
Understanding the behavioural aspects and functional attributes of an existing software system is an important enabler for many software engineering activities including software maintenance and evolution. In this paper, we focus on understanding the differences between subsequent versions of the same system. This allows software engineers to compare the implementation of software features in different versions of the same system so as to estimate the effort required to maintain and test new versions. Our approach consists of exercising the features under study, generate the corresponding execution traces, and compare them to uncover similarities and differences. We propose in this paper to compare feature traces based on their main behavioural patterns instead of a mere event-to-event mapping. Two trace correlation metrics are also proposed and which vary whether the frequency of the patterns is taken into account or not. We show the effectiveness of our approach by applying it to traces generated from an open source object-oriented system.
This paper presents a bio-inspired neural network algorithm for mobile robot path planning in unknown environments. A novel learning algorithm combining Skinner's operant conditioning and a shunting neural dynamics model is applied to the path planning. The proposed algorithm depends mainly on an angular velocity map that has two parts: one from the target, which drives the robot to move toward to target, and the other from obstacles that repels the robot for obstacle avoidance. An improved biological learning algorithm is proposed for mobile robot path planning. Simulation results show that the proposed algorithm not only allows the robot to navigate efficiently in cluttered environments, but also significantly improves the computational and training time. The proposed algorithm offers insights into the research and applications of biologically inspired neural networks.
In this paper a new method to address bearing-only SLAM using particle filters is proposed. We use a set of line pieces to model the uncertainties of landmarks and derive a proper formulation to modify the joint robot and landmark assumptions in the context of a particle filter approach.
We present an evaluative review of various edge detection techniques for color images that have been proposed in the last two decades. The statistics shows that color images contain 10% additional edge information as compared to their gray scale counterparts. This additional information is crucial for certain computer vision tasks. Although, several reviews of the work on gray scale edge detection are available, color edge detection has few. The latest review on color edge detection is presented by Koschan and Abidi in 2005. Much advancement in color edge detection has been made since then, and thus, a thorough review of state-of-art color edge techniques is much needed. The paper makes a review and evaluation of various color edge detection techniques to quantify their accuracy and robustness against noise. It is found that Minimum Vector Dispersion (MVD) edge detector has the best edge detection accuracy and Robust Color Morphological Gradient-Median-Mean (RCMG-MM) edge detector has highest robustness against the noise.
A successful Video-based Simultaneous Localization And Mapping (VSLAM) implementation usually requires a vast amount of feature points to be detected in the environment, which makes the VSLAM problem s computationally demanding operation in mobile robot navigation. This paper presents a VSLAM implementation that is based on a sparse distribution of high-informative artificial landmark features. Additionally, our approach combines the video system analysis results and the inertial measurement unit (IMU) measurements that define the orientation of the video camera. Successful implementation of the VSLAM system can enable autonomous quadrocopter navigation in the structured environment without the presence of the additional external positioning systems.
In this paper, we present a type-2 fuzzy logic based system for robustly extracting the human silhouette which is a fundamental and important procedure for advanced video processing applications, such as pedestrian tracking, human activity analysis and event detection. The presented interval type-2 fuzzy logic system is able to detach moving objects from extracted human silhouette in dynamic environments. Our real-world experimental results demonstrate that the proposed interval type-2 fuzzy logic system works effectively and efficiently for moving objects detachment where the type-2 approach outperforms the type-1 fuzzy system while significantly reducing the misclassification when compared to the type-1 fuzzy system.
In this paper we propose a quantized time series algorithm for spoken word recognition. In particular, we apply the algorithm to the task of spoken Arabic digit recognition. The quantized time series algorithm falls into the category of template matching approach, but with two important extensions. The first is that instead of selecting some typical templates from a set of training data, all the data is processed through vector quantization. The second extension consists of a built-in temporal structure within the quantized time series to facilitate the direct matching, instead of relying on time warping techniques. Experimental results have shown that the proposed approach outperforms the time warping pattern matching schemes in terms of accuracy and processing time.
Recently, a new mobile generation of decision support systems (DSSs) is appearing to seamlessly and ubiquitously support the monitoring of patients’ health status during the activities of daily living. This work proposes MobiFuzzy, a Java Micro Edition fuzzy library characterized by a light-weight and update-versatile implementation for resource-limited mobile devices. The library eases the design process of fuzzy DSSs for Remote Patient Monitoring by providing the user with a wide range of fuzzy connectives, membership functions, implication, aggregation and defuzzification methods. MobiFuzzy has been evaluated on different smart-phones in terms of time-processing with respect to a home-monitoring scenario, proving its capability to proficiently build fuzzy mobile DSSs for healthcare applications where real-time performance demands have to be met.
Combining the output of several speech decoders is considered to be one of the most efficient approaches to reducing the Word Error Rate (WER) in automatic speech transcription. The Recognizer Output Voting Error Reduction (ROVER) is a well known procedure for systems' combination. However, this technique's performance has reached a plateau due to the limitation of the current voting schemes. The ROVER voting algorithms proposed originally rely on the frequency of occurrences and word level confidences, which leads to randomly broken ties and poor voting outcomes due to the unreliability of the decoder's confidence scores. This paper presents a pattern-matching-based voting scheme which has shown to reduce even further the WER.
We present a new heterogeneous particle swarm optimization algorithm, called scouting predator-prey optimizer. This algorithm uses the swarm’s interactions with a predator particle to control the balance between exploration and exploitation. Scout particles are proposed as a straightforward way of introducing new exploratory behaviors into the swarm. These can range from new heuristics that globally improve the algorithm to modifications based on problem specific knowledge. The scouting predator-prey optimizer is compared with several variations of both particle swarm and differential evolution algorithms on a large set of benchmark functions, selected to present the algorithms with different difficulties. The experimental results suggest the new optimizer can outperform the other approaches over most of the benchmark problems.
The use of wireless sensor networks (WSN) is a common situation nowadays. One of the most important aspects in this kind of networks is the energy consumption. In this work, we have added relay nodes to a previously defined static WSN in order to increase its energy efficiency, optimizing both average energy consumption and average coverage. For this purpose, we use two multi-objective evolutionary algorithms: NSGA-II and SPEA-2. We have statistically proven that this method allows us to increase the energy efficiency substantially and NSGA-II provides better results than SPEA-2.
P300 detection is known to be challenging task, as P300 potentials are buried in a large amount of noise. In standard recording of P300 signals, activity at the reference site affects measurements at all the active electrode sites. Analyses of P300 data would be improved if reference site activity could be separated out. This step is an important one before the extraction of P300 features. The essential goal is to improve the signal to noise ratio (SNR) significantly, i.e. to separate the task-related signal from the noise content, and therefore is likely to support the most accurate and rapid P300 Speller. Different techniques have been proposed to remove common sources of artifacts in raw EEG signals. In this research, twelve different techniques have been investigated along with their application for P300 speller in three different Datasets. The results as a whole demonstrate that common average reference CAR technique proved best able to distinguish between targets and non-targets. It was significantly superior to the other techniques.
Vehicular Ad-hoc Networks (VANETs) have attracted attention in the support of safe driving, intelligent navigation, and emergency and entertainment applications. VANET can be viewed as an intelligent component of the Transportation Systems as vehicles communicate with each other as well as with roadside base stations located at critical points of the road, such as intersections or construction sites. In this paper, we provide an overview of the context-aware processing and communication gateway associated with Vehicular Ad-hoc Network (VANET). The concept of context-awareness, the recent advances and various challenges involved in context-aware processing are discussed. Some arising ideas such as based on context ontology, relevancy, hybrid dissemination, service oriented routing are also presented. This paper further briefly describes the communication gateway in VANET which includes its functional view together with the standards and their detailed preliminary specifications applicable to VANET.
The job shop scheduling problem (JSSP) and the facility layout planning (FLP) are two important factors influencing productivity and cost-controlling activities in any manufacturing system. In the past, a number of attempts have been made to solve these stubborn problems. Although, these two problems are strongly interconnected and solution of one significantly impacts the performance of other, so far, these problems are solved independently. Also, the majority of studies on JSSPs assume that the transportation delays among machines are negligible. In this paper, we introduce a general method using multi-objective genetic algorithm for solving the integrated problems of the FLP and the JSSP considering transportation delay having three objectives to optimize: makespan, total material handling costs, and closeness rating score. The proposed method makes use of Pareto dominance relationship to optimize multiple objectives simultaneously and a set of non-dominated solutions are obtained providing additional degrees of freedom for the production manager.
An autonomous capacitive sensor system for high accuracy and stability position measurement, such as required in high-precision industrial equipment, is presented. The system incorporates a self- alignment function based on a thermal stepping motor and a built-in capacitive reference, to guarantee that the relative position between the sensor electrodes is set to 10±0.1 μm. This is needed to achieve the performance specifications with the capacitive readout. In addition, an electronic zoom-in method is used to reach the 10 pm resolution with minimum power dissipation. Finally, periodic self-calibration of the electronic capacitance readout is realized using a very accurate and stable built-in resistive reference. The performance is evaluated experimentally and with simulations.
Resource planning is one of the most important operational issues for many companies. This is especially crucial for telecommunications companies. Resource planning aims to provide a high quality of service to the customers while trying to keep the cost as low as possible. This is done by trying to utilize the available resources workforce as much as possible so that they can match the expected demand for services. Tactical resource planning looks at medium-term planning periods, i.e. weeks to months, and aims to establish coarse-grain resource deployments. This paper focuses on fuzzy based resource planning approach in British Telecom BT. We will present a hierarchical based fuzzy logic system which calculates the compatibility between resources technicians and the allocated tasks, and then matches the most compatible tasks and technicians to each other. The proposed hierarchical fuzzy logic based system in an experimental setting was able to achieve very good results in comparison to the original system, where the proposed system was able to achieve 12.2% improvement in utilization, 34% increase in technician deployment ,10.8% decrement in travel time and 116.2% improvement in number of important tasks being completed. The proposed system is being incorporated in the workforce planning system in BT.
A novel, satellite-guided rescue system is under development, utilizing an autonomously acting rescue boat to salvage a person overboard to increase significantly the chance of survival. This advanced technology requires new approaches for naval architecture and integration of computer-aided tools to develop and operate such devices. A substantial challenge is the design and the automation of the self-acting autonomous rescue boat which navigates to the person overboard automatically. The design of this free fall rescue vessel guarantees that it will be self-righting. The developed cascaded control concepts were designed to ensure the fastest possible approach to the casualty without endangering the person. A specifically integrated monitoring system supports the entire rescue operation. In this paper, a complex Search-and-Rescue-System for a satellite-supported rescue operation at sea will be presented which couples efficiently independent engineering tasks like naval architecture, control system design as well as information processing and monitoring.
This paper is an attempt to enhance query classification in call routing applications. We have introduced a new method to learn weights from training data by means of regression model. In this work, we have tested our method with tf-idf weighting scheme, but the approach can be applied to any weighting scheme. Empirical evaluations with several classifiers including Support Vector Machines SVM, Maximum Entropy, Naive Bayes, and K-Nearest Neighbor KNN show substantial improvement in both macro and micro F1 measure.
Vehicular Ad-hoc Network (VANET) has become an active area of research due to its major role to improve vehicle and road safety, traffic efficiency, and convenience as well as comfort to both drivers and passengers. This paper thus addresses some of the attributes and challenging issues related to Vehicular Ad-hoc Networks (VANETs). A lot of VANET research work have focused on specific areas including routing, broadcasting, Quality of Service (QoS), and security. In this paper, a detailed overview of the current information gathering and data fusion capabilities and challenges in the context of VANET is presented. In addition, an overall VANET framework, an illustrative VANET scenario are provided in order to enhance safety, flow, and efficiency of the transportation system.
In recent years, teleoperation has shown great potentials in different fields such as spatial, mining, under-water, etc. When this technology is required to be bilateral, the time delay induced by a potentially large physical distance prevents a good performance of the controller, especially in the case of contact. When bilateral teleoperation is introduced to the field of medicine, a new challenge arises: the controller must perform well in both hard and soft environments. For example, in the context of telesurgery, the robot can enter in contact with both bone hard and organ soft. In an attempt to enrich existing controller designs to better suit the medical needs, an adaptive fuzzy logic controller AFLC is designed in this paper. It simulates human intelligence and adapts to environments of different stiffness coefficients. The simulation results prove that this controller demonstrates very interesting potential.