Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Brytmånens utformning vid trädfällning - Jämförande studier av böjmotstånd och gångjärnseffekt : Designing felling hinge in tree felling - Comparative studies of bending resistance and hinge effect

Vid trädfällning med motorsåg sparar man en så kallad brytmån som skall fungera som ett gång¬järn när trädet fälls. Om brytmånen går av tidigt finns en risk att trädet faller okontrolle¬rat. De rekommendationer som finns säger att brytmånens bredd skall göras proportionell mot trädets diameter. Genom att teoretiskt och praktiskt undersöka vilka krafter brytmånen utsätts för och vad den håller för har det varit möjligt att dra vissa slutsatser om hur en bra brytmån skall se ut. Ett viktigt resultat är att en bred brytmån (över 30-40 mm) är mycket trög att böja och inte fungerar i det avseendet att den går av redan vid små böjningar. Teoretiska be¬räkningar och praktiska försök visar att en relativt smal brytmån håller för belastningen vid rakt motlut även på stora träd. Som ny rekommendationen föreslås att brytmånens bredd inte bör vara mer än 30 mm. Av försöken kan man också dra slutsatsen att frusen ved är stel och brister tidigt, varför svår¬fällda träd inte bör fällas när veden är fryst.A felling hinge is used when felling trees by help of chain saw. If the hinge breaks early in the fall of the tree there is a great risk that the tree will fall without control. Present recommenda¬tions in Sweden say that the thickness of the felling hinge shall be made in proportion to the stem diameter. By use of theoretical and practical examinations of the forces stressing the felling hinge, and the strength of the wood itself, it has been possible to draw conclusions regarding the correct design of a felling hinge. One important result is that a thick felling hinge (over 30-40 mm) is very hard to bend and does not work well as it looses most of its strength already at a small forward bending angel. Theoretical calculations and practical tests show that a relatively narrow felling hinge will manage very well the forces when felling trees with lean opposite to the felling direction even for large trees. Our new recommendation is that the thickness of the felling hinge in normal Swedish conditions should not exceed 30 mm. Through the studies it can also be seen that frozen, brittle wood breaks at small bending angels. For that reason particularly difficult trees not should be felled when the wood is frozen.

Kraftutveckling för manuella trädfällningsredskap : Force development for manual tree felling tools

The objective with this study has been to build general models of the mechanics in tree felling with chain-saw and to compare felling torque for different tools. The theoretical models are completed and validated with a comparative study. The study includes a great number of felling tools of which some are used with different methods. Felling torque was measured using a naturally like measuring arrangement where a tree is cut at about 3.7 m height and then anchored with a dynamometer to a tree opposite to the felling direction. Notch and felling cut was made as ordinary with exception that the hinge was made extra thin to reduce bending resistance. The tree was consequently not felled during the trials and several combinations of felling tools and individuals could be used on the same tree.The results show big differences between tools, methods and persons. The differences were, however, not general, but could vary depending on conditions (first of all tree diameters). Tools and methods that push or pull on the stem are little affected by the size of the tree, while tools that press on the stump are very much dependent of a large stump-diameter. Hand force asserted on a simple pole is consequently a powerful tool on small trees. For trees of medium size there are several alternative methods with different sizes and brands of felling levers and wedges. Larger and more ungainly tools and methods like tree pusher, winch, etc. develop very high felling torque on all tree sizes. On large trees also the felling wedge and especially the use of several wedges together develop very high felling torque.

Quality management for vital forest tree seedlings : Final report, Project no: P33854-1

The work concerns development of a prototype molecular tests to identify vitality status of conifer seedlings. The work is done by NSure, Holland, Dalarna University and SUAS. In case for spruce, a successful validation experiment has been performed to validate the identified frost tolerance and vitality genes. Multiple indicators were identified that can be used to either reinforce the existing ColdnSure test, but also for development of a vitality test. The identified frost tolerance and vitality genes for pine still need to be validated. NSure together with Dalarna University aim to perform a validation next season. Multiple LN indicators were identified in spruce that can be used to determine the effectiveness of a LN treatment, but they are not yet validated. In spruce and pine hardly any scientific research is performed to study the effect of a LN treatment, particularly not at molecular level. Therefore NSure together with Dalarna Research Station want to apply for a project. Within this project, we would be able to develop the tests further.

Predictive models for chronic renal disease using decision trees, naïve bayes and case-based methods

Data mining can be used in healthcare industry to “mine” clinical data to discover hidden information for intelligent and affective decision making. Discovery of hidden patterns and relationships often goes intact, yet advanced data mining techniques can be helpful as remedy to this scenario. This thesis mainly deals with Intelligent Prediction of Chronic Renal Disease (IPCRD). Data covers blood, urine test, and external symptoms applied to predict chronic renal disease. Data from the database is initially transformed to Weka (3.6) and Chi-Square method is used for features section. After normalizing data, three classifiers were applied and efficiency of output is evaluated. Mainly, three classifiers are analyzed: Decision Tree, Naïve Bayes, K-Nearest Neighbour algorithm. Results show that each technique has its unique strength in realizing the objectives of the defined mining goals. Efficiency of Decision Tree and KNN was almost same but Naïve Bayes proved a comparative edge over others. Further sensitivity and specificity tests are used as statistical measures to examine the performance of a binary classification. Sensitivity (also called recall rate in some fields) measures the proportion of actual positives which are correctly identified while Specificity measures the proportion of negatives which are correctly identified. CRISP-DM methodology is applied to build the mining models. It consists of six major phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.