This article presents opportunities for enriching anthropological knowledge and methods with machine learning and data analysis. Different examples show how quantitative methods empower anthropologists and how computa...
详细信息
This article presents opportunities for enriching anthropological knowledge and methods with machine learning and data analysis. Different examples show how quantitative methods empower anthropologists and how computational methods supplement ethnography, from sensor data and interview transcripts to designing technology solutions and automatically labeling cultural heritage. Conversely, the authors discuss the benefits of qualitative approaches in contemporary anthropological research and show how to transition from data analysis to ethnography and vice versa. Finally, the article pinpoints aspects in which each method can fail individually. It discusses why a combination of the two approaches, called circular mixed methods, minimizes the chance of failure and maximizes insights from the data.
Introduction Recently, a tool called the positron emission tomography (PET)-assisted reporting system (PARS) was developed and presented to classify lesions in PET/computed tomography (CT) studies in patients with lun...
详细信息
Introduction Recently, a tool called the positron emission tomography (PET)-assisted reporting system (PARS) was developed and presented to classify lesions in PET/computed tomography (CT) studies in patients with lung cancer or lymphoma. The aim of this study was to validate PARS with an independent group of lung-cancer patients using manual lesion segmentations as a reference standard, as well as to evaluate the association between PARS-based measurements and overall survival (OS). methods This study retrospectively included 115 patients who had undergone clinically indicated (18F)-fluorodeoxyglucose (FDG) PET/CT due to suspected or known lung cancer. The patients had a median age of 66 years (interquartile range [IQR]: 61-72 years). Segmentations were made manually by visual inspection in a consensus reading by two nuclear medicine specialists and used as a reference. The research prototype PARS was used to automatically analyse all the PET/CT studies. The PET foci classified as suspicious by PARS were compared with the manual segmentations. No manual corrections were applied. Total lesion glycolysis (TLG) was calculated based on the manual and PARS-based lung-tumour segmentations. Associations between TLG and OS were investigated using Cox analysis. Results PARS showed sensitivities for lung tumours of 55.6% per lesion and 80.2% per patient. Both manual and PARS TLG were significantly associated with OS. Conclusion Automatically calculated TLG by PARS contains prognostic information comparable to manually measured TLG in patients with known or suspected lung cancer. The low sensitivity at both the lesion and patient levels makes the present version of PARS less useful to support clinical reading, reporting and staging.
Awkward kneeling in sloped shingle installation operations exposes roofers to knee musculoskeletal disorder (MSD) risks. To address the varying levels of risk associated with different phases of shingle installation, ...
详细信息
Awkward kneeling in sloped shingle installation operations exposes roofers to knee musculoskeletal disorder (MSD) risks. To address the varying levels of risk associated with different phases of shingle installation, this research investigated utilizing machine learning to automatically classify seven distinct phases in a typical shingle installation task. The classification process relied on analyzing knee kinematics data and roof slope information. Nine participants were recruited and performed simulated shingle installation tasks while kneeling on a sloped wooden platform. The knee kinematics data were collected using an optical motion capture system. Three supervised machine learning classification methods (i.e., k-nearest neighbors (KNNs), decision tree (DT), and random forest (RF)) were selected for evaluation. The KNN classifier provided the best performance for overall accuracy. The results substantiated the feasibility of applying machine learning in classifying shingle installation phases from workers' knee joint rotation and roof slope angles, which may help facilitate method and tool development for automated knee MSD risk surveillance and assessment among roofers.
Here, we present an automatic data generation method which is fully computer-based for a variate X with an absolutely continuous probability density function ( pdf ) f exactly computable. The method uses computer-base...
详细信息
Here, we present an automatic data generation method which is fully computer-based for a variate X with an absolutely continuous probability density function ( pdf ) f exactly computable. The method uses computer-based on calculations of integrals (trapezoidal and/or the Monte-carlo method) for approximating the cumulative distribution function and next, the dichotomy algorithm to get the quantile function from which we obtain data from f . We apply the method to generate gig(a,b,c) data. The comparison with analogues, as in R Software is very successful. The method may work where the rejection method fails because of a lack of pdf bound which can be generated. The method might be slower but the area of more and more powerful computer is favorable to it. The implementation for gamma and/or gig laws in R codes are presented. Dans ce papier, nous proposons une méthode automatique de génération aléatoire de données basée sur l’évaluation des intégrales par la méthode trapezoidale ou par la méthode Monte-Carlo et l’algorithme de dichotomie pour le calcul des fonctions des quantiles. Cette méthode à été utilisée pour la génération de données gamma et gig.
A well-known application of water engineering is drinking water distribution through pipe networks in urban and rural areas. The present work addresses this issue with a specific focus on the network design. First, th...
详细信息
A well-known application of water engineering is drinking water distribution through pipe networks in urban and rural areas. The present work addresses this issue with a specific focus on the network design. First, the paper presents a brief review of computer-based design methods and shows that a significant number of efforts have been pursued. Secondly, it proposes the approach of geometric analysis of the distribution networks as complementary points of the former optimization methods. Finally, an original illustrative application is proposed. The geometric and multi-scale optimization known as the constructal design is used to analytically optimize T-shaped network architectures subject to an operational water quality constraint. This illustrative application leads to the determination of an optimal geometry of the network that minimizes head losses (factor of pumping energy). (C) 2012 Elsevier Ltd. All rights reserved.
Research Questions: It is becoming more and more important to stabilize the contents of conventional face to face therapy with computer-based therapy materials. With this method of self-conducted intervention, a highl...
详细信息
Research Questions: It is becoming more and more important to stabilize the contents of conventional face to face therapy with computer-based therapy materials. With this method of self-conducted intervention, a highly intensive therapy can be realized. In the present study the efficacy of a computer-based therapy was reviewed in which subjects relearned in a self-conducted manner the lexical retrieval of randomly generated items. Method: A commercial version of a computerised therapy programme (ITS/aphasiaware, Siemens) was applied in the experiment. Due to the pilot character of the study, a small-n design with two subjects with contrasting symptoms of aphasia was chosen: Subject A suffered from an acute, fluent aphasia with mild anomia;Subject B suffered from a chronic, nonfluent aphasia with severe anomia. Both patients named in 17/20 sessions 60 items at a time, which were randomly generated from an 832 items sized pool. On average every single item was presented only two times (range: I - 12). The computer-based training was completed without additional therapeutic help but the procedure was controlled, In addition, the subjects achieved unspecific motivation in their learning behaviour. Reactions were recorded, classified and assessed with a session-related item-score. Results: From session to session, the two subjects demonstrated a continuously and significantly improvement in performance. In pre- and post-tests, both Subjects showed more correct reactions. The responses became more related to the target-item. In addition, the influence of lexical parameters like length and frequency decreased. The benefit for both single cases underlines the assumption that Supervised, computer-based, self-conducted training of lexical retrieval is feasible and effective in different types of aphasia.
Objectives First, to compare the impact of nasally and orally dosed estradiol on breast density;second, to investigate the utility of computer-based automated approaches to the assessment of breast density with refere...
详细信息
Objectives First, to compare the impact of nasally and orally dosed estradiol on breast density;second, to investigate the utility of computer-based automated approaches to the assessment of breast density with reference to traditional methods. methods Digitized images from two 2-year, randomized, placebo-controlled trials formed the basis of the present post hoc analysis. Active treatments were 1 mg estradiol continuously combined with 0.125 mg trimegestone (oral hormone replacement therapy, HRT) or low-dose (150 or 300 mu g estradiol) nasal estradiol cyclically combined with 200 mg micronized progesterone (nasal HRT). The effects on breast density were assessed by a radiologist, providing the BI-RADS (R) score and the interactive threshold, and by a computer-based approach, providing the measure of stripiness and the HRT-effect specific measure of breast density. Results In the oral HRT trial, active treatment induced a significant increase in breast density, which was consistent in all methods used (all p0.05). In contrast, none of the methods detected significant changes in women receiving nasal HRT. The sensitivity of automated methods to discriminate HRT- from placebo-treated women was equal or better than the sensitivity of methods performed by the radiologist. Conclusions The markedly different pharmacokinetic profile of nasal estrogen seems to be associated with better breast safety. Automated computer-based analysis of digitized mammograms provides a sensitive measure of changes in breast density induced by hormones and could serve as a useful tool in future clinical trials.
暂无评论