Decision tree ensembles based on kernel features

A classifier ensemble is a set of classifiers whose individual decisions are combined to classify new examples. Classifiers, which can represent complex decision boundaries are accurate. Kernel functions can also represent complex decision boundaries. In this paper, we study the usefulness of kernel features for decision tree ensembles as they can improve the representational power of individual classifiers. We first propose decision tree ensembles based on kernel features and found that the performance of these ensembles is strongly dependent on the kernel parameters; the selected kernel and the dimension of the kernel feature space. To overcome this problem, we present another approach to create ensembles that combines the existing ensemble methods with the kernel machine philosophy. In this approach, kernel features are created and concatenated with the original features. The classifiers of an ensemble are trained on these extended feature spaces. Experimental results suggest that the approach is quite robust to the selection of parameters. Experiments also show that different ensemble methods (Random Subspace, Bagging, Adaboost.M1 and Random Forests) can be improved by using this approach.     

JackHare: a framework for SQL to NoSQL translation using MapReduce

As data exploration has increased rapidly in recent years, the datastore and data processing are getting more and more attention in extracting important information. To find a scalable solution to process the large-scale data is a critical issue in either the relational database system or the emerging NoSQL database. With the inherent scalability and fault tolerance of Hadoop, MapReduce is attractive to process the massive data in parallel. Most of previous researches focus on developing the SQL or SQL-like queries translator with the Hadoop distributed file system. However, it could be difficult to update data frequently in such file system. Therefore, we need a flexible datastore as HBase not only to place the data over a scale-out storage system, but also to manipulate the changeable data in a transparent way. However, the HBase interface is not friendly enough for most users. A GUI composed of SQL client application and database connection to HBase will ease the learning curve. In this paper, we propose the JackHare framework with SQL query compiler, JDBC driver and a systematical method using MapReduce framework for processing the unstructured data in HBase. After importing the JDBC driver to a SQL client GUI, we can exploit the HBase as the underlying datastore to execute the ANSI-SQL queries. Experimental results show that our approaches can perform well with efficiency and scalability.     

A Middleware-Based Simulation and Control Framework for Mobile Service Robots

A mobile service robot is a complex distributed system integrating various technologies and having large heterogeneity. In order to facilitate component development and system integration of the mobile service robots, a middleware-based simulation and control framework for system integration and application development, as well as the robotic functional component (RFC) framework with a simplified structure and an efficient transmission scheme, is proposed for mobile service robot systems. Designed to implement a distributed modular mechanism for a mobile service robot, the middleware-based framework for simulation and control is comprised of four layers: low-level abstraction layer, communication layer, high-level abstraction layer, and application layer. Common Object Request Broker Architecture (CORBA) and Robot Technology Middleware (RTM) are employed as middleware for the development of RFCs and for system integration. Communication between the components and the graphical programming tool is done by the communication layer (CORBA ORB). The conducted experiments validated the proposed framework in terms of ideal performance of reusability, interoperability, and extensibility, as well as indicated that the proposed RFC framework is simplified and easy enough to perform well in data transmission, which will reduce the costs and the threshold of robot development.     

DMODULA: A distributed programming language

This paper presents an overview of a distributed programming language calledDMODULA,which is intended for the programming in a distributed environment.DMODULA develops module concepts of its ancestor,MODULA-2,and providesfeatures of generic and remote procedure calls.DMODULA has been implemented onthe ZOZ system,a distributed microcomputer system consisting of several LSI-11microcomputers,which was designed and implemented at Nanjing University in 1982.     

Parallelizing Complex Streaming Applications on Distributed Scratchpad Memory Multicore Architecture

Multicore processors can provide sufficient computing power and flexibility for complex streaming applications, such as high-definition video processing. For less hardware complexity and power consumption, the distributed scratchpad memory architecture is considered, instead of the cache memory architecture. However, the distributed design poses new challenges to programming. It is difficult to exploit all available capabilities and achieve maximal throughput, due to the combined complexity of inter-processor communication, synchronization, and workload balancing. In this study, we developed an efficient design flow for parallelizing multimedia applications on a distributed scratchpad memory multicore architecture. An application is first partitioned into streaming components and then mapped onto multicore processors. Various hardware-dependent factors and application-specific characteristics are involved in generating efficient task partitions and allocating resources appropriately. To test and verify the proposed design flow, three popular multimedia applications were implemented: a full-HD motion JPEG decoder, an object detector, and a full-HD H.264/AVC decoder. For demonstration purposes, SONY PlayStation \(^{\circledR }\) 3 was selected as the target platform. Simulation results show that, on PS3, the full-HD motion JPEG decoder with the proposed design flow can decode about 108.9 frames per second (fps) in the 1080p format. The object detection application can perform real-time object detection at 2.84 fps at \(1280 \times 960\) resolution, 11.75 fps at \(640 \times 480\) resolution, and 62.52 fps at \(320 \times 240\) resolution. The full-HD H.264/AVC decoder applications can achieve nearly 50 fps.     

A Scalable Farm Skeleton for Hybrid Parallel and Distributed Programming

Multi-core processors and clusters of multi-core processors are ubiquitous. They provide scalable performance yet introducing complex and low-level programming models for shared and distributed memory programming. Thus, fully exploiting the potential of shared and distributed memory parallelization can be a tedious and error-prone task: programmers must take care of low-level threading and communication (e.g. message passing) details. In order to assist programmers in developing performant and reliable parallel applications Algorithmic Skeletons have been proposed. They encapsulate well-defined, frequently recurring parallel and distributed programming patterns, thus shielding programmers from low-level aspects of parallel and distributed programming. In this paper we take on the design and implementation of the well-known Farm skeleton. In order to address the hybrid architecture of multi-core clusters we present a two-tier implementation built on top of MPI and OpenMP. On the basis of three benchmark applications, including a simple ray tracer, an interacting particles system, and an application for calculating the Mandelbrot set, we illustrate the advantages of both skeletal programming in general and this two-tier approach in particular.     

Outline of the Personal Sequential Inference machine: PSI

PSI is a personal computer system being developed as a tool for providing researchers with an efficient programming environment. It directly supports logic programming language, KL0 (Fifth Generation Kernel Language, Version 0), with firmware and hardware. Its interpreter is implemented in the firmware and several hardware mechanisms are provided to attain almost the same level of performance as the DEC-10 Prolog on DEC2060. It also provides the user with a large memory space, 40 bits × 2 to 16 MW, which is essential for developing actual application programs like an expert system. To make efficient man-machine interaction possible, such input and output devices as bit-map display, pointing device and key-board are provided. A local area network is also being developed to build a distributed system.     

Partial evaluation of metaprograms in a “multiple worlds” logic language

This paper describes a partial evaluation system specifically designed to be used as an automatic compilation tool for metaprograms in a KBMS (EPSILON) based on Prolog. EPSILON main underlying concepts are the extension of Prolog with theories (“multiple worlds”) and the use of metaprogramming as the basic technique to define new inference engines and tools. Our partial evaluator is oriented towards theories and metainterpreter specialization. Being designed to be used as an automatic compiler, it does not require declarations from the user to control the unfolding process. It handles full Prolog and provides also an elegant solution to the problem of the partial evaluation of incomplete and self-modifying programs, by exploiting the multiple worlds feature added to Prolog. EPSILON partial evaluation system turned out to be a very useful and powerful tool to combine the low cost and the flexibility of metaprogramming with the performance requirements of a practical knowledge based system.     

Throughput models of CSMA network with stations uniformly distributed along the bus

The distribution of station locations in a CSMA network can have significant effect onnetwork throughput. In this paper, we develop an analytic model for unslotted, non-persistentCSMA bus network where the stations are uniformly distributed along the bus. We derive aclosod form expression for throughput approximation, and discuss the fairness of CSMAprotocol using the bus topology. Analytic and simulation results are presented and compared.     

A Distributed Address Configuration Scheme for a MANET

This paper proposes a distributed address configuration scheme for a Mobile Ad hoc Network (MANET). The architecture for a MANET, the algorithm of constructing a MANET, and the algorithm for calculating a unique address space for the assignment are proposed. In the architecture, a common node has a unique address space for the assignment, and an isolated node can acquire a unique address from a neighboring common node without performing duplicate address detection. In this way, the address configuration task is distributed around common nodes. In this scheme, the control packets used for address configuration are exchanged within a one-hop scope, so the scalability is enhanced. This paper also presents an address recovery algorithm that can effectively retrieve the address resources released by failed nodes and the MANET merging/partitioning algorithm that can ensure a node’s address uniqueness. This paper compares the performance parameters of the proposed scheme and the existing schemes, including strong duplicate address detection and prime dynamic host configuration protocol, and the comparative results show that the address configuration cost of the proposed scheme is lower and the delay is shorter.     

“LIGA2.X” process for mass production of single polymeric LIGA micro parts

The new modification of the LIGA process “LIGA2.X” is a promising process chain to replicate high accuracy single polymeric LIGA micro parts in large scale to feasible costs. The advantages of this new approach compared to the standard LIGA process are the reduction of fabrication costs, the elimination of any rework after replication, industry suitable mold technology for injection molding using a new developed demolding concept, optimized injection molding parameters for every single cavity, shot volumes of the parts below 0.5 mm³ and a new freedom in the arrangement of structure cavities in multicavity molds. Aspects covered in this paper are the introduction of the complete process chain of the new “LIGA2.X” process and the used mold concept for the micro-män 50 micro injection molding machine. Furthermore replicated single polymeric LIGA microparts fabricated using the new process chain are shown. To conclude, potential process improvements and future work will be outlined.     

RFID-based intelligent shopping environment: a comprehensive evaluation framework with neural computing approach

This research proposes a radio frequency identification (RFID)-based intelligent shopping environment and its distributed reading capability to raise quality of service through improving the automation of product presentation, inventory monitor, billing procedures, manpower logistics, and customer lifetime value prediction. This research also uses RFID to successfully create a smart-shelf-enabled system as an advanced decision-making mechanism for managers. A case study based on a well-known fashion retailing company is used to demonstrate how the proposed system can significantly improve daily business operations. In addition, this research also used artificial neural network to predict the VIP member classification and customer retention rate. The experimental results figure out that the artificial intelligence approach would be outperformed the statistical and decision tree methods. Finally, a questionnaire was administered to 120 customers and investigated their degree of RFID usage willingness and purchase intention based on the Unified Theory of Acceptance and Use of Technology model. The empirical results of our study present the easy-to-use and social influence factors that would be most influenced the customers’ usage willing and purchase intention with RFID technology.     

Asynchronous distributed termination—parallel and symmetric solutions with echo algorithms

The principle of message counting is used to detect termination of distributed computations which consist of processes asynchronously communicating over non-FIFO channels. The solution is symmetric and not based on a predefined communication structure. An efficient variant of the echo algorithm, which dynamically builds a spanning tree, allows a parallel and distributed evaluation of the termination predicate in time proportional to the diameter of the communication graph. Concurrent and repeated initiation of the detection algorithm by different processes is possible at any time without prior synchronization due to a subtle method of collision detection and wave extinction, which can be regarded as a distributed election scheme where the average message complexity increases only logarithmically with the number of concurrent initiators. Control messages have a small length and additional communication links are not required. Only a fixed number of simple variables is needed in every process, global knowledge such as the total number of processes or the structure of the network is not used, making the scheme useful for dynamic systems. Several variations of the basic principle are presented, important issues such as message complexity and fault-tolerance are discussed.     

Process parameters optimization for micro end-milling operation for CAPP applications

In Computer Aided Process Planning (CAPP), process parameters selection for the given manufacturing feature is the final activity and it is the key area for research and development. In this work, an attempt has been made to optimize parameters for micro end-milling operation as a part of CAPP system development for micromachining processes using Artificial Intelligence (AI) approach. Genetic Algorithm (GA) has been found to be the robust and efficient tool to solve nonlinear optimization problems involved in process planning. Microfeatures of size 0.7 and 1 mm are considered and polymethyl methacrylate is chosen as the work material due to its potential application in microparts fabrication. Initially, experimental investigation has been carried out to analyze the impact of process conditions such as spindle speed and feed rate on surface roughness and machining time. Further multiobjective optimization for minimization of responses is carried out using GA. Finally, confirmation experiments are carried out to validate the accuracy of GA results. The optimized process parameters are stored in the database and it ensures foolproof parameters for micro end-milling operation for CAPP applications apart from manuals and catalogues. The proposed approach can be repeated for various other end mill features and for different work and tool material combination to ensure a complete parameters selection module for CAPP system applications.     

A built-in test pattern generator

Built-in testing is currently of more concern due to the difficulties in testing a VLSI byusing an external tester.In addition,Built-In Testing is also necessary for on-line testing and afault-tolerant computing system.Using a Linear Feedback Shift Register(LFSR)as a built-intest pattern generator(BITPG)is a realistic and simple approach.An LFSR with maximumlength can generate pseudo-random test patterns or all non-null vectors for exhaustive testing.This paper presents an LFSR design with non-maximum length to serve as a BITPG to generatea given test set T,which efficiently saves testing time.A search-verification process fordesigning this kind of LFSR is employed and implemented by the program SVBITPG.Thispaper presents the diagram of tire program and gives stone examples to illustrate the design ofthe BITPG.     

Robust predictive augmented unscented Kalman filter

This paper presents a new Unscented Kalman Filtering (UKF) method by using robust model prediction. This method incorporates system driving noise in system state through augmentation of state space dimension to expand the input of system state information. The system model error is constructed by model prediction, and is then used to rectify the UKF process to obtain the estimate of the real system state. The proposed method endows the robustness to the traditional UKF, thus overcoming the limitation that the traditional UKF is sensitive to system model error. Experimental results show that the convergence rate and accuracy of the proposed filtering method is superior to the Extended Kalman Filtering and traditional UKF.     

In-memory application-level checkpoint-based migration for MPI programs

Process migration provides many benefits for parallel environments including dynamic load balancing, data access locality or fault tolerance. This paper describes an in-memory application-level checkpoint-based migration solution for MPI codes that uses the Hierarchical Data Format 5 (HDF5) to write the checkpoint files. The main features of the proposed solution are transparency for the user, achieved through the use of CPPC (ComPiler for Portable Checkpointing); portability, as the application-level approach makes the solution adequate for any MPI implementation and operating system, and the use of the HDF5 file format enables the restart on different architectures; and high performance, by saving the checkpoint files to memory instead of to disk through the use of the HDF5 in-memory files. Experimental results prove that the in-memory approach reduces significantly the I/O cost of the migration process.     

Knowledge information processing language: ShapeUp

A new logic programming language, ShapeUp, is developed. ShapeUp is an expanded Prolog system with string matching facilities. The language has been developed to give programmers a new computer programming environment, especially for knowledge information processing. This area includes natural language comprehension and intelligent text processing systems with better man-machine interfaces. For this kind of application, character string data play a principal part rather than conventional numerical data. In ShapeUp, string patterns are introduced as Prolog ‘terms’. Their matching process is performed inside the unification. Thus, a program is far simpler and easier to write and read in ShapeUp, than in conventional Prolog systems, and program size is extremely reduced.