Stroke is a serious cerebrovascular condition, in which brain cells die due to an abrupt blockage of arteries supplying blood and oxygen or due to bleeding in the brain tissue when a blood vessel bursts or ruptures. Because stroke occurs suddenly in most people, prevention is oftentimes difficult. In Japan, this condition is one of the major causes of death, which is associated with high medical cost, especially among the society’s aging population. Therefore, stroke prediction and treatment is important. Stroke incidences can be avoided by a preventive treatment based on the risk of onset. However, since judgment of the onset risk largely depends on the individual experience and skill of the doctor, a highly accurate prediction method that is independent of the doctor’s experience and skill is the focus of this study. The target of prediction for this research is subarachnoid hemorrhage that is part of stroke. Logistic regression and support vector machine that predict cerebral aneurysm rupture by machine learning using combined medical data and cerebral blood-flow-simulation data were employed to analyze 338 cerebral aneurysm samples (35 ruptured, 303 unruptured). SMOTE algorithm solved the imbalance of data, while the SelectKBest algorithm was used to extract important features from the total 70 features obtained from both data. Out of the 27 important features extracted, 40% belonged to the medical data and the remaining 60% were from the blood-flow-simulation data. Using logistic regression as a classification model, we found the sensitivity of 0.64 and the specificity of 0.85. The results validated the possibility of a highly accurate method of cerebral aneurysm rupture prediction by machine learning using engineering information obtained from mechanical simulation.

The demand for information services considering personal preferences is increasing. In this paper, we propose a system for automatically acquiring personal preferences from TV viewer’s behaviors. Our system firstly extracts intervals of interest and estimates the interest degree for each extracted interval based on the temporal patterns in facial changes by Hidden Markov Models (HMMs). Then, the viewer profile is created by associating the interest degrees with the content information described in the metadata of the watched program. Experimental results have shown that the proposed methods are able to correctly estimate interest degrees for extracted intervals with a precision rate of 73.1% and a recall rate of 68.8%, and that the created viewer profiles are comparable to the actual preferences of each viewer.

Multicast packets are lost when collisions occur on IEEE 802.11 wireless LANs with DCF because the IEEE 802.11 MAC protocol does not use a packet loss recovery mechanism for multicast packets. Therefore, an application that uses wireless multicast should be provided with a recovery mechanism. This paper studies the multicast packet loss due to collision with TCP packets on IEEE 802.11b DCF infrastructure wireless LANs. The results of analysis and simulation show that the multicast packet loss ratio has an upper limit, and that FEC is effective for recovering the multicast packet losses.

FM-FDM (frequency division multiplexing) optical transmission equipment has been developed for 34-channel MUSE HDTV (high-definition television) signals to realize optical CATV (cable television) systems. The equipment uses an LD (laser diode) with a 1.3 mu m wavelength, a single-mode optical fiber, and an avalanche photodiode (APD). A good picture is received after a 42 km transmission. A part of the multiplexed signals is distorted near or below the threshold of an LD. When the number of transmission channels is small and the total optical modulation depth is large, this nonlinearity governs the power ratio of an FM signal to one distortion component-the DU ratio. However, when the number of transmission channels is large, the DU ratio is determined by the effective optical modulation depth rather than the total optical modulation depth. Furthermore, the method of system design is clarified for an optical trunk line CATV system. If no restriction on the transmission bandwidth of optical devices exists, approximately 30 km transmission of 100-channel MUSE HDTV signals is available with a received CN ratio of 17.5 dB.>