Dynamic feature selection for spam filtering using support vector machine

Spam is commonly defined as unsolicited email messages and the goal of spam filtering is to differentiate spam from legitimate email. Much work have been done to filter spam from legitimate emails using machine learning algorithm and substantial performance has been achieved with some amount of false positive (FP) tradeoffs. In this paper, architecture of spam filtering has been proposed based on support vector machine (SVM,) which will get better accuracy by reducing FP problems. In this architecture an innovative technique for feature selection called dynamic feature selection (DFS) has been proposed which is enhanced the overall performance of the architecture with reduction of FP problems. The experimental result shows that the proposed technique gives better performance compare to similar existing techniques.

How much physical activity is enough to prevent unhealthy weight gain? Outcome of the IASO 1st Stock Conference and consensus statement

A consensus meeting was held in Bangkok, 21–23 May 2002, where experts and young scientists in the field of physical activity, energy expenditure and bodyweight regulation discussed the different aspects of physical activity in relation to the emerging problem of obesity worldwide. The following consensus statement was accepted unanimously.
‘The current physical activity guideline for adults of 30 minutes of moderate
intensity activity daily, preferably all days of the week, is of importance for
limiting health risks for a number of chronic diseases including coronary heart disease and diabetes. However for preventing weight gain or regain this guideline is likely to be insufficient for many individuals in the current environment. There is compelling evidence that prevention of weight regain in formerly obese individuals requires 60–90 minutes of moderate intensity activity or lesser amounts of vigorous intensity activity. Although definitive data are lacking, it seems likely that moderate intensity activity of approximately 45 to 60 minutes per day, or 1.7 PAL (Physical Activity Level) is required to prevent the transition to overweight or obesity. For children, even more activity time is recommended. A good approach for many individuals to obtain the recommended level of physical activity is to reduce sedentary behaviour by incorporating more incidental and leisure-time activity into the daily routine. Political action is imperative
to effect physical and social environmental changes to enable and encourage physical activity. Settings in which these environmental changes can be implemented include the urban and transportation infrastructure, schools, and workplaces.’

Identifying the energy gap: magnitude and determinants of 5-year weight gain in midage women

Objective: The aims of this study were to estimate average yearly weight gain in midage women and to identify the determinants of weight gain and gaining weight at double the average rate.
Research Methods and Procedures: The study sample comprised 8071 participants (45 to 55 years old) in the Australian Longitudinal Study on Women's Health who completed mailed surveys in 1996, 1998, and 2001.
Results: On average, the women gained almost 0.5 kg per year [average 2.42 kg (95% confidence interval, 2.29 to 2.54) over 5 years]. In multivariate analyses, variables associated with energy balance (physical activity, sitting time, and energy intake), as well as quitting smoking, menopause/hysterectomy, and baseline BMI category were significantly associated with weight gain, but other behavioral and demographic characteristics were not. After adjustment for all of the other biological and behavioral variables, the odds of gaining weight at about twice the average rate (>5 kg over 5 years) were highest for women who quit smoking (odds ratio = 2.94; 95% confidence interval, 2.17, 3.96). There were also independent relationships between the odds of gaining >5 kg and lower levels of habitual physical activity, more time spent sitting, energy intake (but only in women with BMI > 25 at baseline), menopause transition, and hysterectomy.
Discussion: The average weight gain equates with an energy imbalance of only about 10 kcal or 40 kJ per day, which suggests that small sustained changes in the modifiable behavioral variables could prevent further weight gain.

A meta-learning approach to automatic kernel selection for support vector machines

Appropriate choice of a kernel is the most important ingredient of the kernel-based learning methods such as support vector machine (SVM). Automatic kernel selection is a key issue given the number of kernels available, and the current trial-and-error nature of selecting the best kernel for a given problem. This paper introduces a new method for automatic kernel selection, with empirical results based on classification. The empirical study has been conducted among five kernels with 112 different classification problems, using the popular kernel based statistical learning algorithm SVM. We evaluate the kernels’ performance in terms of accuracy measures. We then focus on answering the question: which kernel is best suited to which type of classification problem? Our meta-learning methodology involves measuring the problem characteristics using classical, distance and distribution-based statistical information. We then combine these measures with the empirical results to present a rule-based method to select the most appropriate kernel for a classification problem. The rules are generated by the decision tree algorithm C5.0 and are evaluated with 10 fold cross validation. All generated rules offer high accuracy ratings.

Improved support vector machine generalization using normalized input space

Data pre-processing always plays a key role in learning algorithm performance. In this research we consider data pre-processing by normalization for Support Vector Machines (SVMs). We examine the normalization affect across 112 classification problems with SVM using the rbf kernel. We observe a significant classification improvement due to normalization. Finally we suggest a rule based method to find when normalization is necessary for a specific classification problem. The best normalization method is also automatically selected by SVM itself.

On rapid vector alignment in permanent magnet brushless motor

A software replacement for the commutation signals of a permanent magnet brushless motor is presented. The feedback observed acceleration loop or equivalently the high-order position polynomial controller allows finding the initial relative orientation between the two magnetic fields of the motors within a fraction of a second. Also, using the proposed method allows a considerable cost saving, since the transducer that is usually used for this purpose can be eliminated. The cost saving is most obvious in the case of linear motors and angle motors with large diameters. The way the problem is posed is an essential part of this work and it is the reason behind the apparent simplicity of the solution. The method has been tested when a relative encoder was used and the motor current was regulated.

Nonlinear discrimination using support vector machine

Appropriate training data always play an important role in constructing an efficient classifier to solve the data mining classification problem. Support Vector Machine (SVM) is a comparatively new approach in constructing a model/classifier for data analysis, based on Statistical Learning Theory (SLT). SVM utilizes a transformation of the basic constrained optimization problem compared to that of a quadratic programming method, which can be solved parsimoniously through standard methods. Our research focuses on SVM to classify a number of different sizes of data sets. We found SVM to perform well in the case of discrimination compared to some other existing popular classifiers.

Where pain = no gain : perspectives on sport, exercise and health, c. 1850-1920

A common perspective today is that sportspeople must train and compete to a level of exertion beyond the ‘pain threshold’ if they are to succeed; a view that has given rise to the popular expression ‘No Pain, No Gain’. Indeed, a common aphorism is that the health and quality of life of individuals and of the wider population is positively correlated with the frequency and vigour of physical exercise. In the period when modern sports were taking on their present characteristics (approximately 1850-1920), the prevailing opinions about the health and well-being effects of exercise were far more cautious, however. While the benefits of moderate exercise for physical and mental well-being went without question, too great an exertion was considered to be as risky as too little, causing ‘strain’ with the potential to inflict lasting and potentially fatal damage, including mental and physical complaints as diverse as neuralgia and ‘athletes’ heart’. The supposedly more strenuous sports, such as football, athletics and rowing, and the training required for them came under particular scrutiny in medical and popular discourses. This paper, an exercise in historical sociology, examines these discourses to demonstrate how advice about the risks on health of participating in sports and of too little or too much exercise more generally, was informed by prevailing physiological models and the interpretation of these within the medical profession and the wider population. The data sources include medical journals and texts, and sports training manuals from the period under investigation.

Economic Evaluation of a Primary Care Trial to Reduce Weight Gain in Overweight/Obese Children: The LEAP Trial

Background:- A common policy response to the childhood obesity epidemic is to recommend that primary care physicians screen for and offer counseling to the overweight/obese. As the literature suggests, this approach may be ineffective; it is important to document the opportunity costs incurred by brief primary care obesity interventions that ultimately may not alter body mass index (BMI) trajectory.

Methods:- Live, Eat and Play (LEAP) was a randomized controlled trial of a brief secondary prevention intervention delivered by family physicians in 2002-2003 that targeted overweight/ mildly obese children aged 5 to 9 years. Primary care utilization was prospectively audited via medical records, and parents reported family resource use by written questionnaire. Outcome measures were BMI (primary) and parent-reported physical activity and dietary habits (secondary) in intervention compared with control children.

Results:- The cost of LEAP per intervention family was AU $4094 greater than for control families, mainly due to increased family resources devoted to child physical activity. Total health sector costs were AU $873 per intervention family and AU $64 per control, a difference of AU $809 {P < .001). At 15 months, intervention children did not differ significantly in adjusted BMI or daily physical activity scores compared with the control group, but dietary habits had improved.

Conclusions:- This brief intervention resulted in higher costs to families and the health care sector, which could have been devoted to other uses that do create benefits to health and/or family well-being. This has implications for countries such as the United States, the United Kingdom, and Australia, whose current guidelines recommend routine surveillance and counseling for high child BMI in the primary care sector.

Reducing unhealthy weight gain in children through community capacity−building: results of a quasi−experimental intervention program, Be Active Eat Well

Background:
Be Active Eat Well (BAEW) was a multifaceted community capacity-building program promoting healthy eating and physical activity for children (aged 4–12 years) in the Australian town of Colac.
Objective:
To evaluate the effects of BAEW on reducing children's unhealthy weight gain.
Methods:
BAEW had a quasi-experimental, longitudinal design with anthropometric and demographic data collected on Colac children in four preschools and six primary schools at baseline (2003, n=1001, response rate: 58%) and follow-up (2006, n=839, follow-up rate: 84%). The comparison sample was a stratified random selection of preschools (n=4) and primary schools (n=12) from the rest of the Barwon South Western region of Victoria, with baseline assessment in 2003–2004 (n=1183, response rate: 44%) and follow-up in 2006 (n=979, follow-up rate: 83%).
Results:
Colac children had significantly lower increases in body weight (mean: -0.92 kg, 95% CI: -1.74 to -0.11), waist (-3.14 cm, -5.07 to -1.22), waist/height (-0.02, -0.03 to -0.004), and body mass index z-score (-0.11, -0.21 to -0.01) than comparison children, adjusted for baseline variable, age, height, gender, duration between measurements and clustering by school. In Colac, the anthropometric changes were not related to four indicators of socioeconomic status (SES), whereas in the comparison group 19/20 such analyses showed significantly greater gains in anthropometry in children from lower SES families. Changes in underweight and attempted weight loss were no different between the groups.
Conclusions:
Building community capacity to promote healthy eating and physical activity appears to be a safe and effective way to reduce unhealthy weight gain in children without increasing health inequalities.