Delivering superior search services is crucial for enhancing customer experience and driving revenue growth in e-commerce. Conventionally, search systems model user behaviors by combining user preference and query-ite...
详细信息
ISBN:
(纸本)9798400712746
Delivering superior search services is crucial for enhancing customer experience and driving revenue growth in e-commerce. Conventionally, search systems model user behaviors by combining user preference and query-item relevance statically, often through a fixed logical 'and' relationship. This paper reexamines existing approaches through a unified lens using causal graphs and Venn diagrams, uncovering two prevalent yet significant issues: entangled preference and relevance effects, and a collapsed modeling space. To surmount these challenges, our research introduces a novel framework, DRP, which enhances search accuracy through two components to reconstruct the behavior modeling space. Specifically, we implement preference editing to proactively remove the relevance effect from preference predictions, yielding untainted user preferences. Additionally, we employ adaptive fusion, which dynamically adjusts fusion criteria to align with the varying patterns of relevance and preference, facilitating more nuanced and tailored behavior predictions within the reconstructed modeling space. Empirical validation on two public datasets and a proprietary e-commerce search dataset underscores the superiority of our proposed methodology, demonstrating marked improvements in performance over existing approaches. The code is available at https://***/Applied-Machine-Learning-Lab/DRP.
A heterogeneous material with a certain periodic microstructure may have specific properties, such as negative Poisson's ratio and zero thermal expansion coefficients, which can satisfy some requirement of high te...
详细信息
A heterogeneous material with a certain periodic microstructure may have specific properties, such as negative Poisson's ratio and zero thermal expansion coefficients, which can satisfy some requirement of high technology. However, currently research about how to fabricate such 3-D periodic microstructures is rarely reported in the published literature and only some 2D fabrication procedures were developed. To fabricate such components, a hybrid-layered manufacturing process has been developed and applies spraying, engraving, and refinishing technologies, among which the engraving is the key technology for generating the voids of periodic microstructures with their required dimensions and accuracies. To implement such an accurate engraving, it is important to study its engraving behavior. This paper establishes a behavior model of the engraving operation and performs its behavior simulation, thus providing a reliable basis for future practical manufacturing.
Train control systems like most digital controllers are, by definition, hybrid systems as they interact with or try to control some aspects of the physical world. Detailed behavior modeling with constraints specificat...
详细信息
Train control systems like most digital controllers are, by definition, hybrid systems as they interact with or try to control some aspects of the physical world. Detailed behavior modeling with constraints specification and formal verification, required for reliability prediction, is a great challenge for hybrid system *** control systems further intensify this challenge with extensive interaction between computing units and their physical environment and their mutual dependence on each other. In this paper, we investigate behavior modeling and formal verification of Chinese Train Control System Level 3(CTCS-3) using Architectural Analysis & Design Language(AADL) to cope with this challenge. AADL is an architecture description language for embedded systems and is based on model-based engineering paradigm. Along with structural modeling of embedded systems using the core language constructs, AADL also provides support for language extension through annex sublanguages. In system requirements specification document, the behavior of the CTCS-3 is specified as a set of basic operation scenarios that cooperate with each other to achieve safe and secure functionality of *** Authority(MA) scenario, explored in this paper, is considered as a basic and most crucial scenario to prevent trains from colliding with each other. The detailed discrete behavior of control system is modeled and verified using the behavior Language for Embedded Systems with Software(BLESS) annex sublanguage of AADL, and the continuous behavior of train with the cyber–physical interaction(communication between train and control system) is modeled using the Hybrid annex sublanguage. The behavior of the MA scenario at system level is verified using the Hybrid Hoare Logic theorem prover. behavior constraints are specified as assertions using first-order logic formulas augmented with a simple temporal operator.
作者:
Velay, V.Matsumoto, H.Vidal, V.Chiba, A.Univ Toulouse
Campus Jarlard F-81013 Albi France UPS
CNRS Mines Albi ISAE SUPAERO Campus Jarlard F-81013 Albi France ICA
Campus Jarlard F-81013 Albi France Kagawa Univ
Fac Engn Dept Adv Mat Sci 2217-20 Hayashi Cho Takamatsu Kagawa 7610396 Japan Tohoku Univ
Inst Mat Res Aoba Ku 2-1-1 Katahira Sendai 9808577 Miyagi Japan
Ti-6Al-4V alloy is widely used in superplastic forming process. The conventional conditions require high forming temperatures (T >= 900 degrees C) and low strain rates ((epsilon) over dot = 800 degrees C) are parti...
详细信息
Ti-6Al-4V alloy is widely used in superplastic forming process. The conventional conditions require high forming temperatures (T >= 900 degrees C) and low strain rates ((epsilon) over dot <= 10(-3) s(-1)). In order to reduce the costs of the industrial process, recent investigations focus on the micro-structural refinement of the material. It allows an improvement of the forming conditions which makes lower forming temperatures and higher strain rates eligible whereas low strain rates ((epsilon) over dot <= 10(-3) s(-1)) and high temperatures (T >= 800 degrees C) are particularly suitable for conventional superplastic forming conditions. However, the mechanical response of the Titanium alloy strongly depends on the starting micro-structure considered and on its evolution with the temperature and the deformation. The objective of the present investigation is to observe the micro-structural evolutions of Ti-6Al-4V alloy under thermal and mechanical loadings from different starting micro-structures. Hence, an internal grain growth variable is identified by the use of these observations. Then, it is introduced into the behavior model and its influence on the mechanical response of the material is analyzed. The final constitutive equations are able to take into account viscosity, strain hardening and grain size evolution for a wide range of strain rates and forming temperatures (10(-4) s(-1) <= (epsilon) over dot <= 10(-2) s(-1);650 degrees C <= T <= 870 degrees C). Moreover, the model is able to consider several starting microstructures (different initial grain sizes) and to predict their influence on the viscous flow and the strain hardening. At last, some model verifications are conducted to check the validity of the non isothermal model formulation. Some predictions are also performed by considering several starting microstructures. (C) 2016 Elsevier Ltd. All rights reserved.
In modern training, entertainment and education applications, behavior trees (BTs) have been the fantastic alternative to FSMs to model and control autonomous agents. However, manually creating BTs for various task sc...
详细信息
ISBN:
(纸本)9781538626184
In modern training, entertainment and education applications, behavior trees (BTs) have been the fantastic alternative to FSMs to model and control autonomous agents. However, manually creating BTs for various task scenarios is expensive. Recently the genetic programming method has been devised to learn BTs automatically but produced limited success. One of the main reasons is the scalability problem stemming from random space search. This paper proposes a modified evolving behavior trees approach to model agent behavior as a BT. The main features lay on the model free method through dynamic frequent subtree mining to adjust select probability of crossover point then reduce random search in evolution. Preliminary experiments, carried out on the Mario AI benchmark, show that the proposed method outperforms standard evolving behavior tree by achieving better final behavior performance with less learning episodes. Besides, some useful behavior subtrees can be mined to facilitate knowledge engineering.
Cyber-Physical Systems (CPSs), characterized by deeply integrating computing, communication and control, are large-sale, complex, embedded systems with hybrid characteristic. The uncertainty of discrete states and con...
详细信息
ISBN:
(纸本)9781479948970
Cyber-Physical Systems (CPSs), characterized by deeply integrating computing, communication and control, are large-sale, complex, embedded systems with hybrid characteristic. The uncertainty of discrete states and concurrency of continuous process, caused by hybrid interaction between computing and physical process, make it difficult to be fully described by the traditional hybrid model. In view of the above problems, this paper, taking a typical CPS case-the scene of lunar rover autonomous walking for example, adopts the Discrete Hybrid Automata (DHA) modeling frame and Hybrid System Description Language (HYSDEL) to build and analyze its behavior model. Furthermore, combined with the related toolbox for MATLAB, the trajectories of the continuous states are simulated. The outcomes demonstrate that the modeling technique can overcome the above problems well and lay a model foundation for the further simulation and verification.
A type of services that require human physical actions and intelligent decision making exists in various real fields, such as nursing in hospitals and caregiving in nursing homes. The authors' group call such serv...
详细信息
ISBN:
(纸本)9781479935642
A type of services that require human physical actions and intelligent decision making exists in various real fields, such as nursing in hospitals and caregiving in nursing homes. The authors' group call such services "physical and adaptive intelligent services," and is developing an IT-based system that is aims to assist cooperation and knowledge sharing among staffs. In this paper, we propose a new method for analyzing changes in the behavior of staffs before/after introducing the system. The method is based on probabilistic modeling of staffs' behavior. Using event-logs recorded by the system, behavior models are learned in the form of N-gram models. The method is also used for detection of unusual human behavior in the event-logs.
Accurate PMSM drive simulation which utilizes a behavior model produced from FEA results to consider the nonlinear characteristics has been requested to evaluate the driving performance. This paper proposes an advance...
详细信息
ISBN:
(纸本)9781479943883
Accurate PMSM drive simulation which utilizes a behavior model produced from FEA results to consider the nonlinear characteristics has been requested to evaluate the driving performance. This paper proposes an advanced behavior motor model based on the flux linkage model instead of the inductance model to be able to simplify the derivation of the equations and to reduce the amount of table data produced from FEA results. The effectiveness of the proposed model which includes the magnetic saturation and cross-coupling, moreover spatial harmonics is verified in the circuit simulation by comparing the direct FEA results and measurement result. The results of the proposed model agree fairly well with the FEA results and measurement result.
Traditionally, in building energy modeling (BEM) programs, occupant behavior (OB) inputs are deterministic and less indicative of real world scenarios, contributing to discrepancies between simulated and actual energy...
详细信息
Traditionally, in building energy modeling (BEM) programs, occupant behavior (OB) inputs are deterministic and less indicative of real world scenarios, contributing to discrepancies between simulated and actual energy use in buildings. This paper presents a new OB modeling tool, with an occupant behavior functional mock-up unit (obFMU) that enables co-simulation with BEM programs implementing functional mock-up interface (FMI). The components detailed in the development of the obFMU include an overview of the DNAS (drivers-needs-actions-systems) ontology and the occupant behavior eXtensible Markup Language (obXML) schema, in addition to details on the creation of the obFMU that contains the co-simulation interface, the data model and solvers. To demonstrate functionality of the tool, three examples of occupant behaviors were simulated, including: (1) turning on and off lights, (2) opening and closing windows, and (3) turning on and off the air conditioners. The obFMU can be used via co-simulation with all building simulation programs that implement the FMI, thus users are not limited to a particular tool. Another advantage is the use of obXML schema to represent occupant behavior, standardize the description of occupant behavior enabling information exchange. (C) 2015 Elsevier B.V. All rights reserved.
暂无评论