基礎講座 電気泳動(Electrophoresis)

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Principal characteristics of speech speech production models speech analysis and analysis-synthesis systems linear predictive coding (LPC) analysis speech coding speech synthesis speech recognition future directions of speech processing. Appendices: convolution and z-transform vector quantization algorithm neural nests.

Digital speech processing, synthesis, and recognition

Gæðastjórnunarkerfi : grunnatriði og íðorðasafn = Quality Management Systems : fundamentals and vocabulary.

There is presented a technique of transcribing Lithuanian text into phonemes for speech recognition. Text-phoneme transformation has been made by formal rules and the dictionary. Formal rules were designed to set the relationship between segments of the text and units of formalized speech sounds - phonemes, dictionary - to correct transcription and specify stress mark and position. Proposed the automatic transcription technique was tested by comparing its results with manually obtained ones. The experiment has shown that less than 6p of transcribed words have not matched.

/pdf/automatic-transcription-of-lithuanian-text-using-dictionary-a9bhepnii0.pdf

Automatic Transcription of Lithuanian Text Using Dictionary

The problem of speech corpus for design of human-computer interfaces working in voice recognition and synthesis mode is investigated. Specific requirements of speech corpus for speech recognizers and synthesizers were accented. It has been discussed that in order to develop above mentioned speech corpus, it has to consist of two parts. One part of speech corpus should be presented for the needs of Lithuanian text-to-speech synthesizers, another part of speech corpus – for the needs of Lithuanian speech recognition engines. It has been determined that the part of speech corpus designed for speech recognition engines has to ensure the availability to present language specificity by the use of different sets of phonemes. According to the research results, the speech corpus Liepa, which consists of two parts, was developed. This speech corpus opens possibilities for cost-effective and flexible development of human-computer interfaces working in voice recognition and synthesis mode.

/pdf/lithuanian-speech-corpus-liepa-for-development-of-human-cr7kpqpdsp.pdf

Lithuanian Speech Corpus Liepa for Development of Human-Computer Interfaces Working in Voice Recognition and Synthesis Mode

UML is the main modeling language used in model-driven development (MDD). In many cases, UML-based modeling systems need to be extended by plug-ins to support different modeling approaches. This paper proposes a conceptual framework for model-driven development of plug-ins, which enables reuse of UML modeling capabilities for defining executable plug-in models. This approach suggests that UML-based modeling system should provide for their users a set of extension profiles that make up Application Modeling Interface (AMI), which is MDD alternative to Application Programming Interface (API). The paper describes three cases of AMI - model validation, methodology wizards, and model patterns - and sample plug-in models based on them. The presented samples are implemented in MagicDraw, which is one of the most popular UML-based modeling systems worldwide. The paper also discusses the benefits and drawbacks of the proposed approach and its further research directions. http://dx.doi.org/10.5755/j01.itc.40.3.627

/pdf/model-driven-plug-in-development-for-uml-based-modeling-1ktvjid3cz.pdf

Model-Driven Plug-in Development for UML Based Modeling Systems. Information Technology and Control

The methodology described in this article will significantly reduce the time required for understanding the relations between chromatographic data and bioactivity assays. The methodology is a hybrid of hypothesis-based and data-driven scientific approaches. In this work, a novel chromatographic data segmentation method is proposed, which demonstrates the capability of finding what volatile substances are responsible for antiviral and cytotoxic effects in the medicinal plant extracts. Up until now, the full potential of the separation methods has not been exploited in the life sciences. This was due to the lack of data ordering methods capable of adequately preparing the chromatographic information. Furthermore, the data analysis methods suffer from multidimensionality, requiring a large number of investigated data points. A new method is described for processing any chromatographic information into a vector. The obtained vectors of highly complex and different origin samples can be compared mathematically...

Chromatographic Data Segmentation Method: A Hybrid Analytical Approach for the Investigation of Antiviral Substances in Medicinal Plant Extracts.

The quality feature set is a key of importance of successful speech recognition system. The quality of features is estimated by classification error. Yet, this method is limited as the classification experiments must be run with each feature system. The major issue of this paper is to propose the method for quality estimation of speech recognition features that is based on metrics and does not require classification experiments. Experimental researches were made in context of Nearest neighbour classifier usage. Within the proposed method PLP was established to have the higher quality comparing to LFCC. The adequateness of the method was validated by Nearest neighbour classification error. Ill. 3, bibl. 25, tabl. 1 (in English; abstracts in English and Lithuanian). DOI: http://dx.doi.org/10.5755/j01.eee.118.2.1165

/pdf/quality-measurement-of-speech-recognition-features-in-4wr50i473c.pdf

Laimutis Telksnys

Papers

Automatic Transcription of Lithuanian Text Using Dictionary

Lithuanian Speech Corpus Liepa for Development of Human-Computer Interfaces Working in Voice Recognition and Synthesis Mode

Model-Driven Plug-in Development for UML Based Modeling Systems. Information Technology and Control

Chromatographic Data Segmentation Method: A Hybrid Analytical Approach for the Investigation of Antiviral Substances in Medicinal Plant Extracts.

Quality Measurement of Speech Recognition Features in Context of Nearest Neighbour Classifier