Showing papers on "Component (UML) published in 2022"

Attention meets long short-term memory: A deep learning network for traffic flow forecasting

Abstract: Accurate forecasting of future traffic flow has a wide range of applications, which is a fundamental component of intelligent transportation systems. However, timely and accurate traffic forecasting remains an open challenge due to the high nonlinearity and volatility of traffic flow data. Canonical long short-term memory (LSTM) networks are easily drawn to focus on min-to-min fluctuations rather than the long term dependencies of the traffic flow evolution. To address this issue, we propose to introduce an attention mechanism to the long short-term memory network for short-term traffic flow forecasting. The attention mechanism helps the network model to assign different weights to different inputs, focus on critical and important information, and make accurate predictions. Extensive experiments on four benchmark data sets show that the LSTM network equipped with an attention mechanism has superior performance compared with commonly used and state-of-the-art models.

The role and application of convex modeling and optimization in electrified vehicles

Abstract: Component sizing and energy management are essential for minimizing vehicle costs and maximizing energy efficiency in electrified vehicles. Usually, a hierarchical optimization framework is used to solve the component sizing problem. The possible component sizes are enumerated in the outer loop, and their effectiveness is assessed in the inner loop. When optimizing energy consumption, highly robust and effective energy management strategies are important for both individual vehicles and vehicle platoons. Convex optimization has become an effective and important method to solve multi-dimensional problems due to its computational efficiency. In this paper, we reviewed the component sizing and energy management issues in electrified vehicles and summarized a variety of convex optimization methods for solving these problems. The prospects and future trends of the convex optimization method in the design and control of electrified vehicles were presented and discussed.

Short-term traffic prediction based on time series decomposition

Abstract: Traffic flow decomposition is an alternative method to explore the composition of traffic flow and improve prediction accuracy. However, most of them suffer from the inability to fully utilize the character of traffic data. This paper presents a novel framework for traffic flow decomposition and modeling named Time Series Decomposition (TSD). The traffic flow is adaptively decomposed into periodic component, residual component and volatile component which are modeled respectively. Empirical Mode Decomposition (EMD) is applied to extract the intrinsic mode functions (IMFs) of traffic flow, the periodic patterns are intuitively presented via Hilbert transform in terms of frequencies. Then the periodic component can be described as a Fourier series based on obtained frequencies. Meanwhile, the residual component is presented by IMF with the lowest frequency. The remaining part is the volatile component modeled by supervised learning. The proposed hybrid model is evaluated on the real-world dataset and compared with classical baseline models. The results demonstrate that TSD can unearth the underlying periodic patterns and provide an explicable composition of the traffic flow. Furthermore, the volatile component ensures the accuracy of single-step prediction while periodic and residual components show promising abilities in improving the multi-step prediction accuracy of short-term traffic flow.

Adaptive Risk-Based Life-Cycle Management for Large-Scale Structures Using Deep Reinforcement Learning and Surrogate Modeling

Abstract: Optimal life-cycle management is a challenging task for large-scale structures. The complexity of structural states, represented by the numerous combinations of component conditions, and th...

Product Representation for Disassembly Sequence Planning

Abstract: Most disassembly optimisation problems start with designing a mathematical representation that can describe component relations. This chapter discusses and compares three major groups of component relation models: the matrix-based model, graph-based model and hybrid-based model.

UML for Embedded Systems

Abstract: One of the models we studied in Chap. 3 is the heterogeneous object-oriented model. The majority of software systems are implemented using this model, as it is close to real-life systems. Unified Modeling Language (UML) is an object-oriented modeling language standardized by Object Management Group (OMG) mainly for software system development. In software development, UML has become de-facto standard as CASE methodology. Now it is invariably used in embedded systems because of the growing complexity of embedded systems. In this chapter, we use the term system engineering as an equivalent CASE for embedded systems. An embedded system is represented in UML using multiple models through different diagrams. Each model describes the system from a distinctly different perspective. In industry, any project cycle has several people involved in different roles with certain tasks assigned. Section 5.2 describes typical tasks and roles in system engineering. Section 5.3 describes different diagrams supported in UML. Section 5.4 describes with examples, different structural diagrams, viz, class, association, concept of aggregation, composition, signals, and interfaces. Section 5.5 explains different behavioral diagrams with examples, viz, use cases, state, activity, and sequence diagrams. To summarize, Unified Modeling Language (UML) is very established standard to represent a system, its static and dynamic behavior. End to end development of systems, whether it is software system or any embedded system, can be specified. The models can be easily exchanged across design teams. The UML models will be very useful for documentation, skeleton code generation, and verifying the behavior well before coding. Though several books are available to learn UML, we have included this chapter just sufficient to start off the design with UML standard and to represent the extensive set of models we have studied in Chap. 3.

Providing Security and Managing Quality Through Machine Learning Techniques for an Image Processing Model in the Industrial Internet of Things

Abstract: Currently, the transfer of defect-free, high-quality products is a significant factor for success in the manufacturing industries. The Internet of Things (IoT) has become a major part of day-to-day life. The IoT links physical things in the environment, and these things are controlled with the aid of sensors. A sensor is a component used to determine the physical property of an element, any procedures or modifications observed in the environment, as well as send the information to other devices such as computers. Numerous research studies are being conducted on the sensors used in IoT systems to provide smart services and knowledge for smart manufacturing and industry. Creating a system which aids in controlling the quality that enhances competence and production speed by eliminating abnormal products automatically is of the utmost importance. The industrial image processing model uses special cameras installed within the production line. The proposed model can be used to efficiently computerize the structure of the CPU production lines in an industry, for example, outcome images of production lines are scanned, some structure abnormalities are noted by the system and data are sent to the system administrator through cloud system networks. Here machine learning techniques are proposed for suitable classification. Machine learning is a way of making computers learn from the data of previous experiences. It helps machines have the capability of learning as well as improving from past experiences without having to be programmed every time. The main focus is on abnormalities and security concerns regarding sending data to the cloud.

Knowledge-based decision support for machine component design: A case study

Abstract: This paper describes research conducted during a project with a multinational company that focuses on product design. The project tackles two different goals: providing sales staff with a tool that allows them to autonomously handle routine requests, and providing the company’s engineers with a decision support system to help them design products for more challenging application areas. For the first goal, we make use of a deterministic decision process, represented in the recent Decision Model and Notation (DMN) standard. For the second goal, we propose a constraint-based method. There, we use the IDP system to provide a number of interactive functionalities based on a logical representation of the relevant constraints. To ensure that the system is maintainable, we want the constraints to be updated by the engineers themselves. The IDP language is not ideal for this. Instead, we propose the cDMN notation, which extends the user-friendly DMN to constraints.

The Nature and Extent of Component Analyses for Improving or Mitigating Behavior: A Systematic Review:

Abstract: A component analysis is an approach where two or more independent variables are evaluated as a package and independently. The approach is used to assess and identify which component of a treatment package is the most effective. The purpose of this review is to document the application of component analyses to improve or mitigate non-academic behaviors with individuals with disabilities. We identified 21 research articles that used a component analysis to evaluate treatment packages with students who were identified as having or at-risk for a disability in classroom and/or alternative settings. Results from reviewing 21 articles (22 cases) indicate that 11 intervention packages had a single component that was critical for successful behavior change. Two articles suggested the entire intervention package was necessary while nine articles did not report a critical component or had variable results pertaining to critical components. The benefits and drawbacks of using component analyses for single case research are discussed. Implications for future research are also presented.