Keywords : Accuracy
A Computational Methodology Towards the Detection of Diabetic Retinopathy
European Journal of Molecular & Clinical Medicine,
2022, Volume 9, Issue 8, Pages 1155-1165
Diabetic retinopathy is an eye-related neurological disorder, the diabetic patient eye damaged by blood vessel in the retina area of the eye. Computational methodology is a proper way for detecting and predicting the diabetic retinopathy disease. The aim is to identify and detect the Diabetic Retinopathy, so this present work focusses on detection of Diabetic Retinopathy. This work proposed the novel WMD-MSVM -Weighted Mahalanobis Distance based Multiclass Support Vector Machine oriented; upon Diabetic Retinopathy diagnosis system for the purpose of feature selection, also ROI extraction method being utilized to fetch features from Diabetic Retinopathy images. From the results, it is clear that the performance of WMD-MSVM on instance selected training dataset yields improved detection accuracy compared with the performance of WMD-MSVM on full-training-dataset. There is an improvement of around 1% of detection accuracy in case instance selected dataset. This proposed work is benefit for diabetic patients to gain the proper treatment by physicians at an early stage for Diabetic Retinopathy. This computational approach to detect the diabetic which results the best solutions for ophthalmology. The diabetic image analysis and machine learning approach considered as a challenging research area that aims to provide a computational approach to assist in the early diagnosis and detection of Diabetic Retinopathy problems.
Accuracy and role of FNAC in diagnosis of etiological profiles of lymphadenopathy
European Journal of Molecular & Clinical Medicine,
2022, Volume 9, Issue 2, Pages 3020-3024
Introduction: Enlargement of lymph node may result from the proliferation of lymphocytes intrinsic to lymph nodes, due to an infection or a lymphoproliferative disorder or from the migration and infiltration of nodal tissue by either intrinsic inflammatory cells or metastatic malignant cells. The aim of the present study was to investigate the Accuracy and role of FNAC in diagnosis of etiological profiles of lymphadenopathy and its comparison to histo-pathology examination.
Materials and Methods: Lymph node biopsies were received in 72 patients and the biopsy specimens were subjected to FNAC examination after fixing in 10% formalin. Histopathological examination was done and the results were correlated with the cytological reports to evaluate efficacy of the procedure. They were subjected to FNAC and only those thyroid swelling cases admitted to indoor and subsequently underwent surgery were included in this study. After HP study they were compared with preoperative FNAC report.
Result: During histo-pathological examination commonest cause of lymphadenopathy wastubercular lymphnoditis(29.1%) and metastatic carcinoma (27.7%). Reactive hyperplasia was (20.8%) at second place. Lymphomas constituted 18.0%. Granulomatous inflammatory lesion accounted for 4.16% of lymphnodeenlargement. Out of 72 cases, cytological diagnosis was matched with histopathological diagnosis in 66 cases.
Conclusion: Commonest cases of lymphadenopathy in children was reactive hyperplasia; in adult’s tubercular lymphadentis and lymphoma; while metastasis in older age. The commonest cause of metastasis in lymph node was squamous cell carcinoma. We have found FNAC a satisfactory tool in the diagnosis of tubercular and malignant lymphadenopathy.
Evaluating accuracy of digital impressions and conventional impression in implant placement
European Journal of Molecular & Clinical Medicine,
2021, Volume 8, Issue 4, Pages 2321-2325
Background: The clinical feasibility of implant restorations is heavily influenced by the accuracy of digital impressions. The purpose of this research is to compare the accuracy of conventional impressions with impressions made digitally using three-dimensional analysis. Materials and methods: Twenty implants in eight patients in the posterior region of the oral cavity formed the study sample. Two operators with good inter-examiner reliability performed the procedure. Conventional impression were taken using polyether impression material and stock trays. Digital impressions of the same patient were taken after 2-3 weeks. Outcomes assessed were total time taken, distance between scanbodies, angulation, rotation, and vertical shift were all evaluated as clinical outcomes. SPSS 23.0 version (SPSS Inc., Chicago, IL, USA) software was used for data analysis.
Results: In comparison to digital impressions, conventional impressions took longer time, which was statistically significant at p<0.001. In both impression approaches, the measurements of distance between scan bodies, angulation, and vertical shift were practically identical, which was not statistically significant.
Conclusion: Digital impressions outperformed conventional impressions during implant placement.
ENERGY-EFFICIENT FILTER DESIGN USING REVERSE CARRY PROPAGATE ADDERS
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 11, Pages 5242-5251
The reverse propagate adder (RCPA) is presented in this project. In this project. Under the RCPA framework, the transmission signal stretches from the most important to the less significant bit in a counter-flow way; thus the transportation signal is more appropriate than the production. In the case of delay differences, this propagation process improves stability. The cell with a varying pause, capacity, energy and accuracy are implemented in three separate implementations of the reverse transportation (RCPFA). The configuration suggested can be linked along with the precise (forward) adder to shape the hybrid adders with precise tuning levels. In contrast to modern estimated additions, the specification parameters of the proposed RCPA architectures and several hybrids that have been implemented using these frameworks are discussed. Using Reverse Carrier Adder(RCPA), the Fir Filter is applied. Project with Verilog will be created. For simulation and synthesis, the Xilinx ISE tool is used.
AUTISM SPECTRUM DISORDER USING KNN ALGORITHM
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 9, Pages 1628-1637
Autism spectrum disorder (ASD) is a psychiatric disorder which leads to
neurological anddevelopmental growth of a person which starts in early age and gets
carried throughout their life.It is a condition associated with significant healthcare costs
and early diagnosis can reduce these.Unfortunately, waiting time is lengthy for an ASD
diagnosis and it is cost effective. Due to theincrease in economy for autism prediction and
the increase in the number of ASD cases across theworld is in need of easily implemented
and effective screening methods by GUI results. Toovercome the time complexity for
identifying the disorder advanced technologies can be used suchas machine learning
algorithms to improve precision, accuracy and quality of the diagnosisprocess. Machine
learning helps us by providing intelligent techniques to discover the affectedpatient, which
can be utilized in prediction and to improve decision making. And hence, wepropose the
data set features related to autism screening of adult and child to be used for
furtheranalysis and to improve the classification of ASD cases.
FOURIER–MELLIN TRANSFORM FEATURES FOR MALARIA PARASITES CLASSIFICATION USING MICROSCOPIC IMAGES
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 9, Pages 1426-1430
DOI:
10.31838/ejmcm.07.09.150
Malaria is an infectious disease transmitted by mosquitoes that affects humans and other animals. Malaria is responsible for the effects of fever, tiredness, vomiting and headaches. Yellow skin, convulsions, a coma, or death can lead to severe cases. Symptoms usually start 10-15 days after a mosquito is bitten. The early diagnosis is required for malaria. In this study, the automatic classification of malaria system is discussed. Initially, the input images are given to Fourier–Mellin transform for feature extraction and Support Vector Machine (SVM) classifier is used for classification. The performance of malaria system produces the classification accuracy of 92%using SVM classifier.
Deep Learning System for Skin Disorder Segmentation using Neural Network
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 9, Pages 1515-1522
DOI:
10.31838/ejmcm.07.09.163
Skin issue is extremely normal in the day by day lives of people. Consistently a huge number of American individuals are influenced by skin issue of different types. Skin condition conclusion regularly includes a high level of information because of the scope of visual perspectives thereof. Since human judgment is constantly discretionary and infrequently reproducible, a PC helped indicative gadget ought to be considered for accomplishing an increasingly objective and precise conclusion. In this paper, we investigate the plausibility of utilizing profound Convolutional neural system (CNN) to make a widespread structure for determination of skin infection. We train the CNN engineering utilizing the Dermnet dataset's skin illness pictures and check its yield with both Dermnet and OLE, another information assortment for skin ailment, pictures. Our program can accomplish Top-1 exactness of up to 73.1 percent and Top-5 precision of 91.0 percent while running on the Dermnet dataset. Top-1 and Top-5 correctness’s for the OLE dataset check are 31.1 percent and 69.5 separately. We show that if all the more preparing pictures are utilized, those correctness’s can be additionally improved.
A Methodology for SOFTWARE RELIABILITY BASED ON STATISTICAL MODELING
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 4, Pages 804-809
Reliability is one of the quantifiable quality features of the software. Software reliability growth models (SRGMs) are used to assess the reliability achieve at different test times based on statistical learning models. Conventional time based SRGMS may not be accurate enough in all situations and such models cannot identify errors in small and medium sized applications. Numerous traditional reliability measures are used to test software errors during application development and testing. In the software testing and maintenance phase, however, new errors are taken into account in real time in order to determine the reliability estimate. In this article, we suggest using the Weibull model as a computational approach to solving the problem of software reliability modeling. In the anticipated model, a new distribution model is projected to develop the reliability estimation method. We compute the model developed and balance its presentation through additional popular software reliability increase models commencing the literature. Our test consequences demonstrate that the planned Model is greater to S-shaped Yamada, comprehensive Poisson, NHPP.
Crop Value Forecasting using Decision Tree Regressor and Model s
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 2, Pages 3702-32722
Machine Learning is an emerging research field which can be used for the analysis of crop
price prediction and accurately provide solutions for the same. We can use this system as a backhand
while we decide what a farmer should plant while considering factors such as annual rainfall, WPI
and so on which is provided from the dataset and produce a logical conclusion on which products
would give a more reliable outcome. The performance between Random forest ensemble learning and
decision tree regressor is compared and it has been observed that the Random Forest Ensemble
learning method gives a higher accuracy. In this system there are 23 crops whose information can be
accessed upon for deciding collaborated with a simple user friendly UI