A common question around the development of electric vehicles (EVs) is associated with the power, performance and reliability of their battery-powered systems in real world driving situations. The aim of this research work is to evaluate and characterize an EV battery power under real-world driving conditions in order to inform the design of the next generation systems. Also, we develop a framework of Connected Electric Vehicle Cloud (also known as connected EV cloud, or EV-cloud) to collect energy patterns and analyze driving behaviors for EV energy management. In this work we used a machine learning method based on Google's TensorFlow framework (TensorSOM) as our kernel analytic tool. Additionally, we utilized the SOM Toolbox on the Matlab platform to confirm the TensorSOM clustered results. The experimental result demonstrated that our proposed approach is a sensible solution for learning EV drivers' behaviors.

Determining the number of clusters, which is usually approved by domain experts or evaluated by clustering validity indexes, is an important issue in clustering analysis. This study discusses the effectiveness of clustering validity indexes for centroid-based partitional clustering algorithms. Most general-purpose clustering validity indexes take the minimum/maximum distance between a pair of data objects, a pair of cluster centroids, or an object and a centroid as an important evaluation factor; however, they may present unstable results, especially when two centroids are allocated closely. To alleviate this problem, a new clustering validity index, which is termed the Wu-and-Li index (WLI), is proposed in this paper. Our proposed WLI partially allows, to some extent, the existence of closely allocated centroids in the clustering results by considering not only the minimum but the median distances between a pair of centroids as well; therefore possessing better stability. The performances of WLI and some existing clustering validity indexes are evaluated and compared by running the fuzzy c-means algorithm for clustering various types of datasets, including artificial datasets, UCI datasets, and images. Experimental results have shown that WLI has the more accurate and satisfactory performance than other indexes.

Evolvable Hardware (EHW) is a combination of evolutionary algorithm and reconfigurable hardware devices. Due to its flexible and adaptive ability, EHW-based solutions receive a lot of attention in industrial applications. One of the obstacles to realize an EHW-based method is its very long training time. This study deals with the parallelism of EHW-based design of image filters using graphic processing units (GPUs). The design process is analyzed and decomposed into some smaller processes that can run in parallel. Pixel-based data for training and verifying EHW solutions are partitioned according to the architecture of GPU. Several strategies for deploying parallel processes are developed and implemented. With the proposed method, significant improvements on the efficiency of training EHW models are gained. Using a GPU with 240 cores, a speedup of 64 times is obtained. This paper evaluates and compares the performance of the proposed method with other ones.

This paper presents a new SLAM (simultaneous localization and mapping) method using genetic algorithm (GA) for mobile robots. A laser range finder (LRF) is installed on a mobile robot for collecting point-distance information about the surroundings. From the LRF points, several important ones are extracted for describing the main features of the surroundings. A new form of chromosomes for representing the changes of feature LRF points that are caused by the robot's movement is designed. The matching of current LRF features and the robot's possible movement is done by a fast genetic algorithm. A restart mechanism that re-initializes all chromosomes for increasing the diversity of solutions is developed and works with the matching process. Some constrains are developed for filtering out irrational chromosomes after the operation of crossover and mutation. With these mechanisms and constrains, our proposed method generates feasible solutions in several hundreds of GA iterations. Experiments are conducted on a real mobile robot. The experimental results show that our proposed method is efficient and effective for SLAM.

MOTIVATION: Synthetic biology aims to develop the artificial gene networks with desirable behaviors using systematic method. These networks with desired behaviors could be constructed using diverse biological parts, which may limit the development to complex synthetic gene networks. Fortunately, some well-characterized promoter libraries for engineering gene networks are widely available. Thus, a synthetic gene network can be constructed by selecting adequate promoters from promoter libraries to achieve the desired behaviors. However, the present promoter libraries cannot be directly applied to engineer a synthetic gene network. In order to efficiently select adequate promoters from promoter libraries for a synthetic gene network, promoter libraries are needed to be redefined based on the dynamic gene regulation. RESULTS: Based on four design specifications, a library-based search method is proposed to efficiently select the most adequate promoter set from the redefined promoter libraries by a genetic algorithm (GA) to achieve optimal reference tracking design. As the number and size of promoter libraries increase, the proposed method can play an important role in the systematic design of synthetic biology. CONTACT: [email protected]; [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We present and compare implementations of an affine interior-point algorithm for real-time collision detection on a GPGPU and an FPGA. This particular interior-point algorithm is distinguished from other collision detection methods by its ability to perform detection between pairs of objects undergoing fast rotational and translational movement. This enables inter-frame collision detection, i.e. collision that might occur during the transition from one frame to another. In our design for the FPGA, we implemented the algorithm both in single-precision floating point and 32-bit fixed point and analyzed the trade-off between resource usage, data accuracy/precision, and system efficiency. Then, we compare them to a floating point implementation on a GPGPU using CUDA. With an object resolution of 45 vertices (45 vertices representing each polyhedral object), our FPGA implementation processes 1562 frames/sec for floating point and 1350 frames/second for fixed point and offers an 11× speedup over the GPGPU implementation. With object resolutions greater than 242 vertices, our GPGPU implementation outperforms our FPGA implementations.

In this study, a multi-purpose remote controller based on Bluetooth mobile phone (MRCBMP) is proposed to provide users for a convenient control interface. The IR, RF and Bluetooth modules are integrated into the microcontroller module cooperated with Bluetooth mobile phone by Bluetooth module. By MRCBMP, users can control IR, RF and Bluetooth controlled objects without the numerous conventional remote controllers.

At present, the development in the nascent field of synthetic gene networks is still difficult. Most newly created gene networks are nonfunctioning due to intrinsic parameter fluctuations, uncertain interactions with unknown molecules and external disturbances of intra and extracellular environments on the host cell. How to design a completely new gene network, that is to track some desired behaviors under these intrinsic and extrinsic disturbances on the host cell, is the most important topic in synthetic biology. In this study, the intrinsic parameter fluctuations, uncertain interactions with unknown molecules and environmental disturbances, are modeled into the nonlinear stochastic systems of synthetic gene networks in vivo. Four design specifications are introduced to guarantee the stochastic synthetic gene network, which can achieve robust optimal tracking of a desired reference model in spite of these intrinsic and extrinsic disturbances on the host cell. However, the robust optimal reference-tracking design problem of nonlinear synthetic gene networks is still hard to solve. In order to simplify the design procedure of the robust optimal nonlinear stochastic-tracking design for synthetic gene networks, the Takagi-Sugeno (T-S) fuzzy method is introduced to solve the nonlinear stochastic minimum-error-tracking design problem. Hence, the robust optimal reference-tracking design problem under four design specifications can be solved by the linear matrix inequality (LMI)-constrained optimization method using convex optimization techniques. Further, a simple design procedure is developed for synthetic gene networks to meet the four design specifications to achieve robust optimal reference tracking. Finally, an eigenvalue-shifted design method is also proposed as an expedient scheme to improve the stochastic optimal-tracking design method of synthetic gene oscillators.

In this paper, we proposed a novel house prediction model that integrated hybrid genetic-based support vector regression (HGA-SVR) model and feng shui theories for developing a high accuracy appraising real estate price system in Taiwan. In Taiwan, feng shui theory applies in choosing good days, divination and house selection. From the past researches, many factors might affect the real estate price which are the announced land values, the building room age, building total number of floor, the transportation condition and surrounding environment of house etc. However, few studies have been considered the feng shui effects in appraising real estate price. Therefore, the present study pioneers in applying feng shui theories for developing a high accuracy real estate price prediction system with back-propagation neural network (BPN), fuzzy neural network (FNN) and hybrid genetic-based SVR (HGA-SVR) to compare. Our results obtained from the comparison between two house price models with various artificial neural network models. By comparing the accuracy with various network architectures, the result demonstrates that HGA-SVR is the best network architecture and the feng shui model has a better performance in BPN, FNN and HGA-SVR. Our house price prediction system discovers some real estate price much higher than the reasonable prices. This result shows that this unreasonable price needs adjusting to become more reasonable to conform the housing market.

This paper proposed a novel multi-objective affinity set (MO affinity set) classification system comparing with Ant colony optimization (ACO) and affinity set theory on delayed diagnosis dataset classification. The output of MO affinity set classification rules has the higher accuracy than ACO and traditional affinity set. Furthermore, our MO affinity set classification skips the traditional affinity set k-core method, and has fewer rules. It is better and more easily to apply or to construct a support system if the number of rules is smaller.

The interior-point algorithm is a powerful method for solving a linear program (LP). A variety of optimization problems can be formulated as LPs. Often times the limiting factor of deploying an algorithm to solve LPs in a high performance system is the run-time efficiency. In this paper, we present the FPGA implementation of an affine interior-point algorithm that is designed to solve LPs. Specifically, we present the application of this algorithm to solving the LP for the real-time collision detection. The most important feature that distinguishes this particular algorithm from other collision detection methods is its superior ability to perform detection between pairs of objects undergoing fast rotational and translational motions.

Global positioning system (GPS) has been used extensively in various fields. One key to success of using GPS is the positioning accuracy. Geometric dilution of precision (GDOP) is an indicator showing how well the constellation of GPS satellites is organized geometrically. It is known that increasing the number of satellites for positioning reduces GDOP. However, the calculation of GDOP is a time- and power-consuming task which can be done by solving measurement equations with complicated matrix transformation and inversion. Previous studies have partially solved this problem with artificial neural network(ANN). Though ANN is a powerful function approximation technique, it needs costly training and the trained model may not be applicable to data deviating too much from the training data. Using the technique of support vector regression (SVR), this paper presents the effectiveness of SVR for GDOP approximation. The experimental results show that SVR needs less training time to generate a precise model for GDOP than ANN does.

Multiple sequence alignment (MSA) has become an important issue in computational molecular biology. The purpose of MSA is to infer evolutionary history or discover homologous regions among closely related DNA or protein sequences. A wide variety of approaches has been proposed for the MSA problem; however, some of them need prerequisites to find the best alignment or may suffer from the drawbacks of high computational complexity and huge memory requirement so they can be only applied to cases with a limited number of sequences. In this paper, we view the MSA problem as an optimization problem and resolve it by applying a genetic algorithm. In order to improve the search performance and obtain a better alignment quality, we design a few problem-specific genetic operators. Experimental results on real DNA and protein sequences are given to illustrate the feasibility of the proposed approach.

This paper presents a development of mobile load monitoring and control system (MLMCS) in application to remote load management. MLMCS consists of client monitoring and control interface (CMCI) on mobile phone screen and wireless ARM-based automatic meter reading and control system (WAMRCS). To provide a cost-effective, wireless, always-connected, two-way data link between supervisor and WAMRCS, the WAMRCS sends information of power data and outage alarm to supervisor via GPRS network. In emergency conditions WAMRCS will notice supervisor in real time, and then the supervisor can quickly make a response to clear power faults anywhere and anytime through CMCI on mobile phone screen to decrease the users' loss.

Transformation of coordinates usually invokes level-wise processes wherein several sets of complicated equations are calculated. Unfortunately, the accuracy may be corrupted due to the accumulation of inevitable errors between the transformation processes. This letter rephrases the transformation of coordinates from global positioning system (GPS) signals to 2-D coordinates as a regression problem that derives target coordinates from the inputs of GPS signals directly. In this letter, a genetic-based solution is proposed and implemented by the techniques of symbolic regression and genetic programming. Since coordinates for a GPS application are obtained by using simpler transformation formulas, the computational costs and inaccuracy can be reduced. The proposed method, although it does not exclude systematic errors due to the imperfection on defining the reference ellipsoid and the reliability of GPS receivers, effectively reduces statistical errors when accurate Cartesian coordinates are known from independent sources. To our best knowledge, this letter is the first attempt to use genetic-based methods in coordinate transformation for GPS positioning. From the experimental results where the target datums TWD67 and TWD97 are investigated, it seems that the proposed method can serve as a direct and feasible solution to the transformation of GPS coordinates

This paper presents the design and implementation of a grid-computing environment for mining sequential patterns. An Apriori-like algorithm for mining sequential patterns is deployed in the proposed grid-computing environment. Apriori-like algorithm is not of very high performance in comparison to others but it is more convenient to be realized for distributed processing in a grid computing environment due to its loosely coupled processes. Two types of grids are designed, the computing grid and data grid, in the proposed environment. All grids are installed with full functions, each of which is wrapped by Globus toolkit. Grid services are invoked by the users or other grids and able to respond to the invoking side. There are 10 computers serving as grid nodes each of which is equipped with different hardware components and is distributed on two campuses. The experimental results show that the proposed grid-computing environment provides a flexible and efficient platform for mining sequential patterns from large datasets.

We present in this paper a new method for completing missing data using the concept of association rules. The basic idea is that association rules describe the dependency relationships among data entries in a dataset where all data, including the missing ones, should hold the similar relationships. For a missing datum, we guess its possible value according to related association rules. A new completing procedure and a new evaluation function are developed and presented. The evaluation function is scored according to the support, confidence, and lift of association rules, which reasonably reflects the dependency relationships among existing and missing data. Experimental results show that our method is feasible in completing some incomplete datasets.

This paper presents a novel approach to the verification of rule-based systems (RBSs). A graph structure, called the rule-dependency graph (RDG), is introduced to describe the dependency relationship among the rules of an RBS, in which each type of improper knowledge forms a specific topological structure. Knowledge verification is then performed by searching for such topological structures through a token-flow paradigm. An algorithm is provided, which automatically generates a minimally sufficient set of literals as test tokens in the detection procedure. The proposed scheme can be applied to rules of non-Horn clause form in both propositional and first-order logic, and restrictions imposed by other graph-based approaches can be avoided. Furthermore, explicit and potential anomalies of RBSs can be correctly found, and efficient run-time validation is made possible.

Case-based document writing encounters inefficiency and incompleteness due to the use of explicit index-terms. We propose a Petri-net framework which represents and retrieves the semantic concepts of cases for document writing. In our approach, cases of documents are represented as Petri nets according to their semantic concepts. New documents can be made efficiently and completely by retrieving the conceptions of cases.

KJ3 is the first system which incorporates theorem proving techniques with the Petri Net description scheme for knowledge validation of rule based systems (RBSs). By converting the validation tasks of RBSs to reachability problems of Enhanced High-level Petri Net (EHLPN), KJ3 performs validation by proving if the hypothetical reachability problem is true. The establishment of the hypothesis corresponds to the achievement of the validation tasks. Since the properties of RBSs, such as refraction, conservation of facts, variables, closed world assumption, and negative information, can be properly represented and handled by EHLPN, different types of RBSs can be processed in KJ3. Since checking user specifications becomes investigating the reachability problems of EHLPN, all types of validation tasks can be handled by KJ3. The validation results can be directly extracted from the inference process to allow the users to explain the validation results. The inference process is mathematically traceable, sound, and complete, KJ3 guarantees that the validation outcome is reliable.

Exploring the properties of rule-based expert systems through Petri net models has received a lot of attention. Traditional Petri nets provide a straightforward but inadequate method for knowledge verification/validation of rule-based expert systems. We propose an enhanced high-level Petri net model in which variables and negative information can be represented and processed properly. Rule inference is modeled exactly and some important aspects in rule-based systems (RBSs), such as conservation of facts, refraction, and closed-world assumption, are considered in this model. With the coloring scheme proposed in this paper, the tasks involved in checking the logic structure and output correctness of an RES are formally investigated. We focus on the detection of redundancy, conflicts, cycles, unnecessary conditions, dead ends, and unreachable goals in an RES. These knowledge verification/validation (KVV) tasks are formulated as the reachability problem and improper knowledge can be detected by solving a set of equations with respect to multiple colors. The complexity of our method is discussed and a comparison of our model with other Petri net models is presented.

This paper exploits the parallelism of a hyper-linking based theorem prover. We analyze the unique properties of the the hyper-linking proof procedure and present the preliminary results. With respect to these properties four parallel strategies, phase-level, clause-level, literal-level, search level parallelism are designed for different implementation schemes of the prover. Results and analysis of the experiments on these parallel strategies are presented.

A new rule-based expert system language is proposed. Based on the Rete rule network structure, the language represents knowledge in the form of predicates and supports non-Horn clauses. Variables are allowed to be contained in facts. Rules can be added/deleted dynamically, when consulting an expert system built in this language, without causing any inconsistency in the knowledge base.