scholarly journals Interpretable Machine Learning for Genomics

2021 ◽  
Author(s):  
David Watson
Keyword(s):  
Machine Learning ◽  
Cell Function ◽  
State Of The Art ◽  
Future Research ◽  
Computational Statistics ◽  
Close Collaboration ◽  
Current State ◽  
Interpretable Machine Learning ◽  
Underlying Mechanisms ◽  
Generation Sequencing

Abstract High-throughput technologies such as next generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of advanced statistical methods. Machine learning (ML) algorithms, which are designed to automatically find patterns in data, are well suited to this task. Yet these models are often so complex as to be opaque, leaving researchers with few clues about underlying mechanisms. Interpretable machine learning (iML) is a burgeoning subdiscipline of computational statistics devoted to making the predictions of ML models more intelligible to end users. This article is a gentle and critical introduction to iML, with an emphasis on genomic applications. I define relevant concepts, motivate leading methodologies, and provide a simple typology of existing approaches. I survey recent examples of iML in genomics, demonstrating how such techniques are increasingly integrated into research workflows. I argue that iML solutions are required to realize the promise of precision medicine. However, several open challenges remain. I examine the limitations of current state of the art tools and propose a number of directions for future research. While the horizon for iML in genomics is wide and bright, continued progress requires close collaboration across disciplines.

scholarly journals Evolutionary Machine Learning for Multi-Objective Class Solutions in Medical Deformable Image Registration

Algorithms ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 99 ◽  
Author(s):  
Kleopatra Pirpinia ◽  
Peter A. N. Bosman ◽  
Jan-Jakob Sonke ◽  
Marcel van Herk ◽  
Tanja Alderliesten
Keyword(s):  
Machine Learning ◽  
Image Registration ◽  
State Of The Art ◽  
Deformable Image Registration ◽  
Optimization Approach ◽  
High Quality ◽  
Trade Off ◽  
Multi Objective ◽  
Current State ◽  
Image Artefacts

Current state-of-the-art medical deformable image registration (DIR) methods optimize a weighted sum of key objectives of interest. Having a pre-determined weight combination that leads to high-quality results for any instance of a specific DIR problem (i.e., a class solution) would facilitate clinical application of DIR. However, such a combination can vary widely for each instance and is currently often manually determined. A multi-objective optimization approach for DIR removes the need for manual tuning, providing a set of high-quality trade-off solutions. Here, we investigate machine learning for a multi-objective class solution, i.e., not a single weight combination, but a set thereof, that, when used on any instance of a specific DIR problem, approximates such a set of trade-off solutions. To this end, we employed a multi-objective evolutionary algorithm to learn sets of weight combinations for three breast DIR problems of increasing difficulty: 10 prone-prone cases, 4 prone-supine cases with limited deformations and 6 prone-supine cases with larger deformations and image artefacts. Clinically-acceptable results were obtained for the first two problems. Therefore, for DIR problems with limited deformations, a multi-objective class solution can be machine learned and used to compute straightforwardly multiple high-quality DIR outcomes, potentially leading to more efficient use of DIR in clinical practice.

scholarly journals A Lab Model for Symptom Exaggeration: What do we Need?

2016 ◽  
Vol 8 (1) ◽  
pp. 55-75 ◽  
Author(s):  
Isabella J. M. Niesten ◽  
Harald Merckelbach ◽  
Alfons Van Impelen ◽  
Marko Jelicic ◽  
Angel Manderson ◽  
...  
Keyword(s):  
Cognitive Dissonance ◽  
State Of The Art ◽  
Future Research ◽  
Current Form ◽  
Research Participants ◽  
Current State ◽  
Symptom Exaggeration ◽  
Valid Data ◽  
Theoretical Foundations

This article reflects on the current state of the art in research on individuals who exaggerate their symptoms (i.e., feigning). We argue that the most commonly used approach in this field, namely simply providing research participants with instructions to overreport symptoms, is valuable for validating measures that tap into symptom exaggeration, but is less suitable for addressing the theoretical foundations of feigning. That is, feigning serves to actively mislead others and is done deliberately. These characteristics produce experiences (e.g., feelings of guilt) in individuals who feign that lab research in its current form is unable to accommodate for. Paradigms that take these factors into account may not only yield more ecologically valid data, but may also stimulate a shift from the study of how to detect feigning to more fundamental issues. One such issue is the cognitive dissonance (e.g., feelings of guilt) that – in some cases – accompanies feigning and that may foster internalized fabrications. We present three studies (N's = 78, 60, and 54) in which we tried to abate current issues and discuss their merits for future research.

Sport in business studies: a state-of-the-art literature review

2018 ◽  
Vol 8 (5) ◽  
pp. 529-546
Author(s):  
Christofer Laurell ◽  
Sten Soderman
Keyword(s):  
Systematic Review ◽  
Literature Review ◽  
Marketing Strategy ◽  
Design Methodology ◽  
State Of The Art ◽  
Future Research ◽  
Content Type ◽  
Business Studies ◽  
Current State ◽  
State Of Research

PurposeThe purpose of this paper is to provide a systematic review of articles on sport published in leading business studies journals within marketing, organisational studies and strategy.Design/methodology/approachBased on a review of 38 identified articles within the subfields of marketing, strategy and organisation studies published between 2000 and 2015, the articles’ topical, theoretical and methodological orientation within the studied subfields were analysed followed by a cross-subfield analysis.FindingsThe authors identify considerable differences in topical, theoretical and methodological orientation among the studied subfields’ associated articles. Overall, the authors also find that articles across all subfields tend to be focussed on contributing to mature theory, even though the subfield of marketing in particular exhibits contributions to nascent theory in contrast to organisation studies and strategy.Originality/valueThis paper contributes by illustrating the current state of research that is devoted or related to the phenomenon of sport within three subfields in business studies. Furthermore, the authors discuss the role played by leading business studies journalsvis-à-vissport sector-specific journals and offer avenues for future research.

scholarly journals Screen media use and ADHD-related behaviors: Four decades of research

2018 ◽  
Vol 115 (40) ◽  
pp. 9875-9881 ◽  
Author(s):  
Ine Beyens ◽  
Patti M. Valkenburg ◽  
Jessica Taylor Piotrowski
Keyword(s):  
Children And Adolescents ◽  
Media Use ◽  
Differential Susceptibility ◽  
Attention Problems ◽  
Future Research ◽  
Screen Media ◽  
Current State ◽  
The Media ◽  
Screen Media Use ◽  
Underlying Mechanisms

The diagnosis of attention-deficit/hyperactivity disorder (ADHD) among children and adolescents has increased considerably over the past decades. Scholars and health professionals alike have expressed concern about the role of screen media in the rise in ADHD diagnosis. However, the extent to which screen media use and ADHD are linked remains a point of debate. To understand the current state of the field and, ultimately, move the field forward, we provide a systematic review of the literature on the relationship between children and adolescents’ screen media use and ADHD-related behaviors (i.e., attention problems, hyperactivity, and impulsivity). Using the Differential Susceptibility to Media effects Model as a theoretical lens, we systematically organize the existing literature, identify potential shortcomings in this literature, and provide directions for future research. The available evidence suggests a statistically small relationship between media and ADHD-related behaviors. Evidence also suggests that individual child differences, such as gender and trait aggression, may moderate this relationship. There is a clear need for future research that investigates causality, underlying mechanisms, and differential susceptibility to the effects of screen media use on ADHD-related behaviors. It is only through a richer empirical body that we will be able to fully understand the media–ADHD relationship.

scholarly journals Detecting Emotions in English and Arabic Tweets

Information ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 98 ◽  
Author(s):  
Tariq Ahmad ◽  
Allan Ramsay ◽  
Hanady Ahmed
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Learning Algorithms ◽  
General Purpose ◽  
Machine Learning Algorithms ◽  
Current State ◽  
Optimal Thresholds ◽  
Alternative Approach

Assigning sentiment labels to documents is, at first sight, a standard multi-label classification task. Many approaches have been used for this task, but the current state-of-the-art solutions use deep neural networks (DNNs). As such, it seems likely that standard machine learning algorithms, such as these, will provide an effective approach. We describe an alternative approach, involving the use of probabilities to construct a weighted lexicon of sentiment terms, then modifying the lexicon and calculating optimal thresholds for each class. We show that this approach outperforms the use of DNNs and other standard algorithms. We believe that DNNs are not a universal panacea and that paying attention to the nature of the data that you are trying to learn from can be more important than trying out ever more powerful general purpose machine learning algorithms.

System integration of high intensity energy subsystems – a thermal management challenge

2008 ◽  
Vol 112 (1134) ◽  
pp. 477-482
Author(s):  
D. M. Pratt ◽  
D. Moorhouse
Keyword(s):  
Thermal Management ◽  
Air Force ◽  
System Integration ◽  
High Intensity ◽  
State Of The Art ◽  
Cooling Capacity ◽  
Future Research ◽  
Current State ◽  
Management Capability ◽  
Management Challenge

Current and future Air Force weapons systems lack the necessary power and cooling capacity to provide full systems level capability as a result of energy and thermal management limitations. Cooling capacity of fuel is already fully utilised leaving little room for additional cooling needs. Additionally, increasing speed, power, and miniaturisation of future systems continue to stress any thermal management capability that we can now deliver. Thus, the focus of this paper is a conceptual assessment of the key energy and thermal management technologies to meet the future energy challenges. It presents an overview of the current state of the art and also possible future research.

scholarly journals A Survey on Evolutionary Computation Approaches to Feature Selection

2021 ◽  
Author(s):  
Bing Xue ◽  
Mengjie Zhang ◽  
William Browne ◽  
X Yao
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Evolutionary Computation ◽  
State Of The Art ◽  
Search Space ◽  
Mining Machine ◽  
Future Research ◽  
Selection Problems ◽  
Personal Use ◽  
Index Terms

Feature selection is an important task in data miningand machine learning to reduce the dimensionality of the dataand increase the performance of an algorithm, such as a clas-sification algorithm. However, feature selection is a challengingtask due mainly to the large search space. A variety of methodshave been applied to solve feature selection problems, whereevolutionary computation techniques have recently gained muchattention and shown some success. However, there are no compre-hensive guidelines on the strengths and weaknesses of alternativeapproaches. This leads to a disjointed and fragmented fieldwith ultimately lost opportunities for improving performanceand successful applications. This paper presents a comprehensivesurvey of the state-of-the-art work on evolutionary computationfor feature selection, which identifies the contributions of thesedifferent algorithms. In addition, current issues and challengesare also discussed to identify promising areas for future research. Index Terms—Evolutionary computation, feature selection,classification, data mining, machine learning. © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Sign in / Sign up

Export Citation Format

Share Document