Metamodeling live sequence charts for code generation

This article presents a metamodeling study for Live Sequence Charts (LSCs) and Message Sequence Charts (MSCs) with an emphasis on code generation. The article discusses specifically the following points: the approach to building a metamodel for MSCs and LSCs, a metamodel extension from MSC to LSC, support for model-based code generation, and finally action model and domain-specific data model integration. The metamodel is formulated in metaGME, the metamodel language for the Generic Modeling Environment.

Photosensitized free radical polymerization using pyridinium salts

Summary The polymerization of methyl methacrylate (MMA), ethyl acrylate (EA), styrene (St) and 2-vinyl pyridine (VP) is initiated upon irradiation at >350 nm of dichloromethane solutions containing N-ethoxy-2-methylpyridinium hexafluorophosphate (EMP⁺PF₆ ^-) and anthracene or thioxanthone. Initiation mechanisms involving the formation of ethoxyl radicals during the decomposition of EMP⁺ ions via electron transfer are proposed.     

Dynamique des lasers à fibre dopée à I’erbium

The dynamics of the erbium doped fiber laser is analysed both experimentally and theoretically. This laser operates spontaneously in self-pulsing, in sinusoidal or in CW regime. Experiments have allowed to determine the control parameters : the cavity losses, the pumping rate and the ion pairs concentration. An antiphase dynamics is observed when the laser operates simultaneously at 1.55 µn and 1.536 µm. The self-pulsing behavior is attributed to a fast energy transfer which occurs between two neighboring ions (pair induced quenching). A simple model considering the active medium as a mixture of isolated ions and ions pairs is developped and leads to a good qualitative agreement with the experimental results.     

Thermal images generated by a line-scanning technique: statistical properties

The analysis of statistical parameters of computer-generated therfial images by a line-scanning technique indicates an approach to efficient image transmission.     

Detection of COVID-19 and its pulmonary stage using Bayesian hyperparameter optimization and deep feature selection methods

Since the first case of COVID-19 was reported in December 2019, many studies have been carried out on artificial intelligence for the rapid diagnosis of the disease to support health services. Therefore, in this study, we present a powerful approach to detect COVID-19 and COVID-19 findings from computed tomography images using pre-trained models using two different datasets. COVID-19, influenza A (H1N1) pneumonia, bacterial pneumonia and healthy lung image classes were used in the first dataset. Consolidation, crazy-paving pattern, ground-glass opacity, ground-glass opacity and consolidation, ground-glass opacity and nodule classes were used in the second dataset. The study consists of four steps. In the first two steps, distinctive features were extracted from the final layers of the pre-trained ShuffleNet, GoogLeNet and MobileNetV2 models trained with the datasets. In the next steps, the most relevant features were selected from the models using the Sine–Cosine optimization algorithm. Then, the hyperparameters of the Support Vector Machines were optimized with the Bayesian optimization algorithm and used to reclassify the feature subset that achieved the highest accuracy in the third step. The overall accuracy obtained for the first and second datasets is 99.46% and 99.82%, respectively. Finally, the performance of the results visualized with Occlusion Sensitivity Maps was compared with Gradient-weighted class activation mapping. The approach proposed in this paper outperformed other methods in detecting COVID-19 from multiclass viral pneumonia. Moreover, detecting the stages of COVID-19 in the lungs was an innovative and successful approach.     

Revisiting Slotted ALOHA: Density Adaptation in FANETs

Unmanned aerial vehicles have been widely used in many areas of life. They communicate with each other or infrastructure to provide ubiquitous coverage or assist cellular and sensor networks. They construct flying ad hoc networks. One of the most significant problems in such networks is communication among them over a shared medium. Using random channel access techniques is a useful solution. Another important problem is that the variations in the density of these networks impact the quality of service and introduce many challenges. This paper presents a novel density-aware technique for flying ad hoc networks. We propose Density-aware Slotted ALOHA Protocol that utilizes slotted ALOHA with a dynamic random access probability determined using network density in a distributed fashion. Compared to the literature, this paper concentrates on proposing a three-dimensional, easily traceable model and stabilize the channel utilization performance of slotted ALOHA with an optimized channel access probability to its maximum theoretical level, 1/e, where e is the Euler’s number. Monte-Carlo simulation results validate the proposed approach leveraging aggregate interference density estimator under the simple path-loss model. We compare our protocol with two existing protocols, which are Slotted ALOHA and Stabilized Slotted ALOHA. Comparison results show that the proposed protocol has 36.78% channel utilization performance; on the other hand, the other protocols have 24.74% and 30.32% channel utilization performances, respectively. Considering the stable results and accuracy, this model is practicable in highly dynamic networks even if the network is sparse or dense under higher mobility and reasonable non-uniform deployments.

     

Genetic algorithm based approaches to solve the order batching problem and a case study in a distribution center

Journal of Intelligent Manufacturing - The order batching problem is a combinatorial optimization problem that arises in the warehouse order picking process. In the order batching problem, the aim...     

Evolutionary design of neural network architectures: a review of three decades of research

We present a comprehensive review of the evolutionary design of neural network architectures. This work is motivated by the fact that the success of an Artificial Neural Network (ANN) highly depends on its architecture and among many approaches Evolutionary Computation, which is a set of global-search methods inspired by biological evolution has been proved to be an efficient approach for optimizing neural network structures. Initial attempts for automating architecture design by applying evolutionary approaches start in the late 1980s and have attracted significant interest until today. In this context, we examined the historical progress and analyzed all relevant scientific papers with a special emphasis on how evolutionary computation techniques were adopted and various encoding strategies proposed. We summarized key aspects of methodology, discussed common challenges, and investigated the works in chronological order by dividing the entire timeframe into three periods. The first period covers early works focusing on the optimization of simple ANN architectures with a variety of solutions proposed on chromosome representation. In the second period, the rise of more powerful methods and hybrid approaches were surveyed. In parallel with the recent advances, the last period covers the Deep Learning Era, in which research direction is shifted towards configuring advanced models of deep neural networks. Finally, we propose open problems for future research in the field of neural architecture search and provide insights for fully automated machine learning. Our aim is to provide a complete reference of works in this subject and guide researchers towards promising directions.

     

Investigation on replication of microfluidic channels by hot embossing

In this study, effects of embossing temperature, time, and force on production of a microfluidic device were investigated. Polymethyl methacrylate (PMMA) substrates were hot embossed by using a micromilled aluminum mold. The process parameters were altered to observe the variation of replication rate in width and depth as well as symmetry of the replicated microfluidic channels. Analysis of variance (ANOVA) on the experimental results indicated that embossing temperature was the most important process parameter, whereas embossing time and force have less impact. One distinguishing aspect of this study is that, the channels were observed to be skewed to either side of the channel depending on the location of the protrusions on the mold. The mechanism of the skewness was investigated by finite element analysis and discussed in detail. Results showed that the skewness depends on the flow characteristics of the material and could be reduced by increasing the embossing temperature. The best replication rates were obtained at parameter settings of 115°C, 10?kN, and 8?min for the molds with minimum 56?µm wide features of 120?µm depth. We also showed that the fabricated channels could be successfully sealed by solvent-assisted thermo-compressive bonding at 85°C under 5.5?kN force.     

Stochastic two-sided U-type assembly line balancing: a genetic algorithm approach

In this paper, a novel stochastic two-sided U-type assembly line balancing (STUALB) procedure, an algorithm based on the genetic algorithm and a heuristic priority rule-based procedure to solve STUALB problem are proposed. With this new proposed assembly line design, all advantages of both two-sided assembly lines and U-type assembly lines are combined. Due to the variability of the real-life conditions, stochastic task times are also considered in the study. The proposed approach aims to minimise the number of positions (i.e. the U-type assembly line length) as the primary objective and to minimise the number of stations (i.e. the number of operators) as a secondary objective for a given cycle time. An example problem is solved to illustrate the proposed approach. In order to evaluate the efficiency of the proposed algorithm, test problems taken from the literature are used. The experimental results show that the proposed approach performs well.