Perceived Mental Workload Classification Using Intermediate Fusion Multimodal Deep Learning.

A lot of research has been done on the detection of mental workload (MWL) using various bio-signals. Recently, deep learning has allowed for novel methods and results. A plethora of measurement modalities have proven to be valuable in this task, yet studies currently often only use a single modality to classify MWL. The goal of this research was to classify perceived mental workload (PMWL) using a deep neural network (DNN) that flexibly makes use of multiple modalities, in order to allow for feature sharing between modalities. To achieve this goal, an experiment was conducted in which MWL was simulated with the help of verbal logic puzzles. The puzzles came in five levels of difficulty and were presented in a random order. Participants had 1 h to solve as many puzzles as they could. Between puzzles, they gave a difficulty rating between 1 and 7, seven being the highest difficulty. Galvanic skin response, photoplethysmograms, functional near-infrared spectrograms and eye movements were collected simultaneously using LabStreamingLayer (LSL). Marker information from the puzzles was also streamed on LSL. We designed and evaluated a novel intermediate fusion multimodal DNN for the classification of PMWL using the aforementioned four modalities. Two main criteria that guided the design and implementation of our DNN are modularity and generalisability. We were able to classify PMWL within-level accurate (0.985 levels) on a seven-level workload scale using the aforementioned modalities. The model architecture allows for easy addition and removal of modalities without major structural implications because of the modular nature of the design. Furthermore, we showed that our neural network performed better when using multiple modalities, as opposed to a single modality. The dataset and code used in this paper are openly available.

Polythermal structure of a Himalayan debris-covered glacier revealed by borehole thermometry.

Runoff from high-elevation debris-covered glaciers represents a crucial water supply for millions of people in the Hindu Kush-Himalaya region, where peak water has already passed in places. Knowledge of glacier thermal regime is essential for predicting dynamic and geometric responses to mass balance change and determining subsurface drainage pathways, which ultimately influence proglacial discharge and hence downstream water availability. Yet, deep internal ice temperatures of these glaciers are unknown, making projections of their future response to climate change highly uncertain. Here, we show that the lower part of the ablation area of Khumbu Glacier, a high-elevation debris-covered glacier in Nepal, may contain ~56% temperate ice, with much of the colder shallow ice near to the melting-point temperature (within 0.8 °C). From boreholes drilled in the glacier's ablation area, we measured a minimum ice temperature of -3.3 °C, and even the coldest ice we measured was 2 °C warmer than the mean annual air temperature. Our results indicate that high-elevation Himalayan glaciers are vulnerable to even minor atmospheric warming.

Cataract surgical coverage and outcome in the Tibet Autonomous Region of China.

BACKGROUND: A recently published, population based survey of the Tibet Autonomous Region (TAR) of China reported on low vision, blindness, and blinding conditions. This paper presents detailed findings from that survey regarding cataract, including prevalence, cataract surgical coverage, surgical outcome, and barriers to use of services. METHODS: The Tibet Eye Care Assessment (TECA) was a prevalence survey of people from randomly selected households from three of the seven provinces of the TAR (Lhoka, Nakchu, and Lingzhr), representing its three main environmental regions. The survey, conducted in 1999 and 2000, assessed visual acuity, cause of vision loss, and eye care services. RESULTS: Among the 15,900 people enumerated, 12,644 were examined (79.6%). Cataract prevalence was 5.2% and 13.8%, for the total population, and those over age 50, respectively. Cataract surgical coverage (vision <6/60) for people age 50 and older (85-90% of cataract blind) was 56% overall, 70% for men and 47% for women. The most common barriers to use of cataract surgical services were distance and cost. In the 216 eyes with cataract surgery, 60% were aphakic and 40% were pseudophakic. Pseudophakic surgery left 19% of eyes blind (<6/60) and an additional 20% of eyes with poor vision (6/24-6/60). Aphakic surgery left 24% of eyes blind and an additional 21% of eyes with poor vision. Even though more women remained blind than men, 28% versus 18% respectively, the different was not statistically significant (p = 0.25). CONCLUSIONS: Cataract surgical coverage was remarkably high despite the difficulty of providing services to such an isolated and sparse population. Cataract surgical outcome was poor for both aphakic and pseudophakic surgery. Two main priorities are improving cataract surgical quality and cataract surgical coverage, particularly for women.

Blindness and eye diseases in Tibet: findings from a randomised, population based survey.

BACKGROUND: Public health officials of the Tibet Autonomous Region (TAR) of China requested a survey of blindness, eye diseases, and eye care service utilisation to assist the development of a 10 year blindness prevention and treatment plan. The objective of the survey was to determine the prevalence of blindness and visual impairment, as well as cataract surgical coverage and surgical outcome in the TAR. METHODS: The Tibet Eye Care Assessment was a cross sectional prevalence study of three of the seven prefectures (provinces) of the TAR (Lhoka, Nakchu, and Lingzhr) selected to represent its three main environmental regions. The survey sample was selected using a random multistage cluster method. Two teams conducted the survey in a standardised fashion in each prefecture, Lhoka during May and Nakchu during June 1999, and Lingzhr during May 2000. Visual acuity, cause of vision loss, trachoma, and vitamin A deficiency were included in the clinical examination. RESULTS: Among the 15,900 people enumerated, 12,644 were examined for an overall response rate of 79.6%. The crude prevalence of blindness (presenting better eye visual acuity of less than 6/60) was 2.3%; age and sex adjusted blindness prevalence was 1.4% (95% CI 1.3 to 1.5). Visual impairment (better eye presenting visual acuity of 6/24 to 6/60) was found in 10.9% (95% CI 10.5 to 11.2) of the population (age and sex adjusted). Cataract was the primary cause of blindness (50.7%), followed by macular degeneration (12.7%) and corneal opacity (9.7%). CONCLUSION: Blindness is a serious public health problem in Tibet, with prevalence higher than in similar studies in eastern China. As elsewhere in the world, women have an excess burden of blindness compared to men. About 75% of blindness in Tibet can be either prevented or treated. Eye care planning for Tibet must focus on cataract, particularly among women.