ObjectivesSeveral studies have examined the effects of repetitive transcranial magnetic stimulation (rTMS) on associative memory (AM) but findings were inconsistent. Here, we aimed to test whether twice-daily rTMS could significantly improve AM.MethodsIn this single-blind, sham-controlled experiment, 40 participants were randomized to receive twice-daily sham or real rTMS sessions for five consecutive days (a total of 16,000 pulses). The stimulation target in left inferior parietal lobule (IPL) exhibiting peak functional connectivity to the left hippocampus was individually defined for each participant. Participants (...) completed both a picture-cued word association task and Stroop test at baseline and 1 day after the final real or sham rTMS session. Effects of twice-daily rTMS on AM and Stroop test performance were compared using two-way repeated measures analysis of variance with main factors Group (real vs. sham) and Time (baseline vs. post-rTMS).ResultsThere was a significant Group × Time interaction effect. AM score was significantly enhanced in the twice-daily real group after rTMS, but this difference could not survive the post hoc analysis after multiple comparison correction. Further, AM improvement in the twice-daily real group was not superior to a previously reported once-daily rTMS group receiving 8,000 pulses. Then, we combined the twice- and once-daily real groups, and found a significant Group × Time interaction effect. Post hoc analysis indicated that the AM score was significantly enhanced in the real group after multiple comparisons correction.ConclusionOur prospective experiment did not show significant rTMS effect on AM, but this effect may become significant if more participants could be recruited as revealed by our retrospective analysis. (shrink)

ObjectiveTwo subregions of the dorsolateral prefrontal cortex have been identified as effective repetitive transcranial magnetic stimulation targets for the “anxiosomatic” and “dysphoric” symptoms, respectively. We aimed to develop a convenient approach to locate these targets on the scalp.Materials and methodsIn a discovery experiment, the two personalized targets were precisely identified on 24 subjects using a neuronavigation system. Then, a localized approach was developed based on individual scalp landmarks. This “landmark-based approach” was replicated and validated in an independent cohort. Reliability of (...) the approach was tested by calculating the correlation of both the inter-rater and intra-rater results. Validity was tested by comparing the mean distance between the personalized and landmark-based targets to the TMS spatial resolution. We further conducted a total of 24 sham rTMS sessions to estimate the misplacement between the coil center and target during a 10-min stimulation without neuronavigation.ResultsThe parameters of the “landmark-based approach” in the discovery experiment were replicated well in an independent cohort. Using discovery parameters, we successfully identified the symptom-specific targets in the independent cohort. Specifically, the mean distance between the personalized and landmark-based targets on the cortex was not significantly larger than 5 mm. However, the personalized and landmark-based targets distance exceeded 5 mm in more than 50% of subjects. During the 10-min sham rTMS session, the average coil misplacement was significantly larger than 5 mm.ConclusionThe “landmark-based approach” can conveniently and reliably locate the two symptom-specific targets at group level. However, the accuracy was highly varied at individual level and further improvement is needed. (shrink)

Although the management and planning of water resources are extremely significant to human development, the complexity of implementation is unimaginable. To achieve this, the high-precision water consumption prediction is actually the key component of urban water optimization management system. Water consumption is usually affected by many factors, such as weather, economy, and water prices. If these impact factors are directly combined to predict water consumption, the weight of each perspective on the water consumption will be ignored, which will be greatly (...) detrimental to the prediction accuracy. Therefore, this paper proposes a deep neural network-based complex system for urban water management. The essence of it is to formulate a water consumption prediction model with the aid of principal component analysis and the integrated deep neural network, which is abbreviated as UWM-Id. The PCA classifies the factors affecting water consumption in the original data into three categories according to their correlation and inputs them into the neural network model. The results in the previous step are assigned weights and integrated into the form of fully connected layer. Finally, analyzing the sensitivity of the proposed UWM-Id and comparing its performance with a series of commonly used baseline methods for data mining, a large number of experiments have proved that UWM-Id has good performance and can be used for urban water management system. (shrink)

The number of scientific publications is growing exponentially. Research articles cite other work for various reasons and, therefore, have been studied extensively to associate documents. It is argued that not all references carry the same level of importance. It is essential to understand the reason for citation, called citation intent or function. Text information can contribute well if new natural language processing techniques are applied to capture the context of text data. In this paper, we have used contextualized word embedding (...) to find the numerical representation of text features. We further investigated the performance of various machine-learning techniques on the numerical representation of text. The performance of each of the classifiers was evaluated on two state-of-the-art datasets containing the text features. In the case of the unbalanced dataset, we observed that the linear Support Vector Machine achieved 86% accuracy for the “background” class, where the training was extensive. For the rest of the classes, including “motivation,” “extension,” and “future,” the machine was trained on less than 100 records; therefore, the accuracy was only 57 to 64%. In the case of a balanced dataset, each of the classes has the same accuracy as trained on the same size of training data. Overall, SVM performed best on both of the datasets, followed by the stochastic gradient descent classifier; therefore, SVM can produce good results as text classification on top of contextual word embedding. (shrink)