Search

Abstract Objective Transcranial sonography (TCS) is a noninvasive neuroimaging technique, visualizing deep brain structures and the ventricular system. Although widely employed in diagnosing various movement disorders, such as Parkinson's disease and dystonia, by detecting disease‐specific abnormalities, the specific characteristics of the TCS in cerebellar ataxia remain inconclusive. We aimed to assess the potential value of TCS in patients with cerebellar ataxias for disease diagnosis and severity assessment. Methods TCS on patients with genetic and acquired cerebellar ataxia, including 94 with spinocerebellar ataxias (SCAs) containing 10 asymptomatic carriers, 95 with cerebellar subtype of multiple system atrophy (MSA‐C), and 100 healthy controls (HC), was conducted. Assessments included third ventricle width, substantia nigra (SN) and lentiform nucleus (LN) echogenicity, along with comprehensive clinical evaluations and genetic testing. Results The study revealed significant TCS abnormalities in patients with cerebellar ataxia, such as enlarged third ventricle widths and elevated rates of hyperechogenic SN and LN. TCS showed high accuracy in distinguishing patients with SCA or MSA‐C from HC, with an AUC of 0.870 and 0.931, respectively. TCS abnormalities aided in identifying asymptomatic SCA carriers, effectively differentiating them from HC, with an AUC of 0.725. Furthermore, third ventricle width was significantly correlated with SARA and ICARS scores in patients with SCA3 and SCOPA‐AUT scores in patients with MSA‐C. The SN area and SARA or ICARS scores in patients with SCA3 were also positively correlated. Interpretation Our findings illustrate remarkable TCS abnormalities in patients with cerebellar ataxia, serving as potential biomarkers for clinical diagnosis and progression assessment.

Fault diagnosis technology (FDT) is an effective tool to ensure stability and reliable operation in wind turbines. In this paper, a novel fault diagnosis methodology based on a cloud bat algorithm (CBA)-kernel extreme learning machines (KELM) approach for wind turbines is proposed via combination of the multisensor data fusion technique and time-domain analysis. First, the derived method calculates the time-domain indices of raw signals, and the fused time-domain indexes dataset are obtained by the multisensor data fusion. Then, the CBA-based KELM recognition model that can identify fault patterns of a wind turbine gearbox (WTB) is automatically established with the fused dataset. The dataset includes a large number of samples involving 6 fault types under different operational conditions by 5 accelerometers. The effectiveness and feasibility of this proposed method are proved by adopting the datasets originated from the test rig, and it achieves a diagnostic accuracy of 96.25%. Finally, compared with the other peer-to-peer methods, the experimental classification results show that the proposed CBA-KELM technique has the best performances.