J-measure based hybrid pruning for complexity reduction in classification rules

Prism is a modular classification rule generation method based on the ‘separate and conquer’ approach that is alternative to the rule induction approach using decision trees also known as ‘divide and conquer’. Prism often achieves a similar level of classification accuracy compared with decision trees, but tends to produce a more compact noise tolerant set of classification rules. As with other classification rule generation methods, a principle problem arising with Prism is that of overfitting due to over-specialised rules. In addition, over-specialised rules increase the associated computational complexity. These problems can be solved by pruning methods. For the Prism method, two pruning algorithms have been introduced recently for reducing overfitting of classification rules - J-pruning and Jmax-pruning. Both algorithms are based on the J-measure, an information theoretic means for quantifying the theoretical information content of a rule. Jmax-pruning attempts to exploit the J-measure to its full potential because J-pruning does not actually achieve this and may even lead to underfitting. A series of experiments have proved that Jmax-pruning may outperform J-pruning in reducing overfitting. However, Jmax-pruning is computationally relatively expensive and may also lead to underfitting. This paper reviews the Prism method and the two existing pruning algorithms above. It also proposes a novel pruning algorithm called Jmid-pruning. The latter is based on the J-measure and it reduces overfitting to a similar level as the other two algorithms but is better in avoiding underfitting and unnecessary computational effort. The authors conduct an experimental study on the performance of the Jmid-pruning algorithm in terms of classification accuracy and computational efficiency. The algorithm is also evaluated comparatively with the J-pruning and Jmax-pruning algorithms.

Temperature-dependent reduction pathways of complexes fac-[Re(CO)3(N-R-imidazole)(1,10-phenanthroline)]+ (R = H, CH3)

Peculiar reduction pathways of the complexes fac-[Re(imH)(CO)3(phen)]+ and fac-[Re(imCH3)(CO)3(phen)]+ (imH = imidazole, imCH3 = N-methylimidazole and phen = 1,10-phenanthroline) have been unravelled by performing combined cyclic voltammetric and in situ IR spectroelectrochemical experiments. In the temperature range of 293–233 K, the initial reduction of the phen ligand in [Re(imH)(CO)3(phen)]+ results in irreversible conversion of the imidazole ligand to 3-imidazolate by a rapid phen•−→ imH intramolecular electron transfer coupled with N H bond cleavage. This process is followed by second phen-localized 1e− reduction producing [ReI(3-im−)(CO)3(phen•−)]−, similar to the analogous 2,2'-bipyridine complex. In contrast to the bpy analogue, the stability of the phen•−-containing complexes is significantly affected by lowering the temperature. At 233 K, a secondary reaction occurs in both [Re(3-im−)(CO)3(phen•−)]− and [Re(imCH3)(CO)3(phen•−)]. The resulting products exhibit v(CO) wavenumbers indistinguishable from those of the parent phen•− complexes; however, their oxidation occurs at a considerably more positive electrode potential. It is proposed that these species are produced by a new C C bond formation between the C(2) site of 3-im− or imCH3 and the C(2) site of the phen•−ligand.

Investigating the value dairy farmers place on a reduction of lameness in their herds using a willingness to pay approach

A survey was conducted to elicit dairy farmers’ willingness to pay (WTP) to reduce the prevalence of lameness in their herds. A choice experiment questionnaire was administered using face-to-face interviews of 163 farmers in England and Wales. Whole herd lameness assessments by trained researchers recorded a mean lameness prevalence of nearly 24% which was substantially higher than that estimated by farmers. Farmers’ responses to a series of attitudinal questions showed that they strongly agreed that cows can suffer a lot of pain from lameness and believed that they could reduce lameness in their herds. Farmers’ mean WTP to avoid lameness amounted to UK£411 per lame cow but with considerable variation across the sample. Median WTP of UK£249 per lame cow was considered a better measure of central tendency for the sample. In addition, the survey found that farmers had a substantial WTP to avoid the inconvenience associated with lameness control (a median value of UK£97 per lame cow) but that they were generally prepared to incur greater inconvenience if it reduced lameness. The study findings suggest that farmers need a better understanding of the scale and costs of lameness in their herds and the benefits of control. To encourage action, farmers need to be convinced that lameness control measures perceived as inconvenient will be cost effective.

An analysis of UK policies for domestic energy reduction using an agent based tool

This paper introduces a new agent-based model, which incorporates the actions of individual homeowners in a long-term domestic stock model, and details how it was applied in energy policy analysis. The results indicate that current policies are likely to fall significantly short of the 80% target and suggest that current subsidy levels need re-examining. In the model, current subsidy levels appear to offer too much support to some technologies, which in turn leads to the suppression of other technologies that have a greater energy saving potential. The model can be used by policy makers to develop further scenarios to find alternative, more effective, sets of policy measures. The model is currently limited to the owner-occupied stock in England, although it can be expanded, subject to the availability of data.

The real-time optimisation of DNO owned storage devices on the LV network for peak reduction

Energy storage is a potential alternative to conventional network reinforcementof the low voltage (LV) distribution network to ensure the grid’s infrastructure remainswithin its operating constraints. This paper presents a study on the control of such storagedevices, owned by distribution network operators. A deterministic model predictive control (MPC) controller and a stochastic receding horizon controller (SRHC) are presented, wherethe objective is to achieve the greatest peak reduction in demand, for a given storagedevice specification, taking into account the high level of uncertainty in the prediction of LV demand. The algorithms presented in this paper are compared to a standard set-pointcontroller and bench marked against a control algorithm with a perfect forecast. A specificcase study, using storage on the LV network, is presented, and the results of each algorithmare compared. A comprehensive analysis is then carried out simulating a large number of LV networks of varying numbers of households. The results show that the performance of each algorithm is dependent on the number of aggregated households. However, on a typical aggregation, the novel SRHC algorithm presented in this paper is shown to outperform each of the comparable storage control techniques.

Control methodologies: Peak reduction algorithms for DNO owned storage devices on the Low Voltage network

The Distribution Network Operators (DNOs) role is becoming more difficult as electric vehicles and electric heating penetrate the network, increasing the demand. As a result it becomes harder for the distribution networks infrastructure to remain within its operating constraints. Energy storage is a potential alternative to conventional network reinforcement such as upgrading cables and transformers. The research presented here in this paper shows that due to the volatile nature of the LV network, the control approach used for energy storage has a significant impact on performance. This paper presents and compares control methodologies for energy storage where the objective is to get the greatest possible peak demand reduction across the day from a pre-specified storage device. The results presented show the benefits and detriments of specific types of control on a storage device connected to a single phase of an LV network, using aggregated demand profiles based on real smart meter data from individual homes. The research demonstrates an important relationship between how predictable an aggregation is and the best control methodology required to achieve the objective.

A peak reduction scheduling algorithm for storage devices on the low voltage network

Reinforcing the Low Voltage (LV) distribution network will become essential to ensure it remains within its operating constraints as demand on the network increases. The deployment of energy storage in the distribution network provides an alternative to conventional reinforcement. This paper presents a control methodology for energy storage to reduce peak demand in a distribution network based on day-ahead demand forecasts and historical demand data. The control methodology pre-processes the forecast data prior to a planning phase to build in resilience to the inevitable errors between the forecasted and actual demand. The algorithm uses no real time adjustment so has an economical advantage over traditional storage control algorithms. Results show that peak demand on a single phase of a feeder can be reduced even when there are differences between the forecasted and the actual demand. In particular, results are presented that demonstrate when the algorithm is applied to a large number of single phase demand aggregations that it is possible to identify which of these aggregations are the most suitable candidates for the control methodology.

Ring-opening polymerization in molten PEEK: transient reduction of melt-viscosity by macrocyclic aromatic thioetherketones

Blends of PEEK with macrocyclic thioether-ketones show initial melt-viscosities reduced by more than an order of magnitude relative to the polymer itself, enabling more facile processing and fabrication. On raising the temperature of the melt, however, the macrocycle undergoes spontaneous, entropically-driven ring-opening polymerization (ED-ROP), so that the properties of the final polymer should not, in principle, be compromised by the presence of low-MW macrocyclic material.

Effects of high hydrostatic pressure and chemical reduction on the emulsification properties of gum arabic

Gum arabic is widely used in the food industry as an additive, both as a thickener and an emulsifier. This study has compared the emulsification properties of two types of gums, KLTA (Acacia senegal) and GCA (Acacia seyal), both in their native/untreated forms and after exposure to high pressure (800 MPa). Further studies were undertaken to chemically modify the disulphide linkages present and to investigate the effects of their reduction on the diffusion of the carbohydrate materials. The emulsification properties of the gum samples were examined by determining the droplet size distribution in a ‘‘model’’ oil-in-water system. Results showed that high pressure treatment and chemical reduction of gums changed the emulsification properties of both gums. The high molecular weight component in arabinogalactanproteins (AGP/GP), and more ‘‘branched’’ carbohydrates present in gum arabic, may be responsible for the emulsification properties of GCA gum, indicating that the emulsification mechanisms for KLTA and GCA were different.

[M(CO)4(2,2′-bipyridine)] (M = Cr, Mo, W) as efficient catalysts for electrochemical reduction of CO2 to CO at a gold electrode

Group 6 complexes of the type [M(CO)4(bpy)] (M=Cr, Mo, W) are capable of behaving as electrochemical catalysts for the reduction of CO2 at potentials less negative than those for the reduction of the radical anions [M(CO)4(bpy)].−. Cyclic voltammetric, chronoamperometric and UV/Vis/IR spectro-electrochemical data reveal that five-coordinate [M(CO)3(bpy)]2− are the active catalysts. The catalytic conversion is significantly more efficient in N-methyl-2-pyrrolidone (NMP) compared to tetrahydrofuran, which may reflect easier CO dissociation from 1e−-reduced [M(CO)4(bpy)].− in the former solvent, followed by second electron transfer. The catalytic cycle may also involve [M(CO)4(H-bpy)]− formed by protonation of [M(CO)3(bpy)]2−, especially in NMP. The strongly enhanced catalysis using an Au working electrode is remarkable, suggesting that surface interactions may play an important role, too.

Dimensionality reduction assisted tensor clustering

This paper is concerned with tensor clustering with the assistance of dimensionality reduction approaches. A class of formulation for tensor clustering is introduced based on tensor Tucker decomposition models. In this formulation, an extra tensor mode is formed by a collection of tensors of the same dimensions and then used to assist a Tucker decomposition in order to achieve data dimensionality reduction. We design two types of clustering models for the tensors: PCA Tensor Clustering model and Non-negative Tensor Clustering model, by utilizing different regularizations. The tensor clustering can thus be solved by the optimization method based on the alternative coordinate scheme. Interestingly, our experiments show that the proposed models yield comparable or even better performance compared to most recent clustering algorithms based on matrix factorization.

Gaussian processes autoencoder for dimensionality reduction

Learning low dimensional manifold from highly nonlinear data of high dimensionality has become increasingly important for discovering intrinsic representation that can be utilized for data visualization and preprocessing. The autoencoder is a powerful dimensionality reduction technique based on minimizing reconstruction error, and it has regained popularity because it has been efficiently used for greedy pretraining of deep neural networks. Compared to Neural Network (NN), the superiority of Gaussian Process (GP) has been shown in model inference, optimization and performance. GP has been successfully applied in nonlinear Dimensionality Reduction (DR) algorithms, such as Gaussian Process Latent Variable Model (GPLVM). In this paper we propose the Gaussian Processes Autoencoder Model (GPAM) for dimensionality reduction by extending the classic NN based autoencoder to GP based autoencoder. More interestingly, the novel model can also be viewed as back constrained GPLVM (BC-GPLVM) where the back constraint smooth function is represented by a GP. Experiments verify the performance of the newly proposed model.