MeteoBayes: Effective Plan Recognition in a Weather Dialogue System

When you've called a voice portal for any kind of information retrieval, chances are that an automated system guided the entire interaction. It might have correctly identified your goal, but probably only after asking too many questions. MeteoBayes is a meteorological information dialogue system that lets you use natural language to direct the interaction. Based on Bayesian networks, MeteoBayes' inference engine attempts to identify user intentions by consulting its past dialogue repository. For unfamiliar words, MeteoBayes has an unknown-term disambiguation module that learns word similarities from texts to avoid unnecessary system inquiries, thus speeding up the understanding process     

CAD-based simulations and design of experiments for determining thrust force in drilling operations

Drilling thrust force calculations require a large amount of experimental work, which can be greatly reduced, since an extensively validated CAD-based approach, using the DRILL3D software application, has become available. DRILL3D calculates the thrust force of both the cutting areas of the tool (main edges and chisel edge) simultaneously, which means that every simulation can substitute two separate lab experiments. Nevertheless, as the number of parameters involved is increasing, the amount of the necessary simulations becomes substantial. This is the reason that led to the combined use of the DRILL3D and the design of experiments methodology, which reduces the amount of the necessary digital experiments to an impressive degree. The main factors affecting the current analysis are the tool diameter, the web to diameter ratio, the feed rate and the cutting speed used. Using an L16 Taguchi table, a function of the developed thrust force can be calculated using the response surface methodology. This statistical modeling tool employs the regression analysis to establish the relationship between various process parameters and response.     

3-Dimensional kinematics simulation of face milling

Face milling is currently the most effective and productive manufacturing method for roughing and finishing large surfaces of metallic parts. Milling data, such as surface topomorphy, surface roughness, non-deformed chip dimensions, cutting force components and dynamic cutting behavior, are very helpful, especially if they can be accurately produced by means of a simulation program. This paper presents a novel simulation model which has been developed and embedded in a commercial CAD environment. The model simulates the true tool kinematics using the exact geometry of the cutting tool thus accurately forecasting the resulting roughness. The accuracy of the simulation model has been thoroughly verified, with the aid of a wide variety of cutting experiments. The proposed model has proved to be suitable for determining optimal cutting conditions for face milling. The software can be easily integrated into various CAD–CAM systems.     

Integrating thermal and hyperspectral remote sensing for the detection of coastal springs and submarine groundwater discharges

This research focuses on the investigation of remote-sensing techniques for the detection of coastal sub-aerial springs and submarine groundwater discharges using airborne thermal and hyperspectral imagery. Very high spatial resolution thermal and hyperspectral images were acquired using Thermal Airborne Broadband Imager 320 (TABI-320) and Compact Airborne Spectrographic Imager 550 (CASI-550) sensors. Extensive in situ spectroradiometer and oceanographic measurements were carried out in parallel with thermal and hyperspectral image acquisitions. Experiments and analysis of the data show that the combined use of very high spatial resolution airborne thermal and hyperspectral sensors for the detection of relatively small sub-aerial coastal springs and submarine groundwater discharges proves to be a very efficient and operational method. Very high spatial resolution thermal data were able to detect even very small coastal sub-aerial springs. On the other hand, the hyperspectral data were the most appropriate for detecting relatively small submarine groundwater discharges, which were not detected on thermal imagery, due to the increase in turbidity that these discharges cause. This is confirmed by the strong correlations between the hyperspectral data and the in situ measured turbidity-related water inherent optical properties.     

A finite element-based model for pure waterjet process simulation

The utilization of abrasive waterjet (AWJ) cutting/drilling, and in particular its application into hard-to-cut materials, is growing. However, the mechanics of AWJ cutting is complex; the material removal process is not fully understood and, consequently, it has not been accurately modeled. In the current study, work was undertaken to mesh in a first stage the waterflow into the waterjet nozzle in order to use the finite element (FE) method to simulate the pure waterjet flow. The main objective is to investigate and analyze in detail the workpiece material behavior under waterjet impingement; a non-linear FE model (using LS-DYNA 3D code) has been developed, which simulates the erosion of the target material caused by the high-pressure waterjet flow. A combination of Eulerian–Langrangian elements is used for the waterjet and the target material, respectively, in order to handle their interaction. Damaged zones can be localized on impinged materials. Elements’ failure is handled by introducing a threshold strain after which Langrangian elements are removed. The results obtained from this numerical simulation (velocity profile, stress, erosion stages) show a good agreement with the results from previous experimental work that is available in bibliography. The next step of the research will be focused on the simulation of the whole procedure using various abrasives.     

MUSIPER: a system for modeling music similarity perception based on objective feature subset selection

We explore the use of objective audio signal features to model the individualized (subjective) perception of similarity between music files. We present MUSIPER, a content-based music retrieval system which constructs music similarity perception models of its users by associating different music similarity measures to different users. Specifically, a user-supplied relevance feedback procedure and related neural network-based incremental learning allows the system to determine which subset of a set of objective features approximates more accurately the subjective music similarity perception of a specific user. Our implementation and evaluation of MUSIPER verifies the relation between subsets of objective features and individualized music similarity perception and exhibits significant improvement in individualized perceived similarity in subsequent music retrievals.     

Gear skiving—CAD simulation approach

Gear skiving is used as a gear finishing process to reduce distortion errors which occurred on the gears due to the heat treatment. This process is similar to gear hobbing but the difference is that the cutting tool has a negative rake angle and tooth rake offset. The present study simulates the kinematics of the cutting process with the aid of commercial CAD software and allows the precise determination of the non-deformed chips and the developing cutting forces. The simulation model is verified based on the theoretical shape of the produced gear gap and the comparison between measured and calculated cutting forces.     

A Cascade-Hybrid Music Recommender System for mobile services based on musical genre classification and personality diagnosis

In this paper, we present a Cascade-Hybrid Music Recommender System intended to operate as a mobile service. Specifically, our system is a middleware that realizes the recommendation process based on a combination of music genre classification and personality diagnosis. A mobile user is able to query for music files by simply sending an example music file from his/her mobile device. In response to the user query, the system recommends music files that not only belong to the same genre as the user query, but also an attempt has been made to take into account both the user preferences as well as ratings from other users for candidate results. The recommendation mechanism is realized by applying the collaborative filtering technique of personality diagnosis. Using the minimum absolute error and the ranked scoring criteria, our approach is compared to existing recommendation techniques that rely on either collaborative filtering or content-based approaches. The outcome of the comparison clearly indicates that our approach exhibits significantly higher performance.     

Enhancing Enterprise Resource Planning users’ understanding through ontology-based training

An ERP system is a set of highly integrated and parametric applications, designed to fit to a variety of business. Because of this inherent complexity its implementation can be very demanding and the users involved must undertake extensive training, using sophisticated training materials. Existing training materials present major weaknesses, that the current paper aims to overcome, such as (1) semantic inconsistencies, (2) lack of explicit definition of constructs and (3) lack of knowledge reusability.This paper proposes a prototype model for the design and development of ERP training material, where both the multimedia objects used in training scenarios and the knowledge built into them are captured and fully reusable. The proposed approach helps trainees understand: (i) which are the building blocks of an ERP application, (ii) how they relate with each other and (iii) how they can be used in order to solve business specific problems.     

Workplace and organizational accident causation factors in the manufacturing industry

Labor inspectors investigate accidents to identify possible accident causes, initiate prosecution, and plan future accident prevention. The Method of Investigation for Labor Inspectors (MILI) was designed to help them to identify workplace and organizational factors in addition to immediate factors and legal breaches. The present study analyzes the impact of workplace (work design and provision of unsafe equipment) and organizational factors (training and employee involvement) on accident causation and validates MILI on real accident cases. Accident data from the manufacturing sector are analyzed with LISREL structural equation modeling. Results confirm the relationship between work design and training as well as between provision of unsafe equipment and employee involvement. The present study provides evidence that MILI is a structured accident investigation method allowing multiple accident causation factors to be revealed and that it could help all interested parts (not only labor inspectors, but companies as well) to thoroughly investigate occupational accidents. © 2009 Wiley Periodicals, Inc.