Online ISSN: 2515-8260

Keywords : Neural Networks

An Algorithm for Extraction of Decision Trees from Artificial Neural Networks

Dr.M.Rajaiah, Dr.N.Krishna Kumar,Mr. Akula Sujan Kumar,Mr. Amruthala Anil Kumar,Mr. Kamineni Venkat Chowdary,Ms. Addam Vennela .

European Journal of Molecular & Clinical Medicine, 2023, Volume 10, Issue 2, Pages 195-207

Although artificial neural networks can represent a variety of complex systems with a high degree of accuracy, these connectionist models are difficult to interpret. This significantly limits the applicability of neural networks in practice, especially where a premium is placed on the comprehensibility or reliability of systems. A novel artificial neural-network decision tree algorithm (ANN-DT) is therefore proposed, which extracts binary decision trees from a trained neural network. The ANN-DT algorithm uses the neural network to generate outputs for samples interpolated from the training data set. In contrast to existing techniques, ANN-DT can extract rules from feedforward neural networks with continuous outputs. These rules are extracted from the neural network without making assumptions about the internal structure of the neural network or the features of the data. A novel attribute selection criterion based on a significance analysis of the variables on the neural-network output is examined. It is shown to have significant benefits in certain cases when compared.


S. Kausalya; S. Kalaiselvi; D. Thamarai Selvi; Dr.V. Gomathi

European Journal of Molecular & Clinical Medicine, 2021, Volume 8, Issue 3, Pages 2374-2386

Doctor AI imitates human doctor’s forecasting potential and gives diagnostic results that are clinically significant. Prognosticating Clinical Incidents is a timeseries based RNN model. It is implemented and employed to longitudinal time stamped electronic health record data from a twenty thousand patients over a decade. Encounter medical logs of patients data such as diagnosis codes, medication codes and procedure codes are input data to RNN to predict the diagnosis and medication types for a future visit of patients in a hospital. Doctor AI evaluates the history of patient’s to prepare one label for each diagnosis predictions and medication types i.e.,multi-label forecasting/prediction. Leveraging huge historical patient details in electronic health records (EHR), a collective generic and comprehensive predictive model that covers perceived health state and medication uses for EHR, is new approach in disease progress identification.

A Study Of Preprocessing Techniques And Features For Ovarian Cancer Using Ultrasound Images

Ms.ArathiBoyanapalli .; Dr.Shanthini. A

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 10, Pages 293-303

Ovarian Cancer is the third leading cancer among women in India. The early detection-rate of ovarian cancer is very low [1]. Transvaginal ultrasound is the most common screening test to detect the presence of tumors but adnexal masses are very common in patients, the challenging part is to discriminate whether the masses are benign or malignant. This distinction is very essential for optimal surgical management, but reliable pre-surgical differentiation is sometimes difficult using clinical features, ultrasound examination, or tumor markers alone[2]. Recent trends in medical imaging facilitate the detection of most cancers at a very initial stage. Still, an ovarian cancer diagnosis is not accurate. The patient has to undergo painful practices such as biopsies or surgeries, even with benign nodules. Ultrasound images with deep learning techniques in ovarian cysts help in diagnosis whether the cyst is benign or malignant at a very early stage without any surgeries. This method not only cuts the medical expenses of the patient but also reduces the mental stress of the patients.

Detection and Identification of Bogus Profiles in online Social Network using Machine Learning Methods


European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 395-400

Here current creation online social networks (OSNs) become more and more common and the social life of people has become more linked to these pages. They use OSNs to remain in finger with everyone else, distribute news, prepare dealings and still run their personal e-. Out of control of the OSN's evolution and the huge extent of their supporters 'individual developments, they have been attackers and impostors who take individual information, share fake news and disseminate vindictive exercises. Researchers in various fields began inspecting environmentally friendly techniques in order to perform abnormal activity and counterfeit money that is based on accounting and classification algorithms [1]. However, the use of stand-alone classification algorithms no longer yields a straightforward outcome, some of the factors that are manipulated by the account have a low influence or have no impact in the closing results. The paper proposes to use the SVM-NN as a modern algorithm to effectively identify suspected Twitter accounts and bots, to add four choices and to restrict measurements. Three laptop classification mastering algorithms were used to determine the actual or false identity of target accounts. They included the SVM, the Neural Network and our recently urbanized SVM-NN method that utilizes far less hardware but is still able to correctly identify about 98% of the money due to the training data set.

Vision Based Alert System for Road Signs Detection

K. Hemalatha; D.Uma Nandhini; Karthika S

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1872-1877

TOver recent years, there is a huge increase in road accidents which makes us take more surveillance actions to reduce road accidents. In recent due to researches there is a huge improvement in the field of deep learning and computer vision. Our project is mainly focused on developing a vision based alert system for drivers. We built the model with the help of convolution neural networks a sub field of deep learning and computer vision. We have taken road sign data and trained the model to detect 32 different road signs. The data has been collected from German road sign datasets which consists of 20000 images. We developed the learning model with Keras frame- work which is a high-level API. The Keras works on the Tensor Flow backend which is developed by Google. The Keras framework enables us to build a state-of-the-art model to detect the road sign. For developing the model and to pre-processes the image we have used python language which has a vast number of libraries for image computations and to build deep neural networks. The main aim of our project is to develop a vision based alert system for drivers which will help us to improve road safety. Our model will also help new learners to improve the driving experience.


V. Praveena; P. Chinnasamy; P. Muneeswari; R. Ananthakumar; Bensujitha .

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2438-2445

-Plants are very necessary for the earth and for all living organisms. Plants maintain the atmosphere. Plant illness, an impairment of the traditional state of a plant that interrupts or modifies its very important functions. All species of plants, wild and cultivated alike, are subject to illness. These diseases occur totally on leaves, but some might also occur on stems and fruits. Leaf diseases are the foremost common diseases of most plants. Plant pathology is the science study of pathogens and environmental circumstances causing illnesses in crops. Organisms causing transmissible disease include fungi, oomycetes, bacteria, viruses, viroids, etc. The latest technique involves automated classification of diseases from plant leaf images neural networks persecution approach called hunting enhancement of microorganisms primarily focused on executing Neural system relies on planar basic principle. Throughout this article, classic neural network algorithms are used to detect and classify the areas infected with multiple illnesses on the plant leaves in order to increase the velocity and precision of the network. The region's increasing formula will improve the network's potency by searching and grouping seed points with prevalent feature extraction method characteristics. The scheduled methodology achieves greater precision in disease detection and classification.