We propose in this paper a novel algorithm as well as architecture for the fall accident detection and corresponding wide area rescue system based on a smart phone and the third generation (3G) networks. To realize the fall detection algorithm, the angles acquired by the electronic compass (ecompass) and the waveform sequence of the triaxial accelerometer on the smart phone are used as the system inputs. The acquired signals are then used to generate an ordered feature sequence and then examined in a sequential manner by the proposed cascade classifier for recognition purpose. Once the corresponding feature is verified by the classifier at current state, it can proceed to next state; otherwise, the system will reset to the initial state and wait for the appearance of another feature sequence. Once a fall accident event is detected, the user's position can be acquired by the global positioning system (GPS) or the assisted GPS, and sent to the rescue center via the 3G communication network so that the user can get medical help immediately. With the proposed cascaded classification architecture, the computational burden and power consumption issue on the smart phone system can be alleviated. Moreover, as we will see in the experiment that a distinguished fall accident detection accuracy up to 92% on the sensitivity and 99.75% on the specificity can be obtained when a set of 450 test actions in nine different kinds of activities are estimated by using the proposed cascaded classifier, which justifies the superiority of the proposed algorithm.

In this paper, a wireless hand gesture recognition glove is proposed for real-time translation of Taiwanese sign language. To discriminate between different hand gestures, we have flex and inertial sensors embedded into the glove so that the three most important parameters, i.e., the posture of fingers, orientation of the palm, and motion of the hand, defined in Taiwanese Sign Language can be recognized without ambiguity. The finger flexion postures acquired by flex sensors, the palm orientation acquired by G-sensor, and the motion trajectory acquired by gyroscope are used as the input signals of the proposed system. The input signals will be acquired and examined periodically to see if it is a legal sign language gesture or not. Once the sampled signal can last longer than a predefined clock cycles, it is regarded as a valid gesture and will be sent to cell phone via Bluetooth for gesture discrimination and speech translation. With the proposed architecture and algorithm, the accuracy for gesture recognition is quite satisfactory. As we can see in experiments that an accuracy rate up to 94% on sensitivity for gesture recognition can be achieved which justifies the superiority of the proposed architecture.

Many coding methods are more efficient with some images than others. In particular, run-length coding is very useful for coding areas of little changes. Adaptive predictive coding achieves high coding efficiency for fast changing areas like edges. In this paper, we propose a switching coding scheme that will combine the advantages of both run-length and adaptive linear predictive coding. For pixels in slowly varying areas, run-length coding is used; otherwise least-squares (LS)-adaptive predictive coding is used. Instead of performing LS adaptation in a pixel-by-pixel manner, we adapt the predictor coefficients only when an edge is detected so that the computational complexity can be significantly reduced. For this, we use a simple yet effective edge detector using only causal pixels. This way, the proposed system can look ahead to determine if the coding pixel is around an edge and initiate the LS adaptation in advance to prevent the occurrence of a large prediction error. With the proposed switching structure, very good prediction results can be obtained in both slowly varying areas and pixels around boundaries. Furthermore, only causal pixels are used for estimating the coding pixels in the proposed encoder; no additional side information needs to be transmitted. Extensive experiments as well as comparisons to existing state-of-the-art predictors and coders will be given to demonstrate its usefulness.

In predictive image coding, the least squares (LS)-based adaptive predictor is noted as an efficient method to improve prediction result around edges. However pixel-by-pixel optimization of the predictor coefficients leads to a high coding complexity. To reduce computational complexity, we activate the LS optimization process only when the coding pixel is around an edge or when the prediction error is large. We propose a simple yet effective edge detector using only causal pixels. The system can look ahead to determine if the coding pixel is around an edge and initiate the LS adaptation to prevent the occurrence of a large prediction error. Our experiments show that the proposed approach can achieve a noticeable reduction in complexity with only a minor degradation in the prediction results.

Sleep quality evaluation is a major approach to clinical diagnosis of different types of sleep andmental disturbances.How to render it possible for test subjects to complete sleep status detection and quality assessment in a natural environment is what this paper mainly highlights. Clinically, sleep disturbances are analyzed by the so-called Polysomnography (PSG). However, due to limitations in space and high cost, as well as the fact that test subjects must wear various physiological detection equipment during the test, the collected signal is susceptible to interference due to uncomfortable sensations. As such it usually does not reflect the realistic situation of the subject. For this reason,we propose in this paper a pressure-sensor-based smart mattress to realize sleep status detection and quality evaluation. Regarding sleep posture recognition, a proposed convolutional neural network (CNN) model in conjunction with a pressure distribution image formed by the pressure sensing matrix are applied. With respect to assessing the subjects’ time in bed, a support vectormachine (SVM) is used to determine sitting or lying postures, and further recognize the actual time in bed. As for sleep quality assessment, Fuzzy inference is adopted in this paper base on a set of four predefined sleep parameters. Compared with some of prior arts, the proposed systemdoes not require the test subjects to wear any equipment, and as such the subjects can complete the test in a natural environment. Experimental results show that the accuracy of the proposed SVM classifier for differentiating sitting and lying posture and that of CNN model for the recognition of four different sleep postures can be up to 99.986% and 96.987%, respectively. With the proposed model, precise sleep parameters, including time in bed, number of times of bed-leaving, number of times of body movements all night, standard deviation of time interval between body movements, and sleep posture can be provided. Moreover, the system does not use devices such as microphones or surveillance cameras to collect the data of the test subjects; thus, there is no concern about infringing the privacy of the subjects. It is believed that the system will be of considerable help and serve as an aid to clinical diagnosis of sleep disturbance.