Maintenance, as an integral part of the production process, plays a major role in ensuring optimal conditions in which the production process is carried out. The paper presents an example of the optimization of a part of the technical system of a paper machine, an industrial plant for the production of hygienic paper, with the aim of increasing the degree of reliability and reducing total maintenance costs. The starting point for the modernization of part of the production system is the setting up of an optimization algorithm for critical parts of technical systems, the application of which should result in concrete positive effects in the maintenance and production sector. The model considered the criticality analysis of parts of the technical system from the point of view of maintenance, as well as the analysis of technological parameters that have the potential to achieve savings by reducing energy consumption in the technological process. The most significant positive result of the optimization is the reduction of energy consumption per unit of produced goods, which is certainly a priority goal today, given the high costs and unavailability of certain energy sources.

In today`s world of rapid change and transformation, the most significant difference is in the field of technology. Human beings, who have difficulty in keeping up with the speed of technological developments, also strive to increase their standard of living by including technology in every aspect of their lives. This change and transformation also affects organizations. Many organizations have completely surrendered their business processes to technology and established automation systems and unmanned production mechanisms have been developed. This situation has raised the question "is the human element in business life becoming inactive or does technology increase the efficiency of the human element and make their work easier?". In this study, the impact and contribution of the use of artificial intelligence (AI) on management processes was discussed, and evaluations were made on how AI can be utilized in the decision-making process.

For the segmentation of cardiac magnetic resonance images (cMRI), the complex anatomy of the RV chamber is challenging. It becomes more difficult considering the specifics like intensity inhomogeneity, fuzzy boundaries of the right ventricle, similar intensities inside and outside the ventricle, etc. Researchers have proposed different methods for the segmentation of cMR images. This paper reports the advancement of segmentation methods from mostly morphological operations to modern-day approaches like convolution neural networks. Some methods are fully automatic, whereas some methods need user interactions. Detail approach and analysis of segmentation methods are presented here. Future research direction and approaches can be drawn through analysing variant reports of active researchers.

Cardiovascular diseases (CVDs) remain the principal cause of all global death and disabilities worldwide. Cardiac MR Images play an important role in the diagnosis and treatment of cardiac ailments in patients. Automatic segmentation of Cardiac Magnetic Resonance Imaging (Cardiac MRI) is an essential application in clinical practice. In this paper, Cardiac MRI segmentation is performed using a convolutional neural network. ACDC Challenge 2017 dataset is used the training and testing purpose. It consists of data of 100 subjects, including the End Systole and End Diastole phase. The performance of the model is measured using the Dice coefficient, achieving an accuracy of 0.90. The results for basal as well as with apical slices are pretty encouraging.

We view the determinant and permanent as functions on directed weighted graphs and introduce their analogues for the undirected graphs. We prove that the task of computing the undirected determinants as well as permanents for planar graphs, whose vertices have degree at most 4, is \\#P-complete. In the case of planar graphs whose vertices have degree at most 3, the computation of the undirected determinant remains \\#P-complete while the permanent can be reduced to the FKT algorithm, and therefore is polynomial.\n\nThe undirected permanent is a Holant problem and its complexity can be deduced from the existing literature. The concept of the undirected determinant is new. Its introduction is motivated by the formal resemblance to the directed determinant, a property that may inspire generalizations of some of the many algorithms which compute the latter.\n\nFor a sizable class of planar 3-regular graphs, we are able to compute the undirected determinant in polynomial time.

The next generation heterogeneous network will consist of multiple technologies for the device to improve their Quality of Service (QoS) parameters such as capacity and energy efficiency. One of the key technologies is the ability to use machine intelligence in the design of an energy efficient heterogeneous network. That allows users to choose which base station to connect with for optimal performance; the proposed QoS- aware reinforcement learning (RL) algorithm adapts energy efficient reward function to improve the performance of femto base station users without deviating macro base station. The main objective is to guarantee that the users have a certain QoS requirement that is above a defined threshold at every time instant. A dynamic power selection strategy in a heterogeneous network is based on QoS-aware RL algorithm subject to network QoS parameters. Results show that the proposed algorithm provides improved energy efficiency in proportion to the escalating throughput enhancement.

De-speckling of ultra sound images is one of the most challenging issues in medical imaging. All the available speckle noise reduction filters are almost capable of noise reduction but failed to restore the subtle features such as low gray level edges and fine details under the poor contrast background. This paper presents a two phase ultrasound de-speckling framework by utilizing the capability of non-local mean filtering method for de-speckling and edge preservation on anisotropic diffused images. The prior image smoothing along with edge preservation and contrast enhancement by anisotropic diffusion is carried out in first phase which is then followed by non-local means method for de-speckling and edge sharpening in the next phase. The degree of attenuation of speckle noise is evaluated on real and synthetic ultrasound images and the results are compared with state-of-the-art anisotropic diffusion techniques and non-local means methods. The experimental analysis demonstrates the capability of proposed method in reducing the noise and preserving the edges better than the available speckle reduction filters.

People re-identification is a fundamental stage in video surveillance systems. This stage is used to determine labels of people in images considering their visual appearance. It is a challenging task as the appearance may change across the camera’s network. Carried objects and background are some parts of the images which lead to appearance changes and impose further destructive effects on the performance of re-identification systems. The size and position of the carried objects and background directly affect the extent of the appearance changes. These issues are not addressed in existing people re-identification approaches. In this paper a part-based people re-identification approach is proposed using descriptors robust to appearance changes. In the proposed method, first, the input image is semantically segmented into three parts as: person’s body, possible carried objects, and backgrounds. Then, for representing the image, the Gaussian of Gaussian (GOG) and Hierarchical Gaussian Descriptor (HGD) are used in a weighted form considering the importance of each part of the image in re-identifying people. In our proposed approach, the weight map of carried objects and the background region is automatically computed considering their size and the distance of their pixels from the person’s body. Experimental results on people re-identification datasets show the superiority of our proposed approach compared to other existing approaches for people re-identification.

Regression testing provides confidence for any software to work properly after incorporating modifications in the software functionalities. The amendments in the software are visible due to the evolution or the adoption of the new functionalities in the software. New test cases might be added or removed from the test suit during the regression testing. Test case prioritization (TCP) seeks to provide an execution order of test cases when test cases are large in number for the detection of faults at an early stage. This paper provides classification of available TCP techniques that are examined based on the six research questions having higher relevance regarding the TCP. To carry out a systematic literature review (SLR) on TCP techniques, we extracted large number of papers from appropriate repositories of journals, conferences, workshops, and symposiums using various search keywords. In this SLR, total 91 primary studies were considered for review, which includes 59 journals papers, 23 conference papers, 7 symposiums papers and 2 workshop papers. Each TCP approach has its own limitations, potential value, and advantages, which are covered in this SLR in considerable detail. In addition, TCP approaches are discussed in greater detail in software engineering especially for the testing domain. After careful analysis of the literature, we reached out on a conclusion that TCP has a great scope of improvement in terms of different parameters such as cost, time and process flow for regression testing.