Intelligent association selection of embedded agents in intelligent inhabited environments

Recent advances in technology and manufacturing have resulted in more powerful and smaller processors to be embedded in the various artefacts within smart environments. Most of these artefacts are network enabled and thanks to pervasive networking such artefacts can communicate and collaborate together to support our daily lives. Furthermore, these artefacts can also be equipped with embedded agents to provide intelligent reasoning, planning and learning capabilities. However, the multitude of interconnected devices and artefacts can result in major network and processing delays as well as creating inherent complexities in programming and configuring smart environments to personalise themselves to suit the individual needs. Hence, a major challenge to the design and use of smart environments involves finding the best set of device associations and interconnections that are most suitable to the environment and user needs. In this paper, we will present a novel intelligent method for reducing the number of associations and interconnections between the various devices and artefacts within smart environments to minimise the network and processing overheads while reducing the cognitive load associated with configuring and programming smart environments.     

Discriminative touch and emotional touch.

Somatic sensation comprises four main modalities, each relaying tactile, thermal, painful, or pruritic (itch) information to the central nervous system. These input channels can be further classified as subserving a sensory function of spatial and temporal localization, discrimination, and provision of essential information for controlling and guiding exploratory tactile behaviours, and an affective function that is widely recognized as providing the afferent neural input driving the subjective experience of pain, but not so widely recognized as also providing the subjective experience of affiliative or emotional somatic pleasure of touch. The discriminative properties of tactile sensation are mediated by a class of fast-conducting myelinated peripheral nerve fibres--A-beta fibres--whereas the rewarding, emotional properties of touch are hypothesized to be mediated by a class of unmyelinated peripheral nerve fibres--CT afferents (C tactile)--that have biophysical, electrophysiological, neurobiological, and anatomical properties that drive the temporally delayed emotional somatic system. CT afferents have not been found in the glabrous skin of the hand in spite of numerous electrophysiological explorations of this area. Hence, it seems reasonable to conclude that they are lacking in the glabrous skin. A full understanding of the behavioural and affective consequences of the differential innervation of CT afferents awaits a fuller understanding of their function. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A Novel Control Unit for a Friction Welding Machine Based on Computer

Typical friction welds are made by holding a non-rotating sample in contact with a rotating sample under constant or gradually increasing pressure until the interface reaches the welding temperature and then stopping pressure rotating to complete the weld. This process requires additional time and is labor intensive. Recently, several control systems have been introduced to the industry for improving the welding process such as conventional automatic control, microcontroller control, and Programmable Logic Controller (PLC). However, these processes have limitations either on materials selection or on visualization. In this study, continuous monitoring, control and recording are implemented. Computer-controlled platform for the simulation and control of mechanisms is based on a Microsoft Visual Basic environment. Welding parameters such as friction time, forge time and breaking time are entered with a keyboard and can be saved and used again. To show the feasibility and versatility of the study, the evaluation is used for sample joining. It has been observed that this system works successfully and gives good performance.     

Using multiplicative neuron model to establish fuzzy logic relationships

Determination of fuzzy logic relationships between observations is quite effective on the forecasting performance of fuzzy time series approaches. In various studies available in the literature, it has been seen that utilizing artificial neural networks for establishing fuzzy relations increase the forecasting accuracy. In this study, a novel high order fuzzy time series forecasting approach in which multiplicative neuron model is used to define fuzzy relations is proposed in order to reach high forecasting level. Also, particle swarm optimization method is utilized to train multiplicative neuron model. In order to show forecasting performance of the proposed method, it is applied to a well-known data Taiwan future exchange and the results produced by the proposed approach is compared to those obtained from other fuzzy time series forecasting models. As a result of the implementation, it is observed that the proposed approach gives the best forecasts for Taiwan future exchange time series.     

Multi-objective mixture design and optimisation of steel fiber reinforced UHPC using machine learning algorithms and metaheuristics

Ultra-high-performance concrete (UHPC) is a recent class of concrete with improved durability, rheological and mechanical and durability properties compared to traditional concrete. The production cost of UHPC is considerably high due to a large amount of cement used, and also the high price of other required constituents such as quartz powder, silica fume, fibres and superplasticisers. To achieve specific requirements such as desired production cost, strength and flowability, the proportions of UHPC’s constituents must be well adjusted. The traditional mixture design of concrete requires cumbersome, costly and extensive experimental program. Therefore, mathematical optimisation, design of experiments (DOE) and statistical mixture design (SMD) methods have been used in recent years, particularly for meeting multiple objectives. In traditional methods, simple regression models such as multiple linear regression models are used as objective functions according to the requirements. Once the model is constructed, mathematical programming and simplex algorithms are usually used to find optimal solutions. However, a more flexible procedure enabling the use of high accuracy nonlinear models and defining different scenarios for multi-objective mixture design is required, particularly when it comes to data which are not well structured to fit simple regression models such as multiple linear regression. This paper aims to demonstrate a procedure integrating machine learning (ML) algorithms such as Artificial Neural Networks (ANNs) and Gaussian Process Regression (GPR) to develop high-accuracy models, and a metaheuristic optimisation algorithm called Particle Swarm Optimisation (PSO) algorithm for multi-objective mixture design and optimisation of UHPC reinforced with steel fibers. A reliable experimental dataset is used to develop the models and to justify the final results. The comparison of the obtained results with the experimental results validates the capability of the proposed procedure for multi-objective mixture design and optimisation of steel fiber reinforced UHPC. The proposed procedure not only reduces the efforts in the experimental design of UHPC but also leads to the optimal mixtures when the designer faces strength-flowability-cost paradoxes.

     

Decoupled approach to integrated optimum design of structures and robust control systems

Integrated optimum design of structures and control systems is studied by using H ₂ and robust control formulations. It is derived that conventional simultaneous optimization approach by using these robust control laws can be approximated by a decoupled optimization approach in which the structures are optimized by shaping the structural singular values and then the controllers can be designed, namely, decoupled, sequential or successive design approach. It is shown that the proposed decoupled optimization approach can be used to design optimum robust structures and has certain advantages over the conventional simultaneous optimization procedures such as it avoids the drawbacks of pure robust control laws and faster, especially if the number of degrees of freedom (DOF) of the associated structure is large. The bounds for achievable robustness measures are also obtained. Following, simultaneous and decoupled optimization approaches are applied to active control of two structures. The optimization results are presented, and it is concluded that the proposed decoupled optimization approach yields the achieved global minimum much faster than the simultaneous optimization approach.     

Evaluation of a university website’s usability for visually impaired students

Today websites are the tools most commonly used to access information. People with disabilities face difficulties accessing or using information, and the importance of website usability in their lives needs to be recognized. Visually impaired students need to be able to use university websites that inform them about the opportunities and events taking place on campus. This study aims to evaluate the usability of a university website by visually impaired students. In this research, six visually impaired students were interviewed. The assistive technologies they use, as well as the various web pages they wished to use unaided were identified. Following data collection, usability tests were conducted and satisfaction surveys were completed. The usability test was done with five visually impaired students. They were asked to think aloud while performing 11 tasks involving their university’s web pages, including the main page and the pages of student affairs, library and departments and then to accomplish these tasks. In this test, five tasks were not successfully completed by all students. According to the test results, finding final exam dates on the academic calendar posed major difficulties, and accessing the course schedule web page was the task that required the most time. The test results indicated the need for a search engine on each page, a text version for all pages, rearrangement of the web link sequences with tabs and more information about visuals. Suggestions related to the visually impaired students’ needs were offered.     

Vibrations of stretched damped beams under non-ideal boundary conditions

A simply supported damped Euler-Bernoulli beam with immovable end conditions are considered. The concept of non-ideal boundary conditions is applied to the beam problem. In accordance, the boundaries are assumed to allow small deflections and moments. Approximate analytical solution of the problem is found using the method of multiple scales, a perturbation technique.     

Preserving spatial information and overcoming variations in appearance for face recognition

Local feature-based approaches mainly aim to achieve robustness to variations in facial images by assuming that only some parts of the facial images may be affected. However, such approaches may lose spatial information. In this study, a compromise feature extraction scheme is studied which extracts local features while preserving spatial information. The proposed scheme exploits an ensemble of classifiers where each member is constructed using randomly selected design parameters including the size, number and location of sub-images for local feature extraction. Experiments conducted on FERET and ORL databases have shown that proposed scheme surpasses the local feature-based reference systems which focus on either local information or preserving spatial information.