Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
26,308
result(s) for
"Sampling techniques"
Sort by:
importance of correcting for sampling bias in MaxEnt species distribution models
AIM: Advancement in ecological methods predicting species distributions is a crucial precondition for deriving sound management actions. Maximum entropy (MaxEnt) models are a popular tool to predict species distributions, as they are considered able to cope well with sparse, irregularly sampled data and minor location errors. Although a fundamental assumption of MaxEnt is that the entire area of interest has been systematically sampled, in practice, MaxEnt models are usually built from occurrence records that are spatially biased towards better‐surveyed areas. Two common, yet not compared, strategies to cope with uneven sampling effort are spatial filtering of occurrence data and background manipulation using environmental data with the same spatial bias as occurrence data. We tested these strategies using simulated data and a recently collated dataset on Malay civet Viverra tangalunga in Borneo. LOCATION: Borneo, Southeast Asia. METHODS: We collated 504 occurrence records of Malay civets from Borneo of which 291 records were from 2001 to 2011 and used them in the MaxEnt analysis (baseline scenario) together with 25 environmental input variables. We simulated datasets for two virtual species (similar to a range‐restricted highland and a lowland species) using the same number of records for model building. As occurrence records were biased towards north‐eastern Borneo, we investigated the efficacy of spatial filtering versus background manipulation to reduce overprediction or underprediction in specific areas. RESULTS: Spatial filtering minimized omission errors (false negatives) and commission errors (false positives). We recommend that when sample size is insufficient to allow spatial filtering, manipulation of the background dataset is preferable to not correcting for sampling bias, although predictions were comparatively weak and commission errors increased. MAIN CONCLUSIONS: We conclude that a substantial improvement in the quality of model predictions can be achieved if uneven sampling effort is taken into account, thereby improving the efficacy of species conservation planning.
Journal Article
Hyperparameter Optimization and Combined Data Sampling Techniques in Machine Learning for Customer Churn Prediction: A Comparative Analysis
This paper explores the application of various machine learning techniques for predicting customer churn in the telecommunications sector. We utilized a publicly accessible dataset and implemented several models, including Artificial Neural Networks, Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, and gradient boosting techniques (XGBoost, LightGBM, and CatBoost). To mitigate the challenges posed by imbalanced datasets, we adopted different data sampling strategies, namely SMOTE, SMOTE combined with Tomek Links, and SMOTE combined with Edited Nearest Neighbors. Moreover, hyperparameter tuning was employed to enhance model performance. Our evaluation employed standard metrics, such as Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). In terms of the F1-score metric, CatBoost demonstrates superior performance compared to other machine learning models, achieving an outstanding 93% following the application of Optuna hyperparameter optimization. In the context of the ROC AUC metric, both XGBoost and CatBoost exhibit exceptional performance, recording remarkable scores of 91%. This achievement for XGBoost is attained after implementing a combination of SMOTE with Tomek Links, while CatBoost reaches this level of performance after the application of Optuna hyperparameter optimization.
Journal Article
Comparison of reference distributions acquired by direct and indirect sampling techniques: exemplified with the Pediatric Reference Interval in China (PRINCE) study
Background
Our study aimed to compare the reference distributions of serum creatinine and urea obtained by direct sampling technique and two indirect sampling techniques including the Gaussian Mixture Model (GMM) and the Self-Organizing Map (SOM) clustering based on clinical laboratory records, so that the feasibility as well as the potential limitations of indirect sampling techniques could be clarified.
Methods
The direct sampling technique was used in the Pediatric Reference Interval in China (PRINCE) study, in which 15,150 healthy volunteers aged 0 to 19 years were recruited from 11 provinces across China from January 2017 to December 2018. The indirect sampling techniques were used in the Laboratory Information System (LIS) database of Beijing Children’s Hospital, in which 164,710 outpatients were included for partitioning of potential healthy individuals by GMM or SOM from January to December 2016. The reference distributions of creatinine and urea that were established by the PRINCE study and the LIS database were compared.
Results
The density curves of creatinine and urea based on the PRINCE data and the GMM and SOM partitioned LIS data showed a large overlap. However, deviations were found in reference intervals among the three populations.
Conclusions
Both GMM and SOM can identify potential healthy individuals from the LIS data. The performance of GMM is consistent and stable. However, GMM relies on Gaussian fitting, and thus is not suitable for skewed data. SOM is applicable for high-dimensional data, and is adaptable to data distribution. But it is susceptible to sample size and outlier detection strategy.
Journal Article
Designing occupancy studies: general advice and allocating survey effort
1. The fraction of sampling units in a landscape where a target species is present (occupancy) is an extensively used concept in ecology. Yet in many applications the species will not always be detected in a sampling unit even when present, resulting in biased estimates of occupancy. Given that sampling units are surveyed repeatedly within a relatively short timeframe, a number of similar methods have now been developed to provide unbiased occupancy estimates. However, practical guidance on the efficient design of occupancy studies has been lacking. 2. In this paper we comment on a number of general issues related to designing occupancy studies, including the need for clear objectives that are explicitly linked to science or management, selection of sampling units, timing of repeat surveys and allocation of survey effort. Advice on the number of repeat surveys per sampling unit is considered in terms of the variance of the occupancy estimator, for three possible study designs. 3. We recommend that sampling units should be surveyed a minimum of three times when detection probability is high (> 0·5 survey-1), unless a removal design is used. 4. We found that an optimal removal design will generally be the most efficient, but we suggest it may be less robust to assumption violations than a standard design. 5. Our results suggest that for a rare species it is more efficient to survey more sampling units less intensively, while for a common species fewer sampling units should be surveyed more intensively. 6. Synthesis and applications. Reliable inferences can only result from quality data. To make the best use of logistical resources, study objectives must be clearly defined; sampling units must be selected, and repeated surveys timed appropriately; and a sufficient number of repeated surveys must be conducted. Failure to do so may compromise the integrity of the study. The guidance given here on study design issues is particularly applicable to studies of species occurrence and distribution, habitat selection and modelling, metapopulation studies and monitoring programmes.
Journal Article
Smart credit card fraud detection system based on dilated convolutional neural network with sampling technique
Numerous organization including financial industry are highly supported the online service payments due to the massive growth of Internet commerce and banking. But, those financial industry faces global losses due to increases of fraud and also the customer losses the trust in online banking, because credit card frauds (CCF) are mostly occurred due to high usage of Internet. Therefore, financial institutions and merchants faces the heavy losses, because illegal transactions are carried out by unauthorized user without the knowledge of actual card users. In addition, availability of public data, high false alarms, imbalance problems in data, changing nature of frauds increases the challenges in the detection of CCF. Researchers uses the Machine Learning (ML) techniques for designing the Detection system for CCF (CCFD), however, these ML didn’t offers much efficiency. Therefore, to solve these issues of ML, nowadays, Deep Learning (DL) is applied in the area of CCFD. In this research work, one-dimensional Dilated Convolutional Neural Network (DCNN) is designed to solve the issues of CCFD by learning both spatial and temporal features. Here, the base model of CNN is improved by implementing the dilated convolutional layer (DCL). The imbalance problem is solved by under-sampling and over-sampling techniques. The experiments are carried out on three datasets in terms of various parameters and compared with existing CNN model. The simulation results proved that proposed DCNN model with sampling technique achieved 97.39% of accuracy on small card database, where CNN achieved 94.44% of accuracy on the same database.
Journal Article
Advances and development in sampling techniques for marine water resources: a comprehensive review
Marine water resources (including seawater and pore-water) provide important information for understanding the marine environment, studying marine organisms, and developing marine resources. Obtaining high-quality marine water samples is significant to marine scientific research and monitoring of marine resources. Since the 20th century, marine water resources sampling technology has become the key research direction of marine equipment. In order to have a comprehensive understanding of marine water resource sampling technology, promote the development of marine water resource sampling technology, and obtain high-quality marine water samples, this paper summarizes the current development status of the sampling technology of marine water resources from the aspects of research and application. This paper first provides an overview of seawater and pore water sampling techniques. The two sampling technologies are categorized and discussed according to different sampling means, and the advantages of different sampling means are compared. We also found similarities between seawater and pore water sampling means. Then, a comprehensive analysis of existing technologies and equipment reveals the development trend of marine water resources sampling technology, for example, the need for high temporal and spatial accuracy in sampling, etc. Finally, it explores the challenges facing deep-sea water sampling technology regarding future research, development and equipment industrialization. These reviews not only help researchers better understand the current development of marine water sampling technologies but also provide an important reference for the future development of marine water sampling technology, which provides guidance and support for in-depth marine scientific research and effective use of marine resources.
Journal Article
Review and Analysis of Key Techniques in Marine Sediment Sampling
Deep-sea sediment is extremely important in marine scientific research, such as that concerning marine geology and microbial communities. The research findings are closely related to the in-situ information of the sediment. One prerequisite for investigations of deep-sea sediment is providing sampling techniques capable of preventing distortion during recovery. As the fruit of such sampling techniques, samplers designed for obtaining sediment have become indispensable equipment, owing to their low cost, light weight, compactness, easy operation, and high adaptability to sea conditions. This paper introduces the research and application of typical deep-sea sediment samplers. Then, a representative sampler recently developed in China is analyzed. On this basis, a review and analysis is conducted regarding the key techniques of various deep-sea sediment samplers, including sealing, pressure and temperature retaining, low-disturbance sampling, and no-pressure drop transfer. Then, the shortcomings in the key techniques for deep-sea sediment sampling are identified. Finally, prospects for the future development of key techniques for deep-sea sediment sampling are proposed, from the perspectives of structural diversification, functional integration, intelligent operation, and high-fidelity samples. This paper summarizes the existing samplers in the context of the key techniques mentioned above, and can provide reference for the optimized design of samplers and development of key sampling techniques.
Journal Article
Optimising recovery of DNA from minimally invasive sampling methods: Efficacy of buccal swabs, preservation strategy and DNA extraction approaches for amphibian studies
Studies in evolution, ecology and conservation are increasingly based on genetic and genomic data. With increased focus on molecular approaches, ethical concerns about destructive or more invasive techniques need to be considered, with a push for minimally invasive sampling to be optimised. Buccal swabs have been increasingly used to collect DNA in a number of taxa, including amphibians. However, DNA yield and purity from swabs are often low, limiting its use. In this study, we compare different types of swabs, preservation method and storage, and DNA extraction techniques in three case studies to assess the optimal approach for recovering DNA in anurans. Out of the five different types of swabs that we tested, Isohelix MS‐02 and Rapidry swabs generated higher DNA yields than other swabs. When comparing storage buffers, ethanol is a better preservative than a non‐alcoholic alternative. Dried samples resulted in similar or better final DNA yields compared to ethanol‐fixed samples if kept cool. DNA extraction via a Qiagen™ DNeasy Blood and Tissue Kit and McHale's salting‐out extraction method resulted in similar DNA yields but the Qiagen™ kit extracts contained less contamination. We also found that samples have better DNA recovery if they are frozen as soon as possible after collection. We provide recommendations for sample collection and extraction under different conditions, including budgetary considerations, size of individual animal sampled, access to cold storage facilities and DNA extraction methodology. Maximising efficacy of all of these factors for better DNA recovery will allow buccal swabs to be used for genetic and genomic studies in a range of vertebrates. In this multiple‐case study, we tested a comprehensive set of factors impacting DNA recovery from buccal swabs, including the type of swab, storage type and conditions and DNA extraction method. Based on our results, we are able to propose recommendations for improved DNA recovery, taking into consideration budget and field condition constraints.
Journal Article
A new modified estimator of population variance in calibrated survey sampling
In survey statistics, estimating and reducing population variation is crucial. These variations can occur in any sampling design, including stratified random sampling, where stratum weights may increase the variance of estimators. Calibration techniques, which use additional auxiliary information, can help mitigate this issue. This paper examines three calibration-based estimators—calibration variance, calibration ratio, and calibration exponential ratio estimators—within the framework of stratified random sampling. The study generates data from normal, gamma, and exponential distributions to test these estimators. Results demonstrate that the proposed calibration estimators offer more accurate estimates of population variance and outperform existing methods in estimating population variance under stratified random sampling, providing more accurate and reliable estimates.
Journal Article