This research provides a comparison between the performances of Sugeno type versus Mamdani-type fuzzy inference systems. The main motivation behind this research was to assess which approach provides the best performance for satellite image classification. The performance of each approach has been evaluated for six bands (from Landsat-5) for West Iraq image classification and compared with traditional method (Maximum likelihood), based on pixel-by-pixel technique. Due to the importance of performance in online systems we compare the Mamdani model, used previously, with a Sugeno formulation using four types of membership function (MF) generation methods. The first method triangular membership function using the mean, minimum and maximum of the histogram attribute values. The second approach generates triangular membership function using the peak and the standard deviation of attributes values. The third procedure generates Gaussian membership function using the mean and the standard deviation of the histogram attributes values. The fourth approach generates Gaussian membership function using the peak and the standard deviation of the histogram attributes values. The results show that the Mamdani models perform better in most of the case under study.
Obesity is the excess of body weight relative to height above the desired level as a result of excessive increase in the ratio of body fat mass to lean mass. It causes many health problems due to its negative effects on body systems (cardiovascular system, musculoskeletal system, gastrointestinal system, respiratory system, skin, endocrine system, genitourinary system) and psychosocial status. In this study is aimed to effective detection of the eating and physical condition-based obesity stages using machine learning algorithms. The dataset contains data for the estimation of obesity stages in individuals from Mexico, Peru, and Colombia and is available as open source. There are 2111 records and 17 attributes in the dataset. In the records, obesity stages were categorized as insufficient weight, normal weight, overweight level I, overweight level II, obesity type I, obesity type II and obesity type III. The 10-fold cross-validation method was used to validate the model and the performances of the Support Vector Machine (SVM), Random Forest (RF), and Multilayer Perceptron (MLP) classification algorithms were compared. It has been determined that the highest performance among the algorithms whose performances are compared belongs to the RF Algorithm (95.78%). This paper’s abstract has been presented at the International Conference on Computational Mathematics and Engineering Sciences held in Ordu (Turkey), / 20-22 May. 2022.
Internet-based platforms such as social media have a great deal of big data that is available in the shape of text, audio, video, and image. Sentiment Analysis (SA) of this big data has become a field of computational studies. Therefore, SA is necessary in texts in the form of messages or posts to determine whether a sentiment is negative or positive. SA is also crucial for the development of opinion mining systems. SA combines techniques of Natural Language Processing (NLP) with data mining approaches for developing inelegant systems. Therefore, an approach that can classify sentiments into two classes, namely, positive sentiment and negative sentiment is proposed. A Multilayer Perceptron (MLP) classifier has been used in this document classification system. The present research aims to provide an effective approach to improving the accuracy of SA systems. The proposed approach is applied to and tested on two datasets, namely, a Twitter dataset and a movie review dataset; the accuracies achieved reach 85% and 99% respectively.
Cosmetic surgery is more prevalent in the world in recent years. A beautiful and flawless face is everyone's dream. Aging, environmental factors, disease, or poor diet are among the factors that influence body wrinkles. Various methods are used to reduce these lines. It can be said that the simplest and most effective solution is to inject cosmetic fluids into these areas. But, due to the increase in facial injections using cosmetic fluids, which are considered toxins, the risk of injury to the surrounding facial nerves and injury to one of the main facial nerves is increasing, creating a catastrophe or deformation in the face irreversibly. Deep learning algorithms have been used to determine whether cosmetic fluids are injected or not. Deep Convolutional Neural Networks (CNNs), VGG16, ResNet....etc deep learning algorithms have demonstrated excellent performance in terms of object detection, picture classification, and semantic segmentation. all the suggested approach consists of three stages: feature extraction, training, and testing/validation. Deep learning technology is used to train and test the system with before and after photographs. Numerous investigations have been carried out using various deep learning algorithms and databases the main goal is to attain maximum accuracy to ensure that injected cosmetic fluids by specialists have been injected in safe areas in addition to facial recognition and determining whether or not the person received an injection. The most used databases are IIITD plastic surgery and HDA_Plastic surgery.
This research represents part of the current attempts to employ remote sensing data in the scopes of the civil engineering and the geotechnical engineering applications. There is great need to know the kinds of soil and their geotechnical properties, to create recent maps which have the capability and high flexibility to deal with them in digitizing way. Therefore GIS techniques are employed in the soil of area of study . By using ArcView software, a geographical database and information about soil chemical properties analysis have been registered and constructed digitally to represent the geotechnical soil characteristics maps . The work includes the digital image processing ( digital classification techniques) by using ERDAS, ver.,8.4 package, and classify the soil of study area by using the supervise and unsupervised techniques . The geotechnical maps by using GIS techniques depend on remote sensing data are the better to represent the ground truth regarding the characteristics of soil , in comparison with the traditional method, because they are easy way to produce, use, store and update, in addition they save in efforts, time and cost . The results of this study have shown that the soil of study area is gypsum where it ratio exceeded the allowable ratio ( 10.75 % ) for all samples . In addition the total Soluble Salts ratio and SO4 ratio high compared to allowable ratio (10 % , 5 %) respectively .