Evolutionary algorithms have gained widespread recognition as a viable approach to numerous optimization problems that are characterized by infeasible optimal solutions, owing to the presence of large search spaces and computational limitations. Forecasting personnel radiation exposure can be one of these problems. Radiation exposure poses risks to various practitioners as well as patients in the healthcare facilities. In this study, we model the problem as a specific time series instance. Moreover, we investigate the impact of the training an adaptive neuro fuzzy system using evolutionary algorithms, namely, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), on the overall performance of forecasting personnel radiation exposure. The results show that GA and PSO could provide effective solution. On the other hand, they might be highly affected by the initial state of the fuzzy inference system leading to unstable performances. We recommend further experimentation with a combination of other advanced optimization and machine learning methods to assure the most effective results.

Early characterization of security requirements supports system designers to integrate security aspects into early architectural design. However, distinguishing security related requirements from other functional and non-functional requirements can be tedious and error prone. To address this issue, machine learning techniques have proven to be successful in the identification of security requirements. In this paper, we have conducted an empirical study to evaluate the performance of 22 supervised machine learning classification algorithms and two deep learning approaches, in classifying security requirements, using the publicly availble SecReq dataset. More specifically, we focused on the robustness of these techniques with respect to the overhead of the pre-processing step. Results show that Long short-term memory (LSTM) network achieved the best accuracy (84%) among non-supervised algorithms, while Boosted Ensemble achieved the highest accuracy (80%), among supervised algorithms.

IoT devices have a wide spectrum of applications in the real-life environment. While these applications range based on the area covered, having the best scenario related to the devices covering the optimal area is a challenge. In this work, we consider the improvement of the industrial laboratory by transferring it to the smart lab using the IoT devices. We analyzed the tradeoffs between different scenarios of the smart lab with the focus on the security and congestion of the network and its effects on the overall performance. For the smart lab case study we can conclude that security-enabled feature will not significantly affect the performance of the smart lab compared to the benefits of the IoT-integrated devices on the overall improvement of the lab experience given that the traditional lab had significant time delay.

This paper proposes an application of the Teager Energy Operator (TEO) next to the Discrete Wavelet Transform (DWT) and Hilbert-Huang Transform (HHT) for the power system fault identification, localization, and classification. Several fault types are simulated in the NE 39 bus test system using DigSILENT Power Factory software. Frequency and voltage signals are obtained and analyzed through the optimal placement of the Phasor Measurement Units (PMUs). The performance and the comparison of the applied techniques are assessed through a large number of the simulated faults for each fault type. The promising results obtained in the TEO analysis highlights the appropriate application of this technique in the power system fault detection. Value of the presented work reflects in the clear fault detection process. For the specified test system 141 fault simulations are made, frequency and voltage signals obtained from 13 measuring points in the system and analyzed with different signal processing techniques providing time, location and type of the fault.

The recent structure of the monitoring, protection, and control of the power systems includes GPS timely synchronized measurement units (Phasor Measurement Units). With the implementation of these units, Wide-Area Monitoring, Protection and Control Systems are required to perform fast and efficient identification of the disturbances that may lead to cascade propagation and blackouts in the power system. The requirements furthermore enable appropriate actions, preventive and corrective measures to minimize effects of the occurring disturbances. This paper proposes the application of the discrete Teager Energy Operator for the power system fault identification, localization, and classification. Identification and localization of the disturbances are performed with the analysis of available signals with the application of the Teager Energy Operator and comparison of its peak values at several points in the system. The proposed classifier of the disturbances is based on the Teager Energy Operator analysis of available signals and values of indicator of active power unbalance at several points in the system. Simulations are performed in the New England 39 bus test system using DIgSILENT Power Factory software. The performance and the comparison of the applied techniques are assessed through a large number of the simulated faults for the specific fault type. Fault identification and localization results are compared with the results obtained in the analysis performed with Discrete Wavelet Transform and Hilbert-Huang Transform indicating on satisfactory performance of the proposed approach. Furthermore, the proposed approach provides notable results in the fault classification performed according to 141 simulated faults. Teager Energy Operator in the proposed method outperforms other techniques with less computational work and faster estimation, enabling the development of a relatively simple algorithm for the fast and efficient identification, localization, and classification of the disturbances in power system.

In the past, ARM and Intel x86 computer processors were leaders in the different specialized areas with no competing interest. While Intel was building processors for the PCs and servers, ARM was concentrated on the handheld devices. Nowadays, with no hard limits in computing power between the different sizes of devices, ARM and Intel-based microprocessors are competitors. In this paper, a comparative study is done to evaluate the performance of the two microprocessors. Both, the in-order and the out-of-order, CPU models are used within each architecture, and four performance metrics (total consumed energy, throughput, average cycles per instruction (CPI), and L2 cache miss rate) are used to evaluate the work. The well-known computer architecture simulator, Gem5, is used to accomplish the work. Results show that ARM microprocessor outperforms x86 microprocessor in the most cases.

Software metrics are used to get reproducible measurements that can be useful for quality assurance. A recent study analyzed the relation between Halstead Complexity (HC), Cyclomatic Complexity (CC), and the number of defects found in software. The number of software defects does not represent a uniform software metric and may not be generalized. This work examines the density of defects (DD) and its relationship with HC and CC metrics. We have used a well-coded open-source project. We have focused our analysis at the class level and examined potential patterns and correlations that may exist between these two software metrics and the density of defects. We found that HC and CC exhibit similar relationships to Defect Density metric. Furthermore, their strong positive linear correlation leads to the conclusion that HC and CC are two consistent software metrics with respect to density of defects.

Wavelet transforms are part of general concept of multires-olutional theory that matured in image compression and gained high popularity in other image processing fields. One of the successful use was in medical engineering, in particular, computer-aided techniques for early breast cancer detection and diagnosis. Different wavelets transforms are employed in different phases to enhance the process of detection and diagnosis. This work reviews literature related with wavelets transforms in the early breast cancer detection and diagnosis.