Deep Learning and Machine Learning Techniques of Diagnosis Dermoscopy Images for Early Detection of Skin Diseases

With the increasing incidence of severe skin diseases, such as skin cancer, endoscopic medical imaging has become urgent for revealing the internal and hidden tissues under the skin. Diagnostic information to help doctors make an accurate diagnosis is provided by endoscopy devices. Nonetheless, most skin diseases have similar features, which make it challenging for dermatologists to diagnose patients accurately. Therefore, machine and deep learning techniques can have a critical role in diagnosing dermatoscopy images and in the accurate early detection of skin diseases. In this study, systems for the early detection of skin lesions were developed. The performance of the machine learning and deep learning was evaluated on two datasets (e.g., the International Skin Imaging Collaboration (ISIC 2018) and Pedro Hispano (PH2)). First, the proposed system was based on hybrid features that were extracted by three algorithms: local binary pattern (LBP), gray level co-occurrence matrix (GLCM), and wavelet transform (DWT). Such features were then integrated into a feature vector and classified using artificial neural network (ANN) and feedforward neural network (FFNN) classifiers. The FFNN and ANN classifiers achieved superior results compared to the other methods. Accuracy rates of 95.24% for diagnosing the ISIC 2018 dataset and 97.91% for diagnosing the PH2 dataset were achieved using the FFNN algorithm. Second, convolutional neural networks (CNNs) (e.g., ResNet-50 and AlexNet models) were applied to diagnose skin diseases using the transfer learning method. It was found that the ResNet-50 model fared better than AlexNet. Accuracy rates of 90% for diagnosing the ISIC 2018 dataset and 95.8% for the PH2 dataset were reached using the ResNet-50 model.

Iterative principal component analysis method for improvised classification of breast cancer disease using blood sample analysis

Breast cancer is the most common cancer in women occurring worldwide. Some of the procedures used to diagnose breast cancer are mammogram, breast ultrasound, biopsy, breast magnetic resonance imaging, and blood tests such as complete blood count. Detecting breast cancer at an early stage plays an important role in diagnostic and curative procedures. This paper aims to develop a predictive model for detecting the breast cancer using blood samples data containing age, body mass index (BMI), glucose, insulin, homeostasis model assessment (HOMA), leptin, adiponectin, resistin, and chemokine monocyte chemoattractant protein 1 (MCP-1).The two main challenges encountered in this process are identification of biomarkers and the precision of disease prediction accuracy. The proposed methodology employs principal component analysis in a peculiar approach followed by random forest tree prediction model to discriminate between healthy and breast cancer patients. This approach extracts high communalities, a linear combination of input attributes in a systematic procedure as principal axis elements. The iteratively extracted principal axis elements combined with minimum number of input attributes are able to predict the disease with higher accuracy of classification with increased sensitivity and specificity score. The results proved that the proposed approach generates a higher predictor performance than the previous reported results by opting relevant extracted principal axis elements and attributes that commend the classifier with increased performance measures.

A New Cascade-Correlation Growing Deep Learning Neural Network Algorithm

In this paper, a proposed algorithm that dynamically changes the neural network structure is presented. The structure is changed based on some features in the cascade correlation algorithm. Cascade correlation is an important algorithm that is used to solve the actual problem by artificial neural networks as a new architecture and supervised learning algorithm. This process optimizes the architectures of the network which intends to accelerate the learning process and produce better performance in generalization. Many researchers have to date proposed several growing algorithms to optimize the feedforward neural network architectures. The proposed algorithm has been tested on various medical data sets. The results prove that the proposed algorithm is a better method to evaluate the accuracy and flexibility resulting from it.

Forecasting stock price index movement using a constrained deep neural network training algorithm

The prediction of stock index movement is considered a rather significant objective in the financial world, since a reasonably accurate prediction has the possibility of gaining profit in stock exchange, yielding high financial benefits and hedging against market risks. Undoubtedly, the area of financial analysis has been dramatically changed from a rather qualitative science to a more quantitative science which is also based on knowledge extraction from databases. During the last years, deep learning constitutes a significant prediction tool in analyzing and exploiting the knowledge acquired from financial data. In this paper, we propose a new Deep Neural Network (DNN) prediction model for forecasting stock exchange index movement. The proposed DNN is characterized by the application of conditions on the weights in the form of box-constraints, during the training process. The motivation for placing these constraints is focused on defining the weights in the trained network in more uniform way, by restricting them from taking large values in order for all inputs and neurons of the DNN to be efficiently exploited and explored. The training of the new DNN model is performed by a Weight-Constrained Deep Neural Network (WCDNN) training algorithm which exploits the numerical efficiency and very low memory requirements of the L-BFGS (Limited-memory Broyden-Fletcher-Goldfarb-Shanno) matrices together with a gradient-projection strategy for handling the bounds on the weights of the network. The performance evaluation carried out on three popular stock exchange indices, demonstrates the classification efficiency of the proposed algorithm.

A five-year (2015 to 2019) analysis of studies focused on breast cancer prediction using machine learning: A systematic review and bibliometric analysis

The objective 1 of this study was to investigate trends in breast cancer (BC) prediction using machine learning (ML) publications by analysing country, first author, journal, institutional collaborations and co-occurrence of author keywords. The objective 2 was to provide a review of studies on BC prediction using ML and a blood analysis dataset (Breast Cancer Coimbra Dataset [BCCD]), and the objective 3 was to provide a brief review of studies based on BC prediction using ML and patients' fine needle aspirate cytology data (Wisconsin Breast Cancer Dataset [WBCD]). The design of this study was as follows: for objective 1: bibliometric analysis, data source PubMed (2015-2019); for objective 2: systematic review, data source: Google and Google Scholar (2018-2019); for objective 3: systematic review, data source: Google Scholar (2016-2019). The inclusion criteria for objective 1 were all publication results yielded from the searches. All English papers that had a 'PDF' option from the search results were included for objective 2. A sample of the 'PDF' English papers were included for objective 3. All 116 female patients from the BCCD, consisting of 64 positive BC patients and 52 controls were included in the study for objective 2. For the WBCD, all 699 female patients comprising of 458 with a benign BC tumour and 241 with a malignant BC tumour were included for objective 3. All 2928 publications were included for objective 1. The results showed that the United States of America (USA) produced the highest number of publications (n=803). In total, 2419 first authors contributed towards the publications. Breast Cancer Research and Treatment was the highest ranked journal. Institutional collaborations mainly occurred within the USA. The use of ML for BC screening and detection was the most researched topic. A total of 19 distinct papers were included for objectives 2 and 3. The findings from these studies were never presented to clinicians for validations. In conclusion, the use of ML for BC screening and detection is promising.

Weight-Constrained Neural Networks in Forecasting Tourist Volumes: A Case Study

Tourism forecasting is a significant tool/attribute in tourist industry in order to provide for careful planning and management of tourism resources. Although accurate tourist volume prediction is a very challenging task, reliable and precise predictions offer the opportunity of gaining major profits. Thus, the development and implementation of more sophisticated and advanced machine learning algorithms can be beneficial for the tourism forecasting industry. In this work, we explore the prediction performance of Weight Constrained Neural Networks (WCNNs) for forecasting tourist arrivals in Greece. WCNNs constitute a new machine learning prediction model that is characterized by the application of box-constraints on the weights of the network. Our experimental results indicate that WCNNs outperform classical neural networks and the state-of-the-art regression models: support vector regression, k-nearest neighbor regression, radial basis function neural network, M5 decision tree and Gaussian processes.

Data-Driven Model-Free Tracking Reinforcement Learning Control with VRFT-based Adaptive Actor-Critic

This paper proposes a neural network (NN)-based control scheme in an Adaptive Actor-Critic (AAC) learning framework designed for output reference model tracking, as a representative deep-learning application. The control learning scheme is model-free with respect to the process model. AAC designs usually require an initial controller to start the learning process; however, systematic guidelines for choosing the initial controller are not offered in the literature, especially in a model-free manner. Virtual Reference Feedback Tuning (VRFT) is proposed for obtaining an initially stabilizing NN nonlinear state-feedback controller, designed from input-state-output data collected from the process in open-loop setting. The solution offers systematic design guidelines for initial controller design. The resulting suboptimal state-feedback controller is next improved under the AAC learning framework by online adaptation of a critic NN and a controller NN. The mixed VRFT-AAC approach is validated on a multi-input multi-output nonlinear constrained coupled vertical two-tank system. Discussions on the control system behavior are offered together with comparisons with similar approaches.

Forecasting Economy-Related Data Utilizing Weight-Constrained Recurrent Neural Networks

During the last few decades, machine learning has constituted a significant tool in extracting useful knowledge from economic data for assisting decision-making. In this work, we evaluate the performance of weight-constrained recurrent neural networks in forecasting economic classification problems. These networks are efficiently trained with a recently-proposed training algorithm, which has two major advantages. Firstly, it exploits the numerical efficiency and very low memory requirements of the limited memory BFGS matrices; secondly, it utilizes a gradient-projection strategy for handling the bounds on the weights. The reported numerical experiments present the classification accuracy of the proposed model, providing empirical evidence that the application of the bounds on the weights of the recurrent neural network provides more stable and reliable learning.

Anomaly Detection Based on Mining Six Local Data Features and BP Neural Network

Key performance indicators (KPIs) are time series with the format of (timestamp, value). The accuracy of KPIs anomaly detection is far beyond our initial expectations sometimes. The reasons include the unbalanced distribution between the normal data and the anomalies as well as the existence of many different types of the KPIs data curves. In this paper, we propose a new anomaly detection model based on mining six local data features as the input of back-propagation (BP) neural network. By means of vectorization description on a normalized dataset innovatively, the local geometric characteristics of one time series curve could be well described in a precise mathematical way. Differing from some traditional statistics data characteristics describing the entire variation situation of one sequence, the six mined local data features give a subtle insight of local dynamics by describing the local monotonicity, the local convexity/concavity, the local inflection property and peaks distribution of one KPI time series. In order to demonstrate the validity of the proposed model, we applied our method on 14 classical KPIs time series datasets. Numerical results show that the new given scheme achieves an average F1-score over 90%. Comparison results show that the proposed model detects the anomaly more precisely.

Using Resistin, Glucose, Age and BMI and Pruning Fuzzy Neural Network for the Construction of Expert Systems in the Prediction of Breast Cancer

Research on predictions of breast cancer grows in the scientific community, providing data on studies in patient surveys. Predictive models link areas of medicine and artificial intelligence to collect data and improve disease assessments that affect a large part of the population, such as breast cancer. In this work, we used a hybrid artificial intelligence model based on concepts of neural networks and fuzzy systems to assist in the identification of people with breast cancer through fuzzy rules. The hybrid model can manipulate the data collected in medical examinations and identify patterns between healthy people and people with breast cancer with an acceptable level of accuracy. These intelligent techniques allow the creation of expert systems based on logical rules of the IF/THEN type. To demonstrate the feasibility of applying fuzzy neural networks, binary pattern classification tests were performed where the dimensions of the problem are used for a model, and the answers identify whether or not the patient has cancer. In the tests, experiments were replicated with several characteristics collected in the examinations done by medical specialists. The results of the tests, compared to other models commonly used for this purpose in the literature, confirm that the hybrid model has a tremendous predictive capacity in the prediction of people with breast cancer maintaining acceptable levels of accuracy with good ability to act on false positives and false negatives, assisting the scientific milieu with its forecasts with the significant characteristic of interpretability of breast cancer. In addition to coherent predictions, the fuzzy neural network enables the construction of systems in high level programming languages to build support systems for physicians’ actions during the initial stages of treatment of the disease with the fuzzy rules found, allowing the construction of systems that replicate the knowledge of medical specialists, disseminating it to other professionals..