European Journal of Molecular & Clinical Medicine

The main reason of increasing mortality rate among women is the breast cancer. It makes several hours with the less availability of systems to identify the diagnosis of cancer manually. Hence there is a need to develop an automatic system for early detection of cancer. Several researchers have focused in order to improve performance and achieved to obtain satisfactory results. But unfortunately it will be very difficult to detect the cancer in beginning stages because the symptoms may be inappropriate.Therefore, there is a need to determine and acquire a new knowledge to prevent and minimizing the risk of getting effected with cancer. Machine learning (ML) is algorithms are widely used in detecting breast cancer patterns and predict the grading level. Machine learning techniques can be used to classify the stage of cancer, where machine can be trained from past data and build a model so that it can predict the category of new input.In this paper we used K-nearest neighbors (K-NN) and Support Vector Machine (SVM) on the dataset collected from UCI repository to detect breast cancerwith respect to the results of accuracy the efficiency of algorithm is also measured and compared.

One of the biggest revolutions of modern history is the invention of agriculture for a healthier lifestyle. It significantly changed the human culture and played an important role in the development of the population and biological improvements in food production and domestication. Study into agriculture is then planned by improving the disease diagnostics method with the use of newer information technology to enhance efficiency and quantity for agricultural production and its allied operation. This project focuses on the identification and diagnosis of plant leaf diseases of tomatoes and pomegranate based on visual symptoms, anthracnose, and powdery mildew. Machine learning and image processing using SVM, KNN require many steps to identify and distinguish disease signs

Over one third of world are employed in agriculture and the quantity is gradually falling because the financial losses of the farmers. One of the causes behind this momentary loss is the shortage for era in agriculture. Continuous cropping and over use of fertilizers cause the decline in soil productiveness and impact the environment as well The paper explains how the amount of soil vitamins and environmental factors followed by the pointers for cropping and special fertilization of the site can be established. 1 The selection of the best crop for the soil and the sowing of it to provide the full yield is one of the key problems in agriculture. The proposed method takes the soil and PH samples as the input and helps to predict the crops that can be recommended suitable for the soil and fertilizer that can be used as the solution in the form of the webpage.So, the soil information is collected through sensors an the data transmitted from the Arduino through Zigbee and WSN ( Wireless Sensor Network) to MATLAB and analyzing the soil data and processing is done with help of ANN (Artificial Neural Network) and crop recommendations is done using SVM ( Support Vector Machine ) .

In this paper we have applied various classification algorithm to demonstrate better classifier to produce a hybrid selection of classifier. It is enlarged with weighted balloting on the idea of Out_Of_Bag blunders charge of man or woman decision bushes. As pre work, we first done evaluation of Random Forest the usage of five one-of-a-kind break up procedures; a unmarried split quantity is used at a time for whole forest. In this paper, we to start with proposed an superior random Forest that utilizes polluting affect optimization strategies just like the bushes in random forests. If there have to be an occurrence of accuracy development, inquire approximately is finished using exceptional belongings assessment procedures and consolidate capacities. A pass breed selection tree model alongside weighted balloting is proposed which recovers the accuracy. Development in getting to know time principally issues on diminishing range of base choice bushes in Random Forest with the aim that learning and for this reason, class is quicker. The methodologies proposed in the bearing of this direction are separate parcels of schooling datasets to get acquainted with the bottom choice bushes, and ranking of training bootstrap samples primarily based on first rate range. Both these methodologies are prompting efficient gaining knowledge of Random Forest classifier.

This paper presents several room occupancy detection methods using statistical learning model. Occupancy detection system is mainly used for energy saving in green buildings such as offices and residential apartments. The system will automatically switched-off the lighting, heating or ventilation appliances when the room is empty. The proposed work uses temperature and humidity sensor to detect human presence. All the input values from this sensor are transmitted to an IoT platform called Blynk (for data monitoring), through the medium of an open-source microcontroller board NodeMCU. The collected data is analyzed using two different approaches which are supervised learning model and unsupervised learning model. Results show that for supervised learning, SVM performs slightly better than Decision Tree. While for unsupervised subspace learning, Minimax yields better probability of detection than SVD in worst case criterion.

This paper presents the design and development of an augmented reality (AR) app to enhance learning Mandarin among university students using a user-centered design life cycle (UCDL). A survey was conducted to investigate the difficulty of learning Mandarin and the thoughts of using technology to assist the students in learning the language. Forty-five students participated in the survey. The results show that participants have difficulty learning to speak, write, read, or listen in Mandarin, with writing was found to be the most difficult (M = 3.49, SD = .94). The majority of the participants (n = 39, 87%) reported having never seen or used an AR education app. However, most (n = 36, 80%) also said that they are interested in using an AR app to learn Mandarin. A low-fidelity prototype of an AR app to assist students in learning Mandarin was designed. An expert usability evaluation was conducted with three experts. Thirty-three usability problems were found, and further changes to the low-fi were designed. A usability evaluation of the low-fi with a group of students will be conducted followed by the app’s development. A final round of usability testing of the final app will also be conducted.

Brain tumour segmentation is one of the most critical and time-consuming jobs in the field of medical image processing since a human-assisted manual categorization may lead to incorrect prognosis and diagnosis. Furthermore, when there is a big quantity of data to be handled, it is a time-consuming job to say the least. There is a great deal of variation in brain tumours. There is a resemblance in appearance between tumour and normal tissues, which allows for the extraction of tumour areas from normal tissues. Images grow stubborn as time goes on. Using 2D Magnetic Resonance Imaging, we presented a technique for extracting brain tumours from brain scans. The Fuzzy C-Means clustering technique was used to cluster brain images (MRIs), which was then followed by conventional classifiers and other methods. A convolution neural network is a kind of neural network. The experimental research was conducted out on a real-time dataset including tumours of varying sizes, and Locations, forms, and varying picture intensities are all explored. In the conventional classifier section, we used six different traditional classifiers. Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Multilayer Perception (MLP), and Logistic Regression are examples of machine learning algorithms. Regression, Nave Bayes, and Random Forest are all machine learning techniques that have been incorporated in scikit-learn. Following that, we went on to Convolution Neural Network (CNN) is a kind of neural network that is built using Keras and Tensor flow since it produces superior results. Performance as compared to the conventional ones CNN had an accuracy rate of 97.87 percent in our research, which is very impressive. The In this article, the primary objective is to differentiate between normal and aberrant pixels using texture-based and statistical methods. Characteristics that are based on
 

Human Activity detection is a talented region has the capacity to earn the human culture by creating assistive advances so that assist old, incessantly sick and for those with exceptional requirements. Precise movement acknowledgment is testing since human action is mind boggling and profoundly assorted. Writing overview acted approximately that has exposed data mining technique are utilized for grouping of exercises. Data mining methods, Naive Bayes with SVM and KNN with Neural Network are end up by proficient in ordering the accelerometers understanding data. This datasets have huge preparation of occurrence by numerous earnings by values. Building categorisers the group like data is as yet a difficult errand. Arbitrary woodland is known for accomplishing high precision in characterization. Its strength in arranging enormous informational indexes is capable. Present paper projects random forest representation for characterizing/anticipating the way of performance. Present data is pre handled to complete stability. Occurrences by organizing dataset are attracted irregular for n tests, and n choice tree are built. Thus, a random based forest is built for ordering initiates depended accelerometers information esteems. To anticipate unlabeled exercise information, total of n trees is presented. Exploratory investigations are led to consider the action acknowledgment capacity of the representation; the outcomes are contrasted and well known managed order strategies. It is seen that the projected representation hits the other grouping methods in relative examination. The planned grouping representation is constrained to perform movement acknowledgment with regards to weight lifting works out. Human Activity acknowledgment is can be applied to some reality, human-driven issues

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.

This Paper introduces the implementation of different supervised learning techniques for producing accurate estimates of ground water, including meteorological and remotely sensed data. The models thus developed can be extended to be used by the personal remote sensing systems developed in the Center for Self-Organizing Intelligent Systems (CSOIS). To analyze these data and to extract relevant features, such as essential climate variables (ECV), specific methodologies need to be exploited.. The new algorithm enhances the temporal resolution of high spatial resolution of soil moisture observations with good quality and can benefit multiple soil moisture-based applications and research