Search results

Authenticating an individual through voice can prove convenient as nothing needs to be stored and cannot easily be stolen. However, if an individual is authenticating under duress, the coerced attempt must be acknowledged and appropriate warnings issued. Furthermore, as duress may entail multiple combinations of emotions, the current f-score evaluation does not accommodate that multiple selected samples possess similar levels of importance. Thus, this study aims to demonstrate an approach to identifying duress within a voice-based authentication system.

Measuring the value that a classifier presents is often done using an f-score. However, the f-score does not effectively portray the proposed value when multiple classes could be grouped as one. The f-score also does not provide any information when numerous classes are often incorrectly identified as the other. Therefore, the proposed approach uses the confusion matrix, aggregates the select classes into another matrix and calculates a more precise representation of the selected classifier’s value. The utility of the proposed approach is demonstrated through multiple tests and is conducted as follows. The initial tests’ value is presented by an f-score, which does not value the individual emotions. The lack of value is then remedied with further tests, which include a confusion matrix. Final tests are then conducted that aggregate selected emotions within the confusion matrix to present a more precise utility value.

Two tests within the set of experiments achieved an f-score difference of 1%, indicating, Mel frequency cepstral coefficient, emotion detection, confusion matrix, multi-layer perceptron, Ryerson audio-visual database of emotional speech and song (RAVDESS), voice authentication that the two tests provided similar value. The confusion matrix used to calculate the f-score indicated that some emotions are often confused, which could all be considered closely related. Although the f-score can represent an accuracy value, these tests’ value is not accurately portrayed when not considering often confused emotions. Deciding which approach to take based on the f-score did not prove beneficial as it did not address the confused emotions. When aggregating the confusion matrix of these two tests based on selected emotions, the newly calculated utility value demonstrated a difference of 4%, indicating that the two tests may not provide a similar value as previously indicated.

This approach’s performance is dependent on the data presented to it. If the classifier is presented with incomplete or degraded data, the results obtained from the classifier will reflect that. Additionally, the grouping of emotions is not based on psychological evidence, and this was purely done to demonstrate the implementation of an aggregated confusion matrix.

The f-score offers a value that represents the classifiers’ ability to classify a class correctly. This paper demonstrates that aggregating a confusion matrix could provide more value than a single f-score in the context of classifying an emotion that could consist of a combination of emotions. This approach can similarly be applied to different combinations of classifiers for the desired effect of extracting a more accurate performance value that a selected classifier presents.

The purpose of this paper is to examine the popular “information transmitted” interpretation of absolute judgments, and to provide an alternative interpretation if one is needed.

The psychologists Garner and Hake and their successors used Shannon's Information Theory to quantify information transmitted in absolute judgments of sensory stimuli. Here, information theory is briefly reviewed, followed by a description of the absolute judgment experiment, and its information theory analysis. Empirical channel capacities are scrutinized. A remarkable coincidence, the similarity of maximum information transmitted to human memory capacity, is described. Over 60 representative psychology papers on “information transmitted” are inspected for evidence of memory involvement in absolute judgment. Finally, memory is conceptually integrated into absolute judgment through a novel qualitative model that correctly predicts how judgments change with increase in the number of judged stimuli.

Garner and Hake gave conflicting accounts of how absolute judgments represent information transmission. Further, “channel capacity” is an illusion caused by sampling bias and wishful thinking; information transmitted actually peaks and then declines, the peak coinciding with memory capacity. Absolute judgments themselves have numerous idiosyncracies that are incompatible with a Shannon general communication system but which clearly imply memory dependence.

Memory capacity limits the correctness of absolute judgments. Memory capacity is already well measured by other means, making redundant the informational analysis of absolute judgments.

This paper presents a long‐overdue comprehensive critical review of the established interpretation of absolute judgments in terms of “information transmitted”. An inevitable conclusion is reached: that published measurements of information transmitted actually measure memory capacity. A new, qualitative model is offered for the role of memory in absolute judgments. The model is well supported by recently revealed empirical properties of absolute judgments.

Each amusement park has a wayfinding system, while symbols are important mediums to guide tourists to find their destinations. It is very important that whether the meanings of symbols recognized by tourists immediately. This paper mainly discusses the recognition of graphic symbols in amusement park, and proposes the improvement suggestions. Materials for this study were drawn from 20 different graphic symbols of a theme amusement park in Taiwan. The testees were required to evaluate the design of graphic symbols based on symbolic meaning and graphics recognition to summarize the confusion matrix. The results show that there are three groups of graphic symbols easy to be confused, and five symbols not meeting a criterion of 67 per cent correct responses. The reasons were discussed, and improvement and relevant suggestions have been proposed, which may be helpful to redesign of symbols.

The field of machine vision, or computer vision, has been growing at fast pace. The growth in this field, unlike most established fields, has been both in breadth and depth of concepts and techniques. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. The goal of a machine vision system is to create a model of the real world from images. Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. The purpose of this paper is to consider recognition of objects manufactured in mechanical industry. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such parts. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects.

The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.

Classification accuracy is affected by the changing network architecture. ANN is computationally demanding and slow. A total of 20 hidden nodes network structure produced the best results at 500 iterations (90 percent accuracy based on overall accuracy and 87.50 percent based on κ coefficient). So, 20 hidden nodes are selected for further analysis. The learning rate is set to 0.1, and momentum term used is 0.2 that give the best results architectures. The confusion matrix also shows the accuracy of the classifier. Hence, with these results the proposed system can be used efficiently for more objects.

After calculating the variation of overall accuracy with different network architectures, the results of different configuration of the sample size of 50 testing images are taken. Table II shows the results of the confusion matrix obtained on these testing samples of objects.

A classifier technique is one of the important tools which may be used to classify the data or information into systematic manner based on certain criteria pertaining to get the accurate statistical information for decision making. It plays a vital role in the various applications, such as business organization, e-commerce, health care, scientific and engineering application. The purpose of this paper is to examine the performance of different classification techniques in lift index (LI) data classification.

The analyses consist of two stages. First, the random data are generated for lifting task through computer programming, which is then put into the National Institute for Occupational Safety and Health equation for LI estimation. Based on the evaluated index, the task may be classified into two groups, i.e. high-risk and low-risk task. The classified task is considered to analyze the performance of different tools like Artificial Neural Network (ANN), discriminant analysis (DA) and support vector machines (SVMs).

The work clearly demonstrates the accuracy and computational ability of ANN, DA and SVM for data classification problems in general and LI data in particular. From the research it may be concluded that SVM may outperform ANN and DA.

The research is limited to a particular kind of data that may be further explored by selecting the different controllable parameters and model specification. The study can also be applied to realistic problem of manual loading. It is expected that this will help researchers, designers and practicing engineers by making them aware of the performance of classification techniques in this area.

The objective of this research work is to assess and compare the relative performance of some well-known classification techniques like DA, ANN and SVM, which suggest that data characteristics considerably impact the classification performance of the methods.

The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.

Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. Object recognition is a type of pattern recognition. Object recognition is widely used in the manufacturing industry for the purpose of inspection. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. In this work, recognition of objects manufactured in mechanical industry is considered. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such mechanical part. Red, green and blue RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

One important finding is that there is not any considerable change in the network performances after 500 iterations. It has been found that for data smaller network structure, smaller learning rate and momentum are required. The relative sample size also has a considerable effect on the performance of the classifier. Further studies suggest that classification accuracy is achieved with the confusion matrix of the data used. Hence, with these results the proposed system can be used efficiently for more objects. Depending upon the manufacturing product and process used, the dimension verification and surface roughness may be integrated with proposed technique to develop a comprehensive vision system. The proposed technique is also highly suitable for web inspections, which do not require dimension and roughness measurement and where desired accuracy is to be achieved at a given speed. In general, most recognition problems provide identity of object with pose estimation. Therefore, the proposed recognition (pose estimation) approach may be integrated with inspection stage.

This paper considers the problem of recognizing and classifying the objects of such mechanical part. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. ANN is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

The identification (listing) and classification (grading) of urban heritage buildings for conservation is a challenging task for urban planners and conservation architects. Most of the world's cities depend on the expert-based evaluation method (EBEM) for listing and grading heritage buildings. The Panaji city in India provided a unique opportunity to assess the performance of the EBEM as two independent agencies carried out the heritage listing and grading process. Considering the case of Panaji, this research aims to measure the performance of EBEM used for listing and grading heritage buildings and identify the issues associated with the existing methodology.

This research presents a comparative analysis of the building listed and graded by the two agencies. The buildings that both agencies graded were identified and analysed using a confusion matrix. The grading classification was tested for accuracy, precision, sensitivity and F-score.

The result shows a low accuracy and F-score, which reflects the level of buildings misclassified. The misclassification is the product of the lack of standardisation of methodology and the subjectivity level involved in the EBEM.

Heritage listing and grading is a time-consuming process, and no city has the time and resource to conduct studies to check the accuracy. The cities in India and across the world, which follow a similar EBEM process, should consider this study's finding and revisit their methodology and develop a more reliable methodology for listing and grading heritage buildings.

The purpose of this paper is surface roughness prediction using pattern recognition for the aluminium hybrid metal matrix composite (HMMC).

Hybrid composites were manufactured using liquid metallurgy technique. The cast HMMC was machined using an industrial CNC turning centre and the machining vibration signals were acquired using an accelerometer. The acquired signals were processed and used to build a machine learning model for predicting surface finish based on the tool signature.

The authors established a technique for predicting and monitoring the surface quality during machining using a low cost accelerometer. It is capable of being integrated with the machine controller for online warning of deviations in surface roughness. The system is reconfigurable for any machining condition with a very short training period. The use of this model facilitates online surface roughness monitoring, avoiding the need for costly measuring equipment.

The model developed is innovative and not reported widely to the best of the authors' knowledge. The use of accelerometer‐based surface roughness prediction and control is an innovative approach for automation of machining process monitoring. These can be integrated into any existing machining centre as a standalone system or can be integrated into the CNC controller like Fanuc or Siemens.

The purpose of this paper is to reveal the smart collaborative learning service. This concept aims to build teams of learners based on the complementarity of their skills, allowing flexible participation and offering interdisciplinary collaboration opportunities for all the learners. The success of this environment is related to predict efficient collaboration between the different teammates, allowing a smartly sharing knowledge in the Smart University environment.

A random forest (RF) approach is proposed, which is based on semantic modelization of the learner and the problem-solving allowing multidisciplinary collaboration, and heuristic completeness processing to build complementary teams. To achieve that, this paper established a Konstanz Information Miner workflow that integrates the main steps for building and evaluating the RF classifier, this workflow is divided into: extracting knowledge from the smart collaborative learning ontology, calculating the completeness using a novel heuristic and building the RF classifier.

The smart collaborative learning service enables efficient collaboration and democratized sharing of knowledge between learners, by using a semantic support decision support system. This service solves a frequent issue related to the composition of learning groups to serve pedagogical perspectives.

The present study harmonizes the integration of ontology, a new heuristic processing and supervised machine learning algorithm aiming at building an intelligent collaborative learning service that includes a qualified classifier of complementary teams of learners.

recent years, facial expression recognition has been widely used in human machine interaction, clinical medicine and safe driving. However, there is a limitation that conventional recurrent neural networks can only learn the time-series characteristics of expressions based on one-way propagation information.

To solve such limitation, this paper proposes a novel model based on bidirectional gated recurrent unit networks (Bi-GRUs) with two-way propagations, and the theory of identity mapping residuals is adopted to effectively prevent the problem of gradient disappearance caused by the depth of the introduced network. Since the Inception-V3 network model for spatial feature extraction has too many parameters, it is prone to overfitting during training. This paper proposes a novel facial expression recognition model to add two reduction modules to reduce parameters, so as to obtain an Inception-W network with better generalization.

Finally, the proposed model is pretrained to determine the best settings and selections. Then, the pretrained model is experimented on two facial expression data sets of CK+ and Oulu- CASIA, and the recognition performance and efficiency are compared with the existing methods. The highest recognition rate is 99.6%, which shows that the method has good recognition accuracy in a certain range.

By using the proposed model for the applications of facial expression, the high recognition accuracy and robust recognition results with lower time consumption will help to build more sophisticated applications in real world.