Enhancing Security of Medical Image Data in the Cloud Using Machine Learning Technique

To prevent medical data leakage to third parties, algorithm developers have enhanced and modified existing models and tightened the cloud security through complex processes. This research utilizes PlayFair and K-Means clustering algorithm as double-level encryption/ decryption technique with ArnoldCat maps towards securing the medical images in cloud. K-Means is used for segmenting images into pixels and auto-encoders to remove noise (de-noising);the Random Forest regressor, tree-method based ensemble model is used for classification. The study obtained CT scan-images as datasets from ‘Kaggle' and classifies the images into ‘Non-Covid' and ‘Covid' categories. The software utilized is Jupyter-Notebook, in Python. PSNR with MSE evaluation metrics is done using Python. Through testing-and-training datasets, lower MSE score (‘0') and higher PSNR score (60%) were obtained, stating that, the developed decryption/ encryption model is a good fit that enhances cloud security to preserve digital medical images.

Design of an Efficient Approach for Performance Enhancement of COVID-19 Detection Using Auxiliary GoogLeNet by Using Chest CT Scan Images

In every country on this planet, COVID-19 disease s right now one of the most unsafe issues. The expedient and precise space of the Covid virus infection s major to see and take better treatment for the infected patients will increase the chance of saving their lives. The quick spread of the Covid virus has blended complete interest and caused greater than 10 lacks cases to date. To battle this spread, Chest CTs arise as a basic demonstrative contraption for the clinical association of COVID-19 related to a lung illness. A modified confirmation device is essential for assisting in the screening for COVID-19 pneumonia by making use of chest CT imaging. The COVID-19 illness detection utilizing supplementary GoogLeNet is shown in this study. Deep Convolutional Neural Networks were built by researchers at Google, and one of their innovations was the Inception Network. GoogLeNet is a 22-layer deep convolutional neural network that is a variation of the inception Network. GoogLeNet is utilized for a variety of additional computer vision applications nowadays, including face identification and recognition, adversarial training, and so on. The findings indicate that the GoogLeNet method is superior to the CNN Method in terms of its ability to detect COVID-19 sickness. © 2022 IEEE.

Sensitivity enhanced tunable plasmonic biosensor using two-dimensional twisted bilayer graphene superlattice

This study theoretically demonstrated an insight for designing a novel tunable plasmonic biosensor, which was created by simply stacking a twisted bilayer graphene (TBG) superlattice onto a plasmonic gold thin film. To achieve ultrasensitive biosensing, the plasmonic biosensor was modulated by Goos-Hänchen (GH) shift. Interestingly, our proposed biosensor exhibited tunable biosensing ability, largely depending on the twisted angle. When the relative twisted angle was optimized to be 55.3°, such a configuration: 44 nm Au film/1-TBG superlattice could produce an ultralow reflectivity of 2.2038 × 10-9and ultra-large GH shift of 4.4785 × 104μm. For a small refractive index (RI) increment of 0.0012 RIU (refractive index unit) in sensing interface, the optimal configuration could offer an ultra-high GH shift detection sensitivity of 3.9570 × 107μm/RIU. More importantly, the optimal plasmonic configuration demonstrated a theoretical possibility of quantitatively monitoring severe acute respiratory syndrome coronavirus (SARS-CoV-2) and human hemoglobin. Considering an extremely small RI change as little as 3 × 10-7RIU, a good linear response between detection concentration of SARS-CoV-2 and changes in differential GH shift was studied. For SARS-CoV-2, a linear detection interval was obtained from 0 to 2 nM. For human hemoglobin, a linear detection range was achieved from 0 to 0.002 g/L. Our work will be important to develop novel TBG-enhanced biosensors for quantitatively detecting microorganisms and biomolecules in biomedical application. © 2023 the author(s), published by De Gruyter, Berlin/Boston 2023.

Optimal DG Allocation Based on Pay-back Period by a Proposed Modification for Coronavirus Herd Immunity Optimization

Distribued Generations (DG) have economic, financial, and environmental benefits. DG reduces power losses in the distribution system but has a negative impact on the protection devices. In this article, the IEEE 33 bus system will be used and tested by adding up to three DG units using MATLAB/SIMULINK software. the optimization techniques that will be used are Grey Wolf Optimizer, Whale Optimization Algorithm, Genetic Algorithm, and Coronavirus Herd Immunity or COVID-19 optimization techniques to select the optimal site and size of the DG units based on the lowest pay-back period considering the voltage limits and power losses. The paper proposes a modified mutation operator for COVID-19 based on Gaussian and Cauchy mutations to have better performance and lower variance. The proposed algorithm is compared with the other optimization techniques. The proposed algorithm achieved better results, which proved to have competitive performance with state-of-the-art evolutionary algorithms. © 2022 IEEE.

Utilization of Robotics for Healthcare: A Scoping Review

Robotics is a disruptive technology that has already revolutionized patient healthcare globally. This technology is presently helping to perform various essential tasks such as conducting operations via numerous specializations and managing the entire operating room. Robot surgery is, in reality, available worldwide for knee substitution, correction of the hernia, and colon resection. Surgical robots entered the operating theatres far before entering other medicine-related robotics applications and now facilitate better outcomes for a whole range of healthcare products. In the COVID-19 pandemic, some robots were used in hospitals to deliver medicines, screen, perform odd jobs, and maintain hygienic conditions. This paper provides an overview about robotics and its various applications useful for healthcare. Significant enhancement, quality services, and advancements in healthcare services are also discussed. Here, we have identified the role of robotics in healthcare as a technology that dramatically changes the healthcare field. An artificial intelligence robot can duplicate creativity via algorithms, and its programming too plays a crucial role. Hospitals can now save time and money by removing the need for physical chores for different jobs. It is helpful for surgical training, exoskeletons, intelligent prostheses and bionics, robotic nurses, treatment, medicines, logistics, telepresence, and cleaning services. Robotics technologies such as gesture control, machine view, voice recognition, and touch sensor technology are also available. The future is bright with lower installation and maintenance costs.

Enhancing Security of Medical Image Data in the Cloud Using Machine Learning Technique

To prevent medical data leakage to third parties, algorithm developers have enhanced and modified existing models and tightened the cloud security through complex processes. This research utilizes PlayFair and K-Means clustering algorithm as double-level encryption/ decryption technique with ArnoldCat maps towards securing the medical images in cloud. K-Means is used for segmenting images into pixels and auto-encoders to remove noise (de-noising);the Random Forest regressor, tree-method based ensemble model is used for classification. The study obtained CT scan-images as datasets from ‘Kaggle’ and classifies the images into ‘Non-Covid’ and ‘Covid’ categories. The software utilized is Jupyter-Notebook, in Python. PSNR with MSE evaluation metrics is done using Python. Through testing-and-training datasets, lower MSE score (‘0’) and higher PSNR score (60%) were obtained, stating that, the developed decryption/ encryption model is a good fit that enhances cloud security to preserve digital medical images. © 2022 MECS.

Sensitivity enhancement of microelectromechanical sensors using femtosecond laser for biological and chemical applications

Rapid, selective, and highly sensitive microelectromechanical sensors are a promising technology for biosensing, medical recognition, and the detection of chemical hazards. At the same time, the surfaces of silicon microcantilevers cannot bond with thiols and cannot be functionalized without a bonding layer, such as gold. Therefore, in past literature, the surfaces of silicon microcantilevers have been coated with gold to facilitate their bonding with the thiol functional groups on the probe layers. However, gold coating produces thermal noise in the results owing to the metallic effect. Accordingly, this study aimed to modify the surface of silicon microcantilevers by patterning it using femtosecond laser (FSL) micromachining so that it could bond with the thiol functional groups with high sensitivity. The surface patterning of silicon microcantilevers enhances their physical, micromechanical, and chemical properties, increasing sensitivity by increasing the quality factor, specific surface area, and creating trapping areas on the microcantilever surfaces. The surfaces of the silicon microcantilever were patterned by microgrooves aligned from the free end to the bounded end, with each microgroove comprising submicrogrooves. To demonstrate their use in a biosensing applications, the modified microcantilevers were functionalized to detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2;COVID-19) by immobilizing thiolated oligonucleotides on the surfaces, which worked as the probe layer. The modified biosensor was used to detect low concentrations of SSDNA sequence targets ranging from 300 nM down to 100 pM. The modified silicon-microcantilever sensors were directly functionalized without a joining layer, such as a gold layer. The results revealed a selective response to SARS-CoV-2 SSDNA down to a 9-nM concentration. To detect hazardous chemicals, the modified microcantilever was functionalized using reduced L-cysteine to detect Pb2+ at low concentrations down to 100 pM. The results revealed enhanced sensitivity and selectivity and demonstrated that the FSL patterning activated the microcantilevers to bond with probe layers through the interaction of the silanol created on the surface with the functional groups, such as the thiols, on the probe layers. The microcantilevers patterned with 10 microgrooves exhibited higher responses than those patterned with seven microgrooves. © 2022 John Wiley & Sons Ltd.

Steganography Adaptation Model for Data Security Enhancement in Ad-Hoc Cloud Based V-BOINC Through Deep Learning

Cloud computing’s automation, scalability, and availability were vital features in the early days of digital transformation. Meanwhile, substantial concerns were expressed about cloud security and privacy. Due to the COVID-19 outbreak, several businesses have had serious issues speeding up their cloud migration efforts. This work intends to improve steganography in ad-hoc cloud systems using deep learning. This study is implemented in two phases. Phase 1: The ‘Ad-hoc Cloud System’ concept and deployment method were created using V-BOINC, a tool that allows developers to bypass application-level security checks, the implemented ad-hoc cloud system was compared Amazon AC2 and showed high evaluation rate in some matrices. Phase 2: We evaluate the data transmission security in ad-hoc cloud systems using a modified steganography with deep learning usage to replace or enhance an image-hiding system. In this study, the proposed model inputs data/images into the ad-hoc cloud system to guarantee high rate of data/image concealing. Statistically, a systematic steganography model hides lower message detection rates, the proposed deep steganography approach outperformed several attacks in the ad-hoc cloud environment. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

There and back again: the shape of telemedicine in U.S. nursing homes following COVID-19.

INTRODUCTION: Telemedicine use in nursing homes (NHs) expanded during the COVID-19 pandemic. The objectives of this study were to characterize plans to continue telemedicine among newly adopting NHs and identify factors limiting its use after COVID-19. METHODS: Key informants from 9 Wisconsin NHs that adopted telemedicine during COVID-19 were recruited. Semi-structured interviews and surveys were employed to identify participant perceptions about the value of telemedicine, implementation challenges encountered, and plans and barriers to sustaining its delivery after COVID-19. Directed content analysis and a deductive thematic approach using the Systems Engineering Initiative for Patient Safety (SEIPS) model was used during analyses. Quantitative and qualitative data were integrated to identify participant views on the value of telemedicine and the tools and work system enhancements needed to make telemedicine easier and more effective. RESULTS: All participating NHs indicated a preference to continue telemedicine after COVID-19. Urgent assessments of resident change-in-condition and cognitively based sub-specialty consultations were identified as the encounter types most amenable to telemedicine. Reductions in resident off-site encounters and minimization of resident therapy interruptions were identified as major benefits of telemedicine. Twelve work system enhancements needed to better sustain telemedicine were identified, including improvements to: 1) equipment/IT infrastructure; 2) scheduling; 3) information exchange; and 4) telemedicine facilitators. DISCUSSION: NHs that adopted telemedicine during COVID-19 wish to continue its use. However, interventions that enhance the integration of telemedicine into NH and off-site clinic work systems require changes to existing regulations and reimbursement models to sustain its utilization after COVID-19.

COVID-19 Detection from Chest X-Ray Using Deep Learning and Contrast Enhancement

In the current COVID-19 pandemic, it has become extremely important to detect the affected patients as soon as possible and isolate them in order to break the chain of the spreading virus. Testing in large numbers at laboratories has overwhelmed their resources. Furthermore, the diagnosis report often takes more than a day to be returned. All this adds up to the incapability of our healthcare infrastructure to test all the possibly infected patients. Radiologists across the world have used chest X-rays to detect chest diseases. X-rays being readily available in far less time than RT-PCR reports make them an easy and quick alternative in comparison to current testing methods. However, examining a vast number of X-rays in an already overwhelmed healthcare facility may still lead to delays in determining the presence of the disease. In addition, it would require expertise and profound knowledge about the much recently explored COVID-19 virus in order to make an accurate assessment of the X-rays. In this study, to find solutions to these problems, we have made use of deep learning for the detection of coronavirus. The proposed system uses three different Convolutional Neural Network (CNN) models to detect COVID-19 from pre-processed chest X-ray images with reliable accuracy and hence provide an alternative for people to be aware of being infected rather than wait days for results. © 2021 IEEE.

Health system resilience: Ensuring TB services during COVID-19 pandemic in Kerala, India.

COVID-19 pandemic has affected TB case detection and continuity of care globally. Kerala, the southern Indian state has experienced a reduction in TB notification during second and third quarter of 2020. Through (1) causal analysis (2) meticulous planning and establishment of systems (3) locally customised guidelines (4) better management of resources (5) integration with other programs and (6) good partnership with private sector, Kerala was able to catch up the TB notification and ensure that TB services remain intact even during the COVID-19 pandemic. Approach to catch up TB diagnosis included (1) Field based active case finding among the vulnerable individuals, (2) bilateral screening for TB and COVID-19, (3) enhancement of biosafety in laboratories, (4) strengthening of specimen collection and transportation systems, (5) targeted advocacy and communication to find out missed cases and (6) effective partnership with the private sector. Current experiences also show that TB case finding could be improved and delay in diagnosis could be averted by integrating TB case finding into the screening and testing systems established for COVID-19. The experiences of ensuring TB services during pandemic in Kerala also affirms the importance of maintaining an integrated and strong TB control component in the public health sector and vesting ownership of the TB control programme with the primary health care team. Community-based and community-led responses that take diagnosis, care, and support to the doors of those affected have much potential in delivering TB services in the subsequent years of pandemic.