ASG-YOLOv5: Improved YOLOv5 unmanned aerial vehicle remote sensing aerial images scenario for small object detection based on attention and spatial gating.

With the accelerated development of the technological power of society, aerial images of drones gradually penetrated various industries. Due to the variable speed of drones, the captured images are shadowed, blurred, and obscured. Second, drones fly at varying altitudes, leading to changing target scales and making it difficult to detect and identify small targets. In order to solve the above problems, an improved ASG-YOLOv5 model is proposed in this paper. Firstly, this research proposes a dynamic contextual attention module, which uses feature scores to dynamically assign feature weights and output feature information through channel dimensions to improve the model's attention to small target feature information and increase the network's ability to extract contextual information; secondly, this research designs a spatial gating filtering multi-directional weighted fusion module, which uses spatial filtering and weighted bidirectional fusion in the multi-scale fusion stage to improve the characterization of weak targets, reduce the interference of redundant information, and better adapt to the detection of weak targets in images under unmanned aerial vehicle remote sensing aerial photography; meanwhile, using Normalized Wasserstein Distance and CIoU regression loss function, the similarity metric value of the regression frame is obtained by modeling the Gaussian distribution of the regression frame, which increases the smoothing of the positional difference of the small targets and solves the problem that the positional deviation of the small targets is very sensitive, so that the model's detection accuracy of the small targets is effectively improved. This paper trains and tests the model on the VisDrone2021 and AI-TOD datasets. This study used the NWPU-RESISC dataset for visual detection validation. The experimental results show that ASG-YOLOv5 has a better detection effect in unmanned aerial vehicle remote sensing aerial images, and the frames per second (FPS) reaches 86, which meets the requirement of real-time small target detection, and it can be better adapted to the detection of the weak and small targets in the aerial image dataset, and ASG-YOLOv5 outperforms many existing target detection methods, and its detection accuracy reaches 21.1% mAP value. The mAP values are improved by 2.9% and 1.4%, respectively, compared with the YOLOv5 model. The project is available at https://github.com/woaini-shw/asg-yolov5.git.

Combining multisensor images and social network data to assess the area flooded by a hurricane event.

In this study, multisensor remote sensing datasets were used to characterize the land use and land covers (LULC) flooded by Hurricane Willa which made landfall on October 24, 2018. The landscape characterization was done using an unsupervised K-means algorithm of a cloud-free Sentinel-2 MultiSpectral Instrument (MSI) image, acquired during the dry season before Hurricane Willa. A flood map was derived using the histogram thresholding technique over a Synthetic Aperture Radar (SAR) Sentinel-1 C-band and combined with a flood map derived from a Sentinel-2 MSI image. Both, the Sentinel-1 and Sentinel-2 images were obtained after Willa landfall. While the LULC map reached an accuracy of 92%, validated using data collected during field surveys, the flood map achieved 90% overall accuracy, validated using locations extracted from social network data, that were manually georeferenced. The agriculture class was the dominant land use (about 2,624 km2), followed by deciduous forest (1,591 km2) and sub-perennial forest (1,317 km2). About 1,608 km2 represents the permanent wetlands (mangrove, salt marsh, lagoon and estuaries, and littoral classes), but only 489 km2 of this area belongs to aquatic surfaces (lagoons and estuaries). The flooded area was 1,225 km2, with the agricultural class as the most impacted (735 km2). Our analysis detected the saltmarsh class occupied 541 km2in the LULC map, and around 328 km2 were flooded during Hurricane Willa. Since the water flow receded relatively quickly, obtaining representative imagery to assess the flood event was a challenge. Still, the high overall accuracies obtained in this study allow us to assume that the outputs are reliable and can be used in the implementation of effective strategies for the protection, restoration, and management of wetlands. In addition, they will improve the capacity of local governments and residents of Marismas Nacionales to make informed decisions for the protection of vulnerable areas to the different threats derived from climate change.

Towards global insect biomonitoring with frugal methods.

None of the global targets for protecting nature are currently met, although humanity is critically dependent on biodiversity. A significant issue is the lack of data for most biodiverse regions of the planet where the use of frugal methods for biomonitoring would be particularly important because the available funding for monitoring is insufficient, especially in low-income countries. We here discuss how three approaches to insect biomonitoring (computer vision, lidar, DNA sequences) could be made more frugal and urge that all biomonitoring techniques should be evaluated for global suitability before becoming the default in high-income countries. This requires that techniques popular in high-income countries should undergo a phase of 'innovation through simplification' before they are implemented more broadly. We predict that techniques that acquire raw data at low cost and are suitable for analysis with AI (e.g. images, lidar-signals) will be particularly suitable for global biomonitoring, while techniques that rely heavily on patented technologies may be less promising (e.g. DNA sequences). We conclude the opinion piece by pointing out that the widespread use of AI for data analysis will require a global strategy for providing the necessary computational resources and training. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Combining environmental DNA and remote sensing for efficient, fine-scale mapping of arthropod biodiversity.

Arthropods contribute importantly to ecosystem functioning but remain understudied. This undermines the validity of conservation decisions. Modern methods are now making arthropods easier to study, since arthropods can be mass-trapped, mass-identified, and semi-mass-quantified into 'many-row (observation), many-column (species)' datasets, with homogeneous error, high resolution, and copious environmental-covariate information. These 'novel community datasets' let us efficiently generate information on arthropod species distributions, conservation values, uncertainty, and the magnitude and direction of human impacts. We use a DNA-based method (barcode mapping) to produce an arthropod-community dataset from 121 Malaise-trap samples, and combine it with 29 remote-imagery layers using a deep neural net in a joint species distribution model. With this approach, we generate distribution maps for 76 arthropod species across a 225 km2 temperate-zone forested landscape. We combine the maps to visualize the fine-scale spatial distributions of species richness, community composition, and site irreplaceability. Old-growth forests show distinct community composition and higher species richness, and stream courses have the highest site-irreplaceability values. With this 'sideways biodiversity modelling' method, we demonstrate the feasibility of biodiversity mapping at sufficient spatial resolution to inform local management choices, while also being efficient enough to scale up to thousands of square kilometres. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Towards a toolkit for global insect biodiversity monitoring.

Insects are the most diverse group of animals on Earth, yet our knowledge of their diversity, ecology and population trends remains abysmally poor. Four major technological approaches are coming to fruition for use in insect monitoring and ecological research-molecular methods, computer vision, autonomous acoustic monitoring and radar-based remote sensing-each of which has seen major advances over the past years. Together, they have the potential to revolutionize insect ecology, and to make all-taxa, fine-grained insect monitoring feasible across the globe. So far, advances within and among technologies have largely taken place in isolation, and parallel efforts among projects have led to redundancy and a methodological sprawl; yet, given the commonalities in their goals and approaches, increased collaboration among projects and integration across technologies could provide unprecedented improvements in taxonomic and spatio-temporal resolution and coverage. This theme issue showcases recent developments and state-of-the-art applications of these technologies, and outlines the way forward regarding data processing, cost-effectiveness, meaningful trend analysis, technological integration and open data requirements. Together, these papers set the stage for the future of automated insect monitoring. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Monitoring aerial insect biodiversity: a radar perspective.

In the current biodiversity crisis, populations of many species have alarmingly declined, and insects are no exception to this general trend. Biodiversity monitoring has become an essential asset to detect biodiversity change but remains patchy and challenging for organisms that are small, inconspicuous or make (nocturnal) long-distance movements. Radars are powerful remote-sensing tools that can provide detailed information on intensity, timing, altitude and spatial scale of aerial movements and might therefore be particularly suited for monitoring aerial insects and their movements. Importantly, they can contribute to several essential biodiversity variables (EBVs) within a harmonized observation system. We review existing research using small-scale biological and weather surveillance radars for insect monitoring and outline how the derived measures and quantities can contribute to the EBVs 'species population', 'species traits', 'community composition' and 'ecosystem function'. Furthermore, we synthesize how ongoing and future methodological, analytical and technological advancements will greatly expand the use of radar for insect biodiversity monitoring and beyond. Owing to their long-term and regional-to-large-scale deployment, radar-based approaches can be a powerful asset in the biodiversity monitoring toolbox whose potential has yet to be fully tapped. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Global marine phytoplankton dynamics analysis with machine learning and reanalyzed remote sensing.

Phytoplankton are the world's largest oxygen producers found in oceans, seas and large water bodies, which play crucial roles in the marine food chain. Unbalanced biogeochemical features like salinity, pH, minerals, etc., can retard their growth. With advancements in better hardware, the usage of Artificial Intelligence techniques is rapidly increasing for creating an intelligent decision-making system. Therefore, we attempt to overcome this gap by using supervised regressions on reanalysis data targeting global phytoplankton levels in global waters. The presented experiment proposes the applications of different supervised machine learning regression techniques such as random forest, extra trees, bagging and histogram-based gradient boosting regressor on reanalysis data obtained from the Copernicus Global Ocean Biogeochemistry Hindcast dataset. Results obtained from the experiment have predicted the phytoplankton levels with a coefficient of determination score (R2) of up to 0.96. After further validation with larger datasets, the model can be deployed in a production environment in an attempt to complement in-situ measurement efforts.

Characterising illness stages and recovery trajectories of eating disorders in young people via remote measurement technology (STORY): a multi-centre prospective cohort study protocol.

BACKGROUND: Eating disorders (EDs) are serious, often chronic, conditions associated with pronounced morbidity, mortality, and dysfunction increasingly affecting young people worldwide. Illness progression, stages and recovery trajectories of EDs are still poorly characterised. The STORY study dynamically and longitudinally assesses young people with different EDs (restricting; bingeing/bulimic presentations) and illness durations (earlier; later stages) compared to healthy controls. Remote measurement technology (RMT) with active and passive sensing is used to advance understanding of the heterogeneity of earlier and more progressed clinical presentations and predictors of recovery or relapse. METHODS: STORY follows 720 young people aged 16-25 with EDs and 120 healthy controls for 12 months. Online self-report questionnaires regularly assess ED symptoms, psychiatric comorbidities, quality of life, and socioeconomic environment. Additional ongoing monitoring using multi-parametric RMT via smartphones and wearable smart rings ('Oura ring') unobtrusively measures individuals' daily behaviour and physiology (e.g., Bluetooth connections, sleep, autonomic arousal). A subgroup of participants completes additional in-person cognitive and neuroimaging assessments at study-baseline and after 12 months. DISCUSSION: By leveraging these large-scale longitudinal data from participants across ED diagnoses and illness durations, the STORY study seeks to elucidate potential biopsychosocial predictors of outcome, their interplay with developmental and socioemotional changes, and barriers and facilitators of recovery. STORY holds the promise of providing actionable findings that can be translated into clinical practice by informing the development of both early intervention and personalised treatment that is tailored to illness stage and individual circumstances, ultimately disrupting the long-term burden of EDs on individuals and their families.

Internet of Things-Enabled Patch With Built-in Microsensors and Wireless Chip: Real-Time Remote Monitoring of Patch Treatment.

Purpose: We aimed to design, develop, and evaluate an internet of things-enabled patch (IoT patch) for real-time remote monitoring of adherence (or patch wear time) during patch treatment in child participants in clinical trials. This study provides healthcare providers with a tool for objective, real-time, and remote assessment of adherence and for making required adjustments to treatment plans. Methods: The IoT patch had two temperature microsensors and a wireless chip. One sensor was placed closer to the skin than the other, resulting in a temperature difference depending on whether the patch was worn. When the patch was worn, it measured temperatures every 30 seconds and transmitted temperature data to a cloud server via a mobile application every 15 seconds. The patch was evaluated via 2 experiments with 30 healthy adults and 40 children with amblyopia. Results: Excellent monitoring accuracy was observed in both adults (mean delay of recorded time data, 0.4 minutes) and children (mean, 0.5 minutes). The difference between manually recorded and objectively recorded patch wear times showed good agreement in both groups. Experiment 1 showed accurate monitoring over a wide range of temperatures (from 0 to 30°C). Experiment 2 showed no significant differences in wearability (ease-of-use and comfort scores) between the IoT and conventional patches. Conclusions: The IoT patch offers an accurate, real-time, and remote system to monitor adherence to patch treatment. The patch is comfortable and easy to use. The utilization of an IoT patch may increase adherence to patch treatment based on accurate monitoring. Translational Relevance: Results show that the IoT patch can enable real-time adherence monitoring in clinical trials, improving treatment precision, and patient compliance to enhance outcomes.

Using image segmentation models to analyse high-resolution earth observation data: new tools to monitor disease risks in changing environments.

BACKGROUND: In the near future, the incidence of mosquito-borne diseases may expand to new sites due to changes in temperature and rainfall patterns caused by climate change. Therefore, there is a need to use recent technological advances to improve vector surveillance methodologies. Unoccupied Aerial Vehicles (UAVs), often called drones, have been used to collect high-resolution imagery to map detailed information on mosquito habitats and direct control measures to specific areas. Supervised classification approaches have been largely used to automatically detect vector habitats. However, manual data labelling for model training limits their use for rapid responses. Open-source foundation models such as the Meta AI Segment Anything Model (SAM) can facilitate the manual digitalization of high-resolution images. This pre-trained model can assist in extracting features of interest in a diverse range of images. Here, we evaluated the performance of SAM through the Samgeo package, a Python-based wrapper for geospatial data, as it has not been applied to analyse remote sensing images for epidemiological studies. RESULTS: We tested the identification of two land cover classes of interest: water bodies and human settlements, using different UAV acquired imagery across five malaria-endemic areas in Africa, South America, and Southeast Asia. We employed manually placed point prompts and text prompts associated with specific classes of interest to guide the image segmentation and assessed the performance in the different geographic contexts. An average Dice coefficient value of 0.67 was obtained for buildings segmentation and 0.73 for water bodies using point prompts. Regarding the use of text prompts, the highest Dice coefficient value reached 0.72 for buildings and 0.70 for water bodies. Nevertheless, the performance was closely dependent on each object, landscape characteristics and selected words, resulting in varying performance. CONCLUSIONS: Recent models such as SAM can potentially assist manual digitalization of imagery by vector control programs, quickly identifying key features when surveying an area of interest. However, accurate segmentation still requires user-provided manual prompts and corrections to obtain precise segmentation. Further evaluations are necessary, especially for applications in rural areas.

SLMFNet: Enhancing land cover classification of remote sensing images through selective attentions and multi-level feature fusion.

Land cover classification (LCC) is of paramount importance for assessing environmental changes in remote sensing images (RSIs) as it involves assigning categorical labels to ground objects. The growing availability of multi-source RSIs presents an opportunity for intelligent LCC through semantic segmentation, offering a comprehensive understanding of ground objects. Nonetheless, the heterogeneous appearances of terrains and objects contribute to significant intra-class variance and inter-class similarity at various scales, adding complexity to this task. In response, we introduce SLMFNet, an innovative encoder-decoder segmentation network that adeptly addresses this challenge. To mitigate the sparse and imbalanced distribution of RSIs, we incorporate selective attention modules (SAMs) aimed at enhancing the distinguishability of learned representations by integrating contextual affinities within spatial and channel domains through a compact number of matrix operations. Precisely, the selective position attention module (SPAM) employs spatial pyramid pooling (SPP) to resample feature anchors and compute contextual affinities. In tandem, the selective channel attention module (SCAM) concentrates on capturing channel-wise affinity. Initially, feature maps are aggregated into fewer channels, followed by the generation of pairwise channel attention maps between the aggregated channels and all channels. To harness fine-grained details across multiple scales, we introduce a multi-level feature fusion decoder with data-dependent upsampling (MLFD) to meticulously recover and merge feature maps at diverse scales using a trainable projection matrix. Empirical results on the ISPRS Potsdam and DeepGlobe datasets underscore the superior performance of SLMFNet compared to various state-of-the-art methods. Ablation studies affirm the efficacy and precision of SAMs in the proposed model.

A Hybrid convolution neural network for the classification of tree species using hyperspectral imagery.

In recent years, the advancement of hyperspectral remote sensing technology has greatly enhanced the detailed mapping of tree species. Nevertheless, delving deep into the significance of hyperspectral remote sensing data features for tree species recognition remains a challenging endeavor. The method of Hybrid-CS was proposed to addresses this challenge by synergizing the strengths of both deep learning and traditional learning techniques. Initially, we extract comprehensive correlation structures and spectral features. Subsequently, a hybrid approach, combining correlation-based feature selection with an optimized recursive feature elimination algorithm, identifies the most valuable feature set. We leverage the Support Vector Machine algorithm to evaluate feature importance and perform classification. Through rigorous experimentation, we evaluate the robustness of hyperspectral image-derived features and compare our method with other state-of-the-art classification methods. The results demonstrate: (1) Superior classification accuracy compared to traditional machine learning methods (e.g., SVM, RF) and advanced deep learning approaches on the tree species dataset. (2) Enhanced classification accuracy achieved by incorporating SVM and CNN information, particularly with the integration of attention mechanisms into the network architecture. Additionally, the classification performance of a two-branch network surpasses that of a single-branch network. (3) Consistent high accuracy across different proportions of training samples, indicating the stability and robustness of the method. This study underscores the potential of hyperspectral images and our proposed methodology for achieving precise tree species classification, thus holding significant promise for applications in forest resource management and monitoring.

Remote sensing of emperor penguin abundance and breeding success.

Emperor penguins (Aptenodytes forsteri) are under increasing environmental pressure. Monitoring colony size and population trends of this Antarctic seabird relies primarily on satellite imagery recorded near the end of the breeding season, when light conditions levels are sufficient to capture images, but colony occupancy is highly variable. To correct population estimates for this variability, we develop a phenological model that can predict the number of breeding pairs and fledging chicks, as well as key phenological events such as arrival, hatching and foraging times, from as few as six data points from a single season. The ability to extrapolate occupancy from sparse data makes the model particularly useful for monitoring remotely sensed animal colonies where ground-based population estimates are rare or unavailable.

The rectangular tile classification model based on Sentinel integrated images enhances grassland mapping accuracy: A case study in Ordos, China.

Arid zone grassland is a crucial component of terrestrial ecosystems and plays a significant role in ecosystem protection and soil erosion prevention. However, accurately mapping grassland spatial information in arid zones presents a great challenge. The accuracy of remote sensing grassland mapping in arid zones is affected by spectral variability caused by the highly diverse landscapes. In this study, we explored the potential of a rectangular tile classification model, constructed using the random forest algorithm and integrated images from Sentinel-1A (synthetic aperture radar imagery) and Sentinel-2 (optical imagery), to enhance the accuracy of grassland mapping in the semiarid to arid regions of Ordos, China. Monthly Sentinel-1A median value images were synthesised, and four MODIS vegetation index mean value curves (NDVI, MSAVI, NDWI and NDBI) were used to determine the optimal synthesis time window for Sentinel-2 images. Seven experimental groups, including 14 experimental schemes based on the rectangular tile classification model and the traditional global classification model, were designed. By applying the rectangular tile classification model and Sentinel-integrated images, we successfully identified and extracted grasslands. The results showed the integration of vegetation index features and texture features improved the accuracy of grassland mapping. The overall accuracy of the Sentinel-integrated images from EXP7-2 was 88.23%, which was higher than the accuracy of the single sensor Sentinel-1A (53.52%) in EXP2-2 and Sentinel-2 (86.53%) in EXP5-2. In all seven experimental groups, the rectangular tile classification model was found to improve overall accuracy (OA) by 1.20% to 13.99% compared to the traditional global classification model. This paper presents novel perspectives and guidance for improving the accuracy of remote sensing mapping for land cover classification in arid zones with highly diverse landscapes. The study presents a flexible and scalable model within the Google Earth Engine framework, which can be readily customized and implemented in various geographical locations and time periods.

Integrating plant morphological traits with remote-sensed multispectral imageries for accurate corn grain yield prediction.

Sustainable crop production requires adequate and efficient management practices to reduce the negative environmental impacts of excessive nitrogen (N) fertilization. Remote sensing has gained traction as a low-cost and time-efficient tool for monitoring and managing cropping systems. In this study, vegetation indices (VIs) obtained from an unmanned aerial vehicle (UAV) were used to detect corn (Zea mays L.) response to varying N rates (ranging from 0 to 208 kg N ha-1) and fertilizer application methods (liquid urea ammonium nitrate (UAN), urea side-dressing and slow-release fertilizer). Four VIs were evaluated at three different growth stages of corn (V6, R3, and physiological maturity) along with morphological traits including plant height and leaf chlorophyll content (SPAD) to determine their predictive capability for corn yield. Our results show no differences in grain yield (average 13.2 Mg ha-1) between furrow-applied slow-release fertilizer at ≥156 kg N ha-1 and 208 kg N ha-1 side-dressed urea. Early season remote-sensed VIs and morphological data collected at V6 were least effective for grain yield prediction. Moreover, multivariate grain yield prediction was more accurate than univariate. Late-season measurements at the R3 and mature growth stages using a combination of normalized difference vegetation index (NDVI) and green normalized difference vegetation index (GNDVI) in a multilinear regression model showed effective prediction for corn yield. Additionally, a combination of NDVI and normalized difference red edge index (NDRE) in a multi-exponential regression model also demonstrated good prediction capabilities.

Research on potential disruptive technology identification based on technology network.

Three evident and meaningful characteristics of disruptive technology are the zeroing effect that causes sustaining technology useless for its remarkable and unprecedented progress, reshaping the landscape of technology and economy, and leading the future mainstream of technology system, all of which have profound impacts and positive influences. The identification of disruptive technology is a universally difficult task. Therefore, this paper aims to enhance the technical relevance of potential disruptive technology identification results and improve the granularity and effectiveness of potential disruptive technology identification topics. According to the life cycle theory, dividing the time stage, then constructing and analyzing the dynamic of technology networks to identify potential disruptive technology. Thereby, using the Latent Dirichlet Allocation (LDA) topic model further to clarify the topic content of potential disruptive technologies. This paper takes the large civil unmanned aerial vehicles (UAVs) as an example to prove the feasibility and effectiveness of the model. The results show that the potential disruptive technology in this field is the data acquisition, main equipment, and ground platform intelligence.

Mapping burned areas in Thailand using Sentinel-2 imagery and OBIA techniques.

Monitoring burned areas in Thailand and other tropical countries during the post-harvest season is becoming increasingly important. High-resolution remote sensing data from Sentinel-2 satellites, which have a short revisit time, is ideal for accurately and efficiently mapping burned regions. However, automating the mapping of agriculture residual on a national scale is challenging due to the volume of information and level of detail involved. In this study, a Sentinel-2A Level-1C Multispectral Instrument image (MSI) from February 27, 2018 was combined with object-based image analysis (OBIA) algorithms to identify burned areas in Mae Chaem, Chom Thong, Hod, Mae Sariang, and Mae La Noi Districts in Chiang Mai, Thailand. OBIA techniques were used to classify forest, agricultural, water bodies, newly burned, and old burned regions. The segmentation scale parameter value of 50 was obtained using only the original Sentinel-2A band in red, green, blue, near infrared (NIR), and Normalized Difference Vegetation Index (NDVI). The accuracy of the produced maps was assessed using an existing burned area dataset, and the burned area identified through OBIA was found to be 85.2% accurate compared to 500 random burned points from the dataset. These results suggest that the combination of OBIA and Sentinel-2A with a 10 m spatial resolution is very effective and promising for the process of burned area mapping.

Remote Sensing Techniques: Hyperspectral Imaging and Data Analysis.

Hyperspectral imaging is a remote sensing technique that enables remote, noninvasive measurement of plant traits. Here, we outline the procedures for camera setup, scanning, and calibration, along with the acquisition of black and white reference materials, which are the key steps in collecting hyperspectral imagery. We also discuss the development of predictive models such as partial least-squares regression, using both large and small datasets, which are used to predict plant traits from hyperspectral data. To ensure practical applicability, we provide code examples that allow readers to immediately implement these techniques in real-world scenarios. We introduce these topics to beginners in an accessible and understandable manner.

Remote monitoring of amyotrophic lateral sclerosis using wearable sensors detects differences in disease progression and survival: a prospective cohort study.

BACKGROUND: There is an urgent need for objective and sensitive measures to quantify clinical disease progression and gauge the response to treatment in clinical trials for amyotrophic lateral sclerosis (ALS). Here, we evaluate the ability of an accelerometer-derived outcome to detect differential clinical disease progression and assess its longitudinal associations with overall survival in patients with ALS. METHODS: Patients with ALS wore an accelerometer on the hip for 3-7 days, every 2-3 months during a multi-year observation period. An accelerometer-derived outcome, the Vertical Movement Index (VMI), was calculated, together with predicted disease progression rates, and jointly analysed with overall survival. The clinical utility of VMI was evaluated using comparisons to patient-reported functionality, while the impact of various monitoring schemes on empirical power was explored through simulations. FINDINGS: In total, 97 patients (70.1% male) wore the accelerometer for 1995 days, for a total of 27,701 h. The VMI was highly discriminatory for predicted disease progression rates, revealing faster rates of decline in patients with a worse predicted prognosis compared to those with a better predicted prognosis (p < 0.0001). The VMI was strongly associated with the hazard for death (HR 0.20, 95% CI: 0.09-0.44, p < 0.0001), where a decrease of 0.19-0.41 unit was associated with reduced ambulatory status. Recommendations for future studies using accelerometery are provided. INTERPRETATION: The results serve as motivation to incorporate accelerometer-derived outcomes in clinical trials, which is essential for further validation of these markers to meaningful endpoints. FUNDING: Stichting ALS Nederland (TRICALS-Reactive-II).

Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys.

Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.