European Journal of Molecular & Clinical Medicine

        A summary of existing work on the use of machine learning and deep learning       methods in biometrics is presented here. Biometrics traits covered include physiological (image, voice) as well as behavioral (gait, signature) features. This study shows that machine learning has a high potential to improve the performance of biometrics systems due to ML’s ability to mine, search and analyze big sets of data, performing matching tasks more quickly and reliably than the conventional methods. At the end some key challenges in use of adopting ML in biometrics systems are pointed out.

Much attention has been paid to the usage of handwritten mathematical equations and symbols, including pattern recognition industry consolidation Using a novel and sophisticated algorithm, it is now possible to identify the handwritten characters, a more diverse variety of handwritten digits is now visible. A number of machine learning algorithms, including conventional Neural Networks, Support Vector Machines, and Multilayer Perception. Finding the most effective and efficient approach for pattern recognition is the key goal or objective. Paper displays the accuracy of various classification methods varies. The Bayesian Network makes a "rough" classification of a binary image. The use of neural networks for classification contents.

In recent years, Malignant Melanoma Cancer has caused an increased exponential in human diseases, for this reason, it is essential to detect it from its early stages. Deep Learning is one of the most applied technologies for the analysis of images oriented to medicine, facilitating the diagnosis of diseases in patients, allowing them to make accurate decisions about their health. In this paper, we propose a convolutional neural network architecture derived from the evaluation of different convolutional neural networks that meet the objective of obtaining more pressure on the information of the acquired image. The model for the problem is based on a binary distribution, 1 in case of malignant and 0 for benign, so that melanoma can be detected early and is very useful, for this we used 2 different datasets with a total of 2650 images for training the architecture. Finally, a comparison of the results obtained in other research has been made, where the metrics of our project are considerably improved by having 3 layers. This new architecture is a proposed solution for the optimization of training and validation of images.

A program has been planned and developed to diagnose and identify brain cancer. The program employs computer-based techniques in the detections of tumor fragments or tumors, and in photographs of various Astrocytoma brain tumor patients, it classifies the type of tumor utilizing Artificial Neural Network. For the diagnosis of the brain tumor, photographs of the patients afflicted by cancer were created utilizing image processing technique such as imaging segmentation,histogram equalization, image enhancement, morphologic surgery and feature extraction.Gray Level Co-occurrence Matrix (GLCM) is used for the detection of surface characteristics in the observed tumor. Such properties are contrasted with the functionality contained in the knowledge base.To order to identify various forms of brain cancers, a neuro fuzzy concept was eventually created. The entire system was verified in two stages: first, the phase of learning / training as well as second, the phase of recognition / testing.The device was equipped through documented MRI images from patients with impaired brain cancer from the Department of Radiology of Tata Memorial Hospital (TMH). Known brain cancer tests of impacted MRI scans are often obtained from TMH and used for device monitoring. The method has been shown to be effective in classifying these samples.

Plants are very important to the earth and all living things. Plant diseases are a kind of destruction of the normal state of plants, which can interrupt or change their life functions. Leaf disease is the most common disease in most plants. One of the ultimate key factors in reducing production is the onset of disease. Peanut plant diseases, such as fungi, soil-borne and viruses. In this article, the software certainty to automatically classify peanut leaf diseases is used. This method will increase the yield of crops. It includes the number of steps. Various image processing techniques use K nearest neighbours (KNN). In order to improve the performance of existing algorithms, the SVM classifier is replaced with KNN classification. n order to improve the speed and accuracy of the network for identifying and classifying different disease-infected areas on peanut leaves, a classic neural network algorithm is used. In this article, the KNN classifier algorithm is used to classify 4 different diseases.

One of the major concerns of software industries is to develop invulnerable and secure software. A project is successful if it is delivered within provided time constraints with the required quality. The aim of this research is to enhance the project planning phase by risk assessment at the start of software development life cycle. The proposed model is developed to accurate estimation of risk in software project. The software risk estimation model is being made using neuro-fuzzy approach which is beneficial to the project manager in the first phase of software development life cycle. This methodology is different from the other risk assessment process as it uses the vague factors of different type of risk parameters in software projects. Two main activities of project planning phase are risk assessment and effort estimation. Effort estimation is mostly influencing with the probability of risk estimation at the early phase of software development life cycle. Implement result shows that it reduces risk caused due to vague parameters in software projects. The intelligent system so developed is also capable of identifying the risk of similar kind in any software project for hospital network system.

Myocardial infractions are the main explanation for death within the world nowadays, significantly in India. The need to predict this is often a serious necessity for rising the country’s health-care sector. Exact and precise prognosis of the consumers illness in the main depends on graphical record of cardiogram information and clinical data. This record is being fed to a nonlinear contagion prediction model. This nonlinear cardiac function observing module is having the ability to notice cardiac abnormalities. The predictable system develops consociate in developing productive approach to gather the clinical and graphical record of cardiogram data, thus to train the simulated neural network to accurately predict the cardiac abnormalities. The proposed system can analyze the graphical record of cardiogram and clinical information to train the neural network for predicting opportunities of the myocardial infraction and it can generate a report expecting the deviations within the cardiac or its functioning.

Forest fire is a significant natural issue, making practical and biological harm while imperiling the human lives. The key component for controlling such marvel is fast identification .To accomplish this, one option is using neural networks to identify the fires, such that we implement Forest fire Detection. By using this convolution Neural Networks we detecting the fires that occur in the forest. Later we intimate message to forest officers then they take immediate action. CNN is a calculation that takes an input picture, assign the consequences (learnable loads and predispositions) to dissimilar perspectives in the picture and have the option to divide one from the other.

Brain-computer interface (BCI) decoding connects the human nervous world to the external world.
People's brain signals to commands that computer devices can detect. In-depth study the performance
of brain-computer interface systems has recently increased. In this article, we will systematically
Investigate brain signal types for BCI and explore relevant in-depth study concepts for brain signal
analysis. In this study, we have a comparison of different traditional classification algorithms new
methods of in-depth study. We explore two different types Deep learning methods, i.e., traditional
neural networks Architecture with Long Short term Memory and Repetitive Neural Networks. We
check the classification Accuracy of Recent 5-Class Study-State Visual Evoked Opportunities dataset.
The results demonstrate in-depth expertise learning methods compared to traditional taxonomy
Algorithms.

This article provides an assessment of the investment potential of the regions of the Republic of Uzbekistan and the development of science-based measures to ensure sustainable growth of the enterprise, achieving global competitiveness - affecting investment efficiency. opinions and comments on in-depth and comprehensive analysis of factors, identification of quantitative relationships between them.

Cardiac arrhythmia can be identified using abnormal electrical activity of heart, this is a great menace to humans. In order to diagnose cardiac problems ECG signal is widely used. When the background noise is rejected from the ECG signal we obtain a QRS component. This QRS component consists of high frequency and high energy waves that are very easy to detect and study. Once QRS component is obtained, it is further spited into various classes that can aid in diagnosing the abnormalities. Previously extracted features are compared to find the heart abnormalities. In this paper Feed-Forward neural network is selected and data base are used to store and analyze the data.

With growing use of sensitive equipment, studies on power quality had developed to conduct data analysis on power quality. Wavelet transformation method has been very useful in investigating diverse types of events in power quality. Present paper associates the utilization of different wavelets at various scales and level of disintegration in examining real Power Quality (PQ) occasions from a link model or signal is produced utilizing MATLAB background. In this system voltage sag, swell, harmonics, momentary interruption, fault conditions and transient events are performed. The system proposed includes elements smaller than the traditional procurement process. In this method wavelet transform identified different power quality events and then classified them via Artificial Neural Network (ANN). Power quality disturbances are defined by the load received after neural network training. Separate MATLAB simulation model is designed to produce various power quality events like voltage sag, swell, passing disruption, harmonics, temporary and fault signals. ANN learning also wiped out MATLAB simulation using NN toolbox for power quality disturbance detection through the aliasing of voltage signals energy. Satisfactory results obtained in MATLAB simulink using such techniques.

Emotions are very present in our daily life. They are manifested by physiological reactions (palpitations, heat, and acceleration of the pulse), motor reactions (gestural expressions, facial expressions) and changes in the voice. The complexity of emotions was capable to seek attention of various researchers. Differing representations of emotions were then proposed to produce a set of theories. The automation of facial expression detection can then be approached in a variety of ways. We concentrated on the face expression detection. Concerning to this the recognition is based on different visual characteristics of the expression.
This paper is dedicated at first to the exhibition of the definition of emotions, followed by the great theories that have emerged in this area. In a second step, we present the methods of extraction of the facial characteristics and the methods of selection. Finally, some databases used for automatic recognition of emotions are presented.

Due to the advancement of computer technology image-processing techniques have become increasingly important in a wide variety of applications. Image segmentation plays a important role in image processing. Image segmentation refers to partition of an image into different regions that are similar and different in some characteristics like color, intensity or texture. Different algorithms and techniques have been developed for image segmentation. This paper investigates and compiles some of the technologies used for image segmentation. The various segmentation techniques like Edge Detection, Threshold, Region based, Feature Based Clustering and Neural Network Image Segmentation were discussed in this paper

Produces from agriculture which feeds the entire population is dependent on proper farming practices. The growth of technology must pay a way for increasing the produce per acre and also help in reducing the onset of frequently affecting plant disease. Timely help in detecting the diseases coupled with solution helps in productivity and quality of the produce. This paper aims to detect the plant leaf disease based on image detection and using machine learning to identify the disease with accuracy and suggest the solution. The product must cater to the needs of urban and rural farmer and also the person with only lay man knowledge of taking photo. This project mainly focuses on leaf disease like Anthracnose, Bacterial Blight, Cercospora, Alternaria Altermata diseases in the Pomegranate, Indian Beech, Tobacco, and Bitter Gourd leaves. This project aims to identify the disease even with lesser region of Interest and predict the leaf diseases using Convolutional Neural Network Algorithm