Search

Depressive disorders (including major depressive disorder and dysthymia) and anxiety (generalized anxiety disorder or GAD) disorders are the two most prevalent mental illnesses. Early diagnosis of these afflictions can lead to cost-effective treatment with a better outcome prospectus. With the advent of digital technology and platforms, people express themselves by various means, such as social media posts, blogs, journals, instant messaging services, etc. Text remains the most common and convenient form of expression. Therefore, it can be used to predict the onset of anxiety and depression. Scopus and Web of Science (WoS) databases were used to retrieve the relevant literature using a set of predefined search strings. Irrelevant publications were filtered using multiple criteria. The research meta data was subsequently analyzed using the Biblioshiny Tool of R. Finally, a comparative analysis of most suitable documents is presented. A total of 103 documents were used for bibliometric mapping in terms of research outcome over the past years, productivity of authors, institutions, and countries, collaborations, trend topics, keyword co-occurrence, etc. Neural networks and support vector machines are the most popular ML techniques; word embeddings are extensively used for text representations. There is a shift toward using multiple modalities. SVM, Naive Bayes, and LSTM are the most used ML methods; social media is the most used source of data (Twitter is the most common platform); and audio is the most used modality that is combined with text for depressive and anxiety disorders (DAD) detection. Text data provides good cues for the detection of DAD using machine learning. However, the findings in most of the cases are based on a limited amount of data. Using large amounts of data with other modalities can help develop more generalized DAD-detection systems. Asian countries are leading in the research output with China and India being the top countries in terms of the number of research publications. However, more international collaborations are needed. Limited research exists for anxiety disorders. Co-occurrence of anxiety and depressive disorders is high (33% of studies). [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to analyze publications on artificial intelligence (AI) for falls in older people from a bibliometric perspective. Methods: The Web of Science database was searched for titles of English‐language articles containing the words "artificial intelligence," "deep learning," "machine learning," "natural language processing,", "neural artificial network," "fall," "geriatric," "elderly," "aging," "older," and "old age." An R‐based application (Biblioshiny for bibliometrics) and VOSviewer software were used for analysis. Results: Thirty‐seven English articles published between 2018 and 2024 were included. The year 2023 is the year with the most publications with 16 articles. The most productive research field was "Engineering Electrical Electronic" with seven articles. The most productive country was the United States, followed by China. The most common words were "injuries," "people," and "risk factors." Conclusion: Publications on AI and falls in the elderly are both few in number and the number of publications has increased in recent years. Future research should include relevant analyses in scientific databases, such as Scopus and PubMed. [ABSTRACT FROM AUTHOR]

The Zhuang ethnic minority in China possesses its own ethnic language and no ethnic script. Cultural exchange and transmission encounter hurdles as the Zhuang rely exclusively on oral communication. An online cloud-based platform was required to enhance linguistic communication. First, a database of 200 h of annotated Zhuang speech was created by collecting standard Zhuang speeches and improving database quality by removing transcription inconsistencies and text normalization. Second, SAformerNet, a more efficient and accurate transformer-based automatic speech recognition (ASR) network, is achieved by inserting additional downsampling modules. Subsequently, a Neural Machine Translation (NMT) model for translating Zhuang into other languages is constructed by fine-tuning the BART model and corpus filtering strategy. Finally, for the network's responsiveness to real-world needs, edge-computing techniques are applied to relieve network bandwidth pressure. An edge-computing private cloud system based on FPGA acceleration is proposed to improve model operation efficiency. Experiments show that the most critical metric of the system, model accuracy, is above 93%, and inference time is reduced by 29%. The computational delay for multi-head self-attention (MHSA) and feed-forward network (FFN) modules has been reduced by 7.1 and 1.9 times, respectively, and terminal response time is accelerated by 20% on average. Generally, the scheme provides a prototype tool for small-scale Zhuang remote natural language tasks in mountainous areas. [ABSTRACT FROM AUTHOR]

The emergence of various types of everyday urban problems poses severe challenges to the conventional top-down designed urban problem-handling protocols. Social sensing data, such as the urban problem complaint hotline records, constitute good sources for collecting bottom-up information on urban problems. Nevertheless, a partially obsolete urban problem categorization standard, a manually operated and experience-dependent workflow for problem classification and pushing, and an unoptimized problem-handling responsibility designation among the municipal departments have been impairing the sufficient utilization of the collected complaint data toward more efficient urban problem-handling performance. In this paper, based on the 12345-hotline data collected in Sanya City, China, we 1) construct an urban problem tree that presents a new and expandable classification of everyday urban problems with 7 super-types, 34 types, and 105 sub-types of events, thus complementing that in the existing National Standard which merely contains 6 types and 66 sub-types; 2) design an auto-classification algorithm for the complaint records with Natural Language Processing and Supervised Machine Learning methods, which achieves an accuracy of up to 75% at the super-type level; and 3) optimize the urban problem-handling responsibility designation among the municipal departments for improved departmental function distinction and balanced workloads, which combined with the auto-classification algorithm yield a decrease of the problem pushing failure ratio from the current 73.8% to 14.6%. We integrate all the above functions in a web-based information system to establish a digital platform for practical urban problem-handling. We conclude the paper with discussions on the paper's implications of an overhaul of urban legislative and executive systems following a bottom-up paradigm and reflections on the paper's limitations and theoretical implications from a complex-system theory perspective. • An urban problem tree constructed from the "12345" Hotline is a complement to the National Standard. • Developing NLP and supervised ML algorithms for effective classification of crowd-sourced hotline complaints. • Optimizing the local government structure for urban problem-handling from a bottom-up approach. • Implementing a web-based system for hotline handling which decreases the failed pushes from 73.8% to 14.6%. [ABSTRACT FROM AUTHOR]

This article aims to gain insights into the prevailing public sentiment during the policy relaxation period by examining whether the post-COVID-19 landscape reflects signs of withering or booming conditions. Employing methods from natural language processing (NLP) and machine learning (ML), the analysis reveals a predominance of positive sentiment from December 7, 2022 to May 17, 2023, indicative of an optimistic perspective and a potentially flourishing environment. A predictive model based on logistic regression emerges as a notably effective tool for sentiment prediction, suggesting potential utility in predicting future public health crises. A comparison of sentiments in translations by the government aligns with previous research, revealing a less favorable depiction of translated texts compared to the source texts. Furthermore, the commonality index, a measure of group consensus value, surpasses the typical range, while the certainty index, a measure of confidence, slightly falls below the norm. These findings offer valuable insights for policy considerations while highlighting areas for international communication and understanding improvement. [ABSTRACT FROM AUTHOR]

Background: Differentiating between ulcerative colitis (UC), Crohn's disease (CD) and intestinal tuberculosis (ITB) using endoscopy is challenging. We aimed to realize automatic differential diagnosis among these diseases through machine learning algorithms.Methods: A total of 6399 consecutive patients (5128 UC, 875 CD and 396 ITB) who had undergone colonoscopy examinations in the Peking Union Medical College Hospital from January 2008 to November 2018 were enrolled. The input was the description of the endoscopic image in the form of free text. Word segmentation and key word filtering were conducted as data preprocessing. Random forest (RF) and convolutional neural network (CNN) approaches were applied to different disease entities. Three two-class classifiers (UC and CD, UC and ITB, and CD and ITB) and a three-class classifier (UC, CD and ITB) were built.Results: The classifiers built in this research performed well, and the CNN had better performance in general. The RF sensitivities/specificities of UC-CD, UC-ITB, and CD-ITB were 0.89/0.84, 0.83/0.82, and 0.72/0.77, respectively, while the values for the CNN of CD-ITB were 0.90/0.77. The precisions/recalls of UC-CD-ITB when employing RF were 0.97/0.97, 0.65/0.53, and 0.68/0.76, respectively, and when employing the CNN were 0.99/0.97, 0.87/0.83, and 0.52/0.81, respectively.Conclusions: Classifiers built by RF and CNN approaches had excellent performance when classifying UC with CD or ITB. For the differentiation of CD and ITB, high specificity and sensitivity were achieved as well. Artificial intelligence through machine learning is very promising in helping unexperienced endoscopists differentiate inflammatory intestinal diseases.Conference: The abstract of this article has won the first prize of the Young Investigator Award during the Asian Pacific Digestive Week (APDW) 2019 held in Kolkata, India. [ABSTRACT FROM AUTHOR]