Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Linda Nici, Claudio Donner, Emiel Wouters, Richard Zuwallack, Nicolino Ambrosino, Jean Bourbeau, Mauro Carone, Bartolome Celli, Marielle Engelen, Bonnie Fahy, Chris Garvey, Roger Goldstein, Rik Gosselink, Suzanne Lareau, Neil MacIntyre, Francois Maltais, Mike Morgan, Denis O’Donnell, Christian Prefault, Jane Reardon, Carolyn Rochester, Annemie Schols, Sally Singh, and Thierry Troosters, on behalf of the ATS/ERS Pulmonary Rehabilitation Writing Committee

/pdf/american-thoracic-society-european-respiratory-society-fshcxcru7i.pdf

American Thoracic Society/European Respiratory Society Statement on Pulmonary Rehabilitation

https://pubag.nal.usda.gov/download/21951/PDF

The US Department of Agriculture Automated Multiple-Pass Method reduces bias in the collection of energy intakes

"Pulmonary rehabilitation is a process which systematically uses scientifically based diagnostic management and evaluation options to achieve the optimal daily functioning and health-related quality of life of individual patients, suffering from impairment and disability due to chronic respiratory disease as measured by clinically and/or physiologically relevant outcome parameters." This recent definition by the European Respiratory Society (ERS) task force "Rehabilitation and chronic care" [1] stresses the aims of a pulmonary rehabilitation treatment: "optimal daily functioning" and "quality of life". It also indicates that outcome parameters should be measured, and that they should be clinically and physiologically relevant. The ERS-position paper further requires that all existing treatment options available for the widest possible range of patients with chronic lung disease should be applied in rehabilitation. Components of such a programme are: exercise training; gymnastic exercise; respiratory muscle training; chest physiotherapy and breathing retraining; education; psychological counselling; nutritional therapy; ventilatory support, long-term oxygen therapy, and nursing care. Consequently, pulmonary rehabilitation is a very complex and expensive treatment, and should be performed by a team of several professionals working in close co-operation in one institute. The cost is such, that a careful selection of motivated patients, a scientifically based diagnosis and a meticulous quantification of the outcome is mandatory. The place for rehabilitation in asthma, cystic fibrosis, or in the context of lung volume reduction surgery has been outlined by several authors, but remains outside the scope of this editorial. The above suggests that the efficacy of all treatment modalities is unequivocal. This is not always true. Previously, there was an almost universal agreement that the impairment at the level of lung function can hardly be improved by rehabilitation. However, recent findings by C AS A BURI [2] showed that in patients with severe chronic obstructive pulmonary disease (COPD), the forced expiratory volume in one second (FEV1) can also improve by 9%. This seems to be a small change in FEV1, but considering the hyperbolic relationship between airway resistance and FEV1, this modest improvement in the low ranges of FEV1 means a considerable decrease in airway resistance. It is not clear how and why this change in FEV1 was brought about; it must have contributed to the improvement in exercise performance of 36%, probably by a less dynamic hyperinflation during exercise? The latter will contribute to a lower level of exercise dyspnoea [3]. Impairment of peripheral muscle function occurs in patients with COPD, due to a reduced amount of oxidative enzymes [4, 5]. Apart from the ventilatory limitation due to airway obstruction and limited respiratory muscle function, this peripheral muscle weakness substantially contributes to the exercise limitation in patients with COPD. G OS S E LI N K et al. [6] showed that the maximal oxygen consumption (V 'O2,max) and the 6 min walking distance correlated significantly with the maximal force of the quadriceps muscle. Nutritional depletion can be one of the factors in the malfunctioning of peripheral and respiratory muscles: the energy expenditure of patients with COPD often exceeds the caloric intake. Nutritional supplementation, anabolic steroids, and training can improve the function of these muscle groups, and also improve exercise performance [7, 8]. Dysfunction of peripheral muscles can be substantially reversed by training in patients with COPD. An increase in oxidative enzyme content in peripheral muscles was shown to occur after endurance training at 60% of pretreatment work loads, in patients with severe COPD (FEV1 36% pred), thus improving oxidative exercise capacity. The lactate threshold increased, and exercise hyperpnoea decreas

https://erj.ersjournals.com/content/erj/11/3/520.full.pdf

Pulmonary rehabilitation in chronic obstructive pulmonary disease.

Exercise Physiology: Energy, Nutrition and Human Performance

Undereating and underrecording of habitual food intake in obese men: selective underreporting of fat intake

Tissue depletion and health related quality of life in patients with chronic obstructive pulmonary disease.

Purpose of reviewThis is a review of recent studies on the analysis of misreporting of food intake and on the consequences of misreporting for the interpretation of dietary surveys. Bias in the assessment of dietary intake was analysed from studies comparing reported intake with doubly labelled wate

Validity of the assessment of dietary intake: problems of misreporting.

Objective: The aim of this study was to develop models for the detection of type, duration, and intensity of human physical activity using one triaxial accelerometer.

Methods: Twenty subjects (age = 29 +/- 6 yr, BMI = 23.6 +/- 3.2 kg[middle dot]m-2) performed 20 selected activities, including walking, running, and cycling, wearing one triaxial accelerometer mounted on the lower back. Identification of activity type was based on a decision tree. The decision tree evaluated attributes (features) of the acceleration signal. The features were measured in intervals of defined duration (segments). Segment size determined the time resolution of the decision tree to assess activity duration. Decision trees with a time resolution of 0.4, 0.8, 1.6, 3.2, 6.4, and 12.8 s were developed, and the respective classification performances were evaluated. Multiple linear regression was used to estimate speed of walking, running, and cycling based on acceleration features.

Results: Maximal accuracy for the classification of activity type (93%) was reached when the segment size of analysis was 6.4 or 12.8 s. The smaller the segment size, the lower the classification accuracy achieved. Segments of 6.4 s gave the highest time resolution for measuring activity duration without decreasing the classification accuracy. The developed models estimated walking, running, and cycling speeds with a standard error of 0.20, 1.26, and 1.36 km[middle dot]h-1, respectively.

Conclusions: This study demonstrated the ability of a triaxial accelerometer in detecting type, duration, and intensity of physical activity using models based on acceleration features. Future studies are needed to validate the presented models in free-living conditions.

/pdf/detection-of-type-duration-and-intensity-of-physical-6t1ui4x5l6.pdf

Detection of type, duration, and intensity of physical activity using an accelerometer.

Accelerometers are often used to quantify the acceleration of the body in arbitrary units (counts) to measure physical activity (PA) and to estimate energy expenditure. The present study investigated whether the identification of types of PA with one accelerometer could improve the estimation of energy expenditure compared with activity counts. Total energy expenditure (TEE) of 15 subjects was measured with the use of double-labeled water. The physical activity level (PAL) was derived by dividing TEE by sleeping metabolic rate. Simultaneously, PA was measured with one accelerometer. Accelerometer output was processed to calculate activity counts per day (AC(D)) and to determine the daily duration of six types of common activities identified with a classification tree model. A daily metabolic value (MET(D)) was calculated as mean of the MET compendium value of each activity type weighed by the daily duration. TEE was predicted by AC(D) and body weight and by AC(D) and fat-free mass, with a standard error of estimate (SEE) of 1.47 MJ/day, and 1.2 MJ/day, respectively. The replacement in these models of AC(D) with MET(D) increased the explained variation in TEE by 9%, decreasing SEE by 0.14 MJ/day and 0.18 MJ/day, respectively. The correlation between PAL and MET(D) (R(2) = 51%) was higher than that between PAL and AC(D) (R(2) = 46%). We conclude that identification of activity types combined with MET intensity values improves the assessment of energy expenditure compared with activity counts. Future studies could develop models to objectively assess activity type and intensity to further increase accuracy of the energy expenditure estimation.

/pdf/improving-assessment-of-daily-energy-expenditure-by-xikw8jzp06.pdf

Annelies H. C. Goris

Papers

Undereating and underrecording of habitual food intake in obese men: selective underreporting of fat intake

Tissue depletion and health related quality of life in patients with chronic obstructive pulmonary disease.

Validity of the assessment of dietary intake: problems of misreporting.

Detection of type, duration, and intensity of physical activity using an accelerometer.

Improving assessment of daily energy expenditure by identifying types of physical activity with a single accelerometer