulation in industrial systems,\u0000 especially in the field of tele surgery. Even though, in remote-surgery environment the data transfer is subjected to various attack points. Hence, in order to understand the real capacity of safe tele-surgery, it is needed to develop a safe verification and key agreement protocol for tele-surgery.\u0000 We offer here an effective, secure and common verification method in the field of biomedical application in the field of robotic tele-operation. The developed protocol ensures safe interaction samidst the surgeon, robotic arm, and the devoted jurisdiction; The results obtained express the\u0000 flexibility of the protocol against offline password assuming attacks, replay attacks, imitation attacks, man-in-the-middle attacks, DoS attacks, etc.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114162967","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}
In order to gather, transmit, and develop input from the patients for monitoring their health condition through smart devices or devices which use embedded systems, such as processors and transducers and equipment for communication in the healthcare system, the Internet of Medical Things (IoMT) maintains a huge network infrastructure. These devices therefore comprise of a powerful, scalable, lightweight storage knot, which requires power and batteries to run from a practical standpoint. The above shows that the energy collection plays a significant part in the enhancement of IoMT devices’ efficiency and lifespan for its application in healthcare systems. Moreover, in view of the energy acquisition from the operational environment, energy collection is required to make the IoMT devices network more ecologically sustainable. In large solar PV generating systems, partly shading situations usually develop, causing system losses. Thus, in power-voltage curves characteristic of solar systems, the appearance of several peak levels is conceivable. These kinds of problems can be handled by using new multilayer link inverter monitoring techniques. A Maximum Point Tracking Scheme (MPPT) is being suggested for self-proposed Internet of Medical Things for the purpose of optimizing harvesting of solar power on entire PV chain with the usage of RGWO (Robust Wolf Optimization) dependent PI with PWM. The mistaken PV error might create inconsistent power supply to the 7-level H-bridge inverter linked to a grid. The modulation compensation is included in the control system in order to stabilize the grid power. The suggested technique is applied to a 7-level inverter under partial shade conditions. The multi-level modular H-bridge inverter is used for the grid-linked PV system. In addition to a DC link across all H-bridges, a short PV panel string is used for feeding each phase of n H-bridge converters which is connected in series. For pulse switching inverters, the usage of RGWO-based PI with PWM is used. The PWM is used. Then L filters used to reduce the switch harmonics found in the grid are used to link the Cascade multilevel inverter with the grid. A seven-level threephase inverter with three H-bridges allows the individual MPPT control need. The harvester is under direct sunlight and sometimes overcast circumstances realistically tested outside. The wearable IoMT sensor node uses a mean power of 20, 23 mW in a wake-up mode for one hour, and the node’s service life is 28 hours. The performance analysis is finally performed and MATLAB/SIMULINK simulation is performed.
{"title":"Design of Self Powered Internet of Medical Things Using Robust Wolf Optimization Based PI Controller for Health Care Monitoring System","authors":"C. Karuppasamy, S. Venkatanarayanan","doi":"10.1166/jmihi.2021.3921","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3921","url":null,"abstract":"In order to gather, transmit, and develop input from the patients for monitoring their health condition through smart devices or devices which use embedded systems, such as processors and transducers and equipment for communication in the healthcare system, the Internet of Medical Things\u0000 (IoMT) maintains a huge network infrastructure. These devices therefore comprise of a powerful, scalable, lightweight storage knot, which requires power and batteries to run from a practical standpoint. The above shows that the energy collection plays a significant part in the enhancement\u0000 of IoMT devices’ efficiency and lifespan for its application in healthcare systems. Moreover, in view of the energy acquisition from the operational environment, energy collection is required to make the IoMT devices network more ecologically sustainable. In large solar PV generating\u0000 systems, partly shading situations usually develop, causing system losses. Thus, in power-voltage curves characteristic of solar systems, the appearance of several peak levels is conceivable. These kinds of problems can be handled by using new multilayer link inverter monitoring techniques.\u0000 A Maximum Point Tracking Scheme (MPPT) is being suggested for self-proposed Internet of Medical Things for the purpose of optimizing harvesting of solar power on entire PV chain with the usage of RGWO (Robust Wolf Optimization) dependent PI with PWM. The mistaken PV error might create inconsistent\u0000 power supply to the 7-level H-bridge inverter linked to a grid. The modulation compensation is included in the control system in order to stabilize the grid power. The suggested technique is applied to a 7-level inverter under partial shade conditions. The multi-level modular H-bridge inverter\u0000 is used for the grid-linked PV system. In addition to a DC link across all H-bridges, a short PV panel string is used for feeding each phase of n H-bridge converters which is connected in series. For pulse switching inverters, the usage of RGWO-based PI with PWM is used. The PWM is used. Then\u0000 L filters used to reduce the switch harmonics found in the grid are used to link the Cascade multilevel inverter with the grid. A seven-level threephase inverter with three H-bridges allows the individual MPPT control need. The harvester is under direct sunlight and sometimes overcast circumstances\u0000 realistically tested outside. The wearable IoMT sensor node uses a mean power of 20, 23 mW in a wake-up mode for one hour, and the node’s service life is 28 hours. The performance analysis is finally performed and MATLAB/SIMULINK simulation is performed.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127006846","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}
To adapt to varied working situations, the latest biomedical imaging applications require low energy consumption, high performance, and extensive energy-performance scalability. State-of-the-art electronics with higher sensitivity, higher counting rate, and finer time resolution are required to create higher precision, higher temporal resolution, and maximum contrast biomedical images. In recent days, the system’s power consumption is important critically in modern VLSI circuits particularly for the low power application. In order to decrease the power, a power optimization technique must be used at various design levels. The low power use of logic cells is a proficient technique for decreasing the circuit level power. Dual Feedback edge triggered Flip Flop (DFETFF) is considered for biomedical imaging applications in the proposed system. Initially, the high dynamic range voltage is given as input signal. The comparator output is then retried at the comparator end. The integration capacitor is employed for storing remaining voltage signal. The comparator voltage is then given to the capacitor reset block. In the proposed work, a capacitor-reset block that employs clock signal takes up a dual-feedbackedge-triggered Flip-flop as an alternative of a conventional type for reducing the final output signals errors. Dual feedback loops assure that feedback loops do not tri-state at the time of SET restoration, a scheme that could lead to SEUs in latches if a single delay component and a single feedback loop are used. In digital system, Clock gating is a competent method of lessening the overall consumption of power along with deactivating the clock signal selectively and is useful for controlling the usage of clock signal asynchronously in reference to input-signal current. The integration-control (Vint) signal is employed in controlling the integration time. On the termination of integration, the signal level phase is kept, also similar one is send to arrangement all through read period. As a result, the simulation was carried out after the design layout and the estimations of performance were made and are compared with traditional approaches to prove the proposed mechanism effectiveness for future biomedical applications.
{"title":"Ultra-Low Power and High Sensitivity of Joint Clock Gating Based Dual Feedback Edge Triggered Flip Flop for Biomedical Imaging Applications","authors":"S. Prema, N. Karthikeyan, S. Karthik","doi":"10.1166/jmihi.2021.3919","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3919","url":null,"abstract":"To adapt to varied working situations, the latest biomedical imaging applications require low energy consumption, high performance, and extensive energy-performance scalability. State-of-the-art electronics with higher sensitivity, higher counting rate, and finer time resolution are\u0000 required to create higher precision, higher temporal resolution, and maximum contrast biomedical images. In recent days, the system’s power consumption is important critically in modern VLSI circuits particularly for the low power application. In order to decrease the power, a power\u0000 optimization technique must be used at various design levels. The low power use of logic cells is a proficient technique for decreasing the circuit level power. Dual Feedback edge triggered Flip Flop (DFETFF) is considered for biomedical imaging applications in the proposed system. Initially,\u0000 the high dynamic range voltage is given as input signal. The comparator output is then retried at the comparator end. The integration capacitor is employed for storing remaining voltage signal. The comparator voltage is then given to the capacitor reset block. In the proposed work, a capacitor-reset\u0000 block that employs clock signal takes up a dual-feedbackedge-triggered Flip-flop as an alternative of a conventional type for reducing the final output signals errors. Dual feedback loops assure that feedback loops do not tri-state at the time of SET restoration, a scheme that could lead to\u0000 SEUs in latches if a single delay component and a single feedback loop are used. In digital system, Clock gating is a competent method of lessening the overall consumption of power along with deactivating the clock signal selectively and is useful for controlling the usage of clock signal\u0000 asynchronously in reference to input-signal current. The integration-control (Vint) signal is employed in controlling the integration time. On the termination of integration, the signal level phase is kept, also similar one is send to arrangement all through read period. As a result,\u0000 the simulation was carried out after the design layout and the estimations of performance were made and are compared with traditional approaches to prove the proposed mechanism effectiveness for future biomedical applications.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117197979","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 disorder based on neurological can be considered as epilepsy that leads to the recurrent seizures in occurrence. The electronic characteristics of brain can be monitor by the electroencephalogram (EEG). It is most commonly used in the medical application. The function monitoring records can be non linear as well as non stationary functioning. The present work produce a novel methodology, it is depend on Fast Fourier series (FFS) and wavelet transform based on Haar. These methods are used for the various kinds of epileptic seizure the electroencephalogram based signal. The detection of boundary is occur by the representation of scale-space and it also adapted to the image segmentation of the spectrum depends on the FBSE that can be obtained with the electroencephalogram based signal and the purpose of the EWT is also used to attain the narrow sub band based signals. These image segmentation and classification process implementation by FPGA based microprocessor and systems. The FFS-HMT can produce the sub band signal from the Hilbert marginal spectrum it is represented as HMS. The HMS can be used to compute the line length and the entropy characteristics due to the corresponding various kinds of the level based oscillatory of the electroencephalogram signal. Here we apply the selected feature extraction depends on the ranking parallel vector. With the use of an electroencephalogram signal, the robust random forest is utilized to classify selected feature extraction in normal and epileptic participants. The assessment of performance based on classification can be measured in FPGA microprocessor the term of classification accuracy for different sample length of EEG. The current methodology aids neurologists in distinguishing between healthy and epileptic people using electroencephalogram signals.
{"title":"Novel Model for Automatic Classification of the Epileptic Seizures Using Fast Fourier Series-Haar Wavelet Transform","authors":"P. Geetha, S. Nagarani","doi":"10.1166/jmihi.2021.3918","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3918","url":null,"abstract":"The disorder based on neurological can be considered as epilepsy that leads to the recurrent seizures in occurrence. The electronic characteristics of brain can be monitor by the electroencephalogram (EEG). It is most commonly used in the medical application. The function monitoring\u0000 records can be non linear as well as non stationary functioning. The present work produce a novel methodology, it is depend on Fast Fourier series (FFS) and wavelet transform based on Haar. These methods are used for the various kinds of epileptic seizure the electroencephalogram based signal.\u0000 The detection of boundary is occur by the representation of scale-space and it also adapted to the image segmentation of the spectrum depends on the FBSE that can be obtained with the electroencephalogram based signal and the purpose of the EWT is also used to attain the narrow sub band based\u0000 signals. These image segmentation and classification process implementation by FPGA based microprocessor and systems. The FFS-HMT can produce the sub band signal from the Hilbert marginal spectrum it is represented as HMS. The HMS can be used to compute the line length and the entropy characteristics\u0000 due to the corresponding various kinds of the level based oscillatory of the electroencephalogram signal. Here we apply the selected feature extraction depends on the ranking parallel vector. With the use of an electroencephalogram signal, the robust random forest is utilized to classify selected\u0000 feature extraction in normal and epileptic participants. The assessment of performance based on classification can be measured in FPGA microprocessor the term of classification accuracy for different sample length of EEG. The current methodology aids neurologists in distinguishing between\u0000 healthy and epileptic people using electroencephalogram signals.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129193309","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 early diagnosis of Parkinson’s Disease (PD) is a challenging practice for doctors. Currently, there are no separate diagnostics and tests to be done to predict onset PD. However, the PD can be predicted through repeated clinical trials and tests. Sometimes, early prediction of PD can become tedious based on trials and tests. The computer-aided prediction will help medical professionals predict PD accurately during one’s onset stages to improve the PD patients’ quality of life. Hence, early prediction of PD is essential. In this article, Convolution Neural Networks (CNN) is proposed to classify PD patients and healthy individuals. The brain MRI images are given as input for the proposed methodology. The CNN deep neural network will first extract the features from the images. Then, it will classify the PD patients and healthy individuals from the extracted features. The automatic feature extraction will improve the accuracy of the classifier and reduce human error. The brain MRI images are taken from the PPMI dataset for experimentation. The sensitivity, specificity, and accuracy are calculated to assess the performance of the proposed methodology. The loss is also calculated to verify the performance of the classifier. It is observed that the CNN classifier has produced a higher accuracy of more than 98% in classifying PD patients and healthy individuals when compared to multi-layer perceptron deep learning.
{"title":"Early Prediction of Parkinson's Disease from Brain MRI Images Using Convolutional Neural Network","authors":"G. A. Mary, N. Suganthi, M. Hema","doi":"10.1166/jmihi.2021.3897","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3897","url":null,"abstract":"The early diagnosis of Parkinson’s Disease (PD) is a challenging practice for doctors. Currently, there are no separate diagnostics and tests to be done to predict onset PD. However, the PD can be predicted through repeated clinical trials and tests. Sometimes, early prediction\u0000 of PD can become tedious based on trials and tests. The computer-aided prediction will help medical professionals predict PD accurately during one’s onset stages to improve the PD patients’ quality of life. Hence, early prediction of PD is essential. In this article, Convolution\u0000 Neural Networks (CNN) is proposed to classify PD patients and healthy individuals. The brain MRI images are given as input for the proposed methodology. The CNN deep neural network will first extract the features from the images. Then, it will classify the PD patients and healthy individuals\u0000 from the extracted features. The automatic feature extraction will improve the accuracy of the classifier and reduce human error. The brain MRI images are taken from the PPMI dataset for experimentation. The sensitivity, specificity, and accuracy are calculated to assess the performance of\u0000 the proposed methodology. The loss is also calculated to verify the performance of the classifier. It is observed that the CNN classifier has produced a higher accuracy of more than 98% in classifying PD patients and healthy individuals when compared to multi-layer perceptron deep learning.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128028855","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}
Autism Spectrum Disorder is one of the major investigation area in current era. There are many research works introduced earlier for handling the Autism Spectrum Disorders. However those research works doesn’t achieve the expected accuracy level. The accuracy and prediction efficiency can be increased by building a better classification system using Deep Learning. This paper focuses on the deep learning technique for Autism Diagnosis and the domain identification. In the proposed work, an Enhanced Deep Recurrent Neural Network has been developed for the detection of ASD at all ages. It attempts to predict the autism spectrum in the children along with prediction of areas which can predict the autism in the prior level. The main advantage of EDRNN is to provide higher accuracy in classification and domain identification. Here Artificial Algal Algorithm is used for identifying the most relevant features from the existing feature set. This model was evaluated for the data that followed Indian Scale for Assessment of Autism. The results obtained for the proposed EDRNN has better accuracy, sensitivity, specificity, recall and precision.
{"title":"An Enhanced Deep Recurrent Neural Network for Autism Spectrum Disorder Diagnosis","authors":"D. Pavithra, A. Jayanthi","doi":"10.1166/jmihi.2021.3893","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3893","url":null,"abstract":"Autism Spectrum Disorder is one of the major investigation area in current era. There are many research works introduced earlier for handling the Autism Spectrum Disorders. However those research works doesn’t achieve the expected accuracy level. The accuracy and prediction efficiency\u0000 can be increased by building a better classification system using Deep Learning. This paper focuses on the deep learning technique for Autism Diagnosis and the domain identification. In the proposed work, an Enhanced Deep Recurrent Neural Network has been developed for the detection of ASD\u0000 at all ages. It attempts to predict the autism spectrum in the children along with prediction of areas which can predict the autism in the prior level. The main advantage of EDRNN is to provide higher accuracy in classification and domain identification. Here Artificial Algal Algorithm is\u0000 used for identifying the most relevant features from the existing feature set. This model was evaluated for the data that followed Indian Scale for Assessment of Autism. The results obtained for the proposed EDRNN has better accuracy, sensitivity, specificity, recall and precision.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127803968","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}
Sundarambal Balaraman, Ramesh Ramamoorthy, R. Krishnamoorthi
Machine learning is a current topic of interest in research and industry, with the implementation of novel strategies all the time. The main purpose of this research activity is to determine the efficiency of machine learning techniques in the detection research of breast cancer. The incidence and mortality of breast cancer in women are increasing day by day. Worldwide, researchers have worked hard to help clinicians provide the best model for detecting diagnosis and breast cancer. In this work, learning UCI machine Wisconsin breast cancer data from a set of databases, model, and analyze the performance of existing work use, compared to the same data set. The dataset is analyzed, and the revamped dataset is constructed by eliminating redundant features and appending new features essential for prediction. Logistic regression, K nearest neighbors (KNN), support vector machine (SVM), decision trees, random forest, XGBoost, using a machine learning algorithm, such as re-organized data set of artificial neural network AdaBoost, 8 one of prediction build the model application (ANN). Standard to analyze the accuracy rate. In the experiment, these classifications have been shown to work for breast cancer with >97% accuracy. Logistic regression, XGBoost and Adaboost, stand on top with 99.28 percent accuracy. The experiment also, the balanced data set of removal outliers and balance, shows that have a significant impact on the model’s prediction performance.
{"title":"Breast Cancer Detection with Revamped Dataset Using Machine Learning Techniques","authors":"Sundarambal Balaraman, Ramesh Ramamoorthy, R. Krishnamoorthi","doi":"10.1166/jmihi.2021.3892","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3892","url":null,"abstract":"Machine learning is a current topic of interest in research and industry, with the implementation of novel strategies all the time. The main purpose of this research activity is to determine the efficiency of machine learning techniques in the detection research of breast cancer. The\u0000 incidence and mortality of breast cancer in women are increasing day by day. Worldwide, researchers have worked hard to help clinicians provide the best model for detecting diagnosis and breast cancer. In this work, learning UCI machine Wisconsin breast cancer data from a set of databases,\u0000 model, and analyze the performance of existing work use, compared to the same data set. The dataset is analyzed, and the revamped dataset is constructed by eliminating redundant features and appending new features essential for prediction. Logistic regression, K nearest neighbors (KNN), support\u0000 vector machine (SVM), decision trees, random forest, XGBoost, using a machine learning algorithm, such as re-organized data set of artificial neural network AdaBoost, 8 one of prediction build the model application (ANN). Standard to analyze the accuracy rate. In the experiment, these classifications\u0000 have been shown to work for breast cancer with >97% accuracy. Logistic regression, XGBoost and Adaboost, stand on top with 99.28 percent accuracy. The experiment also, the balanced data set of removal outliers and balance, shows that have a significant impact on the model’s prediction\u0000 performance.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132338946","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}
There have been significant advances in sensors and device structures in the medical industry, particularly in implanted medical devices. Increasingly complex electronic circuitry may now be implanted in the human body thanks to compact, high-energy batteries and hermetic packaging. These gadgets must adhere to strict power consumption guidelines due to the battery recharging schedule. Designing energy-efficient circuits and systems becomes increasingly important as a result of this fact. Adiabatic circuits provide a hopeful alternative for traditional circuitry in case of low energy design. Because of power-clock phases synchronization complexity, designing and functionally verifying presenting 4-phase adiabatic circuitry takes longer. Accordingly, multiple clock generators are used typically and can reveal enhanced consumption of energy in the network of clock distribution. Furthermore, they are not suitable for designing in high-speed because of their clock skew management and high complexity issues. In this paper, TMEL (True multi-phase energy recovering logic), the first energyrecovering/adiabatic logic family is presented for biomedical applications, which functions using the scheme multiple-phase sinusoidal clocking. Moreover, a system of SCAL, a source-coupled variation with TMEL having enhanced energy efficiency and supply voltage scalability, is introduced. A novel true multi-phase Approach and Source-coupled adiabatic logic for energy effective communication system is proposed. The adiabatic logic is employed for both write and read side operation. The CMOS inverter is integrated with TMEL cascades, which in turn reduces leakage loss. In SCAL, the optimal performance at any operating circumstance is attained byan adjustable current source in each gate. SCAL, and TMEL, are capable of outperforming existing adiabatic logic families concerning operating speed and energy efficiency. The performance analysis was carried and simulated through 45 nm CMOS inverter in terms of leakage power, delay, and power consumption. In particular, for the clock rates that range from 10 MHz to 200 MHz, the proposed SCAL was more energy-efficient and less dissipative on comparing their pipelined or purely combinational CMOS counterparts. In biomedical equipment, the system may be included into the low-power design since it is energy efficient and very robust. Improvements in VLSI technology, such as increased dynamic range, low-voltage EEPROMs (electrically eraseable programmable ROMs), and specific sensor techniques, are also expected to contribute to advancements in implanted medical devices in the near future.
{"title":"Low Power Adiabetic Logic System for Biomedical Applications","authors":"M. Mailsamy, V. Rukkumani, K. Srinivasan","doi":"10.1166/jmihi.2021.3910","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3910","url":null,"abstract":"There have been significant advances in sensors and device structures in the medical industry, particularly in implanted medical devices. Increasingly complex electronic circuitry may now be implanted in the human body thanks to compact, high-energy batteries and hermetic packaging.\u0000 These gadgets must adhere to strict power consumption guidelines due to the battery recharging schedule. Designing energy-efficient circuits and systems becomes increasingly important as a result of this fact. Adiabatic circuits provide a hopeful alternative for traditional circuitry in case\u0000 of low energy design. Because of power-clock phases synchronization complexity, designing and functionally verifying presenting 4-phase adiabatic circuitry takes longer. Accordingly, multiple clock generators are used typically and can reveal enhanced consumption of energy in the network of\u0000 clock distribution. Furthermore, they are not suitable for designing in high-speed because of their clock skew management and high complexity issues. In this paper, TMEL (True multi-phase energy recovering logic), the first energyrecovering/adiabatic logic family is presented for biomedical\u0000 applications, which functions using the scheme multiple-phase sinusoidal clocking. Moreover, a system of SCAL, a source-coupled variation with TMEL having enhanced energy efficiency and supply voltage scalability, is introduced. A novel true multi-phase Approach and Source-coupled adiabatic\u0000 logic for energy effective communication system is proposed. The adiabatic logic is employed for both write and read side operation. The CMOS inverter is integrated with TMEL cascades, which in turn reduces leakage loss. In SCAL, the optimal performance at any operating circumstance is attained\u0000 byan adjustable current source in each gate. SCAL, and TMEL, are capable of outperforming existing adiabatic logic families concerning operating speed and energy efficiency. The performance analysis was carried and simulated through 45 nm CMOS inverter in terms of leakage power, delay, and\u0000 power consumption. In particular, for the clock rates that range from 10 MHz to 200 MHz, the proposed SCAL was more energy-efficient and less dissipative on comparing their pipelined or purely combinational CMOS counterparts. In biomedical equipment, the system may be included into the low-power\u0000 design since it is energy efficient and very robust. Improvements in VLSI technology, such as increased dynamic range, low-voltage EEPROMs (electrically eraseable programmable ROMs), and specific sensor techniques, are also expected to contribute to advancements in implanted medical devices\u0000 in the near future.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130321962","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}
Yi-Wen Chen, C. Shih, Chen-Yang Cheng, Yu-Cheng Lin
Cranial defects can result in compromised physical protection for the brain and a how risky the brain infection is. Cranioplasty is commonly performed by doing the bone graft onto the deficient area or areas and/or using the metal to support them for restoring the cranial cavity integrity and maintain the physiological intracranial pressure stability. Nowadays, the suitable shape of skull prosthesis can be created and operated precisely and efficiently during cranioplasty process, because the technological development of additive manufacturing or 3D printing. Additive manufacturing has great potential in regard to addressing irregular cranial defects because it can be used to create customized shapes rapidly. However, an unsuitable cranial prosthesis that made from synthetic polymer or a metal implantation will cause a serious infections, and required additional surgery. This paper proposes a geometric model of skull defects by using the superellipse and Differential Evolution (DE). The defects of skill bones in each tomography slice can be modeled by superellipse. The DE optimizes the parameters of superellipse to emulate and compensate the suitable curvature. In a rapid 2D image process and 3D cranial model construction system, the clinical surgeons’ ability is determining, processing, and implanting a customized prosthesis for patients just in a short time in surgery and with maximum surgical quality, especially in emergency cases.
{"title":"Solving the Prosthesis Modeling for Skull Repair Through Differential Evolution Algorithm","authors":"Yi-Wen Chen, C. Shih, Chen-Yang Cheng, Yu-Cheng Lin","doi":"10.1166/jmihi.2021.3884","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3884","url":null,"abstract":"Cranial defects can result in compromised physical protection for the brain and a how risky the brain infection is. Cranioplasty is commonly performed by doing the bone graft onto the deficient area or areas and/or using the metal to support them for restoring the cranial cavity integrity\u0000 and maintain the physiological intracranial pressure stability. Nowadays, the suitable shape of skull prosthesis can be created and operated precisely and efficiently during cranioplasty process, because the technological development of additive manufacturing or 3D printing. Additive manufacturing\u0000 has great potential in regard to addressing irregular cranial defects because it can be used to create customized shapes rapidly. However, an unsuitable cranial prosthesis that made from synthetic polymer or a metal implantation will cause a serious infections, and required additional surgery.\u0000 This paper proposes a geometric model of skull defects by using the superellipse and Differential Evolution (DE). The defects of skill bones in each tomography slice can be modeled by superellipse. The DE optimizes the parameters of superellipse to emulate and compensate the suitable curvature.\u0000 In a rapid 2D image process and 3D cranial model construction system, the clinical surgeons’ ability is determining, processing, and implanting a customized prosthesis for patients just in a short time in surgery and with maximum surgical quality, especially in emergency cases.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"86 (2016) 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129318524","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 rapid developing international of internet, Semantic Web has become a platform for intelligent agents mainly in the healthcare sector. Inside the beyond few years there is a widening in the Semantic web data field in the healthcare industry. With a growth in the quantity of Semantic web data field in health industry, there exist some challenges to be resolved. One such challenge is to provide an efficient querying mechanism that can handle large number of Semantic web data. Consider many query languages; especially SPARQL (SPARQL Protocol and RDF Query Language) is the most popular query language. Each of these query languages has their own design strategy and it was identified in research that it is difficult to handle and query large quantity of RDF data efficiently using these languages. In the proposed process, Harmony search identify met heuristic algorithm to optimize the SPARQL queries in the healthcare data in the applicable manner. The application of Harmony search algorithm is evaluated with large Resource Description Framework (RDF) datasets and SPARQL queries. To assess performance, the algorithm’s implementation is compared to existing nature-inspired algorithms. The performance analysis shows that the proposed application performs well for large RDF datasets.
{"title":"Application of Harmony Search Algorithm to Optimize SPARQL Protocol and Resource Description Framework Query Language Queries in Healthcare Data","authors":"G. Ramalingam, S. Dhandapani","doi":"10.1166/jmihi.2021.3877","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3877","url":null,"abstract":"The rapid developing international of internet, Semantic Web has become a platform for intelligent agents mainly in the healthcare sector. Inside the beyond few years there is a widening in the Semantic web data field in the healthcare industry. With a growth in the quantity of Semantic\u0000 web data field in health industry, there exist some challenges to be resolved. One such challenge is to provide an efficient querying mechanism that can handle large number of Semantic web data. Consider many query languages; especially SPARQL (SPARQL Protocol and RDF Query Language) is the\u0000 most popular query language. Each of these query languages has their own design strategy and it was identified in research that it is difficult to handle and query large quantity of RDF data efficiently using these languages. In the proposed process, Harmony search identify met heuristic algorithm\u0000 to optimize the SPARQL queries in the healthcare data in the applicable manner. The application of Harmony search algorithm is evaluated with large Resource Description Framework (RDF) datasets and SPARQL queries. To assess performance, the algorithm’s implementation is compared to existing\u0000 nature-inspired algorithms. The performance analysis shows that the proposed application performs well for large RDF datasets.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"32 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125708627","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：