scholarly journals Neural hierarchical models of ecological populations

2019 ◽  
Author(s):  
Maxwell B. Joseph
Keyword(s):  
Neural Networks ◽  
Hierarchical Models ◽  
Large Data ◽  
Ecological Processes ◽  
Natural Systems ◽  
Bird Populations ◽  
Continental Scale ◽  
North American Bird ◽  
The Relationship

AbstractNeural networks are increasingly being used in science to infer hidden dynamics of natural systems from noisy observations, a task typically handled by hierarchical models in ecology. This paper describes a class of hierarchical models parameterized by neural networks: neural hierarchical models. The derivation of such models analogizes the relationship between regression and neural networks. A case study is developed for a neural dynamic occupancy model of North American bird populations, trained on millions of detection/non-detection time series for hundreds of species, providing insights into colonization and extinction at a continental scale. Flexible models are increasingly needed that scale to large data and represent ecological processes. Neural hierarchical models satisfy this need, providing a bridge between deep learning and ecological modeling that combines the function representation power of neural networks with the inferential capacity of hierarchical models.

scholarly journals Persistent impacts of West Nile virus on North American bird populations

2015 ◽  
Vol 112 (46) ◽  
pp. 14290-14294 ◽  
Author(s):  
T. Luke George ◽  
Ryan J. Harrigan ◽  
Joseph A. LaManna ◽  
David F. DeSante ◽  
James F. Saracco ◽  
...  
Keyword(s):  
West Nile Virus ◽  
Disease Risk ◽  
Phylogenetic Analyses ◽  
West Nile ◽  
Factors Affecting ◽  
Bird Populations ◽  
Continental Scale ◽  
North American Bird ◽  
Avian Populations ◽  
The Impact

Since its introduction to North America in 1999, West Nile virus (WNV) has had devastating impacts on native host populations, but to date these impacts have been difficult to measure. Using a continental-scale dataset comprised of a quarter-million birds captured over nearly two decades and a recently developed model of WNV risk, we estimated the impact of this emergent disease on the survival of avian populations. We find that populations were negatively affected by WNV in 23 of the 49 species studied (47%). We distinguished two groups of species: those for which WNV negatively impacted survival only during initial spread of the disease (n = 11), and those that show no signs of recovery since disease introduction (n = 12). Results provide a novel example of the taxonomic breadth and persistent impacts of this wildlife disease on a continental scale. Phylogenetic analyses further identify groups (New World sparrows, finches, and vireos) disproportionally affected by temporary or persistent WNV effects, suggesting an evolutionary dimension of disease risk. Identifying the factors affecting the persistence of a disease across host species is critical to mitigating its effects, particularly in a world marked by rapid anthropogenic change.

scholarly journals Using Deep Learning to Predict Sentiments: Case Study in Tourism

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
C. A. Martín ◽  
J. M. Torres ◽  
R. M. Aguilar ◽  
S. Diaz
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Short Term Memory ◽  
Tourism Industry ◽  
Digital Platforms ◽  
Mass Tourism ◽  
Link Type ◽  
Learning Techniques ◽  
The Relationship

Technology and the Internet have changed how travel is booked, the relationship between travelers and the tourism industry, and how tourists share their travel experiences. As a result of this multiplicity of options, mass tourism markets have been dispersing. But the global demand has not fallen; quite the contrary, it has increased. Another important factor, the digital transformation, is taking hold to reach new client profiles, especially the so-called third generation of tourism consumers, digital natives who only understand the world through their online presence and who make the most of every one of its advantages. In this context, the digital platforms where users publish their impressions of tourism experiences are starting to carry more weight than the corporate content created by companies and brands. In this paper, we propose using different deep-learning techniques and architectures to solve the problem of classifying the comments that tourists publish online and that new tourists use to decide how best to plan their trip. Specifically, in this paper, we propose a classifier to determine the sentiments reflected on the http://booking.com and http://tripadvisor.com platforms for the service received in hotels. We develop and compare various classifiers based on convolutional neural networks (CNN) and long short-term memory networks (LSTM). These classifiers were trained and validated with data from hotels located on the island of Tenerife. An analysis of our findings shows that the most accurate and robust estimators are those based on LSTM recurrent neural networks.

scholarly journals Examining the Presence of Symmetry within Acheulean Handaxes: A Case Study in the British Palaeolithic

2015 ◽  
Vol 25 (4) ◽  
pp. 713-732 ◽  
Author(s):  
James Cole
Keyword(s):  
Material Culture ◽  
Social Relationships ◽  
Large Data ◽  
Data Set ◽  
Large Data Set ◽  
The Relationship ◽  
Lower Palaeolithic

This paper examines the relationship between the presence of symmetry and the Acheulean biface within a predominantly British Lower Palaeolithic context. There has been a long-standing notion within Palaeolithic studies that Acheulean handaxes are symmetrical and become increasingly so as time progress as a reflection of increasing hominin cognitive and behavioural complexity. Specifically, the presence of symmetry within Acheulean handaxes is often seen as one of the first examples of material culture being used to mediate social relationships. However, this notion has never been satisfactorily tested against a large data set. This paper seeks to address the issue by conducting an analysis of some 2680 bifaces across a chronological and geographical span. The results from the sample presented here are that symmetrical bifaces do not appear to have a particularly strong presence in any assemblage and do not appear to increase as time progress. These results have significant implications for modern researchers assessing the cognitive and behavioural complexities of Acheulean hominins.

Sales Forecast for Garment Companies with Cluster Analysis and Modified Neural Networks

2011 ◽  
Vol 127 ◽  
pp. 490-495
Author(s):  
Li Yu ◽  
Yun Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Cluster Analysis ◽  
Sales Forecast ◽  
The Neural Network ◽  
Linkage Cluster ◽  
Relationship Of ◽  
Marketing Resource Allocation ◽  
The Relationship

For the companies of the garment industry, managers often dedicate their efforts to forecast the sales accurately while making decisions for marketing resource allocation and scheduling. Based on the historical database, this paper constructs a method to investigate the relationship of the relating factors and sales values. The proposed method combines the cluster analysis and modified neural networks to fulfill the sales forecast task. Firstly, the average linkage cluster algorithm is applied to cluster similar sales values. Secondly, a modified neural network is used to investigate the mapping relationship between those influencing factors and the sales clusters. The method employs a self-adjust mechanism to determine the structure of the neural network. The effectiveness of the proposed method is illustrated with a case study of a garment company in Shanghai.

scholarly journals An algorithm for quantifying and characterizing misleading trajectories in ecological processes

2020 ◽  
Author(s):  
Christie A. Bahlai ◽  
Easton R. White ◽  
Julia D. Perrone ◽  
Sarah Cusser ◽  
Kaitlin Stack Whitney
Keyword(s):  
Fundamental Problem ◽  
Sampled Data ◽  
Short Term ◽  
Ecological Processes ◽  
Temporal Aspects ◽  
Long Term Ecological Research ◽  
Long Term Trends ◽  
The Relationship

AbstractA fundamental problem in ecology is understanding how to scale discoveries: from patterns we observe in the lab or the plot to the field or the region or bridging between short term observations to long term trends. At the core of these issues is the concept of trajectory—that is, when can we have reasonable assurance that we know where a system is going? In this paper, we describe a non-random resampling method to directly address the temporal aspects of scaling ecological observations by leveraging existing data. Findings from long-term research sites have been hugely influential in ecology because of their unprecedented longitudinal perspective, yet short-term studies more consistent with typical grant cycles and graduate programs are still the norm.We directly address bridging the gap between the short-term and the long-term by developing an automated, systematic resampling approach: in short, we repeatedly ‘sample’ moving windows of data from existing long-term time series, and analyze these sampled data as if they represented the entire dataset. We then compile typical statistics used to describe the relationship in the sampled data, through repeated samplings, and then use these derived data to gain insights to the questions: 1) how often are the trends observed in short-term data misleading, and 2) can we use characteristics of these trends to predict our likelihood of being misled? We develop a systematic resampling approach, the ‘bad-breakup’ algorithm, and illustrate its utility with a case study of firefly observations produced at the Kellogg Biological Station Long-Term Ecological Research Site (KBS LTER). Through a variety of visualizations, summary statistics, and downstream analyses, we provide a standardized approach to evaluating the trajectory of a system, the amount of observation required to find a meaningful trajectory in similar systems, and a means of evaluating our confidence in our conclusions.

scholarly journals EVALUATING VISUAL IMPRESSIONS BASED ON GAZE ANALYSIS AND DEEP LEARNING: A CASE STUDY OF ATTRACTIVENESS EVALUATION OF STREETS IN DENSELY BUILT-UP WOODEN RESIDENTIAL AREA

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 887-894
Author(s):  
T. Oki ◽  
S. Kizawa
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Residential Area ◽  
Eye Tracker ◽  
Residential Areas ◽  
Evaluation Result ◽  
The Relationship ◽  
Activation Mapping

Abstract. This paper examines the possibility of impression evaluation based on gaze analysis of subjects and deep learning, using an example of evaluating street attractiveness in densely built-up wooden residential areas. Firstly, the relationship between the subjects' gazing tendency and their evaluation of street image attractiveness is analysed by measuring the subjects' gaze with an eye tracker. Next, we construct a model that can estimate an attractiveness evaluation result using convolutional neural networks (CNNs), combined with the method of gradient-weighted class activation mapping (Grad-CAM) - these in in visualizing which street components can contribute to evaluating attractiveness. Finally, we discuss the similarity between the subjects' gaze tendencies and activation heatmaps created by Grad-CAM.

Sign in / Sign up

Export Citation Format

Share Document