Feature-Based Aggregation and Deep Reinforcement Learning:A Survey and Some New Implementations

In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement.

Feature-based Image Sequence Compression Coding

A novel compressing method for video teleconference applications is presented. Semantic-based coding based on human image feature is realized, where human features are adopted as parameters. Model-based coding and the concept of vector coding are combined with the work on image feature extraction to obtain the result.

Stability ofWorkpkce Setup in Feature-Based Fixture Planning System

Analyzed the issues of stability of workpiece during clamping and machining. Discussed classification of the stability problem according to the forces acting on the part in the commonly used machining processes; gave the methods of calculating clamping force and measures to guarantee the stability of workpiece in the feature-based fixture planning design system.

Coding of Topological Entities in Feature-Based Parametric Modeling System

How to identify topological entities during rebuilding features is a critical problem in Feature-Based Parametric Modeling System (FBPMS). In the article, authors proposes a new coding approach to distinguish different entities. The coding mechanism is expatiated,and some typical examples are presented. At last, the algorithm of decoding is put forward based on set theory.

Comparison of Ontology-Based Semantic-Similarity Measures in the Biomedical Text

In recent years, there are many types of semantic similarity measures, which are used to measure the similarity between two concepts. It is necessary to define the differences between the measures, performance, and evaluations. The major contribution of this paper is to choose the best measure among different similarity measures that give us good result with less error rate. The experiment was done on a taxonomy built to measure the semantic distance between two concepts in the health domain, which are represented as nodes in the taxonomy. Similarity measures methods were evaluated relative to human experts’ ratings. Our experiment was applied on the ICD10 taxonomy to determine the similarity value between two concepts. The similarity between 30 pairs of the health domains has been evaluated using different types of semantic similarity measures equations. The experimental results discussed in this paper have shown that the Hoa A. Nguyen and Hisham Al-Mubaid measure has achieved high matching score by the expert’s judgment.

Feature Technology in Product Modeling

A unified feature definition is proposed.Feature is form-concentrated,and can be used to model product func- tionalities,assembly relations,and part geometries.The feature model is given and a feature classification is introduced including functional,assembly,structural,and manufacturing features.A prototype modeling system is developed in Pro/ENGINEER that can define the assembly and user-defined form features.

A Novel Features Prioritization Mechanism for Controllers in Software-Defined Networking

The controller in software-defined networking(SDN)acts as strategic point of control for the underlying network.Multiple controllers are available,and every single controller retains a number of features such as the OpenFlow version,clustering,modularity,platform,and partnership support,etc.They are regarded as vital when making a selection among a set of controllers.As such,the selection of the controller becomes a multi-criteria decision making(MCDM)problem with several features.Hence,an increase in this number will increase the computational complexity of the controller selection process.Previously,the selection of controllers based on features has been studied by the researchers.However,the prioritization of features has gotten less attention.Moreover,several features increase the computational complexity of the selection process.In this paper,we propose a mathematical modeling for feature prioritization with analytical network process(ANP)bridge model for SDN controllers.The results indicate that a prioritized features model lead to a reduction in the computational complexity of the selection of SDN controller.In addition,our model generates prioritized features for SDN controllers.

An Integrated Die Casting Design System

Die casting process is one of the prime options for m anufacturing precisely dimensioned, sharply defined metal parts. The design of d ie casting dies comprises several stages and entails a large amount of time. Tra ditionally, the different stages of the die design were not integrated but exist as separate entities. Moreover, recurring modifications or even redesigns are r equired due to the complexity in achieving an accurate initial die design. As a result, die design is usually time-consuming and costly with respect to resourc es. The die casting industry will greatly benefit if proper application software are developed that integrates the different die design stages and allows editin g of die design as and when needed. Hence it is imperative to create an integrat ed die design system that shortens the die design time. This paper presents a research that establishes a prototype of an integrated die design system. It is developed using the commercial SolidWorks CAD system and n amed DiWorks. The aim of building the system on a commercial CAD system is to ut ilise the resources and features of the CAD system to speed up the die design pr ocess. DiWorks consists of six distinct modules: Project Manager, Cavity Insert Builder, Gating System Constructor, Die Base Designer, Ejector System Constructo r and Standard Components Library. Through these six modules, the die designer c an create a complete die casting die beginning from a product part model. It is a user-friendly system that allows both experienced and novice die designers to easily accomplish the task of die design. The practical goal of this research is twofold: to develop a system that integra tes the die design process and at the same time facilitates the editing of d ie design during or after the course of the design process. The research approac h includes (i) parametric design, (ii) feature-based design (iii) system modeli ng and implementation. Parametric design deals with variable dimensions as contr ol parameters, and it is an efficient tool for creating models based on paramete rs. Parametric design not only increases the design efficiency, but also makes t he updates and modifications of existing designs easier and faster, since these can be achieved by changing the parameters of the parametric model. Feature-bas ed design is used to design a product with features that are functionally define d by attributes and are geometrically represented by a set of parameters. The re sults of this research will aid the automation of the die design process, thus i mproving the efficiency and quality of, and reducing the cost of die design.

A Method for Integrating Modelling with Decomposition

To make a bridge between engineering information and the geometry of product model, it is crucial to manipulate product model with form features containing high-level engineering information. In recent years much research has been undergone in the area of form feature recognition. In many previous works form feature recognition usually starts with a finished CAD model. The shape of a finished model consisted of a number of features is much more complex than that of a single feature. This problem was ignored by many previous works. In this paper a completely context-independed method is provided. In designing the part,. the feature-based model is decomposed into a quasi-feature-based one that can be converted into various context-oriented feature models required by specific context-oriented applications. In order to decompose features into quasi-features which have convex volumes, this paper proposes a method which integrates modelling with decomposition.

A procedural footprint enhancement of global topographic surface with multiple levels of detail

Virtual globes are technologies for visual navigation through a threedimensional,multi-resolution model of the entire planet.Data representations used in virtual globes,however,lack geometric flexibility at high-resolution levels of the planet-wide terrain surface.This is a problem especially if boundaries between individual geospatial features and the terrain are important.A novel integration of individual polygonal boundaries with a specific multi-resolution representation of the planet-wide terrain is developed in this article.In the preparation stage,the integration relies on an original simplification algorithm applied to the polygonal boundaries between geospatial features and the terrain.Its output is a multiple level-of-detail(LOD)geometry,which can be combined with a known multi-LOD representation of the terrain that uses run-time triangulation.This data representation is suitable for storage in existing database systems,avoids any data redundancy across LODs,and is even independent of the subdivision schema that partitions the planet’s surface for the sake of dealing with LODs.At runtime,a novel reconstruction algorithm stitches geometric parts from different LODs together in a manner that augments the multi-LOD representation of the terrain.Within a certain proximity range from a given position,the method reconstructs a scene that preserves topological relations between the boundaries of geospatial features with the terrain.The method also guarantees that certain nearest proximity to the given position consists of the best geometries that correspond to the original datasets.Such properties of the method close up the gap between a mere exploratory visualization of static,pre-generated models and the models supporting geospatial analysis,which is deemed crucial for applications in Geographic Information Systems,Building Information Modelling and other software industries.A prototype implementation and experiment results that prove this method are also presented.