High-level Recognition Research Articles

Context-Independent Multilingual Emotion Recognition from Speech Signals

This paper presents and discusses an analysis of multilingual emotion recognition from speech with database-specific emotional features. Recognition was performed on English, Slovenian, Spanish, and French InterFace emotional speech databases. The InterFace databases included several neutral speaking styles and six emotions: disgust, surprise, joy, fear, anger and sadness. Speech features for emotion recognition were determined in two steps. In the first step, low-level features were defined and in the second high-level features were calculated from low-level features. Low-level features are composed from pitch, derivative of pitch, energy, derivative of energy, and duration of speech segments. High-level features are statistical presentations of low-level features. Database-specific emotional features were selected from high-level features that contain the most information about emotions in speech. Speaker-dependent and monolingual emotion recognisers were defined, as well as multilingual recognisers. Emotion recognition was performed using artificial neural networks. The achieved recognition accuracy was highest for speaker-dependent emotion recognition, smaller for monolingual emotion recognition and smallest for multilingual recognition. The database-specific emotional features are most convenient for use in multilingual emotion recognition. Among speaker-dependent, monolingual, and multilingual emotion recognition, the difference between emotion recognition with all high-level features and emotion recognition with database-specific emotional features is smallest for multilingual emotion recognition—3.84%.

都市における多世代居住の親世代から子世代への役割分担の移行と居住空間の柔軟性

This paper analyzes the multiple generation living from the viewpoint of transfer of managing roles in urban living in order to find out the importance of multiple generation living and an indicator of multiple generation house planning. The results are as follows : 1) Roles move from parent generation to child generation along lifestages progress and the changes of family structure, regardless of the space division between generations. 2) Sharing spaces between generations promotes recognition about shared family area, shared generation area, and divided individual area. 3) High level recognition of multiple generation living promoted by past multiple generation living experience and the progress of lifestages must be taken in to the planning of multiple generation houses. 4) There is a gap between the actual and potential extent of flexibility, so greater consideration needs to be given to the possibilities of the future use of housing at an early stage of its planning.

PARALLEL MATCHING OF 3D ARTICULATED OBJECT RECOGNITION

In dealing with large volume image data, sequential methods usually are too slow and unsatisfactory. This paper introduces a new system employing parallel matching in high-level recognition of 3D articulated objects. A new structural strategy using linear combination and parallel graphic matching techniques is presented for 3D polyhedral objects representable by 2D line-drawings. It solves one of the basic concerns in diffusion tomography complexities, i.e. patterns can be reconstructed through fewer projections, and 3D objects can be recognized by a few learning sample views. It also improves some of the current methods while overcoming their drawbacks. Furthermore, it can distinguish very similar objects and is more accurate than other methods in the literature. An online webpage system for understanding and recognizing 3D objects is also illustrated.

The role of general practice in promoting teenage health: a review of the literature.

Teenagers are acknowledged to be at high risk of health-damaging behaviours including smoking, teenage pregnancy, and drug and alcohol use. Additionally, the recognition of high levels of psychological distress is cause for serious concern about teenage health. This paper reviews health promotion interventions for teenagers in general practice. Medline, BIDS, Psyclit and SIGLE databases for January 1990-February 1997 were systematically searched for English language studies on adolescent/teenage health and health promotion interventions in primary health care/general practice; reference sections of articles were checked for earlier work. The literature indicates that teenagers rarely receive health promotion advice from their physicians. The impact on behaviour change, of screening and health promotion for teenagers in general practice requires further evaluation to asssess the potential effectiveness in preventing the onset or continuation of health-damaging behaviours.

An Approach to Analysis of EEGs Recorded During Music Listening

In this paper, we propose and examine methods for analyzing EEG (Electroencephalogram) in particular during music listening. The relationship between EEG and music cognition is also discussed. Music can be regarded as input to the brain system which influences the human mentality along with time. Since music cognition has many emotional aspects, it is expected that EEGs recorded during music listening may reflect the electrical activities of brain regions related to those emotional aspects. The brain system consists of dozens of functional subsystems and we are in agreement with the hypothesis that their cooperative process enables high level recognition such as music listening. From the point of view of informational neurobiology, the spatial and temporal frequency pattern was extracted from EEG. First, the autoregressive model was applied to the power spectrums of EEGs of different brain regions. Then, the frequency structures were compared using a statistical model. We focused on change of frequency and spatial pattern of the brain's activated area in response to the music structure. Several observations show that there was a sudden drop in the frequency's average at the beginning of recapitulation and a difference in activated areas between relaxing and music listening conditions. We also calculate the information flow between EEG channels by directional coherence analysis. The experimental results showed that information flow pattern also respond to the music structure and this was thought to be peculiar to the cognitive process. In conclusion, our methods were more precise and easier to use in understanding brain activity than the conventional one. The results reflect the level of consciousness and the brain's activated area during music listening. It is anticipated that this approach will provide a new perspective on cognitive musicology.

STRATEGIC AWARENESS AND THE PROCESS OF INNOVATION

Inherent to enterprising behaviour is the exercise of strategic awareness, a process of understanding and learning from the environment in which the entrepreneur and the small business operate. This paper notes that a growing recognition of high levels of change and uncertainty in the environment infers a need to increase small business understanding of what is changing and why. Strategic awareness is an individual and organisational capability, tailored to contextual needs and contingencies, that describes processes for identifying, understanding, interpreting and acting on events and influences. It also contributes to the process of innovation. Research in the UK, and later in Western Australia, identified a customer needs-focused and outwardly-directed approach to innovation that relies on understanding the external environment. This paper concludes by stressing the relationship between strategic awareness and innovation, and suggests that the nature of these processes demands a rethink in how we support and research small businesses and entrepreneurs.

Role of learning in three-dimensional form perception.

One of the most remarkable characteristics of the human visual system is its ability to perceive specific three-dimensional forms in single two-dimensional contour images. This has often been attributed to a few general purpose and possibly innately specified shape biases, such as those favouring symmetry and other structural regularities (Fig. 1). An alternative approach proposed by the early empiricists and since tested suggests that this ability may also be acquired from visual experience, with the three-dimensional percept being the manifestation of a learned association between specific two-dimensional projections and the correlated three-dimensional structures. These studies of shape learning have been considered inconclusive, however, because their results can potentially be accounted for as cognitive decisions that might have little to do with shape perception per se. Here we present an experimental system that enables objective verification of the role of learning in shape perception by rendering the learning to be perceptually manifest. We show that the human visual system can learn associations between arbitrarily paired two-dimensional pictures and (projectionally consistent) three-dimensional structures. These results implicate high-level recognition processes in the task of shape perception.

A machine vision system for inspecting wood surface defects by using neural network

With the development of wood industry, the processing of wood products become more significant. This paper discusses the development of machine vision system used to inspect and classify the various types of defects of wood surface. The surface defects means the variations of colour and texture. The machine vision system is to detect undesirable “defects” that can appear on the surface of rough wood lumber. A neural network was used within the Blackboard framework for a labeling verification step of the high-level recognition module of vision system. The system has been successfully tested on a number of boards from several different species.

Treating elevated cholesterol levels: the great Satan in perspective.

The purpose of this review is to provide perspective on the developments leading to the recognition of high cholesterol levels as a risk factor for coronary heart disease (CHD). Another objective is to consider the unfolding controversies regarding the relative value of cholesterol-lowering drug therapy in primary and secondary prevention. Should physicians use lipid-lowering drugs to treat patients with elevated cholesterol levels but no clinical evidence of coronary disease, or limit intervention to patients with a previous history of angina, coronary angioplasty, coronary artery bypass surgery, or myocardial infarction? This review finds inadequate data to support a recommendation for screening large populations for the presence of elevated cholesterol levels or for primary prevention in those known to have high cholesterol. On the other hand, there is mounting evidence to support vigorous intervention in those with known coronary disease. Further study is needed to determine whether a subset of patients with one or more well-defined risk factors would benefit from primary prevention.

A HYBRID METHOD TOWARDS THE SEGMENTATION OF RANGE IMAGES FOR 3-D OBJECT RECOGNITION

This paper presents a hybrid approach towards accomplishing the task of range image segmentation. It tends to combine region growing and one-dimensional orthogonal polynomial fitting techniques for the detection of edges in range images. Edges detected by such a method possesses good localisation property. This aids to steer the region growing process towards accomplishing accurate border partitioning. In addition, the incorporation of region growing process eliminates internal micro edges and provides for missing border reconstruction as it is able to detect weak edges. It is believed that the edge and segmentation maps produced, when conveyed to the higher level recognition process, may prove valuable not only for CAD based modeling purposes but may also aid to provide descriptive syntax to the object identification process.

Method for utilizing formant frequencies in speech recognition

A speech recognizer which utilizes hypothesis testing to determine formant frequencies for use in speech recognition. A pre-processor (36) receives speech signal frames and utilizes linear predictive coding to generate all formant frequency candidates. An optimum formant selector (38) operates with a comparator (40) to select from the formant candidates those formants which best match stored reference formants. A dynamic time warper (42) and high level recognition logic (44) operate to determine whether or not to declare a recognized word.

A graph grammar programming style for recognition of music notation

Graph grammars are a promising tool for solving picture processing problems. However, the application of graph grammars to diagram recognition has been limited to rather simple analysis of local symbol configurations. This paper introduces the Build-Weed-Incorporate programming style for graph grammars and shows its application in determining the meaning of complex diagrams, where the interaction among physically distant symbols is semantically important. Diagram recognition can be divided into two stages: symbol recognition and high-level recognition. Symbol recognition has been studied extensively in the literature. In this work we assume the existence of a symbol recognizer and use a graph grammar to assemble the diagram's information content from the symbols and their spatial relationships. The Build-Weed-Incorporate approach is demonstrated by a detailed discussion of a graph grammar for high-level recognition of music notation.

What is distance and why do we need the metric model for pattern learning?

The concept of distance, its role in pattern recognition, and some advantages of the new model for pattern learning proposed recently by the author are discussed. The universality, flexibility, and the ability to connect intrinsically the low-level process that selects the primitives for the pattern representation with the higher level recognition process make the model clearly superior to other models proposed so far. The fundamentally new analytical feature of the model, which allows the learning machine to reconfigure itself efficiently, is the introduction of continuity in the classical discrete computational model.

Knowledge-based 3D analysis from 2D medical images

An anatomical knowledge-based system for image analysis that interprets CT/MR (computed tomography/magnetic resonance) images of the human chest cavity is reported. The approach utilizes a low-level image analysis system with the ability to analyze the data in bottom-up (or data-driven) and top-down (or model-driven) modes to improve the high-level recognition process. Several image segmentation algorithms, including K-means clustering, pyramid-based region extraction, and rule-based merging, are used for obtaining the segmented regions. To obtain a reasonable number of well-segmented regions that have a good correlation with the anatomy, a priori knowledge in the form of masks is used to guide the segmentation process. Segmentation of the brain is also considered.

Knowledge-based analysis and understanding of medical images

Knowledge-based image analysis and interpretation of radiological images is of significant interest for several reasons including a means to identify and label each part of the image for further automated diagnostic analysis. Also, there is a need to develop a knowledge-based biomedical image analysis system which can analyze and interpret the anatomical images (such as those obtained from X-ray computed tomography (CT) scanning) in order to help analysis of functional images (such as those obtained from positron emission tomography (PET) scanning) of the organ of the same patient. This paper deals with the design and implementation of a knowledge-based system to analyze and interpret CT anatomical images of the human chest. In the approach presented here, the emphasis has been on the development of a strong low-level analysis system with the capability of analyzing in both bottom-up and top-down modes; and on the use of hierarchical relational, spatial, and structural knowledge of human anatomy in the process of high-level analysis and recognition.

Naval Sea System Command's Approach to Human Factors in the 1980's: Changing Times

There is an emerging concern for applying human factors to the design and support of naval ships and weapon systems. The Naval Sea Systems Command (NAVSEA) is making significant progress in the application of human factors technology for the ultimate benefit of those who must operate and maintain the fleets of the future. This paper will address the current status of human factors within NAVSEA. In doing so, we shall review what has been done in the past, then assess the present, and finally we will suggest additional requirements that need attention. Higher level recognition of the role of human factors is evidenced by promulgation of formal directives from the Department of Defense, the Secretary of the Navy, the Chief of Naval Operations, the Chief of Naval Material, and Commander, Naval Sea Systems Command. Principal contributions expected from the application of an effective human factors program are to define human functions in man-machine systems and to design procedures and equipment to ensure that those functions can be performed under all expected operational conditions. The specific outcome would be realized in the form of a high level of personnel readiness in the fleet to assure that a system's assigned functions can indeed be performed, with the ultimate aim being to sustain a high level of system readiness and ship's effectiveness.

Pathogenic effects of Eimeria necatrix in young chickens

Freshly sporulated oocysts of Eimeria necatrix were administered to 2- and 6-week-old chickens in single doses ranging from 312 to 1,280,000 oocysts. Doses of 312 to 5000 oocysts led to small decreases in weight gain and a relatively low production of oocysts which ranged from 8 to 16 million oocysts per bird, scattered petechial hemorrhages, and small white circular colonies of schizonts were present under the serosa of the jejunum. After infection with 20,000 or more oocysts, morbidity and mortality were high with typical lesions of severe hemorrhagic enteritis. There were no survivors when the birds received 80,000 or more oocysts. Sudden death was a characteristic feature of the disease. Oocyst production and mortality were useful criteria in the recognition of low and high levels of infection, respectively. Changes in weight and packed red cell volume were of limited value in the assessment of the pathogenicity of E. necatrix. At low levels of infection four times as many oocysts were necessary to produce the same effect on weight and packed red cell volume in 6-week-old chickens as in 2-week-old chickens.