Twisted van der Waals Quantum Materials: Fundamentals, Tunability, and Applications.

Twisted van der Waals (vdW) quantum materials have emerged as a rapidly developing field of two-dimensional (2D) semiconductors. These materials establish a new central research area and provide a promising platform for studying quantum phenomena and investigating the engineering of novel optoelectronic properties such as single photon emission, nonlinear optical response, magnon physics, and topological superconductivity. These captivating electronic and optical properties result from, and can be tailored by, the interlayer coupling using moiré patterns formed by vertically stacking atomic layers with controlled angle misorientation or lattice mismatch. Their outstanding properties and the high degree of tunability position them as compelling building blocks for both compact quantum-enabled devices and classical optoelectronics. This paper offers a comprehensive review of recent advancements in the understanding and manipulation of twisted van der Waals structures and presents a survey of the state-of-the-art research on moiré superlattices, encompassing interdisciplinary interests. It delves into fundamental theories, synthesis and fabrication, and visualization techniques, and the wide range of novel physical phenomena exhibited by these structures, with a focus on their potential for practical device integration in applications ranging from quantum information to biosensors, and including classical optoelectronics such as modulators, light emitting diodes, lasers, and photodetectors. It highlights the unique ability of moiré superlattices to connect multiple disciplines, covering chemistry, electronics, optics, photonics, magnetism, topological and quantum physics. This comprehensive review provides a valuable resource for researchers interested in moiré superlattices, shedding light on their fundamental characteristics and their potential for transformative applications in various fields.

TACOS: a novel approach for accurate prediction of cell-specific long noncoding RNAs subcellular localization.

Long noncoding RNAs (lncRNAs) are primarily regulated by their cellular localization, which is responsible for their molecular functions, including cell cycle regulation and genome rearrangements. Accurately identifying the subcellular location of lncRNAs from sequence information is crucial for a better understanding of their biological functions and mechanisms. In contrast to traditional experimental methods, bioinformatics or computational methods can be applied for the annotation of lncRNA subcellular locations in humans more effectively. In the past, several machine learning-based methods have been developed to identify lncRNA subcellular localization, but relevant work for identifying cell-specific localization of human lncRNA remains limited. In this study, we present the first application of the tree-based stacking approach, TACOS, which allows users to identify the subcellular localization of human lncRNA in 10 different cell types. Specifically, we conducted comprehensive evaluations of six tree-based classifiers with 10 different feature descriptors, using a newly constructed balanced training dataset for each cell type. Subsequently, the strengths of the AdaBoost baseline models were integrated via a stacking approach, with an appropriate tree-based classifier for the final prediction. TACOS displayed consistent performance in both the cross-validation and independent assessments compared with the other two approaches employed in this study. The user-friendly online TACOS web server can be accessed at https://balalab-skku.org/TACOS.

BERT6mA: prediction of DNA N6-methyladenine site using deep learning-based approaches.

N6-methyladenine (6mA) is associated with important roles in DNA replication, DNA repair, transcription, regulation of gene expression. Several experimental methods were used to identify DNA modifications. However, these experimental methods are costly and time-consuming. To detect the 6mA and complement these shortcomings of experimental methods, we proposed a novel, deep leaning approach called BERT6mA. To compare the BERT6mA with other deep learning approaches, we used the benchmark datasets including 11 species. The BERT6mA presented the highest AUCs in eight species in independent tests. Furthermore, BERT6mA showed higher and comparable performance with the state-of-the-art models while the BERT6mA showed poor performances in a few species with a small sample size. To overcome this issue, pretraining and fine-tuning between two species were applied to the BERT6mA. The pretrained and fine-tuned models on specific species presented higher performances than other models even for the species with a small sample size. In addition to the prediction, we analyzed the attention weights generated by BERT6mA to reveal how the BERT6mA model extracts critical features responsible for the 6mA prediction. To facilitate biological sciences, the BERT6mA online web server and its source codes are freely accessible at https://github.com/kuratahiroyuki/BERT6mA.git, respectively.

Tobacco industry interference to undermine the development and implementation of graphic health warnings in Bangladesh.

BACKGROUND: In Bangladesh, the 2013 Amendment of the Tobacco Control Act made graphic health warnings (GHWs) on the upper 50% of all tobacco packs obligatory. However, at the time of writing (May 2022), GHWs are still being printed on the lower 50% of packs. This paper seeks to explore how the tobacco industry undermined the development and implementation of GHWs in Bangladesh, a country known for a high level of tobacco industry interference (TII) that has rarely been examined in the peer-reviewed literature. METHODS: Analysis of print and electronic media articles and documents. RESULTS: Cigarette companies actively opposed GHWs, while bidi companies did not. The primary strategy used to influence the formulation and delay the implementation of GHWs was direct lobbying by the Bangladesh Cigarette Manufacturers' Association and British American Tobacco Bangladesh. Their arguments stressed the economic benefits of tobacco to Bangladesh and sought to create confusion about the impact of GHWs, for example, claiming that GHWs would obscure tax banderols, thus threatening revenue collection. They also claimed technical barriers to implementation-that new machinery would be needed-leading to delays. Tensions between government bodies were identified, one of which (National Board of Revenue)-seemingly close to cigarette companies and representing their arguments-sought to influence others to adopt industry-preferred positions. Finally, although tobacco control advocates were partially successful in counteracting TII, one self-proclaimed tobacco control group, whose nature remains unclear, threatened the otherwise united approach. CONCLUSIONS: The strategies cigarette companies used closely resemble key techniques from the well-evidenced tobacco industry playbook. The study underlines the importance of continuing monitoring and investigations into industry conduct and suspicious actors. Prioritising the implementation of WHO Framework Convention on Tobacco Control Article 5.3 is crucial for advancing tobacco control, particularly in places like Bangladesh, where close government-industry links exist.

Microplastic pollution: a review of techniques to identify microplastics and their threats to the aquatic ecosystem.

Microplastics (MPs), small synthetic particles, have emerged as perilous chemical pollutants in aquatic habitats, causing grave concerns about their disruptive effects on ecosystems. The fauna and flora inhabiting these specific environments consume these MPs, unwittingly introducing them into the intricate web of the food chain. In this comprehensive evaluation, the current methods of identifying MPs are amalgamated and their profound impacts on marine and freshwater ecosystems are discussed. There are many potential risks associated with MPs, including the dangers of ingestion and entanglement, as well as internal injuries and digestive obstructions, both marine and freshwater organisms. In this review, the merits and limitations of diverse identification techniques are discussed, including spanning chemical analysis, thermal identification, and spectroscopic imaging such as Fourier-transform infrared spectroscopy (FTIR), Raman spectroscopy, and fluorescent microscopy. Additionally, it discusses the prevalence of MPs, the factors that affect their release into aquatic ecosystems, as well as their plausible impact on various aquatic ecosystems. Considering these disconcerting findings, it is imperative that appropriate measures should be taken to assess the potential risks of MP pollution, protect aquatic life and human health, and foster sustainable development.

Integrative machine learning framework for the identification of cell-specific enhancers from the human genome.

Enhancers are deoxyribonucleic acid (DNA) fragments which when bound by transcription factors enhance the transcription of related genes. Due to its sporadic distribution and similar fractions, identification of enhancers from the human genome seems a daunting task. Compared to the traditional experimental approaches, computational methods with easy-to-use platforms could be efficiently applied to annotate enhancers' functions and physiological roles. In this aspect, several bioinformatics tools have been developed to identify enhancers. Despite their spectacular performances, existing methods have certain drawbacks and limitations, including fixed length of sequences being utilized for model development and cell-specificity negligence. A novel predictor would be beneficial in the context of genome-wide enhancer prediction by addressing the above-mentioned issues. In this study, we constructed new datasets for eight different cell types. Utilizing these data, we proposed an integrative machine learning (ML)-based framework called Enhancer-IF for identifying cell-specific enhancers. Enhancer-IF comprehensively explores a wide range of heterogeneous features with five commonly used ML methods (random forest, extremely randomized tree, multilayer perceptron, support vector machine and extreme gradient boosting). Specifically, these five classifiers were trained with seven encodings and obtained 35 baseline models. The output of these baseline models was integrated and again inputted to five classifiers for the construction of five meta-models. Finally, the integration of five meta-models through ensemble learning improved the model robustness. Our proposed approach showed an excellent prediction performance compared to the baseline models on both training and independent datasets in different cell types, thus highlighting the superiority of our approach in the identification of the enhancers. We assume that Enhancer-IF will be a valuable tool for screening and identifying potential enhancers from the human DNA sequences.

LSTM-PHV: prediction of human-virus protein-protein interactions by LSTM with word2vec.

Viral infection involves a large number of protein-protein interactions (PPIs) between human and virus. The PPIs range from the initial binding of viral coat proteins to host membrane receptors to the hijacking of host transcription machinery. However, few interspecies PPIs have been identified, because experimental methods including mass spectrometry are time-consuming and expensive, and molecular dynamic simulation is limited only to the proteins whose 3D structures are solved. Sequence-based machine learning methods are expected to overcome these problems. We have first developed the LSTM model with word2vec to predict PPIs between human and virus, named LSTM-PHV, by using amino acid sequences alone. The LSTM-PHV effectively learnt the training data with a highly imbalanced ratio of positive to negative samples and achieved AUCs of 0.976 and 0.973 and accuracies of 0.984 and 0.985 on the training and independent datasets, respectively. In predicting PPIs between human and unknown or new virus, the LSTM-PHV learned greatly outperformed the existing state-of-the-art PPI predictors. Interestingly, learning of only sequence contexts as words is sufficient for PPI prediction. Use of uniform manifold approximation and projection demonstrated that the LSTM-PHV clearly distinguished the positive PPI samples from the negative ones. We presented the LSTM-PHV online web server and support data that are freely available at http://kurata35.bio.kyutech.ac.jp/LSTM-PHV.

StackIL6: a stacking ensemble model for improving the prediction of IL-6 inducing peptides.

The release of interleukin (IL)-6 is stimulated by antigenic peptides from pathogens as well as by immune cells for activating aggressive inflammation. IL-6 inducing peptides are derived from pathogens and can be used as diagnostic biomarkers for predicting various stages of disease severity as well as being used as IL-6 inhibitors for the suppression of aggressive multi-signaling immune responses. Thus, the accurate identification of IL-6 inducing peptides is of great importance for investigating their mechanism of action as well as for developing diagnostic and immunotherapeutic applications. This study proposes a novel stacking ensemble model (termed StackIL6) for accurately identifying IL-6 inducing peptides. More specifically, StackIL6 was constructed from twelve different feature descriptors derived from three major groups of features (composition-based features, composition-transition-distribution-based features and physicochemical properties-based features) and five popular machine learning algorithms (extremely randomized trees, logistic regression, multi-layer perceptron, support vector machine and random forest). To enhance the utility of baseline models, they were effectively and systematically integrated through a stacking strategy to build the final meta-based model. Extensive benchmarking experiments demonstrated that StackIL6 could achieve significantly better performance than the existing method (IL6PRED) and outperformed its constituent baseline models on both training and independent test datasets, which thereby support its excellent discrimination and generalization abilities. To facilitate easy access to the StackIL6 model, it was established as a freely available web server accessible at http://camt.pythonanywhere.com/StackIL6. It is anticipated that StackIL6 can help to facilitate rapid screening of promising IL-6 inducing peptides for the development of diagnostic and immunotherapeutic applications in the future.

Meta-i6mA: an interspecies predictor for identifying DNA N6-methyladenine sites of plant genomes by exploiting informative features in an integrative machine-learning framework.

DNA N6-methyladenine (6mA) represents important epigenetic modifications, which are responsible for various cellular processes. The accurate identification of 6mA sites is one of the challenging tasks in genome analysis, which leads to an understanding of their biological functions. To date, several species-specific machine learning (ML)-based models have been proposed, but majority of them did not test their model to other species. Hence, their practical application to other plant species is quite limited. In this study, we explored 10 different feature encoding schemes, with the goal of capturing key characteristics around 6mA sites. We selected five feature encoding schemes based on physicochemical and position-specific information that possesses high discriminative capability. The resultant feature sets were inputted to six commonly used ML methods (random forest, support vector machine, extremely randomized tree, logistic regression, naïve Bayes and AdaBoost). The Rosaceae genome was employed to train the above classifiers, which generated 30 baseline models. To integrate their individual strength, Meta-i6mA was proposed that combined the baseline models using the meta-predictor approach. In extensive independent test, Meta-i6mA showed high Matthews correlation coefficient values of 0.918, 0.827 and 0.635 on Rosaceae, rice and Arabidopsis thaliana, respectively and outperformed the existing predictors. We anticipate that the Meta-i6mA can be applied across different plant species. Furthermore, we developed an online user-friendly web server, which is available at http://kurata14.bio.kyutech.ac.jp/Meta-i6mA/.

NeuroPred-FRL: an interpretable prediction model for identifying neuropeptide using feature representation learning.

Neuropeptides (NPs) are the most versatile neurotransmitters in the immune systems that regulate various central anxious hormones. An efficient and effective bioinformatics tool for rapid and accurate large-scale identification of NPs is critical in immunoinformatics, which is indispensable for basic research and drug development. Although a few NP prediction tools have been developed, it is mandatory to improve their NPs' prediction performances. In this study, we have developed a machine learning-based meta-predictor called NeuroPred-FRL by employing the feature representation learning approach. First, we generated 66 optimal baseline models by employing 11 different encodings, six different classifiers and a two-step feature selection approach. The predicted probability scores of NPs based on the 66 baseline models were combined to be deemed as the input feature vector. Second, in order to enhance the feature representation ability, we applied the two-step feature selection approach to optimize the 66-D probability feature vector and then inputted the optimal one into a random forest classifier for the final meta-model (NeuroPred-FRL) construction. Benchmarking experiments based on both cross-validation and independent tests indicate that the NeuroPred-FRL achieves a superior prediction performance of NPs compared with the other state-of-the-art predictors. We believe that the proposed NeuroPred-FRL can serve as a powerful tool for large-scale identification of NPs, facilitating the characterization of their functional mechanisms and expediting their applications in clinical therapy. Moreover, we interpreted some model mechanisms of NeuroPred-FRL by leveraging the robust SHapley Additive exPlanation algorithm.

Immune modulation by nutritional intervention in malnourished children: Identifying the phenotypic distribution and functional responses of peripheral blood mononuclear cells.

Malnourished children are susceptible to an increased risk of mortality owing to impaired immune functions. However, the underlying mechanism of altered immune functions and its interaction with malnutrition is poorly understood. This study investigates the immune function and evaluates the effect of a particular nutritional intervention on the immune cells of undernourished children. Stunted (LAZ <-2) and at-risk of being stunted (length-for-age Z-scores, LAZ <-1 to -2) children aged between 12 and 18 months were enrolled and were provided with the daily nutritional intervention of one egg and 150 mL cow's milk for 90 days. Peripheral blood mononuclear cells (PBMCs) were isolated at enrolment and upon completion of the intervention. Phenotypic profiles for CD3+ cells, CD4+ cells, CD8+ cells, NKT cells, and B cells were similar in both cohorts, both before and after the intervention. However, activated B cells (CD25+) were increased after nutritional intervention in the at-risk of being stunted cohort. Several pro-inflammatory cytokines, IL-6, IFN-γ, and TNF-α, were elevated in the stunted children following the nutritional intervention. The results of the study indicate that nutritional intervention may have a role on activated B cells (CD25+) s in children who are at-risk of being stunted and may alter the capacity of PBMC to produce inflammatory cytokines in stunted children.

A case report on para-kala-azar dermal leishmaniasis: an unresolved mystery.

BACKGROUND: Post-kala-azar dermal leishmaniasis (PKDL) is a dermatosis that occurs 2-3 years after an apparently successful treatment of visceral leishmaniasis (VL). In rare cases, PKDL occurs concurrently with VL and is characterized by fever, splenomegaly, hepatomegaly or lymphadenopathy, and poor nutritional status and is known as Para-kala-azar dermal leishmaniasis (Para-KDL). Co-association of active VL in PKDL patients is documented in Africa, but very few case reports are found in South Asia. We present a case of Para-kala-azar Dermal Leishmaniasis (Para-KDL) in a 50-year-old male patient with a history of one primary Visceral Leishmaniasis (VL) and 2 times relapse of Visceral Leishmaniasis (VL). The patient presented with fever, skin lesions, and hepatosplenomegaly. Laboratory tests revealed LD bodies in the slit skin smear and splenic biopsy. The patient was treated with two cycles of Amphotericin B with Miltefosine in between cycles for 12 weeks to obtain full recovery. CONCLUSION: This case report serves as a reminder that Para-kala-azar dermal leishmaniasis can develop as a consequence of prior visceral leishmaniasis episodes, even after apparently effective therapy. Since para-kala-azar is a source of infectious spread, endemics cannot be avoided unless it is effectively recognized and treated.

StackDPPIV: A novel computational approach for accurate prediction of dipeptidyl peptidase IV (DPP-IV) inhibitory peptides.

The development of efficient and effective bioinformatics tools and pipelines for identifying peptides with dipeptidyl peptidase IV (DPP-IV) inhibitory activities from large-scale protein datasets is of great importance for the discovery and development of potential and promising antidiabetic drugs. In this study, we present a novel stacking-based ensemble learning predictor (termed StackDPPIV) designed for identification of DPP-IV inhibitory peptides. Unlike the existing method, which is based on single-feature-based methods, we combined five popular machine learning algorithms in conjunction with ten different feature encodings from multiple perspectives to generate a pool of various baseline models. Subsequently, the probabilistic features derived from these baseline models were systematically integrated and deemed as new feature representations. Finally, in order to improve the predictive performance, the genetic algorithm based on the self-assessment-report was utilized to determine a set of informative probabilistic features and then used the optimal one for developing the final meta-predictor (StackDPPIV). Experiment results demonstrated that StackDPPIV could outperform its constituent baseline models on both the training and independent datasets. Furthermore, StackDPPIV achieved an accuracy of 0.891, MCC of 0.784 and AUC of 0.961, which were 9.4%, 19.0% and 11.4%, respectively, higher than that of the existing method on the independent test. Feature analysis demonstrated that our feature representations had more discriminative ability as compared to conventional feature descriptors, which highlights the combination of different features was essential for the performance improvement. In order to implement the proposed predictor, we had built a user-friendly online web server at http://pmlabstack.pythonanywhere.com/StackDPPIV.

TGFß1 rs1800469 and SMAD4 rs10502913 polymorphisms and genetic susceptibility to colorectal cancer in Bangladeshi population.

BACKGROUND: Among Bangladeshi males and females, colorectal cancer is the fourth and fifth most prevalent cancer, respectively. Several studies have shown that the transforming growth factor beta 1 (TGFß1) gene and SMAD4 gene have a great impact on colorectal cancer. OBJECTIVE: The present study aimed to investigate whether TGFß1 rs1800469 and SMAD4 rs10502913 genetic polymorphisms are associated with susceptibility to colorectal cancer in the Bangladeshi population. METHODS AND MATERIALS: This case-control study was performed on 167 colorectal cancer patients and 162 healthy volunteers, and polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) method was employed for genotyping. RESULTS: In case of SMAD4 rs10502913 G > A polymorphism, the A allele reduced the colorectal cancer risk significantly (adjusted OR 0.35, 95% CI 0.23-0.52, p < 0.001) when compared to the G allele. It was also found that G/A and A/A genotypes of SMAD4 rs10502913 G > A polymorphism reduced the risk of colorectal cancer in comparison to the G/G genotype (G/A vs. G/G: adjusted OR 0.24, 95% CI 0.12-0.45, p < 0.001 and A/A vs. G/G: adjusted OR 0.06, 95% CI 0.02-0.21, p < 0.001). TGFß1 rs1800469 C > T polymorphism showed an elevated risk of developing colorectal cancer, although the results were not statistically significant. CONCLUSION: This study confirms the association of SMAD4 rs10502913 gene polymorphism with colorectal cancer susceptibility among the Bangladeshi population.

Deepm5C: A deep-learning-based hybrid framework for identifying human RNA N5-methylcytosine sites using a stacking strategy.

As one of the most prevalent post-transcriptional epigenetic modifications, N5-methylcytosine (m5C) plays an essential role in various cellular processes and disease pathogenesis. Therefore, it is important accurately identify m5C modifications in order to gain a deeper understanding of cellular processes and other possible functional mechanisms. Although a few computational methods have been proposed, their respective models have been developed using small training datasets. Hence, their practical application is quite limited in genome-wide detection. To overcome the existing limitations, we propose Deepm5C, a bioinformatics method for identifying RNA m5C sites throughout the human genome. To develop Deepm5C, we constructed a novel benchmarking dataset and investigated a mixture of three conventional feature-encoding algorithms and a feature derived from word-embedding approaches. Afterward, four variants of deep-learning classifiers and four commonly used conventional classifiers were employed and trained with the four encodings, ultimately obtaining 32 baseline models. A stacking strategy is effectively utilized by integrating the predicted output of the optimal baseline models and trained with a one-dimensional (1D) convolutional neural network. As a result, the Deepm5C predictor achieved excellent performance during cross-validation with a Matthews correlation coefficient and an accuracy of 0.697 and 0.855, respectively. The corresponding metrics during the independent test were 0.691 and 0.852, respectively. Overall, Deepm5C achieved a more accurate and stable performance than the baseline models and significantly outperformed the existing predictors, demonstrating the effectiveness of our proposed hybrid framework. Furthermore, Deepm5C is expected to assist community-wide efforts in identifying putative m5Cs and to formulate the novel testable biological hypothesis.

Understanding the behavioral determinants that predict barriers and enablers of screening and treatment behaviors for diabetic retinopathy among Bangladeshi women: findings from a barrier analysis.

BACKGROUND AND AIM: While early detection and timely treatments can prevent diabetic retinopathy (DR) related blindness, barriers to receiving these DR services may cause permanent sight loss. Despite having similar prevalence to diabetes and DR, women are less likely than men to perform these behaviors due to multi-faced barriers in screening and receiving follow-up treatments for DR. This study, therefore, aimed at identifying the barriers to - and enablers of - screening and follow-up treatments behaviors for DR among women aged more than 40 years with diabetes from the behavioral perspectives in Bangladesh. METHODS: This Barrier Analysis study interviewed 360 women (180 "Doers" and 180 "Non-doers") to explore twelve behavioral determinants of four DR behaviors including screening, injection of anti-vascular endothelial growth factor (anti-VEGF medication), laser therapy and vitro-retinal surgery. The data analysis was performed to calculate estimated relative risk to identify the degree of association between the determinants and behaviors, and to find statistically significant differences (at p < 0.05) in the responses between the Doers and Non-doers. RESULTS: Access to healthcare facilities was the major barrier impeding women from performing DR behaviors. Difficulty in locating DR service centers, the need to travel long distances, the inability to travel alone and during illness, challenges of paying for transportation and managing workload significantly affected women's ability to perform the behaviors. Other determinants included women's perceived self-efficacy, perceived negative consequences (e.g. fear and discomfort associated with injections or laser treatment), and cues for action. Significant perceived enablers included low cost of DR treatments, supportive attitudes by healthcare providers, government policy, and perceived social norms. CONCLUSION: The study found a host of determinants related to the barriers to and enablers of DR screening and treatment behaviors. These determinants included perceived self-efficacy (and agency), positive and negative consequences, perceived access, perceived social norms, culture, and perceived risk. Further investments are required to enhance the availability of DR services within primary and secondary health institutions along with health behavior promotion to dispel misconceptions and fears related to DR treatments.

Binocular Rivalry Impact on Macroblock-Loss Error Concealment for Stereoscopic 3D Video Transmission.

Three-dimensional video services delivered through wireless communication channels have to deal with numerous challenges due to the limitations of both the transmission channel's bandwidth and receiving devices. Adverse channel conditions, delays, or jitters can result in bit errors and packet losses, which can alter the appearance of stereoscopic 3D (S3D) video. Due to the perception of dissimilar patterns by the two human eyes, they can not be fused into a stable composite pattern in the brain and hence try to dominate by suppressing each other. Thus, a psychovisual sensation that is called binocular rivalry occurs. As a result, undetectable changes causing irritating flickering effects are seen, leading to visual discomforts such as eye strain, headache, nausea, and weariness. This study addresses the observer's quality of experience (QoE) by analyzing the binocular rivalry impact on the macroblock (MB) losses in a frame and its error propagation due to predictive frame encoding in stereoscopic video transmission systems. To simulate the processing of experimental videos, the Joint Test Model (JM) reference software has been used as it is recommended by the International Telecommunication Union (ITU). Existing error concealing techniques were then applied to the contiguous lost MBs for a variety of transmission impairments. In order to validate the authenticity of the simulated packet loss environment, several objective evaluations were carried out. Standard numbers of subjects were then engaged in the subjective testing of common 3D video sequences. The results were then statistically examined using a standard Student's t-test, allowing the impact of binocular rivalry to be compared to that of a non-rivalry error condition. The major goal is to assure error-free video communication by minimizing the negative impacts of binocular rivalry and boosting the ability to efficiently integrate 3D video material to improve viewers' overall QoE.

An Explainable EEG-Based Human Activity Recognition Model Using Machine-Learning Approach and LIME.

Electroencephalography (EEG) is a non-invasive method employed to discern human behaviors by monitoring the neurological responses during cognitive and motor tasks. Machine learning (ML) represents a promising tool for the recognition of human activities (HAR), and eXplainable artificial intelligence (XAI) can elucidate the role of EEG features in ML-based HAR models. The primary objective of this investigation is to investigate the feasibility of an EEG-based ML model for categorizing everyday activities, such as resting, motor, and cognitive tasks, and interpreting models clinically through XAI techniques to explicate the EEG features that contribute the most to different HAR states. The study involved an examination of 75 healthy individuals with no prior diagnosis of neurological disorders. EEG recordings were obtained during the resting state, as well as two motor control states (walking and working tasks), and a cognition state (reading task). Electrodes were placed in specific regions of the brain, including the frontal, central, temporal, and occipital lobes (Fz, C1, C2, T7, T8, Oz). Several ML models were trained using EEG data for activity recognition and LIME (Local Interpretable Model-Agnostic Explanations) was employed for interpreting clinically the most influential EEG spectral features in HAR models. The classification results of the HAR models, particularly the Random Forest and Gradient Boosting models, demonstrated outstanding performances in distinguishing the analyzed human activities. The ML models exhibited alignment with EEG spectral bands in the recognition of human activity, a finding supported by the XAI explanations. To sum up, incorporating eXplainable Artificial Intelligence (XAI) into Human Activity Recognition (HAR) studies may improve activity monitoring for patient recovery, motor imagery, the healthcare metaverse, and clinical virtual reality settings.

Sex difference and socioeconomic inequality of underweight, overweight and obesity among adult population in Bangladesh.

Background: Due to rapid socioeconomic development and epidemiological transition, socioeconomic inequality of underweight, overweight, and obesity are becoming a public health concern in Bangladesh. There is a need for country-specific evidence of nutrition inequalities in Bangladesh. Aim: The aim of the study was to measure socioeconomic inequality and decomposition analysis along with the sex differences in underweight, overweight, and obesity among the adult population. Methods: A secondary data analysis was performed in the Bangladesh Demographic and Health Survey (BDHS) 2017-18, a cross-sectional survey used a multi-stage cluster sampling technique. Sociodemographic variables including age, sex, education, socioeconomic status, marital status, and anthropometric data of height and weight were considered for analysis. Body mass index was used for defining underweight, overweight, and obesity. Concentration index (CI) and decomposition analysis were performed for underweight, overweight, and obesity. Results: The proportion of underweight was 15.0%, overweight (23.0%), and obese (5.0%). Underweight was higher in males, whereas overweight and obesity were higher in females. The CI of underweight was -0.121 (p < 0.001), indicating socioeconomic inequality concentrated on lowering socioeconomic status; living in rural areas contributed 14.2% to this inequality. The CI of overweight and obesity was 0.213 (p < 0.001) and 0.142 (p < 0.001), respectively, indicating that inequalities of overweight and obesity concentrated in higher socioeconomic status; urban residency contributed 14.1% and 18.0% to socioeconomic inequality of overweight and obesity. Conclusion: Underweight remains a significant problem for poor people in rural areas, but overweight and obesity were highly prevalent in the higher socioeconomic status of urban areas. Education level and young age group significantly contribute to the socioeconomic inequality of malnutrition. A more detailed epidemiological study is required to understand the causes of socioeconomic disparities of nutritional status in Bangladesh.

Seasonal variation in the association between household food insecurity and child undernutrition in Bangladesh: Mediating role of child dietary diversity.

Household food insecurity (HFI) and child dietary diversity (CDD) are variable across seasons. We examined seasonal variation in HFI and child undernutrition association and tested how CDD mediates this association. We analyzed data for 26,353 children aged 6-59 months drawn from nationally representative cross-sectional Food Security and Nutrition Surveillance Project data collected during 2012-2014 in Bangladesh across three seasons annually: Post-Aman harvest (January-April); Monsoon (May-August); and Post-Aus harvest (September-December). Multivariable logistic regression analysis adjusted for individual, maternal, household and geographical characteristics reveals that children of food-insecure households were more likely than food-secure households to be stunted (adjusted odds ratio, AOR: 1.12; 95% confidence interval, CI: 1.02-1.23; p < 0.05), wasted (AOR: 1.21; 95% CI: 1.05-1.39; p < 0.01) and underweight (AOR: 1.16; 95% CI: 1.04-1.3; p < 0.01). CDD mediated 6.1% of the total effect of HFI on underweight. These findings varied across seasons. HFI was associated with greater odds of underweight during Monsoon (AOR: 1.32; 95% CI: 1.08-1.62; p < 0.01) and Post-Aus (AOR: 1.21; 95% CI: 1.06-1.37; p < 0.01) while wasting during Post-Aus (AOR: 1.65; 95% CI: 1.35-2.01; p < 0.001). CDD largely mediated the total effect of HFI on underweight during the Post-Aman in 2012-2014 (23.2%). CDD largely mediated the total effect of HFI on wasting (39.7%) during Post-Aman season in 2014 and on underweight (13.7%) during the same season in 2012. These findings demonstrate that HFI is seasonally associated with child undernutrition and mediated by CDD as well in Bangladesh and seasonality and diversity should be considered while designing appropriate population-level food-based interventions to resolve child undernutrition.