No abstract

The goal of t h i s s t u d y is placed at developing a "Active Human Interface(AII1)" t h a t r e a l i z e s h e a r t -t o h e a r t communication between machine(computer and/or r o b o t ) and human being.

The pulmonary function and microscopic change of the lungs of diabetic patients were examined and compared with those of non-diabetic patients to assess the diabetic microangiopathy in lung.For pulmonary function study, spirogram flow-volume curve, diffusing capacity and arterial blood gas analysis were performed in 52 diabetic patients and 48 age-and sex-matched control subjects. Diffusing capacity, % vital capacity, total lung capacity, residual volume and 25% maximal expiratory flow were significantly less in the diabetic group than in the control group. Pa02 was also decreased in the diabetic group. There were no significant differences between the two groups in the other parameters.For histopathological study, the lungs of 35 autopsied cases of a diabetic group and 26 autopsied cases of a non-diabetic group. There were no significant differences in age and sex between the two groups. The two groups were compared and studied by measuring the thickness of alveolar capillary walls, pulmonary arteriolar walls and alveolar walls with a light microscope and an eye piece micrometer. The alveolar capillary walls, the pulmonary arteriolar walls and the alveolar walls had thickened significantly in the diabetic patients.These studies suggested that histological changes (microangiopathy) in the lungs are a cause of pulmonary function abnormalities.

The Recognition of Basic Facial Expressions by Neural NetworkHiroshi KOBAYASHI* and Fumio HARA**We propose the concept of Active Human Interface (AHI) that makes the machine (computer and/or robot) respond to human being more actively and for establishing the new paradigm to realize the AHI, as the first step of this study, we investigate the method of machine recognition of human emotions.This paper deals with the neural network method of human emotion recognition from facial expressions. Facial expressions were categorized into 6 groups (Surprise, Fear, Disgust, Anger, Happiness and Sadness), and obtained CCD camera-acquired data with respect to facial characteristic points relating to 3 components of face (Eyebrows, Eyes and Mouth). Then we generated the position information and shape information about the 6 basic facial expressions for 30 clients. These information were input into the Input units of the 4-layered neural network and network learning was carried out by back propagation algorithm. The neural network recognition system of facial expressions showed a high recognition rate up to 80% to 6 basic facial expressions for both the position and shape information and particularly the system showed a smaller rate of mis-recognition between some of 6 basic expressions.

We propose the concept of Active Human Interface (AHI) that makes the machine (computer and/or robot) respond to human being more actively and for establishing the new paradigm to realize the AHI, as the first step of this study, we investigate the method of machine recognition of human emotions.This paper deals with the neural network method of human emotion recognition from facial expressions. Facial expressions were categorized into 6 groups (Surprise, Fear, Disgust, Anger, Happiness and Sadness), and obtained CCD camera-acquired data with respect to facial characteristic points relating to 3 components of face (Eyebrows, Eyes and Mouth). Then we generated the position information and shape information about the 6 basic facial expressions for 30 clients. These information were input into the Input units of the 4-layered neural network and network learning was carried out by back propagation algorithm. The neural network recognition system of facial expressions showed a high recognition rate up to 80% to 6 basic facial expressions for both the position and shape information and particularly the system showed a smaller rate of mis-recognition between some of 6 basic expressions.