A novel machine learning approach for early detection of hepatocellular carcinoma patients

Liver cancer is quite common type of cancer among individuals worldwide. Hepatocellular carcinoma (HCC) is the malignancy of liver cancer. It has high impact on individual’s life and investigating it early can decline the number of annual deaths. This study proposes a new machine learning approach to detect HCC using 165 patients. Ten well-known machine learning algorithms are employed. In the preprocessing step, the normalization approach is used. The genetic algorithm coupled with stratified 5-fold cross-validation method is applied twice, first for parameter optimization and then for feature selection. In this work, support vector machine (SVM) (type C-SVC) with new 2level genetic optimizer (genetic training) and feature selection yielded the highest accuracy and F₁-Score of 0.8849 and 0.8762 respectively. Our proposed model can be used to test the performance with huge database and aid the clinicians.     

Application of deep transfer learning for automated brain abnormality classification using MR images

Magnetic resonance imaging (MRI) is the most common imaging technique used to detect abnormal brain tumors. Traditionally, MRI images are analyzed manually by radiologists to detect the abnormal conditions in the brain. Manual interpretation of huge volume of images is time consuming and difficult. Hence, computer-based detection helps in accurate and fast diagnosis. In this study, we proposed an approach that uses deep transfer learning to automatically classify normal and abnormal brain MR images. Convolutional neural network (CNN) based ResNet34 model is used as a deep learning model. We have used current deep learning techniques such as data augmentation, optimal learning rate finder and fine-tuning to train the model. The proposed model achieved 5-fold classification accuracy of 100% on 613 MR images. Our developed system is ready to test on huge database and can assist the radiologists in their daily screening of MR images.     

Combining predictors for multi-layer architecture of adaptive fuzzy inference system

To solve problems with a Sugeno adaptive fuzzy neural network using training data, it is necessary to select the appropriate combination of input characteristics of the sub-adaptive neuro-fuzzy inference system (ANFIS) and to determine the appropriate topology. The multi-layer architecture of a sub-ANFIS (MLA-ANFIS) is a good model for prediction problems and solves them modularity. Since, the combination of several predictors is the current focus in the construction of hybrid intelligent systems; we created many solutions to combine machine learning methods, namely ANFIS, support vector machine (SVM), deep neural network (DNN), naive Bayes (NB), linear regression (LR), extreme learning machine (ELM), and decision tree (DT) mixed predictors, and ensemble bootstrap aggregation based on MLA-ANFIS in order to discover the optimal model of combined predictors based on the MLA-ANFIS with a combination of input features entered in the MLA-ANFIS. We implemented our approaches on 365-day concrete compressive strength, thoracic surgery, fertility diagnosis, breast, energy, and glass identification datasets from UCI. The experimental results prove that the combining predictors for the MLA-ANFIS show performance improvements compared to the pure MLA-ANFIS method.     

运用基因表达式编程的自陈量表数据建模

探讨基因表达式编程对自陈量表测量数据的建模方法。运用威廉斯创造力测验和认知需求量表获得400位中学生的测量分数,通过数据清洗,保留383个被试的分数作为建模的数据集。运用哈曼单因素检验方法没有发现共同方法偏差。采用均匀设计方法对基因表达式编程中的5个参数进行优化配置,在测试拟合度最大的试验条件下,找到了测试误差最小的模型。比较基因表达式编程和BP神经网络、支持向量回归机、多元线性回归、二次多项式回归所建模型的预测精度。研究表明,基因表达式编程能用于自陈量表测量数据的建模,该模型比传统方法所建的模型具有更高的预测精度,而且模型是稳健的。     

Optimal spatial filtering for brain oscillatory activity using the Relevance Vector Machine

Over the past decade, various techniques have been proposed for localization of cerebral sources of oscillatory activity on the basis of magnetoencephalography (MEG) or electroencephalography recordings. Beamformers in the frequency domain, in particular, have proved useful in this endeavor. However, the localization accuracy and efficacy of such spatial filters can be markedly limited by bias from correlation between cerebral sources and short duration of source activity, both essential issues in the localization of brain data. Here, we evaluate a method for frequency-domain localization of oscillatory neural activity based on the relevance vector machine (RVM). RVM is a Bayesian algorithm for learning sparse models from possibly overcomplete data sets. The performance of our frequency-domain RVM method (fdRVM) was compared with that of dynamic imaging of coherent sources (DICS), a frequency-domain spatial filter that employs a minimum variance adaptive beamformer (MVAB) approach. The methods were tested both on simulated and real data. Two types of simulated MEG data sets were generated, one with continuous source activity and the other with transiently active sources. The real data sets were from slow finger movements and resting state. Results from simulations show comparable performance for DICS and fdRVM at high signal-to-noise ratios and low correlation. At low SNR or in conditions of high correlation between sources, fdRVM performs markedly better. fdRVM was successful on real data as well, indicating salient focal activations in the sensorimotor area. The resulting high spatial resolution of fdRVM and its sensitivity to low-SNR transient signals could be particularly beneficial when mapping event-related changes of oscillatory activity.     

Support vector machine for classification of walking conditions of persons after stroke with dropped foot

Walking with dropped foot represents a major gait disorder, which is observed in hemiparetic persons after stroke. This study explores the use of support vector machine (SVMs) to classify different walking conditions for hemiparetic subjects. Seven participants with dropped foot (category 4 of functional ambulatory category) walked in five different conditions: level ground, stair ascent, stair descent, upslope, and downslope. The kinematic data were measured by two portable sensor units, each comprising an accelerometer and gyroscope attached to the lower limb on the shank and foot segments. The overall classification accuracy of stair ascent, stair descent, and other walking conditions was 92.9% using input features from the sensor attached to the shank. It was further improved to 97.5% by adding two more inputs from the sensor attached to the foot. Stair ascent was also classified by the inputs from the foot sensor unit with 96% accuracy. The performance of an SVM was shown to be superior to that of other machine learning methods using artificial neural networks (ANN) and radial basis function neural networks (RBF). The results suggested that the SVM classification method could be applied as a tool for pathological gait analysis, pattern recognition, control signals in functional electrical stimulation (FES) and rehabilitation robot, as well as activity monitoring during rehabilitation of daily activities.     

On simulating one-trial learning using morphological neural networks

“Learning once, remembering forever”, this wonderful cognitive phenomenon sometimes occurs in the learning process of human beings. Psychologists call this psychological phenomenon “one-trial learning”. The traditional artificial neural networks can simulate the psychological phenomenon of “implicit learning”, but can’t simulate the cognitive phenomenon of “one-trial learning”. Therefore, cognitive psychology gives a challenge to the traditional artificial neural networks. From two aspects of theory and practice in this paper, the possibility of simulating this kind of psychological phenomenon was explored by using morphological neural networks. This paper takes advantage of morphological associative memory networks to realize the simulation of “one-trial learning” for the first time, and gives 5 simulating practical examples. Theoretical analysis and simulation experiments show that the morphological associative memory networks are a higher effective machine learning method, and can better simulate the cognitive phenomenon of “one-trial learning”, therefore provide a theoretical basis and technological support for the study of intelligent science and cognitive science.     

Towards a new approach to predict business performance using machine learning

Financial ratio plays a crucial role in business performance prediction, but the ability of the decision maker to use this method in adjusting management strategy has been extensively ignored. In this paper we attempt to build a fuzzy chance constrained least squares twin support vector machine (FCC-LSTSVM) to predict the business performance through the financial ratios. Specifically, machine learning techniques are utilized to build the models and 796 listed companies in China are selected as the data set. We find that different efficiencies are performed for different models with the same industry and different effectiveness are shown for different predicting time periods with the same method. In addition, the predicting achievements of business performance depend on the types of industries. This paper has extent significance both in theoretical development and managerial practices.     

Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour

Automatic disease classification has been one of the most intensively searched in recent years due to the possibility of quickly providing a diagnosis to the patient. In this process, the segmentation of regions of interest of these diseases has a fundamental role in their subsequent classification. With skin lesions segmentation it is no different and in recent years many studies have achieved interesting results, becoming an important tool in aiding the medical diagnosis of skin diseases. In this work, a morphological geodesic active contour segmentation (MGAC) method is proposed with automatic initialization, using mathematical morphology which is a great partial differential equation approximation, with lower computational cost, no stability problems and fully automatic. The proposed method was tested in a stable and well-known dermoscopic images database provided by Pedro Hispano Hospital (PH2) and was compared with both methods that make use of machine learning or deep learning techniques such as fully convolutional networks (FCN), full resolution convolutional networks (FrCN), deep class-specific learning with probability based step-wise integration (DCL-PSI), and others, and also traditional methods like JSEG, statistical region merging (SRM), Level Set, ASLM and others. The MGAC showed good results in all similarity metrics compared in this work like Jaccard Index (86.16%), Dice coefficient (92.09%) and Matthew correlation coefficient (87.52%), and also achieves good results in sensitivity (91.72%), specificity (97.99%), accuracy (94.59%) and F-measure (93.82%). Thus, the proposed method presented better results in relation to all these metrics when compared to the traditional methods and still presented better results in relation to the methods that use machine learning or deep learning techniques in Jaccard Index, Dice coefficient and specificity. This confirm that the MGAC can efficiently segment skin lesions, presenting great potential to be applied in the aid of the medical diagnosis.     

Recognition of extraversion level based on handwriting and support vector machines

This study investigated whether it is possible to train a machine to discriminate levels of extraversion based on handwriting variables. Support vector machines (SVMs) were used as a learning algorithm. Handwriting of 883 people (404 men, 479 women) was examined. Extraversion was measured using the Polish version of the NEO-Five Factor Inventory. The handwriting samples were described by 48 variables. The support vector machines were separately trained and tested for each sex, using 10-fold cross-validation. Good recognition accuracy (around .7) was achieved for 10 handwriting variables, different for men and women. The results suggest the existence of a relationship between handwriting elements and extraversion.     

Automatic detection of ischemic stroke using higher order spectra features in brain MRI images

The gravity of ischemic stroke is the key factor in deciding upon the optimum therapeutic intervention. Ischemic stroke can be divided into three main groups: lacunar syndrome (LACS), partial anterior circulation syndrome (PACS), and total anterior circulation stroke (TACS), where the corresponding severity is mild, medium, and high, respectively. Herein, a unique method for the automatic detection of ischemic stroke severity is presented. The proposed system is based upon the extraction of higher order bispectrum entropy and its phase features from brain MRI (Magnetic Resonance Imaging) images. For classification, which is used to establish stroke severity, a support vector machine was incorporated into the design. The developed technique effectively detected the stroke lesion, and achieved a sensitivity, specificity, accuracy, and positive predictive value equal to 96.4%, 100%, 97.6% and 100%, respectively. The results were obtained without the need for manual intervention. This design is advantageous over state-of-the-art automated stroke severity detection systems, which require the reading neuroradiologist to manually determine the region of interest. Hence, the method is efficacious for delivering decision support in the diagnosis of ischemic stroke severity, thereby aiding the neuroradiologist in routine screening procedures.     

Risk assessment of knowledge fusion in an innovation ecosystem based on a GA-BP neural network

The risk assessment of knowledge fusion in innovation ecosystems is directly related to these ecosystems’ success or failure. A back-propagation (BP) neural network optimized by a genetic algorithm (GA) is thus proposed to evaluate the risk of knowledge fusion in innovation ecosystems. First, an index system is constructed for evaluating the risk of knowledge fusion in innovation ecosystems, and data are collected by questionnaire for use as training data for the neural networks. To realize machine learning, 84 datasets were generated, of which 60 were used to train the network, and 24 were used to test the network in MATLAB (R2014b). Evaluation models were then constructed by the BP neural network and GA-BP neural network, and their accuracy was judged by comparing the evaluation value with the target value. The comparison shows that the GA-BP neural network has faster convergence speed and higher stability, can achieve the goal more often, and reduces the possibility of the BP neural network falling into a local optimum instead of reaching global optimization. The GA-BP neural network model for the knowledge fusion risk assessment of innovation ecosystems provides a new method for practice.     

A method in modeling interactive pedestrian crossing and driver yielding decisions during their interactions at intersections

Investigating pedestrian crossing and driver yielding decisions should be an important focus considering the high risks of pedestrians in exposed to motorized traffic. Limitations, however, exist in previous studies – variables considered previously have been limited; how their behavior affect each other (defined as interactive impacts) were not sufficiently considered. This paper aims to provide a methodological approach for pedestrian crossing and driver yielding decisions during their interactions, considering of different variable types including interactive impact variables, traffic condition variables, road design variables, and environment variables. A Distance-Velocity (DV) framework proposed in an earlier study is introduced for definitions and concepts in studying pedestrian-vehicle interactions. Logistic regression, support vector machines, neural networks and random forests, are introduced as candidate models. A case study involving six crosswalk locations is conducted, focusing on interactions between pedestrians and right-turn vehicles. The proposed methodological approach is applied, with the performance of the four machine learning methods compared in terms of model generalization and confusion matrix. The model with the best performance is further compared to the typical gap-based model. Results show that random forest and logistic regression models performed the best in modeling pedestrian crossing and driver yielding decisions respective, in terms of model generalization. Besides, the DV-based modeling method (average accuracy of over 90% for pedestrians and 80% for drivers) outperformed the traditional gap-based method in all test seeds. As a key finding, interactive impacts from each other (the pedestrian and the driver) act as a key contributing variable on their decisions.     

A neuro-fuzzy network to generate human-understandable knowledge from data

Neuro-fuzzy networks have been successfully applied to extract knowledge from data in the form of fuzzy rules. However, one drawback with the neuro-fuzzy approach is that the fuzzy rules induced by the learning process are not necessarily understandable. The lack of readability is essentially due to the high dimensionality of the parameter space that leads to excessive flexibility in the modification of parameters during learning. In this paper, to obtain readable knowledge from data, we propose a new neuro-fuzzy model and its learning algorithm that works in a parameter space with reduced dimensionality. The dimensionality of the new parameter space is necessary and sufficient to generate human-understandable fuzzy rules, in the sense formally defined by a set of properties. The learning procedure is based on a gradient descent technique and the proposed model is general enough to be applied to other neuro-fuzzy architectures. Simulation studies on a benchmark and a real-life problem are carried out to embody the idea of the paper.     

融合视角下创造力的认知神经机制

创造力的认知神经机制是近年来心理学研究领域的前沿和热点问题。通过融合创造力整体宏观视角和创造性产生过程的微观视角,对创造力的认知神经机制进行了综述。宏观视角下,创造力主要涉及α波和大脑前额叶、内外侧颞叶以及外侧顶叶; 微观视角下,在创造力产生过程中主要涉及α波序列位置效应以及默认网络和执行控制网络的功能耦合。未来研究方向应该结合多模态脑成像数据库,利用机器算法来探究创造力的本质; 关注青少年群体创造力的纵向发展趋势; 结合分子遗传学研究,探究与创造力有关的基因问题。     

Cognitive computing models for estimation of reference evapotranspiration: A review

Irrigation practices can be advanced by the aid of cognitive computing models. Repeated droughts, population expansion and the impact of global warming collectively impose rigorous restrictions over irrigation practices. Reference evapotranspiration (ET₀) is a vital factor to predict the crop water requirements based on climate data. There are many techniques available for the prediction of ET₀. An efficient ET₀ prediction model plays an important role in irrigation system to increase water productivity. In the present study, a review has been carried out over cognitive computing models used for the estimation of ET₀. Review exhibits that artificial neural network (ANN) approach outperforms support vector machine (SVM) and genetic programming (GP). Second order neural network (SONN) is the most promising approach among ANN models.     

A tutorial on kernel methods for categorization

The abilities to learn and to categorize are fundamental for cognitive systems, be it animals or machines, and therefore have attracted attention from engineers and psychologists alike. Modern machine learning methods and psychological models of categorization are remarkably similar, partly because these two fields share a common history in artificial neural networks and reinforcement learning. However, machine learning is now an independent and mature field that has moved beyond psychologically or neurally inspired algorithms towards providing foundations for a theory of learning that is rooted in statistics and functional analysis. Much of this research is potentially interesting for psychological theories of learning and categorization but also hardly accessible for psychologists. Here, we provide a tutorial introduction to a popular class of machine learning tools, called kernel methods. These methods are closely related to perceptrons, radial-basis-function neural networks and exemplar theories of categorization. Recent theoretical advances in machine learning are closely tied to the idea that the similarity of patterns can be encapsulated in a positive definite kernel. Such a positive definite kernel can define a reproducing kernel Hilbert space which allows one to use powerful tools from functional analysis for the analysis of learning algorithms. We give basic explanations of some key concepts—the so-called kernel trick, the representer theorem and regularization—which may open up the possibility that insights from machine learning can feed back into psychology.     

Rolling element bearing fault diagnosis using convolutional neural network and vibration image

Detecting in prior bearing faults is an essential task of machine health monitoring because bearings are the vital components of rotary machines. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of fault signals, which requires signal processing techniques, expert knowledge, and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. With the capacity of automatically learning complex features of input data, deep learning architectures have great potential to overcome drawbacks of traditional intelligent fault diagnosis. This paper proposes a method for diagnosing bearing faults based on a deep structure of convolutional neural network. Using vibration signals directly as input data, the proposed method is an automatic fault diagnosis system which does not require any feature extraction techniques and achieves very high accuracy and robustness under noisy environments.     

Forebrain circuits and control of feeding by learned cues

Professor Richard F. Thompson and his highly influential work on the brain substrates of associative learning and memory have critically shaped my research interests and scientific approach. I am tremendously grateful and thank Professor Thompson for the support and influence on my research and career. The focus of my research program is on associative learning and its role in the control of fundamental, motivated behaviors. My long-term research goal is to understand how learning enables environmental cues to control feeding behavior. We use a combination of behavioral studies and neural systems analysis approach in two well-defined rodent models to study how learned cues are integrated with homeostatic signals within functional forebrain networks, and how these networks are modulated by experience. Here, I will provide an overview of the two behavioral models and the critical neural network components mapped thus far, which include areas in the forebrain, the amygdala and prefrontal cortex, critical for associative learning and decision-making, and the lateral hypothalamus, which is an integrator for feeding, reward and motivation.