As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.

Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches

Objective To investigate the gross α and β radioactivity levels of drinking water source in the city, the largest oil field production base in northeast China, and estimate the annual dose, in order to ensure the safety of drinking water and public health. Methods The water samples from three drinking water sources were collected and tested in the dry and wet season, respectively. The gross α radioactivity was measured by standard curve method, and gross βmeasured by thin sample method. The annual effective dose of internal radiation caused by drinking water was estimated. Results Totally 184 samples were collected from the three sampling areas in dry and wet season respectively. The average values of gross α and β radioactivity levels in the drinking water source area were (0.24±0.09) and (0.30±0.17) Bq/L respectively. The average activity concentration of gross α and gross β in the dry season were (0.23±0.09) and (0.29±0.18) Bq/L, respectively. The average annual effective dose of gross α and β internal radiation caused by drinking water was estimated to be 62.41 and 1.10 μSv/year, respectively. The gross α and β radioactivity levels gradually decreased from the intake to the end of the reservoir of drinking water source areas. Conclusions The gross α and gross β radioactivity levels, distribution and annual effective dose of drinking water source areas in this city were all lower than the drinking water limit stipulated by China and the reference level recommended by the World Health Organization. The radioactivity of water body of the drinking water source was within the normal background level.

The gross α and β radioactivity levels of drinking water source in one oil industrial city in northeast China

Globally, the two main causes of young people dying are mental health issues and suicide. A mental health issue is a condition of physiological disorder that inhibits with the vital process of the brain. The amount of individuals with psychiatric illnesses has considerably increased during the past several years. The majority of individuals with mental disorders reside in India. The mental illness can have an impact on a person’s health, thoughts, behaviour, or feelings. The capacity of controlling one’s thoughts, emotions, and behaviour might help an individual to deal with challenging circumstances, build relationships with others, and navigate life’s problems. With a primary focus on the healthcare domain and human-computer interaction, the capacity to recognize human emotions via physiological and facial expressions opens up important research ideas as well as application-oriented potential. Affective computing has recently become one of the areas of study that has received the greatest interest from professionals and academics in a variety of sectors. Nevertheless, despite the rise in articles published, the reviews of a particular aspect of affective computing in mental health still are limited and have certain inadequacies. As a result, a literature survey on the use of affective computing in India to make decisions about mental health issues is discussed. As a result, the paper focuses on how traditional techniques used to monitor and assess physiological data from humans by utilizing deep learning and machine learning approaches for humans’ affect recognition (AR) using Affective computing (AfC) which is a combination of computer science, AI, and cognitive science subjects (such as psychology and psychosocial).

An enhanced affective computing-based framework using machine learning & medical IoT for the efficient pre-emptive decision-making of mental health problems

The utility of electroencephalographic measures in obsession compulsion disorder

Enhanced Sleep Stage Classification Using EEG and EOG: A Novel Approach for Feature Selection with Deep Learning and Gaussian Noise Data Augmentation

Existing mental health assessment methods mainly rely on experts' experience, which has subjective bias, so convolutional neural networks are applied to mental health assessment to achieve the fusion of face, voice, and gait. Among them, the OpenPose algorithm is used to extract facial and posture features; openSMILE is used to extract voice features; and attention mechanism is introduced to reasonably allocate the weight values of different modal features. As can be seen, the effective identification and evaluation of 10 indicators such as mental health somatization, depression, and anxiety are realized. Simulation results show that the proposed method can accurately assess mental health. Here, the overall recognition accuracy can reach 77.20%, and the F1 value can reach 0.77. Compared with the recognition methods based on face single-mode fusion, face + voice dual-mode fusion, and face + voice + gait multimodal fusion, the recognition accuracy and F1 value of proposed method are improved to varying degrees, and the recognition effect is better, which has certain practical application value.

/pdf/using-convolutional-neural-networks-for-the-assessment-2vtkugij.pdf

Using Convolutional Neural Networks for the Assessment Research of Mental Health

Objective
To investigate the distribution of gross α and gross β radioactive levels in drinking raw water from different regions of Guangdong province, and to establish the radioactive level base line value in raw water.


Methods
The samples from 191 drinking water sources in use in Guangdong province were collected in rainy season and dry season, respectively, and determined and analyzed under the standard examination method for drinking water-radiological parameters (GB/T 5750.13-2006). The levels of gross α and gross β radioactivity were evaluated under the standard for drinking water quality (GB 5749-2006).


Results
A total of 377 raw water samples were taken, including 189 samples in rainy season and 188 samples in dry season, in which 186 samples were matched between rainy season and dry season. In dry season, the gross α levels ranged from 0.008 Bq/L to 0.582 Bq/L, averaged at (0.034±0.060) Bq/L, while the gross β levels ranged from 0.014 Bq/L to 0.637 Bq/L, averaged at (0.108±0.091) Bq/L. In rainy season, the gross α levels ranged from 0.008 Bq/L to 0.402 Bq/L, averaged at (0.045±0.064) Bq/L, while the gross β levels ranged from 0.014 Bq/Lto 0.848 Bq/L, averaged at (0.125±0.128) Bq/L. The gross α and gross β radioactivity levels of other samples were much lower than the guidance values in the national radioactivity standards on drinking water radioactivity, except for a sample from Shanwei area. The gross α and gross β radioactivity levels in the rainy season were higher than in the dry water season, and the gross α radioactivity levels in the rainy season were significantly higher than in the dry water season. There were significant differences in gross α and gross β radioactivity levels in rainy(Frainy season=1.819, 2.709, P<0.05) and dry season (Fdry season=1.985, 8.461, P<0.05)in different water systems, and the levels of gross α and gross β radioactivity in the rivers in western Guangdong were the highest. The gross α and gross β radioactivity levels of groundwater in rainy season were higher than in river water and lake water, and the gross α and gross β radioactivity levels in river water were higher than in lake and reservoir water, with the statistically significant differences(Ftotal α=39.323, Ftotal β=25.911, P<0.05), the gross α and gross β radioactivity levels in dry season were higher than in river water and lake water, with the statistically significant difference(Ftotal α=11.520, Ftotal β=28.435, P<0.05). The highest radioactivity levels is in groundwater, followed by river water, and the lowest is in lake and reservoir water.


Conclusions
The natural radioactivity background levels in drinking raw water in Guangdong province is lower than the limit value on drinking water stipulated by our country. The radioactivity levels in raw water in western Guangdong is significantly higher than in other water systems, and the radioactivity level in river water is also significantly higher than in lake and reservoir water.


Key words: 
Radioactive level; Raw water; Gross αradioactivity; Gross βradioactivity

Monitoring and analysis of gross α and gross β levels in drinking water sources in Guangdong province

In recent years, the optical 4f system has drawn much attention in building high-speed and ultra-low-power optical neural networks (ONNs). Most optical systems suffer from the misalignment of the optical devices during installment. The performance of ONN based on the optical 4f system (4f-ONN) is considered sensitive to the misalignment in the optical path introduced. In order to comprehensively investigate the inﬂuence caused by the misalignment, we proposed a method for estimating the performance of a 4f-ONN in response to various misalignment in the context of the image classiﬁcation task.The misalignment in numerical simulation is estimated by manipulating the optical intensity distributions in the fourth focus plane in the 4f system. Followed by a series of physical experiments to validate the simulation results. Using our method to test the impact of misalignment of 4f system on the classiﬁcation accuracy of two popular image classiﬁcation datasets, MNIST and Quickdraw16. On both datasets, we found that the performances of 4f-ONN generally degraded dramatically as the positioning error increased. Different positioning error tolerance in the misalignment orientations was observed over the two datasets. Classiﬁcation performance could be preserved by positioning errors up to 200 microns in a speciﬁc direction.

Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets

Background As a medium for developing brain-computer interface systems, EEG signals are complex and difficult to identify due to their complexity, weakness, and differences between subjects. At present, most of the current research on sleep EEG signals are single-channel and dual-channel, ignoring the research on the relationship between different brain regions. Brain functional connectivity is considered to be closely related to brain activity and can be used to study the interaction relationship between brain areas. Methods Phase-locked value (PLV) is used to construct a functional connection network. The connection network is used to analyze the connection mechanism and brain interaction in different sleep stages. Firstly, the entire EEG signal is divided into multiple sub-periods. Secondly, Phase-locked value is used for feature extraction on the sub-periods. Thirdly, the PLV of multiple sub-periods is used for feature fusion. Fourthly, the classification performance optimization strategy is used to discuss the impact of different frequency bands on sleep stage classification performance and to find the optimal frequency band. Finally, the brain function network is constructed by using the average value of the fusion features to analyze the interaction of brain regions in different frequency bands during sleep stages. Results The experimental results have shown that when the number of sub-periods is 30, the α (8–13 Hz) frequency band has the best classification effect, The classification result after 10-fold cross-validation reaches 92.59%. Conclusion The proposed algorithm has good sleep staging performance, which can effectively promote the development and application of an EEG sleep staging system.

/pdf/exploration-of-sleep-function-connection-and-classification-2jreq619.pdf

Exploration of sleep function connection and classification strategies based on sub-period sleep stages

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yanbing Liu

Author Tools

Chat about Author

Papers

Using Convolutional Neural Networks for the Assessment Research of Mental Health

Monitoring and analysis of gross α and gross β levels in drinking water sources in Guangdong province

Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets

Exploration of sleep function connection and classification strategies based on sub-period sleep stages