Simultaneous prediction of symptom severity and cause in data from a test battery for Parkinson patients, using machine learning methods

The main purpose of this thesis project is to prediction of symptom severity and cause in data from test battery of the Parkinson’s disease patient, which is based on data mining. The collection of the data is from test battery on a hand in computer. We use the Chi-Square method and check which variables are important and which are not important. Then we apply different data mining techniques on our normalize data and check which technique or method gives good results.The implementation of this thesis is in WEKA. We normalize our data and then apply different methods on this data. The methods which we used are Naïve Bayes, CART and KNN. We draw the Bland Altman and Spearman’s Correlation for checking the final results and prediction of data. The Bland Altman tells how the percentage of our confident level in this data is correct and Spearman’s Correlation tells us our relationship is strong. On the basis of results and analysis we see all three methods give nearly same results. But if we see our CART (J48 Decision Tree) it gives good result of under predicted and over predicted values that’s lies between -2 to +2. The correlation between the Actual and Predicted values is 0,794in CART. Cause gives the better percentage classification result then disability because it can use two classes.

Face Detection and Facial Feature Localization for multi-pose faces and complex backgroundimages

The objective of this thesis work, is to propose an algorithm to detect the faces in a digital image with complex background. A lot of work has already been done in the area of face detection, but drawback of some face detection algorithms is the lack of ability to detect faces with closed eyes and open mouth. Thus facial features form an important basis for detection. The current thesis work focuses on detection of faces based on facial objects. The procedure is composed of three different phases: segmentation phase, filtering phase and localization phase. In segmentation phase, the algorithm utilizes color segmentation to isolate human skin color based on its chrominance properties. In filtering phase, Minkowski addition based object removal (Morphological operations) has been used to remove the non-skin regions. In the last phase, Image Processing and Computer Vision methods have been used to find the existence of facial components in the skin regions.This method is effective on detecting a face region with closed eyes, open mouth and a half profile face. The experiment’s results demonstrated that the detection accuracy is around 85.4% and the detection speed is faster when compared to neural network method and other techniques.

Conceptual Product Development in Small Corporations

The main objective of the thesis “Conceptual Product Development in Small Corporations” is by the use of a case study test the MFD™-method (Erixon G. , 1998) combined with PMM in a product development project. (Henceforth called MFD™/PMM-method). The MFD™/PMM-method used for documenting and controlling a product development project has since it was introduced been used in several industries and projects. The method has been proved to be a good way of working with the early stages of product development, however, there are almost only projects carried out on large industries which means that there are very few references to how the MFD™/PMM-method works in a small corporation. Therefore, was the case study in the thesis “Conceptual Product Development in Small Corporations” carried out in a small corporation to find out whether the MFD™/PMM-method also can be applied and used in such a corporation.The PMM was proposed in a paper presented at Delft University of Technology in Holland 1998 by the author and Gunnar Erixon. (See appended paper C: The chart of modular function deployment.) The title “The chart of modular function deployment” was later renamed as PMM, Product Management Map. (Sweden PreCAD AB, 2000). The PMM consists of a QFD-matrix linked to MIM (Module Indication Matrix) via a coupling matrix which makes it possible to make an unbroken chain from the customer domain to the designed product/modules. The PMM makes it easy to correct omissions made in creating new products and modules.In the thesis “Conceptual Product Development in Small Corporations” the universal MFD™/PMM-method has been adapted by the author to three models of product development; original-, evolutionary- and incremental development.The evolutionary adapted MFD™/PMM-method was tested as a case study at Atlings AB in the community Ockelbo. Atlings AB is a small corporation with a total number of 50 employees and an annual turnover of 9 million €. The product studied at the corporation was a steady rest for supporting long shafts in turning. The project team consisted of management director, a sales promoter, a production engineer, a design engineer and a workshop technician, the author as team leader and a colleague from Dalarna University as discussion partner. The project team has had six meetings.The project team managed to use MFD™ and to make a complete PMM of the studied product. There were no real problems occurring in the project work, on the contrary the team members worked very well in the group, having ideas how to improve the product. Instead, the challenge for a small company is how to work with the MFD™/PMM-method in the long run! If the MFD™/PMM-method is to be a useful tool for the company it needs to be used continuously and that requires financial and personnel resources. One way for the company to overcome the probable lack of recourses regarding capital and personnel is to establish a good cooperation with a regional university or a development centre.

Computational study of the step size parameter of the subgradient optimization method

The subgradient optimization method is a simple and flexible linear programming iterative algorithm. It is much simpler than Newton's method and can be applied to a wider variety of problems. It also converges when the objective function is non-differentiable. Since an efficient algorithm will not only produce a good solution but also take less computing time, we always prefer a simpler algorithm with high quality. In this study a series of step size parameters in the subgradient equation is studied. The performance is compared for a general piecewise function and a specific p-median problem. We examine how the quality of solution changes by setting five forms of step size parameter.

Corporal Punishment : A study about attitudes and opinions to corporal punishment and the connection to children’s rights in South Africa and Sweden

Corporal punishment is a worldwide problem. The purpose withthis thesis is to promote a constructive discussion about the problem andconnect this to children’s rights. This gives the possibility to start adiscussion about suggestions and measures to reduce the problem. Thetheory is that corporal punishment is used as a disciplinary method tochange behavior. Children’s rights is regulated by conventions and nationallaws. The method is to conduct an analysis with interpretations andcommentaries of the research materials from South Africa and Sweden.The conclusion is that those who are positive to corporal punishment thinksit is an efficient working method, and it is about children’s safety. Thosewho are negative have experienced that alternative methods works. Asuggestion is to involve children in the work with children’s rights andeducate them in human and children’s rights with focus on obligations andresponsibility.

Effective measures to decrease air contaminants through risk and control visualization : a study of the effective use of QR codes to facilitate safety training

Woodworking industries still consists of wood dust problems. Young workers are especially vulnerable to safety risks. To reduce risks, it is important to change attitudes and increase knowledge about safety. Safety training have shown to establish positive attitudes towards safety among employees. The aim of current study is to analyze the effect of QR codes that link to Picture Mix EXposure (PIMEX) videos by analyzing attitudes to this safety training method and safety in student responses. Safety training videos were used in upper secondary school handicraft programs to demonstrate wood dust risks and methods to decrease exposure to wood dust. A preliminary study was conducted to investigate improvement of safety training in two schools in preparation for the main study that investigated a safety training method in three schools. In the preliminary study the PIMEX method was first used in which students were filmed while wood dust exposure was measured and subsequently displayed on a computer screen in real time. Before and after the filming, teachers, students, and researchers together analyzed wood dust risks and effective measures to reduce exposure to them. For the main study, QR codes linked to PIMEX videos were attached at wood processing machines. Subsequent interviews showed that this safety training method enables students in an early stage of their life to learn about risks and safety measures to control wood dust exposure. The new combination of methods can create awareness, change attitudes and motivation among students to work more frequently to reduce wood dust.