Neural Network-Based Prediction of Vehicle Fuel Consumption Based on Driving Cycle Data

This paper deals with fuel consumption prediction based on vehicle velocity, acceleration, and road slope time series inputs. Several data-driven models are considered for this purpose, including linear regression models and neural network-based ones. The emphasis is on accounting for the road slope impact when forming the model inputs, in order to improve the prediction accuracy. A particular focus is devoted to conversion of length-varying driving cycles into fixed dimension inputs suitable for neural networks. The proposed prediction algorithms are parameterized and tested based on GPS- and CAN-based tracking data recorded on a number of city buses during their regular operation. The test results demonstrate that a proposed neural network-based approach provides a favorable prediction accuracy and reasonable execution speed, thus making it suitable for various applications such as vehicle routing optimization, synthetic driving cycle validation, transport planning and similar.

A cross-technology benchmark for incremental graph queries

To cope with the increased complexity of systems, models are used to capture what is considered the essence of a system. Such models are typically represented as a graph, which is queried to gain insight into the modelled system. Often, the results of these queries need to be adjusted according to updated requirements and are therefore a subject of maintenance activities. It is thus necessary to support writing model queries with adequate languages. However, in order to stay meaningful, the analysis results need to be refreshed as soon as the underlying models change. Therefore, a good execution speed is mandatory in order to cope with frequent model changes. In this paper, we propose a benchmark to assess model query technologies in the presence of model change sequences in the domain of social media. We present solutions to this benchmark in a variety of 11 different tools and compare them with respect to explicitness of incrementalization, asymptotic complexity and performance.

Big Data Workflows: Locality-Aware Orchestration Using Software Containers

The emergence of the edge computing paradigm has shifted data processing from centralised infrastructures to heterogeneous and geographically distributed infrastructures. Therefore, data processing solutions must consider data locality to reduce the performance penalties from data transfers among remote data centres. Existing big data processing solutions provide limited support for handling data locality and are inefficient in processing small and frequent events specific to the edge environments. This article proposes a novel architecture and a proof-of-concept implementation for software container-centric big data workflow orchestration that puts data locality at the forefront. The proposed solution considers the available data locality information, leverages long-lived containers to execute workflow steps, and handles the interaction with different data sources through containers. We compare the proposed solution with Argo workflows and demonstrate a significant performance improvement in the execution speed for processing the same data units. Finally, we carry out experiments with the proposed solution under different configurations and analyze individual aspects affecting the performance of the overall solution.

Full Text Search Setup on a Website

ntroduction. When implementing the search for text fragments on the site, approaches are used that are different in complexity and performance. There is also a sequence of related tasks: choosing a text indexing option, sending a text for indexing, selecting texts for indexing specifically from the CMS database, choosing a search engine, and others. These approaches do not always provide satisfactory search results. Purpose. The purpose of the article is to the description of existing solutions for full-text search on a website, their advantages, and disadvantages. Development of a full-text search algorithm using the Elasticsearch system. Methods. Analysis of approaches to the implementation of full-text search on a website, varying in complexity and performance. Identification of flaws and vulnerabilities in more primitive approaches and the development of more advanced and complex algorithms that eliminate the identified deficiencies. Step-by-step implementation of full-text search using third-party systems. Results. A method for implementing full-text search using Elasticsearch is described. The advantage of the new approach is the asynchronous sending of the page content and its address to a specific service responsible for communication with Elasticsearch. This allows you not to block the normal work with the CMS and not depend on the availability of the indexing service. The approach described in the article is flexible and adaptable for various website architectures. Asynchronous processing of indexing requests ensures high query execution speed and system fault tolerance. Conclusions. The article discusses various approaches to implementing full-text search on a website, their advantages and disadvantages. Based on the analysis, a more flexible and universal approach to the implementation of a full-text search system has been developed. A solution is proposed with step-by-step implementation and setup of advanced full-text search using Elasticsearch.

A Fast Online Classification Method of Solid Wood Floors Based on Stochastic Sampling and Machine Learning

Solid wood floors are widely used as an interior decoration material, and the color of solid wood surfaces plays a decisive role in the final decoration effect. Therefore, the color classification of solid wood floors is the final and most important step before laying. However, research on floor classification usually focuses on recognizing complex and diverse features but ignores execution speed, which causes common methods to not meet the requirements of online classification in practical production. In this paper, a new online classification method of solid wood floors was proposed by combining probability theory and machine learning. Firstly, a probability-based feature extraction method (stochastic sampling feature extractor) was developed to obtain rapid key features regardless of the disturbance of wood grain. The stochastic features were determined by a genetic algorithm. Then, an extreme learning machine—as a fast classification neural network—was selected and trained with the selected stochastic features to classify solid wood floors. Several experiments were carried out to evaluate the performance of the proposed method, and the results showed that the proposed method achieved a classification accuracy of 97.78% and less than 1 ms for each solid wood floor. The proposed method has advantages including a high execution speed, great accuracy, and flexible adaptability. Overall, it is suitable for online industry production.

A Novel Method for Busbar Design of Electric Vehicle Motor Drive

At present, the DC busbar design is one of the bottlenecks restricting the improvement of the power density of motor drives. Therefore, this paper proposes a three-dimensional line probe algorithm, which can realize the automatic routing of laminated busbar in motor drives. The specific rules and implementation of this method are introduced in detail in this paper. Finally, an example of busbar design of a vehicle motor drive is given to verify the routing rate and execution speed of the algorithm.

Domain-Adaptive Artificial Intelligence-Based Model for Personalized Diagnosis of Trivial Lesions Related to COVID-19 in Chest Computed Tomography Scans

Background: Early and accurate detection of COVID-19-related findings (such as well-aerated regions, ground-glass opacity, crazy paving and linear opacities, and consolidation in lung computed tomography (CT) scan) is crucial for preventive measures and treatment. However, the visual assessment of lung CT scans is a time-consuming process particularly in case of trivial lesions and requires medical specialists. Method: A recent breakthrough in deep learning methods has boosted the diagnostic capability of computer-aided diagnosis (CAD) systems and further aided health professionals in making effective diagnostic decisions. In this study, we propose a domain-adaptive CAD framework, namely the dilated aggregation-based lightweight network (DAL-Net), for effective recognition of trivial COVID-19 lesions in CT scans. Our network design achieves a fast execution speed (inference time is 43 ms on a single image) with optimal memory consumption (almost 9 MB). To evaluate the performances of the proposed and state-of-the-art models, we considered two publicly accessible datasets, namely COVID-19-CT-Seg (comprising a total of 3520 images of 20 different patients) and MosMed (including a total of 2049 images of 50 different patients). Results: Our method exhibits average area under the curve (AUC) up to 98.84%, 98.47%, and 95.51% for COVID-19-CT-Seg, MosMed, and cross-dataset, respectively, and outperforms various state-of-the-art methods. Conclusions: These results demonstrate that deep learning-based models are an effective tool for building a robust CAD solution based on CT data in response to present disaster of COVID-19.

The importance of using circuit training in the development of speed endurance, agility and body control in male U17 handball players

The growing importance of physical preparation in the training plans of handball coaches must be the basis for consolidation and improvement during the specific training of junior handball players. The higher the motor indicators, the higher the difference between the technical and tactical skills of junior handball players in terms of achieving maximum efficiency. The research took place over an eight-month period. The research participants were 32 U17 junior handball players aged 15 and 16 years. They were divided into two groups as follows: the experimental group, consisting of 15 handball players from the Bucharest Municipal Sports Club, and the control group, consisting of 17 handball players from the Bucharest School Sports Club No. 2. The methods used for the experimental group included set training circuits performed in the corresponding part of basic training. Each training circuit was introduced systematically and quantifiably for 15 minutes, three times a week on successive days and according to the training period covered by the U17 male handball team. The training of the control group was based on traditional methods provided in the annual training plan. Throughout this period, the specific physical training parameters of the experimental group were influenced by the chosen training methods: for speed endurance in different directions and at different angles with forward, backward and lateral movements; for the ability to rotate in different directions and at different angles with an emphasis on execution speed, acceleration speed, speed endurance, agility and body control.

Executive Processes and Emotional and Behavioural Problems in Youths Under Protective Measures

This research studies the executive processes of youths under protective measures between 13 and 18years of age, as well as the emotional problems they have and the presence of behavioural problems, such as difficulties to control and direct attention, to control one’s own behaviour and inhibit inadequate or ineffective responses (hyperactivity-impulsiveness) and problems related to emotional regulation. In addition, we study the presence of significant differences according to the sex of the youths. We also analyse to what extent the difficulties in the executive processes are related to and can predict the emotional and behavioural problems. The instruments used were Stroop’s Colour and Word Test (Stroop), the Paths Test (TESen), and the System of Evaluation for Children and Adolescents (SENA). The results indicated that the youths had difficulties in such executive processes as execution, speed, and accuracy in carrying out tasks. Furthermore, they had emotion problems, amongst which the symptoms of anxiety are worthy of note; whilst attention deficit, hyperactivity-impulsiveness, and problems related to emotional regulation could also be observed. The data indicated greater difficulties in the executive processes for males than for females. There was a greater emotional symptomatology in the females, whilst there were greater deficits in attention and hyperactivity/impulsiveness in the males. Similarly, the deficits in the executive processes were related to and predicted emotional and behavioural problems. This research suggests the design of a structured programme focused on systematic training in real, daily situations, recommending the use of restorative techniques to work on the affected cognitive skills and techniques aimed at improving the youths’ emotion regulation.

Adaptation of Random Binomial Graphs for Testing Network Flow Problems Algorithms

Algorithms for network flow problems, such as maximum flow, minimum cost flow, and multi-commodity flow problems, are continuously developed and improved, and so, random network generators become indispensable to simulate the functionality and to test the correctness and the execution speed of these algorithms. For this purpose, in this paper, the well-known Erdős–Rényi model is adapted to generate random flow (transportation) networks. The developed algorithm is fast and based on the natural property of the flow that can be decomposed into directed elementary s-t paths and cycles. So, the proposed algorithm can be used to quickly build a vast number of networks as well as large-scale networks especially designed for s-t flows.