Nowadays, transportation companies look for smart solutions in order to improve quality of their services. Accordingly, an intercity bus company in Istanbul aims to improve their shuttle schedules. This paper proposes...
详细信息
ISBN:
(纸本)9783030238872;9783030238865
Nowadays, transportation companies look for smart solutions in order to improve quality of their services. Accordingly, an intercity bus company in Istanbul aims to improve their shuttle schedules. This paper proposes revising scheduling of the shuttles based on their estimated travel time in the given timeline. Since travel time varies depending on the date of travel, weather, distance, we present a prediction model using both travel history and additional information such as distance, holiday, and weather. The results showed that Random Forest algorithm outperformed other methods and adding additional features increased its accuracy rate.
The paper considers an approach to improving the stability of a cognitive agent functioning in hard real time in the event of anomalous situations (anomalies) associated with its functioning. The approach is based on ...
详细信息
ISBN:
(纸本)9783030500979
The paper considers an approach to improving the stability of a cognitive agent functioning in hard real time in the event of anomalous situations (anomalies) associated with its functioning. The approach is based on the concept of metacognition (metareasoning) and is implemented by means of Active Logic. The principle of metacognition is based on a metacognitive cycle that includes stages of self-observation (introspection), self-evaluation and self-improvement. Introduces the concept of multiple granulation of time, when each inference step of the agent corresponds to the individual temporal granules and these granules are different for the various inference steps. It is shown that in some cases multiple granulation of time contributes to the timely detection of anomalies.
The topic of this review is to demonstrate that even though sleep disordered breathings are considered serious by the doctors, technical literature lacks in research papers devoted to them. Because of the complexity o...
详细信息
ISBN:
(纸本)9783030299934;9783030299927
The topic of this review is to demonstrate that even though sleep disordered breathings are considered serious by the doctors, technical literature lacks in research papers devoted to them. Because of the complexity of the human body may decrease the reliability of linear models, it seems reasonable to try apply nonlinear modeling based on the NARMAX methodology. The purpose of this article is to briefly summarize the current state of knowledge in the area of nonlinear modeling of sleep disordered breathings with particular emphasis on using the NARMAX methodology. So far, only one publication has been found dealing with the application of the NARMAX methodology for modeling sleep disordered breathing. The aim of the future author's research is modeling of the most commonly occurring breathing disorders with the use of up-to-date and comprehensive tool, such as the NARMAX methodology.
The primary objective of hospital managers is to establish appropriate healthcare planning and organisation by allocating facilities, equipment and manpower resources necessary for hospital operation in accordance wit...
详细信息
ISBN:
(纸本)9783030299330;9783030299323
The primary objective of hospital managers is to establish appropriate healthcare planning and organisation by allocating facilities, equipment and manpower resources necessary for hospital operation in accordance with a patients needs while minimising the cost of healthcare. Length of stay (LoS) prediction is generally regarded as an important measure of inpatient hospitalisation costs and resource utilisation. LoS prediction is critical to ensuring that patients receive the best possible level of care during their stay in hospital. A novel approach for the prediction of LoS is investigated in this paper using only data based upon generic patient diagnoses. This data has been collected during a patients stay in hospital along with other general personal information such as age, sex, etc. A number of different classifiers are employed in order to gain an understanding of the ability to perform knowledge discovery on this limited dataset. They demonstrate a classification accuracy of around 75%. In addition, a further set of perspectives are explored that offer a unique insight into the contribution of the individual features and how the conclusions might be used to influence decision-making, staff and resource scheduling and management.
In most electrical applications, the motor is fed by Pulse Width Modulated(PWM) inverters and by design they are usually in separate locations, requiring long motor leads or cables. Overvoltage is a common phenomenon ...
详细信息
ISBN:
(纸本)9783030304652;9783030304645
In most electrical applications, the motor is fed by Pulse Width Modulated(PWM) inverters and by design they are usually in separate locations, requiring long motor leads or cables. Overvoltage is a common phenomenon in AC motor drives that are fed by long cables from PWM inverters, as they use Insulated Gate Bipolar Transistors (IGBT) with small rise time and fall time. This paper proposes an Artificial Neural Network based system to predict overvoltage at the motor terminal with long cable using the parameters cable length and motor capacity.
The paper deals with the use of IoT technology for distributed collection of environmental data, focused mainly on local meteorology in urbanized environment. The requirements for a reliable and long-term use of IoT s...
详细信息
ISBN:
(纸本)9783030299934;9783030299927
The paper deals with the use of IoT technology for distributed collection of environmental data, focused mainly on local meteorology in urbanized environment. The requirements for a reliable and long-term use of IoT sensor network and the communication platform between nodes are summarized, with an emphasis placed on (data) reliability and long-term exterior use. Discussed is used technology, solution of data collection using IoT technologies, energy management of measuring nodes and network structure. Procedures for time series resampling with pseudorandom sampling are described for data processing.
Simulating the possible detector response is a key component of every high-energy physics experiment. The methods used currently for this purpose provide high-fidelity results. However, this precision comes at a price...
详细信息
ISBN:
(纸本)9783030180584;9783030180577
Simulating the possible detector response is a key component of every high-energy physics experiment. The methods used currently for this purpose provide high-fidelity results. However, this precision comes at a price of a high computational cost, which renders those methods infeasible to be used in other applications, e.g. data quality assurance. In this work, we present a proof-of-concept solution for generating the possible responses of detector clusters to particle collisions, using the real-life example of the Time Projection Chamber (TPC) in the ALICE experiment at CERN. We introduce this solution as a first step towards a semi-real-time anomaly detection tool. It's essential component is a generative model that allows to simulate synthetic data points that bear high similarity to the real data. Leveraging recent advancements in machine learning, we propose to use state-of-the-art generative models, namely Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN), that prove their usefulness and efficiency in the context of computer vision and image processing. The main advantage offered by those methods is a significant speedup in the execution time, reaching up to the factor of 103 with respect to the GEANT3, a currently used cluster simulation tool. Nevertheless, this computational speedup comes at a price of a lower simulation quality. In this work we show quantitative and qualitative limitations of currently available generative models. We also propose several further steps that will allow to improve the accuracy of the models and lead to the deployment of anomaly detection mechanism based on generative models in a production environment of the TPC detector.
We present an experiment to gauge student awareness of security threats to cyber-physical systems. Students in a third-year engineering course were tasked with designing, building, and testing small, robotic vehicles ...
详细信息
ISBN:
(纸本)9783030269456;9783030269449
We present an experiment to gauge student awareness of security threats to cyber-physical systems. Students in a third-year engineering course were tasked with designing, building, and testing small, robotic vehicles that could perform basic goal seeking. Unbeknownst to the students, the indoor positioning system for the project was deliberately configured to report incorrect positional information, similar to the effect of GPS spoofing. When asked to conjecture reasons for the spurious behaviour of their robots, none of the students considered the possibility that the feedback system was sending spoofed data, despite being given case studies in cyber-physical system security earlier in the term. The results suggest that students need more direct education in threats and design considerations for security of cyber-physical systems.
Metaheuristics and especially Swarm Intelligence represents one of the mostly used aspect of Artificial Intelligence. In fact, these algorithms are exploited in several domains from theoretical problem solving to air ...
详细信息
ISBN:
(纸本)9783030456900;9783030456917
Metaheuristics and especially Swarm Intelligence represents one of the mostly used aspect of Artificial Intelligence. In fact, these algorithms are exploited in several domains from theoretical problem solving to air traffic management. The evaluation of such methods is defined by the quality of solution they provide or effectiveness and the spent time to reach this solution or efficiency. We explore, in this paper, the technology offered by the Graphic Processing Unit -GPU- to improve the efficiency of the Bees Swarm Optimization algorithm -BSO- by proposing a novel and parallel CPU/GPU version of the later algorithm. The algorithm being greedy when the problem size is important, which is almost always the case. The proposed parallel algorithm is integrated in the proposed method of clustering-solving hard problems presented in [1], adding the exploitation of GPU performance to that of data mining to improve the resolution of hard and complex problems such as Satisfiability problem.
This paper concerned with designing, building, and developing of intelligent Autonomous Environment (IAE). IAE is a system of integrated industrial buildings, or a residential district, or a shopping district, etc., d...
详细信息
ISBN:
(纸本)9783030204945;9783030204938
This paper concerned with designing, building, and developing of intelligent Autonomous Environment (IAE). IAE is a system of integrated industrial buildings, or a residential district, or a shopping district, etc., defined as an intelligent environment that has all systems of self-steering and adaptation. This paper focuses on IAEMS's organizational structure designing and developing. The main problems of designing are complexity and changeability of IAS. The response to such complexity and changeability context of IAE is the presented methodological conception of organizational structure designing, based on agile approach assumes: 1. Continuously scanning the environment and adopting the organizational strategy to the requirements of external and internal stakeholders. 2. Changing the list of business processes of IAE (function tree of IAE) in accordance with the stage of IAE cycle. 3. Flexibility of organizational structure forms in different stages of IAE life cycle. 4. Flexibility transformation organizational structures from one stage of the life cycle to the next one
暂无评论