Wood inspection with non-supervised clustering

Abstract. The appearance of sawn timber has huge natural variations that the human inspector easily compensates for mentally when determining the types of defects and the grade of each board. However, for automatic wood inspection systems these variations are a major source for complication. This makes it difficult to use textbook methodologies for visual inspection. These methodologies generally aim at systems that are trained in a supervised manner with samples of defects and good material, but selecting and labeling the samples is an error-prone process that limits the accuracy that can be achieved. We present a non-supervised clustering-based approach for detecting and recognizing defects in lumber boards. A key idea is to employ a self-organizing map (SOM) for discriminating between sound wood and defects. Human involvement needed for training is minimal. The approach has been tested with color images of lumber boards, and the achieved false detection and error escape rates are low. The approach also provides a self-intuitive visual user interface. Received: 16 December 2000 / Accepted: 8 December 2001 Correspondence to: O. Silvén     

Potential of microbial growth control in water hydraulic systems by UV‐irradiation and filtration

Water hydraulic systems use water as a pressure medium and, thus, do not pose such adverse environmental impacts as oil hydraulics. Microbial deterioration of the pressure medium and biofouling of the surfaces restrict the applicability of the water‐based technology. The potential of microbial growth control by UV‐irradiation and filtration was studied in a pilot‐scale water hydraulic system. The UV‐irradiation (25 m Ws cm^?2) of the pressure medium reduced the total viable counts of bacteria by 1–2 log₁₀ cfu cm^?3, whereas the total microbial cell numbers and the numbers of surface‐attached microorganisms remained unaffected. Prefiltration (1.2 µm, absolute) of the pressure medium decreased the total microbial cell number in the water phase and retarded the attachment of bacteria. The filtration during the operation (2 µm, absolute) decreased the total numbers of microbial cells and the total viable counts in the pressure medium, and microbial attachment on the surfaces. Microbial attachment was not prevented by filtration. The microbial water quality obtained by pre‐ and on‐line filtration of the pressure medium was sufficient to ensure the long‐term operation of the water hydraulic system assuming that clean work practices are complied with in assembly and during the operation. © 2002 Society of Chemical Industry     

Social virtual world continuance among teens: uncovering the moderating role of perceived aggregate network exposure

Engagement in virtual worlds has become pervasive, particularly among the young. At the same time, the number of virtual environments has increased rapidly. Due to intensifying competition, promoting sustained usage, i.e. continuance, has become a top priority for virtual world operators. Prior research has shown that network externalities play a key role in the adoption of communication technologies. However, a small amount of research has examined the role of network externalities in continued IT usage in general or with respect to the virtual world participation in particular. To fill in this gap, we examine how perceived network externalities affect the continuance of social virtual worlds. To this end, we introduce the concept of perceived aggregate network exposure (PANE). We extend the original information systems (IS) continuance model with perceived enjoyment and position PANE as a moderator. We test the model with data collected from 2134 Finnish Habbo Hotel users and employ structural equation modelling in the analysis. The results demonstrate that PANE moderates the influence of motivational factors on continued use intention and satisfaction.     

The ortho-to-para conversion in solid hydrogen,catalyzed by hydrogen atoms

The combined techniques of ESR and NMR were used to investigate the process of ortho-para conversion in solid molecular hydrogen, containing small amounts ( 500 ppm) of hydrogen atoms as impurity. Although the impurity atoms catalyze the effective conversion of the neighboring ortho-H₂, the total catalyzed conversion rate at temperatures from 2.2 K to 4.4 K is much less than expected from the rate of the H atoms recombination. A possible explanation is given in terms of the diffusion of H atoms, which is confined to some defects in the crystal.     

Combining appearance and motion for face and gender recognition from videos

While many works consider moving faces only as collections of frames and apply still image-based methods, recent developments indicate that excellent results can be obtained using texture-based spatiotemporal representations for describing and analyzing faces in videos. Inspired by the psychophysical findings which state that facial movements can provide valuable information to face analysis, and also by our recent success in using LBP (local binary patterns) for combining appearance and motion for dynamic texture analysis, this paper investigates the combination of facial appearance (the shape of the face) and motion (the way a person is talking and moving his/her facial features) for face analysis in videos. We propose and study an approach for spatiotemporal face and gender recognition from videos using an extended set of volume LBP features and a boosting scheme. We experiment with several publicly available video face databases and consider different benchmark methods for comparison. Our extensive experimental analysis clearly assesses the promising performance of the LBP-based spatiotemporal representations for describing and analyzing faces in videos.     

Modeling under-resourced languages for speech recognition

One particular problem in large vocabulary continuous speech recognition for low-resourced languages is finding relevant training data for the statistical language models. Large amount of data is required, because models should estimate the probability for all possible word sequences. For Finnish, Estonian and the other fenno-ugric languages a special problem with the data is the huge amount of different word forms that are common in normal speech. The same problem exists also in other language technology applications such as machine translation, information retrieval, and in some extent also in other morphologically rich languages. In this paper we present methods and evaluations in four recent language modeling topics: selecting conversational data from the Internet, adapting models for foreign words, multi-domain and adapted neural network language modeling, and decoding with subword units. Our evaluations show that the same methods work in more than one language and that they scale down to smaller data resources.     

Water Resource Models in the Mekong Basin: A Review

Development of the water resources of the Mekong Basin is the subject of intense debate both within the Mekong region and internationally. Water resources modelling is playing an increasingly important role in the debate, with significant effort in building integrated modelling platforms to describe the hydrological, ecological, social and economic impacts of water resource development. In the hydrological domain, a comprehensive set of models has been effective in building understanding of the system, and in identifying and describing the issues and trade-offs involved in basin-scale water planning. In the ecological and social domains, quantitative modelling has not progressed very far; geo-spatial analysis and qualitative frameworks remain the most commonly used tools. Economic models have been used to assess the costs and benefits of water resources development and to describe the trade-offs between different sectors and users. These analyses are likely to play an important role in the policy and planning debate, but are hampered by uncertainties in valuation of ecosystem services. Future efforts should focus on optimising the use of existing model platforms for the Mekong, including structured comparison of multiple hydrological models to quantify errors and identify an optimum set of modelling tools for different applications. A comprehensive research effort is needed to incorporate groundwater into hydrological models for regional planning. Options for social impact assessment should be reassessed before major investments are made in complex modelling platforms, and participatory social survey methods evaluated as part of an integrated assessment framework.     

On the existence and convergence of the solution of PML equations

In this article we study the mesh termination method in computational scattering theory known as the method of Perfectly Matched Layer (PML). This method is based on the idea of surrounding the scatterer and its immediate vicinity with a fictitious absorbing non-reflecting layer to damp the echoes coming from the mesh termination surface. The method can be formulated equivalently as a complex stretching of the exterior domain. The article is devoted to the existence and convergence questions of the solutions of the resulting equations. We show that with a special choice of the fictitious absorbing coefficient, the PML equations are solvable for all wave numbers, and as the PML layer is made thicker, the PML solution converge exponentially towards the actual scattering solution. The proofs are based on boundary integral methods and a new type of near-field version of the radiation condition, called here the double surface radiation condition. Partly supported by the Finnish Academy, project 37692.     

The Difficulty of Reduced Error Pruning of Leveled Branching Programs

Induction of decision trees is one of the most successful approaches to supervised machine learning. Branching programs are a generalization of decision trees and, by the boosting analysis, exponentially more efficiently learnable than decision trees. However, this advantage has not been seen to materialize in experiments. Decision trees are easy to simplify using pruning. Reduced error pruning is one of the simplest decision tree pruning algorithms. For branching programs no pruning algorithms are known. In this paper we prove that reduced error pruning of branching programs is infeasible. Finding the optimal pruning of a branching program with respect to a set of pruning examples that is separate from the set of training examples is NP-complete. Because of this intractability result, we have to consider approximating reduced error pruning. Unfortunately, it turns out that even finding an approximate solution of arbitrary accuracy is computationally infeasible. In particular, reduced error pruning of branching programs is APX-hard. Our experiments show that, despite the negative theoretical results, heuristic pruning of branching programs can reduce their size without significantly altering the accuracy.