Spatiotemporal variability of lake surface water temperature and water quality parameters and its interrelationship with water hyacinth biomass in Lake Tana, Ethiopia.

Urbanization, agriculture, and climate change affect water quality and water hyacinth growth in lakes. This study examines the spatiotemporal variability of lake surface water temperature, turbidity, and chlorophyll-a (Chl-a) and their association with water hyacinth biomass in Lake Tana. MODIS Land/ Lake surface water temperature (LSWT), Sentinel 2 MSI Imagery, and in-situ water quality data were used. Validation results revealed strong positive correlations between MODIS LSWT and on-site measured water temperature (R = 0.90), in-situ turbidity and normalized difference turbidity index (NDTI) (R = 0.92), and in-situ Chl-a and normalized difference chlorophyll index (NDCI) (R = 0.84). LSWT trends varied across the lake, with increasing trends in the northeastern, northwestern, and southwestern regions and decreasing trends in the western, southern, and central areas (2001-2022). The spatial average LSWT trend decreased significantly in pre-rainy (0.01 ℃/year), rainy (0.02 ℃/year), and post-rainy seasons (0.01℃/year) but increased non-significantly in the dry season (0.00 ℃/year) (2001-2022, P < 0.05). Spatial average turbidity decreased significantly in all seasons, except in the pre-rainy season (2016-2022). Likewise, spatial average Chl-a decreased significantly in pre-rainy and rainy seasons, whereas it showed a non-significant increasing trend in the dry and post-rainy seasons (2016-2022). Water hyacinth biomass was positively correlated with LSWT (R = 0.18) but negatively with turbidity (R = -0.33) and Chl-a (R = -0.35). High spatiotemporal variability was observed in LSWT, turbidity, and Chl-a, along with overall decreasing trends. The findings suggest integrated management strategies to balance water hyacinth eradication and its role in water purification. The results will be vital in decision support systems and preparing strategic plans for sustainable water resource management, environmental protection, and pollution prevention.

Efficient geospatial mapping of buildings, woodlands, water and roads from aerial imagery using deep learning.

As more aerial imagery becomes readily available, massive volumes of data are being gathered constantly. Several groups can benefit from the data provided by this geographical imagery. However, it is time-consuming to manually analyze each image to gain information on land cover. This research suggests using deep learning methods for precise and rapid pixel-by-pixel classification of aerial imagery for land cover analysis, which would be a significant step forward in resolving this issue. The suggested method has several steps, such as the augmentation and transformation of data, the selection of deep learning models, and the final prediction. The study uses the three most popular deep learning models (Vanilla-UNet, ResNet50 UNet, and DeepLabV3 ResNet50) for the experiments. According to the experimental results, the ResNet50 UNet model achieved an accuracy of 94.37%, the DeepLabV3 ResNet50 model achieved an accuracy of 94.77%, and the Vanilla-UNet model achieved an accuracy of 91.31%. The accuracy, precision, recall, and F1-score of DeepLabV3 and ResNet50 are higher than those of the other two models. The proposed approach is also compared to the existing UNet approach, and the proposed approaches have produced greater probability prediction scores than the conventional UNet model for all classes. Our approach outperforms model DeepLabV3 ResNet50 on aerial image datasets based on the performance.

Neural correlates of motor imagery and execution in real-world dynamic behavior: evidence for similarities and differences.

A large body of evidence shows that motor imagery and action execution behaviors result from overlapping neural substrates, even in the absence of overt movement during motor imagery. To date it is unclear how neural activations in motor imagery and execution compare for naturalistic whole-body movements, such as walking. Neuroimaging studies have not directly compared imagery and execution during dynamic walking movements. Here we recorded brain activation with mobile EEG during walking compared to during imagery of walking, with mental counting as a control condition. We asked 24 healthy participants to either walk six steps on a path, imagine taking six steps, or mentally count from one to six. We found beta and alpha power modulation during motor imagery resembling action execution patterns; a correspondence not found performing the control task of mental counting. Neural overlap occurred early in the execution and imagery walking actions, suggesting activation of shared action representations. Remarkably, a distinctive walking-related beta rebound occurred both during action execution and imagery at the end of the action suggesting that, like actual walking, motor imagery involves resetting or inhibition of motor processes. However, we also found that motor imagery elicits a distinct pattern of more distributed beta activity, especially at the beginning of the task. These results indicate that motor imagery and execution of naturalistic walking involve shared motor-cognitive activations, but that motor imagery requires additional cortical resources.

Non-invasive anticipation of infusion taste in fine-manipulated green teas through hyperspectral appearance analysis guided by ECG content.

The high catechin content in summer-to-autumn tea leaves often results in strong, unpleasant tastes, leading to significant resource waste and economic losses due to lignification of unpicked leaves. This study aims to improve the taste quality of summer-to-autumn green teas by combining fine manipulation techniques with hyperspectral observation. Fine manipulation notably enhanced infusion taste quality, particularly in astringency and its aftertaste (aftertasteA). Using Partial Least Squares Discriminant Analysis (PLSDA) on hyperspectral data, 100% prediction accuracy was achieved for dry tea appearance in the near-infrared spectrum. Astringency and aftertasteA correlated with hyperspectral data, allowing precise estimation with over 90% accuracy in both visible and near-infrared spectrums. Epicatechin gallate (ECG) emerged as a key taste compound, enabling non-invasive taste prediction. Practical applications in processing and quality control are demonstrated by the derived equations (Astringency = -0.88 × ECG + 45.401, AftertasteA = -0.353 × ECG + 18.609), highlighting ECG's role in shaping green tea taste profiles.

From anticipation to action: A RCT on mental imagery exercises in daily life as a motivational amplifier for individuals with depressive symptoms.

Encouraging engagement in rewarding or pleasant activities is one of the most important treatment goals for depression. Mental imagery exercises have been shown to increase the motivation for planned behaviour in the lab but it is unclear whether this is also the case in daily life. Therefore, we aimed to investigate the effect of mental imagery exercises on motivation and behaviour in daily life. Participants with depressive symptoms (N = 59) were randomly assigned to a group receiving mental imagery (MI) exercises or a control group receiving relaxation (RE) exercises via study phones. We employed an experience sampling design with 10 assessments per day for 10 days (three days baseline, four days with two exercises per day and three days post-intervention). Data was analysed using t-tests and multilevel linear regression analyses. As predicted, MI exercises enhanced motivation and reward anticipation during the intervention phase compared to RE. However, MI did not enhance active behaviour or strengthen the temporal association from reward anticipation (t-1) to active behaviour (t). Mental imagery exercises can act as a motivational amplifier but its effects on behaviour and real-life reward processes remain to be elucidated.

A novel temporal-frequency combination pattern optimization approach based on information fusion for motor imagery BCIs.

Motor imagery (MI) stands as a powerful paradigm within Brain-Computer Interface (BCI) research due to its ability to induce changes in brain rhythms detectable through common spatial patterns (CSP). However, the raw feature sets captured often contain redundant and invalid information, potentially hindering CSP performance. Methodology-wise, we propose the Information Fusion for Optimizing Temporal-Frequency Combination Pattern (IFTFCP) algorithm to enhance raw feature optimization. Initially, preprocessed data undergoes simultaneous processing in both time and frequency domains via sliding overlapping time windows and filter banks. Subsequently, we introduce the Pearson-Fisher combinational method along with Discriminant Correlation Analysis (DCA) for joint feature selection and fusion. These steps aim to refine raw electroencephalogram (EEG) features. For precise classification of binary MI problems, an Radial Basis Function (RBF)-kernel Support Vector Machine classifier is trained. To validate the efficacy of IFTFCP and evaluate it against other techniques, we conducted experimental investigations using two EEG datasets. Results indicate a notably superior classification performance, boasting an average accuracy of 78.14% and 85.98% on dataset 1 and dataset 2, which is better than other methods outlined in this article. The study's findings suggest potential benefits for the advancement of MI-based BCI strategies, particularly in the domain of feature fusion.

Prevalence and 20-year trends in meditation, yoga, guided imagery and progressive relaxation use among US adults from 2002 to 2022.

Meditation, yoga, guided imagery, and progressive relaxation are promoted as complementary approaches for health and wellbeing in the United States, but their uptake by different sociodemographic groups is unclear. This study assessed the prevalence and 20 year trends in the use of these practices in US adults between 2002-2022. We examined practice use and associations with sociodemographic and health factors in a population-weighted analysis of n = 134,959 participants across 5 cycles of the National Health Interview Survey. The overall use of meditation (18.3%, 60.53 million), yoga (16.8%, 55.78 million) and guided imagery/progressive relaxation (6.7%, 22.22 million) increased significantly from 2002 to 2022. Growth was consistent across most sociodemographic and health strata, however users of 'Other' race (comprising 54% Indigenous Americans, Odds Ratios; ORs = 1.28-1.70) and users with moderate (ORs = 1.19-1.29) psychological distress were overrepresented across all practices, and those with severe psychological distress were overrepresented in meditation (OR = 1.33) and guided imagery/progressive relaxation (OR = 1.42). Meditation use has accelerated over time for 65 + year olds (OR = 4.22), people not accessing mental health care (OR = 1.39), and less educated (OR = 4.02) groups, potentially reflecting unmet health needs. Health professionals should consider the extensive use of complementary practices in service and treatment planning and consider their risks and benefits.

Characterization and classification of kinesthetic motor imagery levels.

OBJECTIVE: Kinesthetic Motor Imagery (KMI) represents a robust brain paradigm intended for electroencephalography (EEG)-based commands in brain-computer interfaces (BCIs). However, ensuring high accuracy in multi-command execution remains challenging, with data from C3 and C4 electrodes reaching up to 92% accuracy. This paper aims to characterize and classify EEG-based KMI of multilevel muscle contraction without relying on primary motor cortex signals. Approach. A new method based on Hurst exponents is introduced to characterize EEG signals of multilevel KMI of muscle contraction from electrodes placed on the premotor, dorsolateral prefrontal, and inferior parietal cortices. EEG signals were recorded during a hand-grip task at four levels of muscle contraction (0, 10, 40, and 70% of the maximal isometric voluntary contraction). The task was executed under two conditions: first, physically, to train subjects in achieving muscle contraction at each level, followed by mental imagery under the KMI paradigm for each contraction level. EMG signals were recorded in both conditions to correlate muscle contraction execution, whether correct or null accurately. Independent component analysis (ICA) maps EEG signals from the sensor to the source space for preprocessing. For characterization, three algorithms based on Hurst exponents were used: the original (HO), using partitions (HRS), and applying semivariogram (HV). Finally, seven classifiers were used: Bayes network (BN), naive Bayes (NB), support vector machine (SVM), random forest (RF), random tree (RT), multilayer perceptron (MP), and k-nearest neighbours (kNN). Main results. A combination of the three Hurst characterization algorithms produced the highest average accuracy of 96.42% from kNN, followed by MP (92.85%), SVM (92.85%), NB (91.07%), RF (91.07%), BN (91.07%), and RT (80.35%). of 96.42% for kNN. Significance. Results show the feasibility of KMI multilevel muscle contraction detection and, thus, the viability of non-binary EEG-based BCI applications without using signals from the motor cortex.

Relaxation intervention to improve diabetic foot ulcer healing: protocol for a pilot study with a nested qualitative study.

OBJECTIVE: A mixed-methods approach nested in a pilot three-arm randomised controlled trial (RCT) was conducted to evaluate the feasibility and acceptability of an intervention of progressive muscle relaxation with guided imagery (experimental group) compared to a neutral guided imagery placebo (active control group) and a group that did not receive any psychological intervention (passive control group). The purpose was to inform a future definitive RCT that will test its effectiveness. Qualitatively, this study examined patients and health professionals' perspectives regarding the relaxation intervention, in order to assess the acceptability and applicability of relaxation as an adjuvant therapy. METHOD: Participants must have had a diagnosis of diabetes and diabetic foot disease; one or two active hard-to-heal ulcers at the time of the assessment; and clinical levels of stress or anxiety or depression. Participants were randomised and assessed at three timepoints after the first hospital consultation for hard-to-heal diabetic foot ulcer (DFU). RESULTS: Rates of eligibility, recruitment, refusal, adherence to study protocol, participation in follow-up and dropout, and patients' satisfaction with the relaxation intervention were assessed as primary outcomes. Secondary outcomes were DFU healing; patients' DFU-related quality of life; physical and mental quality of life; perceived stress; emotional distress; adherence to DFU care; perceptions of DFU; as well as arterial systolic/diastolic pressure and heart rate. CONCLUSION: The results of this pilot study contributed to clarification and better elucidation of the benefits of relaxation techniques regarding patients' HRQoL and DFU healing. DECLARATION OF INTEREST: Funding: This study was conducted at the Psychology Research Centre (CIPsi/UM) School of Psychology, University of Minho, Portugal and supported by the Foundation for Science and Technology (FCT) through the Portuguese State Budget (UIDB/01662/2020) and by a PhD fellowship from FCT assigned to GF (SFRH/BD/131780/2017) and an FCT grant (PTDC/PSI-GER/28163/2017) assigned to MGP. The authors have no conflicts of interest to declare.

Combining Google Earth historical imagery and UAV photogrammetry for urban development analysis.

Rural-urban migration often triggers additional demand for housing and infrastructural development to cater for the growing population in urban areas. Consequently, town planners and urban development authorities need to understand the urban development trend to make sustainable urban planning decisions. Yet, methods to analyse changes and trends in urban spatial development are often complex and require costly data collection. This article thus presents a simplified method to analyse the urban development trend in an area. The method integrates Google Earth (GE) historical imagery (baseline data) and unmanned aerial vehicle (UAV) photogrammetry (recent data) to quantify the changes over time. This approach can be applied to study the urban development trends in low-income countries with budget constraints. The method is discussed under four main headings: (1) background, (2) method details, (3) limitations, and (4) conclusion.•Google Earth historical image can be extracted with its associated world file.•The population of an area can be estimated by using average household size data and the number of residential buildings in the area.•The building height ratio can be used to ascertain if the land is being used parsimoniously.

Changes in corticospinal excitability during motor imagery by physical practice of a force production task: Effect of the rate of force development during practice.

Transcranial magnetic stimulation studies have indicated that the physical practice of a force production task increases corticospinal excitability during motor imagery (MI) of that task. However, it is unclear whether this practice-induced facilitation of corticospinal excitability during MI depends on a repeatedly practiced rate of force development (RFD). We aimed to investigate whether corticospinal excitability during MI of an isometric force production task is facilitated only when imagining the motor task with the same RFD as the physically practiced RFD. Furthermore, we aimed to examine whether corticospinal excitability during MI only occurs immediately after physical practice or is maintained. Twenty-eight right-handed young adults practiced isometric ramp force production using right index finger abduction. Half of the participants (high group) practiced the force production with high RFD, and the other half (low group) practiced the force production with low RFD. Questionnaire scores indicating MI ability were similar in the two groups. We examined the force error relative to the target force during the force production task without visual feedback, and motor evoked potential (MEP) amplitudes of the first dorsal interosseous (FDI) and abductor pollicis brevis (APB) muscles during the MI of the force production task under practiced and unpracticed RFD conditions before, immediately after, and 20 min after physical practice. Our results demonstrated that the force error in both RFD conditions significantly decreased immediately after physical practice, irrespective of the RFD condition practiced. In the high group, the MEP amplitude of the FDI muscle during MI in the high RFD condition significantly increased immediately after practice compared to that before, whereas the MEP amplitude 20 min after practice was not significantly different from that before practice. Conversely, the MEP amplitude during MI in the high RFD condition did not change significantly in the low group, and neither group had significant changes in MEP amplitude during MI in the low RFD condition. The facilitatory effect of corticospinal excitability during MI with high RFD observed only immediately after physical practice in the high RFD condition may reflect short-term functional changes in the primary motor cortex induced by physical practice.

An optimized EEGNet decoder for decoding motor image of four class fingers flexion.

As a cutting-edge technology of connecting biological brain and external devices, brain-computer interface (BCI) exhibits promising applications on extensive fields such as medical and military. As for the disable individuals with four limbs losing the motor functions, it is a potential treatment way to drive mechanical equipments by the means of non-invasive BCI, which is badly depended on the accuracy of the decoded electroencephalogram (EEG) singles. In this study, an explanatory convolutional neural network namely EEGNet based on SimAM attention module was proposed to enhance the accuracy of decoding the EEG singles of index and thumb fingers for both left and right hand using sensory motor rhythm (SMR). An average classification accuracy of 72.91% the data of eight healthy subjects was obtained, which were captured from the one second before finger movement to two seconds after action. Furthermore, the character of event-related desynchronization (ERD) and event related synchronization (ERS) of index and thumb fingers was also studied in this study. These findings have significant importance for controlling external devices or other rehabilitation equipment using BCI in a fine way.

Combined non-invasive neuromodulation using transcranial direct current stimulation, motor imagery and action observation for motor, cognitive and functional recovery in cortico-basal degeneration: a single case study.

This case report presents a comprehensive assessment and therapeutic intervention using non-invasive motor cortex neuromodulation for a 70-year-old female patient diagnosed with corticobasal degeneration (CBD). The study followed the CARE guidelines. The patient meets the criteria for probable CBD, with neuroimaging evidence of exclusively cortical impairment. The patient underwent a non-invasive neuromodulation protocol involving transcranial direct current stimulation (tDCS) and action observation plus motor imagery (AO+MI). The neuromodulation protocol comprised 20 sessions involving tDCS over the primary motor cortex and combined AO+MI. Anodal tDCS was delivered a 2 mA excitatory current for 20 minutes. AO+MI focused on lower limb movements, progressing over four weeks with video observation and gradual execution, both weekly and monthly. The neuromodulation techniques were delivered online (i.e. applied simultaneously in each session). Outcome measures were obtained at baseline, post-intervention and follow-up (1 month later), and included motor (lower limb), cognitive/neuropsychological and functional assessments. Walking speed improvements were not observed, but balance (Berg Balance Scale) and functional strength (Five Times Sit-to-Stand Test) improved post-treatment. Long-term enhancements in attentional set-shifting, inhibitory control, verbal attentional span, and working memory were found. There was neurophysiological evidence of diminished intracortical inhibition. Functional changes included worsening in Cortico Basal Ganglia Functional Scale score. Emotional well-being and general health (SF-36) increased immediately after treatment but were not sustained, while Falls Efficacy Scale International showed only long-term improvement. The findings suggest potential benefits of the presented neuromodulation protocol for CBD patients, highlighting multifaceted outcomes in motor, cognitive, and functional domains.

Protocol for a home-based self-delivered prehabilitation intervention to proactively reduce fall risk in older adults: a pilot randomized controlled trial of transcranial direct current stimulation and motor imagery.

BACKGROUND: Several changes occur in the central nervous system with increasing age that contribute toward declines in mobility. Neurorehabilitation has proven effective in improving motor function though achieving sustained behavioral and neuroplastic adaptations is more challenging. While effective, rehabilitation usually follows adverse health outcomes, such as injurious falls. This reactive intervention approach may be less beneficial than prevention interventions. Therefore, we propose the development of a prehabilitation intervention approach to address mobility problems before they lead to adverse health outcomes. This protocol article describes a pilot study to examine the feasibility and acceptability of a home-based, self-delivered prehabilitation intervention that combines motor imagery (mentally rehearsing motor actions without physical movement) and neuromodulation (transcranial direct current stimulation, tDCS; to the frontal lobes). A secondary objective is to examine preliminary evidence of improved mobility following the intervention. METHODS: This pilot study has a double-blind randomized controlled design. Thirty-four participants aged 70-95 who self-report having experienced a fall within the prior 12 months or have a fear of falling will be recruited. Participants will be randomly assigned to either an active or sham tDCS group for the combined tDCS and motor imagery intervention. The intervention will include six 40-min sessions delivered every other day. Participants will simultaneously practice the motor imagery tasks while receiving tDCS. Those individuals assigned to the active group will receive 20 min of 2.0-mA direct current to frontal lobes, while those in the sham group will receive 30 s of stimulation to the frontal lobes. The motor imagery practice includes six instructional videos presenting different mobility tasks related to activities of daily living. Prior to and following the intervention, participants will undergo laboratory-based mobility and cognitive assessments, questionnaires, and free-living activity monitoring. DISCUSSION: Previous studies report that home-based, self-delivered tDCS is safe and feasible for various populations, including neurotypical older adults. Additionally, research indicates that motor imagery practice can augment motor learning and performance. By assessing the feasibility (specifically, screening rate (per month), recruitment rate (per month), randomization (screen eligible who enroll), retention rate, and compliance (percent of completed intervention sessions)) and acceptability of the home-based motor imagery and tDCS intervention, this study aims to provide preliminary data for planning larger studies. TRIAL REGISTRATION: This study is registered on ClinicalTrials.gov (NCT05583578). Registered October 13, 2022. https://www. CLINICALTRIALS: gov/study/NCT05583578.

STaRNet: A spatio-temporal and Riemannian network for high-performance motor imagery decoding.

Brain-computer interfaces (BCIs), representing a transformative form of human-computer interaction, empower users to interact directly with external environments through brain signals. In response to the demands for high accuracy, robustness, and end-to-end capabilities within BCIs based on motor imagery (MI), this paper introduces STaRNet, a novel model that integrates multi-scale spatio-temporal convolutional neural networks (CNNs) with Riemannian geometry. Initially, STaRNet integrates a multi-scale spatio-temporal feature extraction module that captures both global and local features, facilitating the construction of Riemannian manifolds from these comprehensive spatio-temporal features. Subsequently, a matrix logarithm operation transforms the manifold-based features into the tangent space, followed by a dense layer for classification. Without preprocessing, STaRNet surpasses state-of-the-art (SOTA) models by achieving an average decoding accuracy of 83.29% and a kappa value of 0.777 on the BCI Competition IV 2a dataset, and 95.45% accuracy with a kappa value of 0.939 on the High Gamma Dataset. Additionally, a comparative analysis between STaRNet and several SOTA models, focusing on the most challenging subjects from both datasets, highlights exceptional robustness of STaRNet. Finally, the visualizations of learned frequency bands demonstrate that temporal convolutions have learned MI-related frequency bands, and the t-SNE analyses of features across multiple layers of STaRNet exhibit strong feature extraction capabilities. We believe that the accurate, robust, and end-to-end capabilities of the STaRNet will facilitate the advancement of BCIs.

Use of Optical and Radar Imagery for Crop Type Classification in Africa: A Review.

Multi-source remote sensing-derived information on crops contributes significantly to agricultural monitoring, assessment, and management. In Africa, some challenges (i.e., small-scale farming practices associated with diverse crop types and agricultural system complexity, and cloud coverage during the growing season) can imped agricultural monitoring using multi-source remote sensing. The combination of optical remote sensing and synthetic aperture radar (SAR) data has emerged as an opportune strategy for improving the precision and reliability of crop type mapping and monitoring. This work aims to conduct an extensive review of the challenges of agricultural monitoring and mapping in Africa in great detail as well as the current research progress of agricultural monitoring based on optical and Radar satellites. In this context optical data may provide high spatial resolution and detailed spectral information, which allows for the differentiation of different crop types based on their spectral signatures. However, synthetic aperture radar (SAR) satellites can provide important contributions given the ability of this technology to penetrate cloud cover, particularly in African tropical regions, as opposed to optical data. This review explores various combination techniques employed to integrate optical and SAR data for crop type classification and their applicability and limitations in the context of African countries. Furthermore, challenges are discussed in this review as well as and the limitations associated with optical and SAR data combination, such as the data availability, sensor compatibility, and the need for accurate ground truth data for model training and validation. This study also highlights the potential of advanced modelling (i.e., machine learning algorithms, such as support vector machines, random forests, and convolutional neural networks) in improving the accuracy and automation of crop type classification using combined data. Finally, this review concludes with future research directions and recommendations for utilizing optical and SAR data combination techniques in crop type classification for African agricultural systems. Furthermore, it emphasizes the importance of developing robust and scalable classification models that can accommodate the diversity of crop types, farming practices, and environmental conditions prevalent in Africa. Through the utilization of combined remote sensing technologies, informed decisions can be made to support sustainable agricultural practices, strengthen nutritional security, and contribute to the socioeconomic development of the continent.

Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data?

Spectral imaging has revolutionisedvarious fields by capturing detailed spatial and spectral information. However, its high cost and complexity limit the acquisition of a large amount of data to generalise processes and methods, thus limiting widespread adoption. To overcome this issue, a body of the literature investigates how to reconstruct spectral information from RGB images, with recent methods reaching a fairly low error of reconstruction, as demonstrated in the recent literature. This article explores the modification of information in the case of RGB-to-spectral reconstruction beyond reconstruction metrics, with a focus on assessing the accuracy of the reconstruction process and its ability to replicate full spectral information. In addition to this, we conduct a colorimetric relighting analysis based on the reconstructed spectra. We investigate the information representation by principal component analysis and demonstrate that, while the reconstruction error of the state-of-the-art reconstruction method is low, the nature of the reconstructed information is different. While it appears that the use in colour imaging comes with very good performance to handle illumination, the distribution of information difference between the measured and estimated spectra suggests that caution should be exercised before generalising the use of this approach.

An end-to-end multi-task motor imagery EEG classification neural network based on dynamic fusion of spectral-temporal features.

Electroencephalograph (EEG) brain-computer interfaces (BCI) have potential to provide new paradigms for controlling computers and devices. The accuracy of brain pattern classification in EEG BCI is directly affected by the quality of features extracted from EEG signals. Currently, feature extraction heavily relies on prior knowledge to engineer features (for example from specific frequency bands); therefore, better extraction of EEG features is an important research direction. In this work, we propose an end-to-end deep neural network that automatically finds and combines features for motor imagery (MI) based EEG BCI with 4 or more imagery classes (multi-task). First, spectral domain features of EEG signals are learned by compact convolutional neural network (CCNN) layers. Then, gated recurrent unit (GRU) neural network layers automatically learn temporal patterns. Lastly, an attention mechanism dynamically combines (across EEG channels) the extracted spectral-temporal features, reducing redundancy. We test our method using BCI Competition IV-2a and a data set we collected. The average classification accuracy on 4-class BCI Competition IV-2a was 85.1 % ± 6.19 %, comparable to recent work in the field and showing low variability among participants; average classification accuracy on our 6-class data was 64.4 % ± 8.35 %. Our dynamic fusion of spectral-temporal features is end-to-end and has relatively few network parameters, and the experimental results show its effectiveness and potential.

Alcohol imagery in popular films in China, 2001-2020.

This study aims to identify the level and trend of alcohol imagery in popular films in China from 2001 to 2020. We divided the running time of the annual 20 top-grossing films in China into 5-min intervals and coded those containing alcohol imagery, the presence of warnings, whether the imagery was related to minors and alcohol brands. Results showed that alcohol imagery occurred in 90.75% (363/400) of the films and 25.26% (2380/9423) of the intervals; these proportions remained stable over time. No film containing alcohol imagery had warnings, alcohol imagery related to minors appeared each year, and 103 alcohol brands were present in 185 intervals across 93 of the 400 films. Chinese films contained more alcohol imagery than international films. National policies are required to restrict alcohol imagery in films and to reduce the availability of such films for viewing by young people.

Vividness of visual imagery is associated with the effect of relaxation response meditation training in elderly people with nonorganic insomnia: A randomized, double-blind, multi-center clinical trial.

BACKGROUND: This study aims to explore the efficacy of Relaxation Response Meditation Training (RRMT) on elderly individuals with different levels of vividness of visual imagery. METHODS: In this randomized controlled, double-blind, multi-center clinical trial, we recruited a total of 136 elderly individuals who were over 60 years with nonorganic sleep disorders to participate in a 4-week RRMT intervention from October 2020 to October 2022. The intervention occurred twice a week, totaling eight times. These individuals were divided into high and low groups based on the vividness of visual imagery, and then randomly assigned to either the control or intervention groups, as follows: low-visualizers intervention group (LI group); low-visualizers control group (LC group); high-visualizers intervention group (HI group); high-visualizers control group (HC group). Their social and psychological parameters were assessed before and after the intervention by the Pittsburgh Sleep Quality Index (PSQI), the Revised Piper's fatigue scale (RPFS), General well-being scale (GWB), and Satisfaction rating. The alpha waves of patients were also collected through electroencephalogram to assess their level of relaxation. RESULTS: Compared to the LI group, the HI group had a greater reduction rate in the PSQI score [25.2 % (18.8 % to 31.7 %), P < 0∙001], shorter sleep latency (P = 0.001), lower frequency of sleep medication (P < 0.001), lower PSQI scores (P < 0.001), and higher GWB scores (P < 0.001). There were significant differences in all indicators in the HI group vs. HC group and in the LI group vs. LC group. In the first five relaxation training sessions, there was no statistically significant difference in the proportion of α waves between the LI group and the LC group; however, from the sixth session onward, we observed a statistically significant difference (t = 2.86, P = 0.019)，while The HI group and HC group showing significant differences in the first relaxation training session (t = 4.464, P < 0.001). There was a statistically significant difference in subjective satisfaction between the intervention group and the control group (x2 = 49.605, P < 0.001). CONCLUSION: In this study, we found that most elderly people benefitted from RRMT regardless of their vividness of visual imagery. However, low-visualizers experienced slower and less effective results, so these patients may benefit more from alternative approaches.