Missing values handling in any collected data is one of the first issues that must be resolved to be able to use that data. This paper presents an approach used for missing values interpolation in PurpleAir particle pollution sensor data, based on a correlation of the measurements from the observed locations with the measurements from its neighboring locations, using KNIME Analytics Platform. Results of our experiments with data from five locations in Bosnia & Herzegovina, presented in this paper, show that this approach, which is relatively simple to implement, gives good results. All modeling and experiments were conducted using KNIME Analytics Platform.

Mathematical modelling to compute ground truth from 3D images is an area of research that can strongly benefit from machine learning methods. Deep neural networks (DNNs) are state-of-the-art methods design for solving these kinds of difficulties. Convolutional neural networks (CNNs), as one class of DNNs, can overcome special requirements of quantitative analysis especially when image segmentation is needed. This article presents a system that uses a cascade of CNNs with symmetric blocks of layers in chain, dedicated to 3D image segmentation from microscopic images of 3D nuclei. The system is designed through eight experiments that differ in following aspects: number of training slices and 3D samples for training, usage of pre-trained CNNs and number of slices and 3D samples for validation. CNNs parameters are optimized using linear, brute force, and random combinatorics, followed by voter and median operations. Data augmentation techniques such as reflection, translation and rotation are used in order to produce sufficient training set for CNNs. Optimal CNN parameters are reached by defining 11 standard and two proposed metrics. Finally, benchmarking demonstrates that CNNs improve segmentation accuracy, reliability and increased annotation accuracy, confirming the relevance of CNNs to generate high-throughput mathematical ground truth 3D images.

Color vision deficiency is a surprisingly frequent vision impairment, but not considered to be a mayor eye disease due to being inherited condition and not progressive condition. However it poses serious restrictions on a visually impaired person because vision deficiency tests are commonly used to disqualify individuals affected by color vision deficiency from certain occupations. Color vision deficiency cannot be cured, thus it is important to develop suitable assistive technology to overcome the restrictions it poses. Virtual reality can project custom and separate images to both eyes in a real-time and thus enabling a new class of assistive technology that can deliver visual information in a highly customized manner. Virtual reality based assistive technology is promising for age-related macular degeneration, diabetic retinopathy and particularly for color vision deficiency. Virtual reality prototype is created based on a video see-through setup using commercial virtual reality headset and stereo camera. The prototype uses custom image processing to transform visual information from the camera to color vision deficiency friendly form. Time-domain color mapping real-time image processing is proposed to improve scores on standard color vision deficiency tests - Ishihara tests. Experiment is conducted to evaluate a protanope time-domain color mapping with sinusoidal envelope.

This research uses artificial intelligence methods for computer network intrusion detection system modeling. Primary classification is done using self-organized maps (SOM) in two levels, while the secondary classification of ambiguous data is done using Sugeno type Fuzzy Inference System (FIS). FIS is created by using Adaptive Neuro-Fuzzy Inference System (ANFIS). The main challenge for this system was to successfully detect attacks that are either unknown or that are represented by very small percentage of samples in training dataset. Improved algorithm for SOMs in second layer and for the FIS creation is developed for this purpose. Number of clusters in the second SOM layer is optimized by using our improved algorithm to minimize amount of ambiguous data forwarded to FIS. FIS is created using ANFIS that was built on ambiguous training dataset clustered by another SOM (which size is determined dynamically). Proposed hybrid model is created and tested using NSL KDD dataset. For our research, NSL KDD is especially interesting in terms of class distribution (overlapping). Objectives of this research were: to successfully detect intrusions represented in data with small percentage of the total traffic during early detection stages, to successfully deal with overlapping data (separate ambiguous data), to maximize detection rate (DR) and minimize false alarm rate (FAR). Proposed hybrid model with test data achieved acceptable DR value 0.8883 and FAR value 0.2415. The objectives were successfully achieved as it is presented (compared with the similar researches on NSL KDD dataset). Proposed model can be used not only in further research related to this domain, but also in other research areas

Organizations can improve efficiency of process execution through a correct resource allocation, as well as increase income, improve client satisfaction, and so on. This work presents a novel approach for solving problems of resource allocation in business processes which combines process mining, statistical techniques, and metaheuristic algorithms for optimization. In order to get more reliable results of the simulation, in this paper, we use process mining analysis and statistical techniques for building a simulation model. For finding optimal human resource allocation in business processes, we use the improved differential evolution algorithm with population adaptation. Because of the use of a stochastic simulation model, noise appears in the output of the model. The differential evolution algorithm is modified in order to include uncertainty in the fitness function. In the end, validation of the model was done on three different data sets in order to demonstrate the generality of the approach, and the comparison with the standard approach from the literature was done. The results have shown that this novel approach gives solutions which are better than the existing model from literature.