Multimodal transformer graph convolution attention isomorphism network (MTCGAIN): a novel deep network for detection of insomnia disorder.

Background: In clinic, the subjectivity of diagnosing insomnia disorder (ID) often leads to misdiagnosis or missed diagnosis, as ID may have the same symptoms as those of other health problems. Methods: A novel deep network, the multimodal transformer graph convolution attention isomorphism network (MTGCAIN) is proposed in this study. In this network, graph convolution attention (GCA) is first employed to extract the graph features of brain connectivity and achieve good spatial interpretability. Second, the MTGCAIN comprehensively utilizes multiple brain network atlases and a multimodal transformer (MT) to facilitate coded information exchange between the atlases. In this way, MTGCAIN can be used to more effectively identify biomarkers and arrive at accurate diagnoses. Results: The experimental results demonstrated that more accurate and objective diagnosis of ID can be achieved using the MTGCAIN. According to fivefold cross-validation, the accuracy reached 81.29% and the area under the receiver operating characteristic curve (AUC) reached 0.8760. A total of nine brain regions were detected as abnormal, namely right supplementary motor area (SMA.R), right temporal pole: superior temporal gyrus (TPOsup.R), left temporal pole: superior temporal gyrus (TPOsup.L), right superior frontal gyrus, dorsolateral (SFGdor.R), right middle temporal gyrus (MTG.R), left middle temporal gyrus (MTG.L), right inferior temporal gyrus (ITG.R), right median cingulate and paracingulate gyri (DCG.R), left median cingulate and paracingulate gyri (DCG.L). Conclusions: The brain regions in the default mode network (DMN) of patients with ID show significant impairment (occupies four-ninths). In addition, the functional connectivity (FC) between the right middle occipital gyrus and inferior temporal gyrus (ITG) has an obvious correlation with comorbid anxiety (P=0.008) and depression (P=0.005) among patients with ID.

Identification and assessment method of cable joint health status based on traveling wave reflection.

Due to the difficulty in accurately detecting the health status of cable joints, a new method of identifying and assessing the cable joints' health status based on traveling wave reflection is proposed. By transmitting nanosecond pulse signals at the head end of the cable, the health status characteristics of the cable joints can be obtained, and the noise reduction of the measurement signals is performed by the wavelet function to identify the reflected wave at the joint and the end of the cable. The equivalent circuits and simulation models of contact resistance and leakage resistance are established, and the contact resistance and leakage resistance of the cable joints are calculated according to the amplitude and phase of the reflected signals at the joint and the end of the cable. By comparing with the resistance when the joint is in healthy operation, any measured parameter exceeding the corresponding standard is considered a joint fault. Simulations and test results show that the method can accurately identify the reflected signals of the cable joints in different operating states, and with changes in joint health, clear regular features can be extracted from the reflected signals, and the quality and health of the joints can be determined. The traveling wave method can be used to detect cable joint faults and provide an early warning of defects, which provides a new idea for online monitoring and early warning of cable joints in both theory and engineering practice.

Quantized recursive filtering for networked systems with stochastic transmission delays.

This paper investigates the recursive filtering problem for a class of networked systems subject to the uniform quantization effects and stochastic transmission delays. The system output is quantized according to a uniform quantization mechanism, and then sent to the remote filter via a communication network undergoing stochastic transmission delays (which are modeled by a sequence of independent and identically distributed variables). To deal with the stochastic transmission delays, an indicator function is delicately designed to ensure that the filtering process is implemented based on the quantized measurement with the newest timestamp available for the filter. With the aid of the indicator function, a free-delay system is obtained by using the augmented system method. The aim of this paper is to design a Kalman-type filter for the augmented system such that an upper bound of the filtering error covariance is guaranteed and minimized. With the aid of the stochastic analysis method, the desired upper bound of the filtering error covariance is derived by recursively solving two Riccati-like difference equations. Then, the upper bound is minimized by properly selecting the filter parameters. Finally, a numerical example is provided to illustrate the validity of the developed filtering scheme.