Integrating simulated annealing and delta technique for constructing optimal prediction intervals

This paper aims at developing a new criterion for quantitative assessment of prediction intervals. The proposed criterion is developed based on both key measures related to quality of prediction intervals: length and coverage probability. This criterion is applied as a cost function for optimizing prediction intervals constructed using delta technique for neural network model. Optimization seeks out to minimize length of prediction intervals without compromising their coverage probability. Simulated Annealing method is employed for readjusting neural network parameters for minimization of the new cost function. To further ameliorate search efficiency of the optimization method, parameters of the network trained using weight decay method are considered as the initial set in Simulated Annealing algorithm. Implementation of the proposed method for a real world case study shows length and coverage probability of constructed prediction intervals are better than those constructed using traditional techniques.

Construction of optimal prediction intervals for load forecasting problems

Short-term load forecasting is fundamental for the reliable and efficient operation of power systems. Despite its importance, accurate prediction of loads is problematic and far remote. Often uncertainties significantly degrade performance of load forecasting models. Besides, there is no index available indicating reliability of predicted values. The objective of this study is to construct prediction intervals for future loads instead of forecasting their exact values. The delta technique is applied for constructing prediction intervals for outcomes of neural network models. Some statistical measures are developed for quantitative and comprehensive evaluation of prediction intervals. According to these measures, a new cost function is designed for shortening length of prediction intervals without compromising their coverage probability. Simulated annealing is used for minimization of this cost function and adjustment of neural network parameters. Demonstrated results clearly show that the proposed methods for constructing prediction interval outperforms the traditional delta technique. Besides, it yields prediction intervals that are practically more reliable and useful than exact point predictions.

Optimizing the quality of bootstrap-based prediction intervals

The bootstrap method is one of the most widely used methods in literature for construction of confidence and prediction intervals. This paper proposes a new method for improving the quality of bootstrap-based prediction intervals. The core of the proposed method is a prediction interval-based cost function, which is used for training neural networks. A simulated annealing method is applied for minimization of the cost function and neural network parameter adjustment. The developed neural networks are then used for estimation of the target variance. Through experiments and simulations it is shown that the proposed method can be used to construct better quality bootstrap-based prediction intervals. The optimized prediction intervals have narrower widths with a greater coverage probability compared to traditional bootstrap-based prediction intervals.

Adaptive intelligent energy management system of plug-in hybrid electric vehicle

Efficient energy management in hybrid vehicles is the key for reducing fuel consumption and emissions. To capitalize on the benefits of using PHEVs (Plug-in Hybrid Electric Vehicles), an intelligent energy management system is developed and evaluated in this paper. Models of vehicle engine, air conditioning, powertrain, and hybrid electric drive system are first developed. The effect of road parameters such as bend direction and road slope angle as well as environmental factors such as wind (direction and speed) and thermal conditions are also modeled. Due to the nonlinear and complex nature of the interactions between PHEV-Environment-Driver components, a soft computing based intelligent management system is developed using three fuzzy logic controllers. The crucial fuzzy engine controller within the intelligent energy management system is made adaptive by using a hybrid multi-layer adaptive neuro-fuzzy inference system with genetic algorithm optimization. For adaptive learning, a number of datasets were created for different road conditions and a hybrid learning algorithm based on the least squared error estimate using the gradient descent method was proposed. The proposed adaptive intelligent energy management system can learn while it is running and makes proper adjustments during its operation. It is shown that the proposed intelligent energy management system is improving the performance of other existing systems. © 2014 Elsevier Ltd.

Microfinance best practice : ten parameters of success for development NGOs

Experience has shown that development NGOs typically do not succeed in transforming themselves into financially sustainable providers of financial intermediation services. The reasons for this failure are complex (see Dichter 1999). Nonetheless, the role that NGOs play as microfinance providers is important and the contribution they could make to poverty reduction would be greatly enhanced if they adhered to some simple but essential parameters of success.

Improving an inverse model of sheet metal forming by neural network based regression

An inverse model for a sheet meta l forming process aims to determine the initial parameter levels required to form the final formed shape. This is a difficult problem that is usually approached by traditional methods such as finite element analysis. Formulating the problem as a classification problem makes it possible to use well established classification algorithms, such as decision trees. Classification is, however, generally based on a winner-takes-all approach when associating the output value with the corresponding class. On the other hand, when formulating the problem as a regression task, all the output values are combined to produce the corresponding class value. For a multi-class problem, this may result in very different associations compared with classification between the output of the model and the corresponding class. Such formulation makes it possible to use well known regression algorithms, such as neural networks. In this paper, we develop a neural network based inverse model of a sheet forming process, and compare its performance with that of a linear model. Both models are used in two modes, classification mode and a function estimation mode, to investigate the advantage of re-formulating the problem as a function estimation. This results in large improvements in the recognition rate of set-up parameters of a sheet metal forming process for both models, with a neural network model achieving much more accurate parameter recognition than a linear model.

Location based power control for energy critical sensors in a disconnected network

This paper provides a location based power control strategy for disconnected sensory nodes deployed for long term service. Power conservation is of importance particularly when sensors communicate with a mobile robot used for data collection. The proposed algorithm uses estimations from a Robust Extended Kalman Filter (REKF) with RSSI measurements, in implementing a sigmoid function based power control algorithm which essentially approaches a desired power emission trajectory based on carrier-to-interference ratios(CIR) to ensure interferenceless reception. The more realistic modelling we use incorporates physical dynamics between the mobile robot and the sensors together with the wireless propagation parameters between the transmitter and receiver to formulate a sophisticated and effective power control strategy for the exclusive usage of energy critical disconnected nodes in a sensory network increasing their life span.

An artificial neural network-based hairiness prediction model for worsted wool yarns

This study evaluated the performance of multilayer perceptron (MLP) and multivariate linear regression (MLR) models for predicting the hairiness of worsted-spun wool yarns from various top, yarn and processing parameters. The results indicated that the MLP model predicted yarn hairiness more accurately than the MLR model, and should have wide mill specific applications. On the basis of sensitivity analysis, the factors that affected yarn hairiness significantly included yarn twist, ring size, average fiber length (hauteur), fiber diameter and yarn count, with twist having the greatest impact on yarn hairiness.

Compounding factors and their effect on the design of long range battery electric vehicles

 It is well known that the one of the main problems concerning battery electric vehicles (BEVs) is their short range compared to conventional petrol and diesel vehicles. In this work the technical factors that will enable long range BEVs are investigated. The concept of Compounding Factors is presented and shows that if certain parameters can be met then BEV’s can have a comparable performance to conventional petrol cars. The development and initial testing of a long range BEW prototype is presented and discussed.

Network management in distributed systems

Applications of localized surface plasmon resonance (LSPR) such as surface enhanced Raman scattering (SERS) devices, biosensors, and nano-optics are growing. Investigating and understanding of the parameters that affect the LSPR spectrum is important for the design and fabrication of LSPR devices. This paper studies different parameters, including geometrical structures and light attributes, which affect the LSPR spectrum properties such as plasmon wavelength and enhancement factor. The paper also proposes a number of rules that should be considered in the design and fabrication of LSPR devices.

A generalised cost-aware caching scheme for caching continuous media objects in best-effort network environments

In this paper, we investigate the potential of caching to improve QoS in the context of continuous media applications over wired best-effort networks. We propose the use of a flexible caching scheme, called GD-Multi in caching continuous media (CM) objects. An important novel feature of our scheme is the provision of user or system administrator inputs in determining the cost function. Based on the proposed flexible cost function, Multi, an improvised Greedy Dual (GD) replacement algorithm called GD-multi (GDM) has been developed for layered multi-resolution multimedia streams. The proposed Multi function takes receiver feedback into account. We investigate the influence of parameters such as loss rate, jitter, delay and area in determining a proxy’s cache contents so as to enhance QoS perceived by clients. Simulation studies show improvement in QoS perceived at the clients in accordance to supplied optimisation metrics. From an implementation perspective, signalling requirements for carrying QoS feedback are minimal and fully compatible with existing RTSP-based Internet applications.

Evaluation of partnership working in cities in phase IV of the WHO healthy cities network

An intersectoral partnership for health improvement is a requirement of the WHO European Healthy Cities Network of municipalities. A review was undertaken in 59 cities based on responses to a structured questionnaire covering phase IV of the network (2003–2008). Cities usually combined formal and informal working partnerships in a pattern seen in previous phases. However, these encompassed more sectors than previously and achieved greater degrees of collaborative planning and implementation. Additional WHO technical support and networking in phase IV significantly enhanced collaboration with the urban planning sector. Critical success factors were high-level political commitment and a well-organized Healthy City office. Partnerships remain a successful component of Healthy City working. The core principles, purpose and intellectual rationale for intersectoral partnerships remain valid and fit for purpose. This applied to long-established phase III cities as well as newcomers to phase IV. The network, and in particular the WHO brand, is well regarded and encourages political and organizational engagement and is a source of support and technical expertise. A key challenge is to apply a more rigorous analytical framework and theory-informed approach to reviewing partnership and collaboration parameters.

A hybrid Kansei engineering system using the self-organizing map neural network

Kansei Engineering (KE), a technology founded in Japan initially for product design, translates human feelings into design parameters. Although various intelligent approaches to objectively model human functions and therelationships with the product design decisions have been introduced in KE systems, many or the approaches are not able to incorporate human subjective feelings and preferenees into the decision-making process. This paper proposes a new hybrid KE system that attempts to make the machine-based decision-making process closely resembles the real-world practice. The proposed approach assimilates human perceptive and associative abililities into the decision-making process of the computer. A number of techniques based on the Self-Organizing Map (SOM) neural network are employed in the backward KE system to reveal the underlying data structures that are involved in the decision-making process. A case study on interior design is presented to evaluate the efficacy of the proposed approach. The results obtained demonstrate tbe effectiveness of the proposed approach in developing an intelligent KE system which is able to combine huiiUUI feelings and preferences into its decision making process.