Age Estimation from fMRI Data Using Recurrent Neural Network

Finding a biomarker that indicates the subject’s age is one of the most important topics in biology. Several recent studies tried to extract a biomarker from brain imaging data including fMRI data. However, most of them focused on MRI data, which do not provide dynamics and lack attempts to apply recently proposed deep learning models. We propose a deep neural network model that estimates the age of a subject from fMRI images using a recurrent neural network (RNN), more precisely, a gated recurrent unit (GRU). However, applying neural networks is not trivial due to the high dimensional nature of fMRI data. In this work, we propose a novel preprocessing technique using the Automated Anatomical Labeling (AAL) atlas, which significantly reduces the input dimension. The proposed dimension reduction technique allows us to train our model with 640 training and validation samples from different projects under mean squared error (MSE). Finally, we obtain the correlation value of 0.905 between the predicted age and the actual age on 155 test samples. The proposed model estimates the age within the range of ±12 on most of the test samples. Our model is written in Python and is freely available for download.

Feature Data-driven Reinforced Fuzzy Radial Basis Function Neural Network Classifier With the Aid of Preprocessing Techniques and Particle Swarm Optimization

In this study, reinforced fuzzy radial basis function neural networks (FRBFNN) classifier driven by feature extracted data completed with the aid of effectively preprocessing techniques and evolutionary optimization, and its comprehensive design methodology are introduced. An Overall structure of the reinforced FRBFNN comprises the preprocessing part, the premise part and the consequence part of fuzzy rules of the network. In the preprocessing part, four types of preprocessing algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), combination of PCA and LDA (Hybrid PCA) and fuzzy transform (FT) are considered. To extract feature data suitable to characterize signal data, the feature extraction of information data is carried out through the dimensionality reduction done by the preprocessing technique, and then the reduced data are used as the input to the FRBFNN classifier. In the premise part of fuzzy rules of the network, the number of fuzzy rules is determined according to the number of clusters by fuzzy c-means (FCM) clustering. The fitness values of individual fuzzy rules are obtained based on data distribution. In the consequence part of fuzzy rules of the network, the parameters of connection weights located between the hidden layer and the output layer of FRBFNN classifier are estimated by means of the least square estimation (LSE). Particle swarm optimization (PSO) is exploited for structural as well as parametric optimization in the FRBFNN classifier. The parameters to be optimized by PSO are related to six factors such as the determination of whether to use data preprocessing, the type of data preprocessing technique, the number of input variables reduced by the preprocessing technique, fuzzification coefficient (FC) and the number of fuzzy rules used in fuzzy c-means (FCM) clustering, and the type of connection weights. By using diverse benchmark dataset obtained from UCI repository, the classification performance of the reinforced FRBFNN classifier was evaluated. Through a variety of classification algorithms existed in the Weka data mining software (Weka), the classification performance of the reinforced FRBFNN classifier was compared as well. The superiority of the proposed classifier is demonstrated through Friedman test. Furthermore, we assessed the classification performance of the reinforced FRBFNN classifier applied to black plastic wastes spectral data acquired from Raman and Laser induced breakdown spectroscopy (LIBS) equipment for the practical application of the material sorting system of the black plastic wastes.

Correlation approach in predictor selection for groundwater level forecasting in areas threatened by water deficits

Reliable long-term groundwater level (GWL) prediction is essential to assess the availability of resources and the risk to drinking water supply in changing climatic and socio-economic conditions, especially in areas with water deficits. The modern approach in this area involves the use of machine learning methods. However, the greatest challenge in these methods lies in the optimization of input selection. The presented research concerns the selection of the best combination of predictors using the Hellwig method. It served as a preprocessing technique before GWL prediction using support vector regression (SVR) and multilayer perceptron (MLP) for three wells in the Greater Poland Province, where the largest water deficits occur, in the period 1975–2014. The results of this method were compared with those of the regression method, general regression model. For the case study under investigation, the Hellwig method found GWL at lags of −1 and −2 months, all precipitation from the current month, and delayed by −1 to −6 months, and past temperature at months −1, −3, −4 and −6 as the most informative input set. Such input led to a model accuracy of 0.003–0.022 for a mean squared error and r2 of >0.8. The results obtained with SVR were slightly better than those with MLP. Moreover, every well required an individual set of predictors, and additional meteorological inputs improved the models’ performance.

A robust hybrid fusion segmentation approach for automated tumor diagnosis and classification in brain MR images

In today’s world, Brain Tumor diagnosis plays a significant role in the field of Oncology. The earlier identification of brain tumors increases the compatibility of treatment of patients and offers an efficient diagnostic recommendation from medical practitioners. Nevertheless, accurate segmentation and feature extraction are the vital challenges in brain tumor diagnosis where the handling of higher resolution images increases the processing time of existing classifiers. In this paper, a new robust weighted hybrid fusion classifier has been proposed to identify and classify the tumefaction in the brain which is of the hybridized form of SVM, NB, and KNN (SNK) classifiers. Primarily, the proposed methodology initiates the preprocessing technique such as adaptive fuzzy filtration and skull stripping in order to remove the noises as well as unwanted regions. Subsequently, an automated hybrid segmentation strategy can be carried out to acquire the initial segmentation results, and then their outcomes are compiled together using fusion rules to accurately localize the tumor region. Finally, a Hybrid SNK classifier is implemented in the proposed methodology for categorizing the type of tumefaction in the brain. The hybrid classifier has been compared with the existing state-of-the-art classifier which shows a higher accuracy result of 99.18% while distinguishing the benign and malignant tumors from brain Magnetic Resonance (MR) images.

Low-Complexity 2D-MUSIC for Joint Range and Angle Estimation of Frequency Modulated Continuous-Wave Radar

A pre-processing technique is proposed to reduce the complexity of two-dimensional multiple signal classification (2D-MUSIC) for the joint range and angle estimation of frequency-modulated continuous-wave (FMCW) radar systems. By using the central symmetry of the angle steering vector from a uniform linear array (ULA) antenna and the linearity of the beat signal in the FMCW radar, this preprocessing technique transforms 2D-MUSIC from complex values into real values. To compare the computational complexity of the proposed algorithm with the conventional 2D-MUSIC, we measured the CPU processing time for various numbers of snapshots, and the evaluation results indicated that the 2D-MUSIC with the proposed pre-processing technique is approximately three times faster than the conventional 2D-MUSIC.

Event Log Preprocessing for Process Mining: A Review

Process Mining allows organizations to obtain actual business process models from event logs (discovery), to compare the event log or the resulting process model in the discovery task with the existing reference model of the same process (conformance), and to detect issues in the executed process to improve (enhancement). An essential element in the three tasks of process mining (discovery, conformance, and enhancement) is data cleaning, used to reduce the complexity inherent to real-world event data, to be easily interpreted, manipulated, and processed in process mining tasks. Thus, new techniques and algorithms for event data preprocessing have been of interest in the research community in business process. In this paper, we conduct a systematic literature review and provide, for the first time, a survey of relevant approaches of event data preprocessing for business process mining tasks. The aim of this work is to construct a categorization of techniques or methods related to event data preprocessing and to identify relevant challenges around these techniques. We present a quantitative and qualitative analysis of the most popular techniques for event log preprocessing. We also study and present findings about how a preprocessing technique can improve a process mining task. We also discuss the emerging future challenges in the domain of data preprocessing, in the context of process mining. The results of this study reveal that the preprocessing techniques in process mining have demonstrated a high impact on the performance of the process mining tasks. The data cleaning requirements are dependent on the characteristics of the event logs (voluminous, a high variability in the set of traces size, changes in the duration of the activities. In this scenario, most of the surveyed works use more than a single preprocessing technique to improve the quality of the event log. Trace-clustering and trace/event level filtering resulted in being the most commonly used preprocessing techniques due to easy of implementation, and they adequately manage noise and incompleteness in the event logs.

Kathakali face expression detection using deep learning techniques

To develop a Deep Learning algorithm that detects the Kathakali face expression (or Navarasas) from a given image of a person who performs Kathakali. One of India’s major classical dance forms is Kathakali. It is a “story play” genre of art, but one distinguished by the traditional male-actor-dancers costumes, face masks and makeup they wear. In the Southern region of India, Kathakali is a Hindu performance art in Malayalam speaking. Most of the plays are epic scenes of Mahabharata and Ramayana. A lot of foreigners visiting India are inspired by this art form and have been curious about the culture. It is still used for entertainment as a part of tourism and temple rituals. An understanding of facial expressions are essential so as to enjoy the play. The scope of the paper is to identify the facial expressions of Kathakali to have a better understanding of the art play. In this paper, Machine Learning and Image Processing techniques are used to decode the expressions. Kathakali face expressions are nine types namely-Adbhutam (wonder), Hasyam (comic), Sringaram(love), Bheebatsam(repulsion), Bhayanakam(fear), Roudram(anger), Veeram(pride), Karunam(sympathy) and Shantham (peace). These Expressions are mapped to real world human emotions for better classification through face detection and extraction to achieve the same. Similarly a lot of research in terms of Preprocessing and Classification is done to achieve the maximum accuracy. Using CNN algorithm 90% of the accuracy was achieved. In order to conserve the pixel distribution and as no preprocessing was used for better object recognition and analysis Fuzzy algorithm is taken into consideration. Using this preprocessing technique 93% accuracy was achieved.

How Different Text-Preprocessing Techniques using the Bert Model Affect the Gender Profiling of Authors

Forensic author profiling plays an important role in indicating possible profiles for suspects. Among the many automated solutions recently proposed for author profiling, transfer learning outperforms many other state-of-the-art techniques in natural language processing. Nevertheless, the sophisticated technique has yet to be fully exploited for author profiling. At the same time, whereas current methods of author profiling, all largely based on features engineering, have spawned significant variation in each model used, transfer learning usually requires a preprocessed text to be fed into the model. We reviewed multiple references in the literature and determined the most common preprocessing techniques associated with authors' genders profiling. Considering the variations in potential preprocessing techniques, we conducted an experimental study that involved applying five such techniques to measure each technique’s effect while using the BERT model, chosen for being one of the most-used stock pretrained models. We used the Hugging face transformer library to implement the code for each preprocessing case. In our five experiments, we found that BERT achieves the best accuracy in predicting the gender of the author when no preprocessing technique is applied. Our best case achieved 86.67% accuracy in predicting the gender of authors.