Search

According to the WHO, the number of mental disorder patients, especially depression patients, has overgrown and become a leading contributor to the global burden of disease. With the rising of tools such as artificial intelligence, using physiological data to explore new possible physiological indicators of mental disorder and creating new applications for mental disorder diagnosis has become a new research hot topic. We present a multi-modal open dataset for mental-disorder analysis. The dataset includes EEG and recordings of spoken language data from clinically depressed patients and matching normal controls, who were carefully diagnosed and selected by professional psychiatrists in hospitals. The EEG dataset includes data collected using a traditional 128-electrodes mounted elastic cap and a wearable 3-electrode EEG collector for pervasive computing applications. The 128-electrodes EEG signals of 53 participants were recorded as both in resting state and while doing the Dot probe tasks; the 3-electrode EEG signals of 55 participants were recorded in resting-state; the audio data of 52 participants were recorded during interviewing, reading, and picture description.

Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention for investigating the disease progression, though most studies did not sufficiently utilize the evolution information. In this paper, we proposed a cerebral similarity network with more progression information to predict the conversion from MCI to AD efficiently. First, we defined the new dynamic morphological feature to mine longitudinal information sufficiently. Second, based on the multiple dynamic morphological features the cerebral similarity network was constructed by sparse regression algorithm with optimized parameters to obtain better prediction performance. Then, leave-one-out cross-validation and support vector machine (SVM) were employed for the training and evaluation of the classifiers. The proposed methodology obtained a high accuracy of 92.31% (Sensitivity = 100%, Specificity = 82.86%) in a three-year ahead prediction of MCI to AD conversion. Experiment results suggest the effectiveness of the dynamic morphological feature, serving as a more sensitive biomarker in the prediction of MCI conversion.

Analysis of mobile big data enables smart cities from aspects of traffic pattern, human mobility, air quality, and so on. Co-occurrence pattern in human mobility has been proposed in recent years and sparked high attentions of academia and industry. Co-occurrence pattern has shown enormous values in aspects of urban planning, business, and social applications, such as shopping mall promotion strategy making, and contagious disease spreading. What’s more, human mobility has strong relation with regional functions, because each urban region owns a major function to offer specialized services for city’s operations and such location-based services attract massive passenger flow, which is exactly the essence of urban human mobility pattern. Therefore, in this paper, we put forward a co-occurrence pattern mining scheme (CoPFun) based on regional function discovery utilizing various mobile data. First, we do traffic modeling to map trajectory data into population groups, which include temporal partition and map segmentation. Then we employ a frequent pattern mining algorithm to mine co-occurrence event data. Meanwhile, we exploit TF-IDF method to process POI data and LDA algorithm to process trajectory data to discover urban regional functions. We apply CoPFun to real mobile data to extract co-occurrence event data and compare it with OD data to analyze urban co-occurrence pattern from a perspective of regional functions. The experiment results verify the effectiveness of CoPFun.

We investigated the effect of cerium oxide on the precipitation of Ag nanoparticles in silicate glass via a femtosecond laser irradiation and successive annealing. Absorption spectra show that Ce3+ ions may absorb part of the laser energy via multiphoton absorption and release free electrons, resulting in an increase of the concentration of Ag atoms and a decrease of the concentration of hole-trapped color centers, which influence precipitation of the Ag nanoparticles. In addition, we found that the formed Ag-0 may reduce Ce4+ ions to Ce3+ ions during the annealing process, which inhibits the growth of the Ag nanoparticles.