This paper presents the improved version of the classification system for supporting glaucoma diagnosis in ophthalmology. In this
paper we propose the new segmentation step based on the support vector clustering algorithm which enables better classification performance.
In recent years, deep learning and especially deep neural networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the convolutional neural networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good generalization abilities. Therefore, a number of methods have been proposed by the researchers to deal with these problems. In this paper, we present the results of applying different, recently developed methods to improve deep neural network training and operating. We decided to focus on the most popular CNN structures, namely on VGG based neural networks: VGG16, VGG11 and proposed by us VGG8. The tests were conducted on a real and very important problem of skin cancer detection. A publicly available dataset of skin lesions was used as a benchmark. We analyzed the influence of applying: dropout, batch normalization, model ensembling, and transfer learning. Moreover, the influence of the type of activation function was checked. In order to increase the objectivity of the results, each of the tested models was trained 6 times and their results were averaged. In addition, in order to mitigate the impact of the selection of learning, test and validation sets, k-fold validation was applied.
Prof. Małgorzata Kossut of the Nencki Institute of Experimental Biology talks about brain plasticity, the mechanisms of learning, and the mysteries of forgetfulness.
The traditional self organizing map (SOM) is learned by Kohonen learning. The main disadvantage of this approach is in epoch based learning when the radius and rate of learning are decreasing functions of epoch index. The aim of study is to demonstrate advantages of diffusive learning in single epoch learning and other cases for both traditional and anomalous diffusion models. We also discuss the differences between traditional and anomalous learning in models and in quality of obtained SOM. The anomalous diffusion model leads to less accurate SOM which is in accordance to biological assumptions of normal diffusive processes in living nervous system. But the traditional Kohonen learning has been overperformed by novel diffusive learning approaches.
This paper proposes a comprehensive study on machine listening for localisation of snore sound excitation. Here we investigate the effects of varied frame sizes, and overlap of the analysed audio chunk for extracting low-level descriptors. In addition, we explore the performance of each kind of feature when it is fed into varied classifier models, including support vector machines, k-nearest neighbours, linear discriminant analysis, random forests, extreme learning machines, kernel-based extreme learning machines, multilayer perceptrons, and deep neural networks. Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.
This paper presents an alternative approach to the sequential data classification, based on traditional machine learning algorithms (neural networks, principal component analysis, multivariate Gaussian anomaly detector) and finding the shortest path in a directed acyclic graph, using A* algorithm with a regression-based heuristic. Palm gestures were used as an example of the sequential data and a quadrocopter was the controlled object. The study includes creation of a conceptual model and practical construction of a system using the GPU to ensure the realtime operation. The results present the classification accuracy of chosen gestures and comparison of the computation time between the CPU- and GPU-based solutions.
To gather reproducible measurement results, metrologists need a variety of competences. Yet, also other groups of staff in a manufacturing enterprise need competences in metrology in order to assure the appropriate specification of tolerances or sufficient consideration of inspectional requirements in production processes.
Therefore, the strict focus of metrological qualification on staff preparing or performing the actual measurements is insufficient for the efficient assurance of conformity. Additionally, on the one hand a demand-oriented qualification concept is needed to impart required fundamental knowledge on manufacturing metrology according to the specific needs of each user group. On the other hand, appropriate measures of knowledge management have to be applied in order to assure a proper application of the gathered knowledge and enhance mutual understanding for the requirements of other involved user groups.
Thus, as amendment for user-specific measures of formal qualification, a concept has been developed to enable knowledge transfer among different groups and departments in an enterprise. By this holistic approach, the impact of measures of qualification can be increased and high product quality can be achieved as a common aim of all related groups of staff.
Nowadays, the Internet connects people, multimedia and physical objects leading to a new-wave of services. This includes learning applications, which require to manage huge and mixed volumes of information coming from Web and social media, smart-cities and Internet of Things nodes. Unfortunately, designing smart e-learning systems able to take advantage of such a complex technological space raises different challenges. In this perspective, this paper introduces a reference architecture for the development of future and big-data-capable e-learning platforms. Also, it showcases how data can be used to enrich the learning process.
Compared with the robots, humans can learn to perform various contact tasks in unstructured environments by modulating arm impedance characteristics. In this article, we consider endowing this compliant ability to the industrial robots to effectively learn to perform repetitive force-sensitive tasks. Current learning impedance control methods usually suffer from inefficiency. This paper establishes an efficient variable impedance control method. To improve the learning efficiency, we employ the probabilistic Gaussian process model as the transition dynamics of the system for internal simulation, permitting long-term inference and planning in a Bayesian manner. Then, the optimal impedance regulation strategy is searched using a model-based reinforcement learning algorithm. The effectiveness and efficiency of the proposed method are verified through force control tasks using a 6-DoFs Reinovo industrial manipulator.
The paper presents the method of assessment of learning outcomes acquirement by students. The analysis is based on the results of the final matriculation exam in mathematics. For crisp and both types of fuzzy relations, cut scores (passing scores) can be defined along with the method of preparing rankings of students. The advantage of applying type 2 fuzzy relations is the lack of the necessity for experts to agree to one level (one number) of verification of learning outcomes by items created for the examination. Based on the results of the exam and experts’ knowledge, the decision support system for calculating the levels of learning outcomes acquirement, making decisions about passing the examination and preparing rankings of students, can be developed. Additionally, the rank reversal phenomenon does not burden the proposed method.