Experimental data can broadly be divided in discrete or continuous data. Continuous data are obtained from measurements that are performed as a function of another quantitative variable, e.g., time, length, concentration, or wavelength. The results from these types of experiments are often used to generate plots that visualize the measured variable on a continuous, quantitative scale. To simplify state-of-the-art data visualization and annotation of data from such experiments, an open-source tool was created with R/shiny that does not require coding skills to operate it. The freely available web app accepts wide (spreadsheet) and tidy data and offers a range of options to normalize the data. The data from individual objects can be shown in 3 different ways: (1) lines with unique colors, (2) small multiples, and (3) heatmap-style display. Next to this, the mean can be displayed with a 95% confidence interval for the visual comparison of different conditions. Several color-blind-friendly palettes are available to label the data and/or statistics. The plots can be annotated with graphical features and/or text to indicate any perturbations that are relevant. All user-defined settings can be stored for reproducibility of the data visualization. The app is dubbed PlotTwist and runs locally or online: https://huygens.science.uva.nl/PlotTwist

The recent surge in enthusiasm for simultaneously inferring relationships from extinct and extant species has reinvigorated interest in statistical approaches for modelling morphological evolution. Current statistical methods use the Mk model to describe substitutions between discrete character states. Although representing a significant step forward, the Mk model presents challenges in biological interpretation, and its adequacy in modelling morphological evolution has not been well explored. Another major hurdle in morphological phylogenetics concerns the process of character coding of discrete characters. The often subjective nature of discrete character coding can generate discordant results that are rooted in individual researchers' subjective interpretations. Employing continuous measurements to infer phylogenies may alleviate some of these issues. Although not widely used in the inference of topology, models describing the evolution of continuous characters have been well examine...

Based on the context of your article, your target labels are Efficiency Ratio and Quality Maintenance Ratio, which are continuous variables derived from multiple factors such as fuel consumption, logistics costs, spoilage, and supply chain bottlenecks.

These labels are not binary, as they represent ratios that indicate performance and quality metrics in agricultural logistics and supply chain management. The values of these ratios are continuous and are used for regression tasks, rather than classification tasks with binary outputs.

So, your article is focused on predicting these continuous values rather than performing binary classification.

You said: write description of the dataset along iwth features it is downloaded form EURO crops etc like that

ChatGPT said: ChatGPT The dataset used in this research was obtained from a large-scale agricultural logistics study conducted across European farms, specifically focusing on key regions known for extensive crop production, such as France, Germany, and the Netherlands. The dataset, named EURO Crops Agricultural Logistics Dataset, contains detailed records of various logistical operations, environmental conditions, and product quality metrics across multiple agricultural supply chains. It spans from June 2018 to June 2024, with hourly data collected from IoT-enabled sensors and GPS devices installed on vehicles, storage units, and monitoring stations.

The dataset includes a total of 53,305 records, with data points capturing critical aspects of agricultural logistics operations, such as transportation efficiency, storage conditions, and product quality. The information is collected in real-time through IoT sensors deployed across the logistics network, tracking the movement and conditions of agricultural products. The data also encompasses environmental monitoring systems, providing insights into weather patterns, soil conditions, and crop health.

The key features of the dataset include:

Vehicle_Type: Categorical data indicating the type of vehicle used for transportation (e.g., Truck, Van). Crop_Type: Categorical data specifying the type of crops being transported (e.g., Wheat, Corn, Rice). Harvest_Date: Date indicating when the crops were harvested. Crop_Yield: Quantitative data showing the total yield of the crop (in kilograms). Storage_Temperature: Continuous data representing the temperature inside the storage unit (in degrees Celsius). Storage_Humidity: Continuous data representing the humidity levels inside the storage unit (in percentage). Fuel_Consumption: Continuous data indicating the amount of fuel used during transportation (in liters per 100 km). Route_Distance: Continuous data showing the total distance covered by the vehicle (in kilometers). Delivery_Time: Continuous data representing the total time taken for the delivery (in hours). Traffic_Level: Continuous data showing the level of traffic congestion on the route (on a scale of 0 to 100). Temperature: Environmental temperature during transportation (in degrees Celsius). Humidity: Environmental humidity during transportation (in percentage). Vehicle_Load_Capacity: The total load capacity of the vehicle (in kilograms). Vibration_Level: Data from sensors measuring the vibration experienced during transportation, which affects crop quality (in arbitrary units). Queue_Time: Time spent in queues or waiting during transit (in hours). Weather_Impact: Index measuring the impact of weather conditions on logistics operations (e.g., heavy rain, wind, etc.). Station_Capacity: Storage capacity of the distribution or logistics station (in kilograms). Operational_Cost: The total cost of logistics operations, including fuel, labor, and storage costs (in USD). Energy_Consumption: Total energy consumption of storage and transportation units (in kWh). IoT_Sensor_Reading_Temperature: Continuous data from IoT sensors monitoring the temperature of the crops during transit (in degrees Celsius). IoT_Sensor_Reading_Humidity: Continuous data from IoT sensors monitoring the humidity of the crops during transit (in percentage). IoT_Sensor_Reading_Light: Continuous data from IoT sensors monitoring light exposure during transportation (in lumens). Warehouse_Storage_Time: Time spent by the crops in warehouse storage before further transportation (in days). Inventory_Levels: Current inventory levels at various storage facilities (in units). Fuel_Costs: Cost of fuel consumed during transportation (in USD per liter). Spoilage_Risk: Probability of spoilage during transportation, based on environmental and operational conditions (as a percentage). The target labels in the dataset include:

Efficiency Ratio: A composite ratio calculated based on fuel consumption, logistics costs, and delivery times, aimed at measuring the overall efficiency of the logistics operation. Quality Maintenance Ratio: A ratio derived from spoi...

The MOD44B Version 6.1 Vegetation Continuous Fields (VCF) yearly product is a global representation of surface vegetation cover as gradations of three ground cover components: percent tree cover, percent non-tree cover, and percent non-vegetated (bare). VCF products provide a continuous, quantitative portrayal of land surface cover at 250 meter (m) pixel resolution, with a sub-pixel depiction of percent cover in reference to the three ground cover components. The sub-pixel mixture of ground cover estimates represents a revolutionary approach to the characterization of vegetative land cover that can be used to enhance inputs to environmental modeling and monitoring applications. The MOD44B data product layers include percent tree cover, percent non-tree cover, percent non-vegetated, cloud cover, and quality indicators. The start date of the annual period for this product begins with day of year (DOY) 65 (March 6 except for leap year which corresponds to March 5). Known Issues For complete information about known issues please refer to the MODIS/VIIRS Land Quality Assessment website.Improvements/Changes from Previous Versions The Version 6.1 Level-1B (L1B) products have been improved by undergoing various calibration changes that include: changes to the response-versus-scan angle (RVS) approach that affects reflectance bands for Aqua and Terra MODIS, corrections to adjust for the optical crosstalk in Terra MODIS infrared (IR) bands, and corrections to the Terra MODIS forward look-up table (LUT) update for the period 2012 - 2017.* A polarization correction has been applied to the L1B Reflective Solar Bands (RSB).

Many aspects of morphological phylogenetics are controversial in the theoretical systematics literature and yet are often poorly explained and justified in empirical studies. In this paper, I argue that most morphological characters describe variation that is fundamentally quantitative, regardless of whether it is coded qualitatively or quantitatively by systematists. Given this view, three fundamental problems in morphological character analysis (character state definition, delimitation, and ordering) may have a common solution: coding morphological characters as continuous quantitative traits. A new parsimony method (step-matrix gap-weighting, a modification of Thiele's approach) is proposed that allows quantitative traits to be analyzed as continuous variables. The problem of scaling or weighting quantitative characters relative to qualitative characters (and to each other) is reviewed, and three possible solutions are described. The new coding method is applied to data from hoplocer...

Coevolution is relentlessly creating and maintaining biodiversity, and therefore has been a central topic in evolutionary biology. Previous theoretical studies have mostly considered coevolution between genetically symmetric traits (i.e., coevolution between two continuous quantitative traits or two discrete Mendelian traits). However, recent empirical evidence indicates that coevolution can occur between genetically asymmetric traits (e.g., between quantitative and Mendelian traits). We examine consequences of antagonistic coevolution mediated by a quantitative predator trait and a Mendelian prey trait, such that predation is more intense with decreased phenotypic distance between their traits (phenotype matching). This antagonistic coevolution produces a complex pattern of bifurcations with bistability (initial state dependence) in a two-dimensional model for trait coevolution. Further, with eco-evolutionary dynamics (so that the trait evolution affects predator-prey population dynamics), we find that coevolution can cause rich dynamics including anti-phase cycles, in-phase cycles, chaotic dynamics, and deterministic predator extinction. Predator extinction is more likely to occur when the prey trait exhibits complete dominance rather than semidominance and when the predator trait evolves very rapidly. Our study illustrates how recognizing the genetic architectures of interacting ecological traits can be essential for understanding the population and evolutionary dynamics of coevolving species.

The MOD44B Version 6 data product was decommissioned on July 31, 2023. Users are encouraged to use the MOD44B Version 6.1 data product.The MOD44B Version 6 Vegetation Continuous Fields (VCF) yearly product is a global representation of surface vegetation cover as gradations of three ground cover components: percent tree cover, percent non-tree cover, and percent non-vegetated (bare). VCF products provide a continuous, quantitative portrayal of land surface cover at 250 meter (m) pixel resolution, with a sub-pixel depiction of percent cover in reference to the three ground cover components. The sub-pixel mixture of ground cover estimates represents a revolutionary approach to the characterization of vegetative land cover that can be used to enhance inputs to environmental modeling and monitoring applications. The MOD44B data product layers include percent tree cover, percent non-tree cover, percent non-vegetated, cloud cover, and quality indicators. The start date of the annual period for this product begins with day of year (DOY) 65 (March 6 except for leap year which corresponds to March 5). Known Issues For complete information about known issues please refer to the MODIS/VIIRS Land Quality Assessment website.Improvements/Changes from Previous Versions The MOD44B Version 6 VCF was produced with the same code and training as the Version 5 products, but improvements to the upstream inputs result in more accurate VCF products.

As our generation and collection of quantitative digital data increase, so do our ambitions for extracting new insights and knowledge from those data. In recent years, those ambitions have manifested themselves in so-called “Grand Challenge” projects coordinated by academic institutions. These projects are often broadly interdisciplinary and attempt to address to major issues facing the world in the present and the future through the collection and integration of diverse types of scientific data. In general, however, disciplines that focus on the past are underrepresented in this environment – in part because these grand challenges tend to look forward rather than back, and in part because historical disciplines tend to produce qualitative, incomplete data that are difficult to mesh with the more continuous quantitative data sets provided by scientific observation. Yet historical information is essential for our understanding of long-term processes, and should thus be incorporated into our efforts to solve present and future problems. Archaeology, an inherently interdisciplinary field of knowledge that bridges the gap between the quantitative and the qualitative, can act as a connector between the study of the past and data-driven attempts to address the challenges of the future. To do so, however, we must find new ways to integrate the results of archaeological research into the digital platforms used for the modeling and analysis of much bigger data.

Planet Texas 2050 is a grand challenge project recently launched by The University of Texas at Austin. Its central goal is to understand the dynamic interactions between water supply, urbanization, energy use, and ecosystems services in Texas, a state that will be especially affected by climate change and population mobility by the middle of the 21st century. Like many such projects, one of the products of Planet Texas 2050 will be an integrated data platform that will make it possible to model various scenarios and help decision-makers project the results of resent policies or trends into the future. Unlike other such projects, however, PT2050 incorporates data collected from past societies, primarily through archaeological inquiry. We are currently designing a data integration and modeling platform that will allow us to bring together quantitative sensor data related to the present environment with “fuzzier” data collected in the course of research in the social sciences and humanities. Digital archaeological data, from LiDAR surveys to genomic information to excavation documentation, will be a central component of this platform. In this paper, I discuss the conceptual integration between scientific “big data” and “medium-sized” archaeological data in PT2050; the process that we are following to catalog data types, identify domain-specific ontologies, and understand the points of intersection between heterogeneous data sets of varying resolution and precision as we construct the data platform; and how we propose to incorporate digital data from archaeological research into integrated modeling and simulation modules.

We hypothesized that (1) correlation of (A) the output of instrumentation to generate quantitative continuous measurements of movements and (B) the quantitative measurements of trained examiners using structured ratings of movements would generate the tools to differentiate the movements of (A) Parkinson's disease (PD), (B) parkinsonian syndromes, and health, and (2) continuous quantitative measurements of movements would improve the ratings generated by visual observations of trained raters, and provide pathognomonic signatures to identify PD and parkinsonian syndromes.

A protocol for a low-cost quantitative continuous measurement of movements in the extremities of people with PD (McKay, et al., 2019) was administered to people with PD and multiple system atrophy-parkinsonian type (MSA-P) and age- and sex-matched healthy control participants. Data from instrumentation was saved as WinDaq files (Dataq Instruments, Inc., Akron, Ohio) and converted into Excel files (McKay, et al., 2019) using the WinDaq Waveform Data Browser (Dataq Instruments, Inc., Akron, Ohio).

Participants were asked to sit in a straight-back chair with arms approximately six inches from the wall to minimize the risk of hitting the wall. The examiner sat in a similar chair facing the participant. The examiner asked the technologist and the videographer to begin recording immediately before instructing the participant to perform each item.

Items were scored live by the examiner at the same time that the quantitative continuous measurements of movements were recorded by the instrumentation.

Healthy control participants were matched for age and sex with participants with PD. The key identifies the diagnosis (PD = Parkinson's disease, MSA-P = Multiple system atrophy - parkinsonian type, HC = healthy control, 1 = male, 0 = female). Participants with PD completed a single test session (0002, 0005, 0007-0009, 0012, 0017-0018, and 0021), a test and a retest session (0001, 0003, 0006, 0010-0011, 0013, 0015, 0019, 0022-0023), or a test and two retest sessions (0014). HC participants completed test and retest sessions (0020, 0024-0030). A participant with MSA-P (0004) completed a test session. Individual files for the WinDaq, Excel, and coding forms for each testing are entered in the dataset. The Excel files for the five repetitive items were converted to fast Fourier transforms (FFTs) and continuous wavelet transforms (CWTs) (MatLab).

None of the files underwent filtering.

Healthy participants exhibited some of the features of disease.

The data provide the basis to determine how a session may predict future performance.

This data is based on the Seshat data release in https://zenodo.org/record/6642230 and aims to dissect the time series of each NGA into culturally and institutionally continuous time series. For both continuity criteria, the central continuous time series is marked in the data (central meaning that this is the time interval during which the NGA has crossed a specified threshold between low-complexity and high-complexity societies). Details can be found in v3 of https://arxiv.org/abs/2212.00563

The dataset and replication package of the study "A continuous open source data collection platform for architectural technical debt assessment".

Abstract

Architectural decisions are the most important source of technical debt. In recent years, researchers spent an increasing amount of effort investigating this specific category of technical debt, with quantitative methods, and in particular static analysis, being the most common approach to investigate such a topic.

However, quantitative studies are susceptible, to varying degrees, to external validity threats, which hinder the generalisation of their findings.

In response to this concern, researchers strive to expand the scope of their study by incorporating a larger number of projects into their analyses. This practice is typically executed on a case-by-case basis, necessitating substantial data collection efforts that have to be repeated for each new study.

To address this issue, this paper presents our initial attempt at tackling this problem and enabling researchers to study architectural smells at large scale, a well-known indicator of architectural technical debt. Specifically, we introduce a novel approach to data collection pipeline that leverages Apache Airflow to continuously generate up-to-date, large-scale datasets using Arcan, a tool for architectural smells detection (or any other tool).

Finally, we present the publicly-available dataset resulting from the first three months of execution of the pipeline, that includes over 30,000 analysed commits and releases from over 10,000 open source GitHub projects written in 5 different programming languages and amounting to over a billion of lines of code analysed.

Daily frequency of spontaneous recurrent seizures in individual mice. The number of seizures observed during continuous video-EEG monitoring is displayed in the table. These data support the results of Fig 4, Table 1, and Table 2. (XLSX)

BackgroundFailure to recognize acute deterioration in hospitalized patients may contribute to cardiopulmonary arrest, unscheduled intensive care unit admission and increased mortality.PurposeIn this systematic review we aimed to determine whether continuous non-invasive respiratory monitoring improves early diagnosis of patient deterioration and reduces critical incidents on hospital wards.Data SourcesStudies were retrieved from Medline, Embase, CINAHL, and the Cochrane library, searched from 1970 till October 25, 2014.Study SelectionElectronic databases were searched using keywords and corresponding synonyms ‘ward’, ‘continuous’, ‘monitoring’ and ‘respiration’. Pediatric, fetal and animal studies were excluded.Data ExtractionSince no validated tool is currently available for diagnostic or intervention studies with continuous monitoring, methodological quality was assessed with a modified tool based on modified STARD, CONSORT, and TREND statements.Data SynthesisSix intervention and five diagnostic studies were included, evaluating the use of eight different devices for continuous respiratory monitoring. Quantitative data synthesis was not possible because intervention, study design and outcomes differed considerably between studies. Outcomes estimates for the intervention studies ranged from RR 0.14 (0.03, 0.64) for cardiopulmonary resuscitation to RR 1.00 (0.41, 2.35) for unplanned ICU admission after introduction of continuous respiratory monitoring,LimitationsThe methodological quality of most studies was moderate, e.g. ‘before-after’ designs, incomplete reporting of primary outcomes, and incomplete clinical implementation of the monitoring system.ConclusionsBased on the findings of this systematic review, implementation of routine continuous non-invasive respiratory monitoring on general hospital wards cannot yet be advocated as results are inconclusive, and methodological quality of the studies needs improvement. Future research in this area should focus on technology explicitly suitable for low care settings and tailored alarm and treatment algorithms.

Dataset of tree (.tre) files and R code for running generalized Robinson-Foulds distance (Smith, 2020a;b) analysis.

The .tre files can be read into R (R Core Team., 2023) using the ape::read.tree function (Paradis et al., 2003), full details in R code file.

Paradis, E., Claude, J., & Strimmer, K. (2004). APE: analyses of phylogenetics and evolution in R language. Bioinformatics, 20(2), 289-290.

R Core Team. (2023). R: A Language and Environment for Statistical Computing. (Version 4.2.2). R Foundation for Statistical Computing, Vienna, Austria: https://www.R-project.org/.

Smith, M. R. (2020a). Information theoretic generalized Robinson–Foulds metrics for comparing phylogenetic trees. Bioinformatics, 36(20), 5007-5013. https://doi.org/10.1093/bioinformatics/btaa614

Smith, M. R. (2020b). TreeDist: distances between phylogenetic trees. R package version 2.7.0. doi:10.5281/zenodo.3528124.

Quantitative Research AI Market Outlook

According to our latest research, the global Quantitative Research AI market size reached USD 1.82 billion in 2024, reflecting robust expansion in the adoption of artificial intelligence for quantitative analysis across industries. The market is expected to grow at a CAGR of 27.6% during the forecast period, with the forecasted market size anticipated to reach USD 16.34 billion by 2033. This significant growth is driven by the increasing demand for advanced data analytics, automation in research processes, and the expanding scope of AI technologies in both academic and commercial quantitative research.

The primary growth driver for the Quantitative Research AI market is the surging volume of data generated across industries and the need for sophisticated tools to extract actionable insights. Organizations are increasingly leveraging AI-powered quantitative research tools to process large datasets efficiently, identify patterns, and predict future trends with higher accuracy. These capabilities are particularly valuable in sectors such as financial services, healthcare, and market research, where data-driven decision-making is critical. The integration of machine learning algorithms and natural language processing further enhances the ability of AI systems to handle complex quantitative tasks, reducing the time and resources required for traditional research methodologies.

Another significant factor contributing to market growth is the rising adoption of cloud-based AI solutions. Cloud deployment offers scalability, flexibility, and cost-effectiveness, enabling organizations of all sizes to access advanced quantitative research tools without the need for substantial upfront investments in infrastructure. The proliferation of AI-as-a-Service (AIaaS) models has democratized access to powerful quantitative research capabilities, allowing even small and medium enterprises (SMEs) to benefit from AI-driven insights. Additionally, continuous advancements in AI hardware, such as specialized processors and accelerators, are further propelling the market by improving the performance and efficiency of AI applications in quantitative research.

The increasing focus on personalized and precision-driven research in industries such as healthcare and finance is also fueling the demand for AI-based quantitative research solutions. In healthcare, for instance, AI-driven quantitative analysis is transforming clinical trials, epidemiological studies, and patient data management, leading to more accurate diagnoses and treatment plans. Similarly, financial institutions are leveraging AI for quantitative trading, risk assessment, and fraud detection. The growing recognition of AI's potential to enhance research accuracy, reduce human error, and accelerate discovery is prompting organizations to invest heavily in quantitative research AI technologies.

From a regional perspective, North America currently dominates the Quantitative Research AI market, accounting for the largest share in 2024, followed closely by Europe and Asia Pacific. The presence of leading technology providers, a mature research ecosystem, and substantial investments in AI R&D are key factors supporting market growth in these regions. Asia Pacific is expected to witness the fastest CAGR during the forecast period, driven by rapid digital transformation, increasing government initiatives to promote AI adoption, and the emergence of innovative startups. Meanwhile, Latin America and the Middle East & Africa are gradually catching up, supported by growing awareness and investments in AI-powered research solutions. These regional dynamics underscore the global nature of the market and the diverse opportunities for growth across different geographies.

Component Analysis

The Component segment of the Quantitative Research AI market is broadly categorized into Software, Hardware, and Services, each playing a vital role in the overall ecosystem. Software represents the largest share of the market, as AI-driven quantitative research platforms and analytics tools are fundamental to the digital transformation of research methodologies. These software solutions encompass machine learning frameworks, data visualization tools, statistical analysis packages, and specialized AI algorithms tailored for quantitative research. The continuous evolution of AI software, coupled with advancements i

Thermal performance curves are an example of continuous reaction norm curves of common shape. Three modes of variation in these curves-- Vertical shift, horizontal shift, and generalist-specialist tradeoffs-- are of special interest to evolutionary biologists. Since two of these modes are nonlinear, traditional methods such as Principal Component Analysis fail to decompose the variation into biological modes and to quantify the variation associated with each mode. Here we present the results of a new method, Template Mode of Variation (TMV), that decomposes the variation into predetermined modes of variation for a particular set of thermal performance curves. We illustrate the method using data on thermal sensitivity of growth rate in Pieris rapae caterpillars. The TMV model explains 67% of the variation in thermal performance curves among families; generalist-specialist tradeoffs account for 38% of the total between-family variation. The TMV method implemented here is applicable to both differences in mean and patterns of variation, and can be used with either phenotypic or quantitative genetic data for thermal performance curves or other continuous reaction norms that have a template shape with a single maximum. The TMV approach may also apply to growth trajectories, age-specific life history traits and other function-valued traits.

We present a comprehensive and updated Python-based open software to calculate continuous symmetry measures (CSMs) and their related continuous chirality measure (CCM) of molecules across chemistry. These descriptors are used to quantify distortion levels of molecular structures on a continuous scale and were proven insightful in numerous studies. The input information includes the coordinates of the molecular geometry and a desired cyclic symmetry point group (i.e., Cs, Ci, Cn, or Sn). The results include the coordinates of the nearest symmetric structure that belong to the desired symmetry point group, the permutation that defines the symmetry operation, the direction of the symmetry element in space, and a number, between zero and 100, representing the level of symmetry or chirality. Rather than treating symmetry as a binary property by which a structure is either symmetric or asymmetric, the CSM approach quantifies the level of gray between black and white and allows one to follow the course of change. The software can be downloaded from https://github.com/continuous-symmetry-measure/csm or used online at https://csm.ouproj.org.il.

A low-cost quantitative continuous measurement of movements in the extremities of people with Parkinson’s disease was developed to enhance the gold-standard structured assessment of people with Parkinson’s disease (PD) assessed by the visual observation by the examiner of the person with PD (Goetz, et al., 2008) with the recorded output of signals to document the three dimensions of the positions in space of the finger and wrist or the toe and ankle of the participant performing tasks that may be impaired by PD (McKay, et al., 2019). The accelerometers were taped to the dorsal surface of the second (middle) phalanx of the index finger and the dorsum of the arm midway between the radius and the ulna two inches from the wrist joint to measure the movements in the upper extremity and to the dorsal surface of the proximal phalanx of the first (big) toe and the anterior surface of the tibia two inches proximal to the medial malleolus to measure the movements of the lower extremity (McKay, et al.,2019). The examiner instructed the participant how to perform each task. The examiner demonstrated the movements. The examiner did not continue to perform the movements while the participant was performing them. The examiner instructed the participant to perform each movement as quickly and fully as possible. The examiner encouraged the participant to execute each motion with the maximal speed and range of motion. The examiner sought to capture at least ten optimal repetitions for each motion. In order to attain a minimum of ten top-notch repetitions the examiner asked the participant to perform many more repetitions. The ten optimal repetitions could later be extracted for further analysis. The data shows trained examiner administering the procedures to a healthy 68-year-old male participant with typical development.

The data from this procedure performed on cohorts of individuals with Parkinson’s disease and multiple system atrophy and healthy age- and sex-matched individuals with typical development have been published (Harrigan, et al., 2020).

A quantitative continuous variable that reflects the risk of tree dieoff during a significant drought period (SPI48 drought = -2).

"A protocol for a low-cost quantitative continuous measurement of movements in the extremities of people with PD (McKay, et al., 2019) was administered to people with PD . . . and age- and sex-matched healthy control participants" (Harrigan, et al., Quantitative continuous measurement of movements in the extremities, 2020). "Healthy control participants were matched for age and sex with participants with PD. Participants with PD completed a single test session . . . , a test and a retest session . . . , or a test and two retest sessions . . . . HC participants completed test and retest sessions " (Harrigan, et al., Quantitative continuous measurement of movements in the extremities, 2020). Thirty-two trained raters who were certified in the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) (Goetz, et al., 2008) were presented the output of the ten participants with PD who completed a single test session (Pilot Test and Retest). Raters were presented two sets of 40 quizzes containing five representations for scoring of (A) output signals and FFTs and (B) CWTs (Pilot Test and Retest). Each quiz contained the panels of the x, y, and z representations of the finger and wrist or the toe and ankle of the five repetitive tasks. Each panel to be scored included six images corresponding to the signals of the three dimensions of the two accelerometers on a single extremity. The laterality of the representations was not stated. Raters were presented five sets of six images of the original signal and the fast Fourier transform (FFT) or the continuous wavelet transforms (CWTs). Raters were presented either five panels of output signals and FFTs or CWTs. Panels did not include output signals and FFTs and CWTs simultaneously. Raters were instructed to score (A) output signals and FFTs and (B) CWTs analogously to the clinical coding forms as indicated the the instructions in the data. The raters also completed the output of the ten participants with PD and eight HCs who completed a two test session (CWT Test and Retest). Raters were presented two sets of 72 quizzes containing five representations for scoring of (CWTs (Pilot Test and Retest). Each quiz contained the panels of averaged signals of the x, y, and z representations of the finger and wrist or the toe and ankle of the five repetitive tasks. Each panel to be scored included two images corresponding to the signals of the three dimensions of the two accelerometers on a single extremity. The laterality of the representations was not stated. Raters were asked to complete ratings independently at convenient times during the week.