Automatic Lameness Detection in a Milking Robot : Instrumentation, measurement software, algorithms for data analysis and a neural network model

The aim of this thesis is to develop a fully automatic lameness detection system that operates in a milking robot. The instrumentation, measurement software, algorithms for data analysis and a neural network model for lameness detection were developed. Automatic milking has become a common practice in dairy husbandry, and in the year 2006 about 4000 farms worldwide used over 6000 milking robots. There is a worldwide movement with the objective of fully automating every process from feeding to milking. Increase in automation is a consequence of increasing farm sizes, the demand for more efficient production and the growth of labour costs. As the level of automation increases, the time that the cattle keeper uses for monitoring animals often decreases. This has created a need for systems for automatically monitoring the health of farm animals. The popularity of milking robots also offers a new and unique possibility to monitor animals in a single confined space up to four times daily. Lameness is a crucial welfare issue in the modern dairy industry. Limb disorders cause serious welfare, health and economic problems especially in loose housing of cattle. Lameness causes losses in milk production and leads to early culling of animals. These costs could be reduced with early identification and treatment. At present, only a few methods for automatically detecting lameness have been developed, and the most common methods used for lameness detection and assessment are various visual locomotion scoring systems. The problem with locomotion scoring is that it needs experience to be conducted properly, it is labour intensive as an on-farm method and the results are subjective. A four balance system for measuring the leg load distribution of dairy cows during milking in order to detect lameness was developed and set up in the University of Helsinki Research farm Suitia. The leg weights of 73 cows were successfully recorded during almost 10,000 robotic milkings over a period of 5 months. The cows were locomotion scored weekly, and the lame cows were inspected clinically for hoof lesions. Unsuccessful measurements, caused by cows standing outside the balances, were removed from the data with a special algorithm, and the mean leg loads and the number of kicks during milking was calculated. In order to develop an expert system to automatically detect lameness cases, a model was needed. A probabilistic neural network (PNN) classifier model was chosen for the task. The data was divided in two parts and 5,074 measurements from 37 cows were used to train the model. The operation of the model was evaluated for its ability to detect lameness in the validating dataset, which had 4,868 measurements from 36 cows. The model was able to classify 96% of the measurements correctly as sound or lame cows, and 100% of the lameness cases in the validation data were identified. The number of measurements causing false alarms was 1.1%. The developed model has the potential to be used for on-farm decision support and can be used in a real-time lameness monitoring system.

Sustainable forest management : ecologically sound and socially accepted

This dissertation explored the ecological dimension of ecologically sustainable forest management in boreal forests, and factors of the socio-cultural dimension that affect how the concept of ecologically sustainable forest management is defined. My approach was problem-oriented and generalistic-holistic. I examined associations between the abundances of wildlife groups (grouse, large predators, small predators, ungulates) and Siberian flying squirrels, and their co-occurrence with tree structural characteristics at the regional level. The trade-offs between ecological, social and economic sustainability in forestry were explored at the regional scale. I identified a potential 'shopping basket' of regional indicators for ecologically sustainable forest management, combining the relative abundance of Siberian flying squirrels, a wildlife richness index (WRI) for grouse, diversity indices of saw-timber trees, tree age classes and the proportion of old-growth (> 120 yr) forests. I suggest that the close association between forestry activity, the proportion of young forests (< 40 yr) and a WRI for small predators can be considered as potential 'alarm bells' for regions in which the creation of trade-offs (negative relationships) between economic and ecological components of sustainable forestry is ongoing. Explorative analyses revealed negative relationships between forestry activity and a WRI of 16 game species, the WRI for grouse and tree age diversity. Socially sustainable communities compete less intensively with ecological components of forests than communities where forestry is important. Interestingly, forest ownership types (farmers, other private forest owners, the forestry industry, the State) correlated significantly with the co-occurrence of flying squirrels, grouse and diverse forest structural characteristics rather than, for instance, with the total number of protection areas, suggesting that private forest ownership can lead to increased ecological sustainability. I examined forest actors’ argumentation to identify characteristics that affect the interpretation of ecologically sustainable forest management. Four argumentation frame types were constructed: information, work, experience and own position based. These differed in terms of their emphasis on external experts or own experiences. The closer ecologically sustainable forest management is to the forest actor’s daily life, the more profiled policy tools (counselling, learning through experiences) are needed to guide management behaviour to become more ecologically sound. I illustrated that forest actors interpret, use and understand information through meaningful framing. I analysed the extent to which ecological research information has been perceived in the Forestry Development Centre TAPIO’s recommendations and revised PEFC Finland criteria. We noticed that the political value for decaying wood was much lower in PEFC Finland critera (4 m3) than could be expected as a socially acceptable level (9 m3) or ecologically sound (10-20 m3). I consider it important for scientists to join political discourses and become involved in policy making concerning sustainable forest management to learn to present their results in a way that is reasonable from the user’s perspective.

Alikasvoksen mittaus ja kartoitus laserkeilauksella

Tasaikäisen metsän alle muodostuvilla alikasvoksilla on merkitystä puunkorjuun, metsänuudistamisen, näkemä-ja maisema-analyysien sekä biodiversiteetin ja hiilitaseen arvioinnin kannalta. Ilma-aluksista tehtävä laserkeilaus on osoittautunut tehokkaaksi kaukokartoitusmenetelmäksi varttuneiden puustojen mittauksessa. Laserkeilauksen käyttöönotto operatiivisessa metsäsuunnittelussa mahdollistaa aiempaa tarkemman tiedon tuottamisen alikasvoksista, mikäli alikasvoksen ominaisuuksia voidaan tulkita laseraineistoista. Tässä työssä käytettiin tarkasti mitattuja maastokoealoja ja kaikulaserkeilausaineistoja (discrete return LiDAR) usealta vuodelta (1–2 km lentokorkeus, 0,9–9,7 pulssia m-2). Laserkeilausaineistot oli hankittu Optech ALTM3100 ja Leica ALS50-II sensoreilla. Koealat edustavat suomalaisia tasaikäisiä männiköitä eri kehitysvaiheissa. Tutkimuskysymykset olivat: 1) Minkälainen on alikasvoksesta saatu lasersignaali yksittäisen pulssin tasolla ja mitkä tekijät signaaliin vaikuttavat? 2) Mikä on käytännön sovelluksissa hyödynnettävien aluepohjaisten laserpiirteiden selitysvoima alikasvospuuston ominaisuuksien ennustamisessa? Erityisesti haluttiin selvittää, miten laserpulssin energiahäviöt ylempiin latvuskerroksiin vaikuttavat saatuun signaaliin, ja voidaanko laserkaikujen intensiteetille tehdä energiahäviöiden korjaus. Puulajien väliset erot laserkaiun intensiteetissä olivat pieniä ja vaihtelivat keilauksesta toiseen. Intensiteetin käyttömahdollisuudet alikasvoksen puulajin tulkinnassa ovat siten hyvin rajoittuneet. Energiahäviöt ylempiin latvuskerroksiin aiheuttivat alikasvoksesta saatuun lasersignaaliin kohinaa. Energiahäviöiden korjaus tehtiin alikasvoksesta saaduille laserpulssin 2. ja 3. kaiuille. Korjauksen avulla pystyttiin pienentämään kohteen sisäistä intensiteetin hajontaa ja parantamaan kohteiden luokittelutarkkuutta alikasvoskerroksessa. Käytettäessä 2. kaikuja oikeinluokitusprosentti luokituksessa maan ja yleisimmän puulajin välillä oli ennen korjausta 49,2–54,9 % ja korjauksen jälkeen 57,3–62,0 %. Vastaavat kappa-arvot olivat 0,03–0,13 ja 0,10–0,22. Tärkein energiahäviöitä selittävä tekijä oli pulssista saatujen aikaisempien kaikujen intensiteetti, mutta hieman merkitystä oli myös pulssin leikkausgeometrialla ylemmän latvuskerroksen puiden kanssa. Myös 3. kaiuilla luokitustarkkuus parani. Puulajien välillä havaittiin eroja siinä, kuinka herkästi ne tuottavat kaiun laserpulssin osuessa puuhun. Kuusi tuotti kaiun suuremmalla todennäköisyydellä kuin lehtipuut. Erityisen selvä tämä ero oli pulsseilla, joissa oli energiahäviöitä. Laserkaikujen korkeusjakaumapiirteet voivat siten olla riippuvaisia puulajista. Sensorien välillä havaittiin selviä eroja intensiteettijakaumissa, mikä vaikeuttaa eri sensoreilla hankittujen aineistojen yhdistämistä. Myös kaiun todennäköisyydet erosivat jonkin verran sensorien välillä, mikä aiheutti pieniä eroavaisuuksia kaikujen korkeusjakaumiin. Aluepohjaisista laserpiirteistä löydettiin alikasvoksen runkolukua ja keskipituutta hyvin selittäviä piirteitä, kun rajoitettiin tarkastelu yli 1 m pituisiin puihin. Piirteiden selitysvoima oli parempi runkoluvulle kuin keskipituudelle. Selitysvoima ei merkittävästi alentunut pulssitiheyden pienentyessä, mikä on hyvä asia käytännön sovelluksia ajatellen. Lehtipuun osuutta ei pystytty selittämään. Tulosten perusteella kaikulaserkeilausta voi olla mahdollista hyödyntää esimerkiksi ennakkoraivaustarpeen arvioinnissa. Sen sijaan alikasvoksen tarkempi luokittelu (esim. puulajitulkinta) voi olla vaikeaa. Kaikkein pienimpiä alikasvospuita ei pystytä havaitsemaan. Lisää tutkimuksia tarvitaan tulosten yleistämiseksi erilaisiin metsiköihin.

Birth of the European individual : Outline of a theory of legal practice

The modern subject is what we can call a self-subjecting individual. This is someone in whose inner reality has been implanted a more permanent governability, a governability that works inside the agent. Michel Foucault s genealogy of the modern subject is the history of its constitution by power practices. By a flight of imagination, suppose that this history is not an evolving social structure or cultural phenomenon, but one of those insects (moth) whose life cycle consists of three stages or moments: crawling larva, encapsulated pupa, and flying adult. Foucault s history of power-practices presents the same kind of miracle of total metamorphosis. The main forces in the general field of power can be apprehended through a generalisation of three rationalities functioning side-by-side in the plurality of different practices of power: domination, normalisation and the law. Domination is a force functioning by the rationality of reason of state: the state s essence is power, power is firm domination over people, and people are the state s resource by which the state s strength is measured. Normalisation is a force that takes hold on people from the inside of society: it imposes society s own reality its empirical verity as a norm on people through silently working jurisdictional operations that exclude pathological individuals too far from the average of the population as a whole. The law is a counterforce to both domination and normalisation. Accounting for elements of legal practice as omnihistorical is not possible without a view of the general field of power. Without this view, and only in terms of the operations and tactical manoeuvres of the practice of law, nothing of the kind can be seen: the only thing that practice manifests is constant change itself. However, the backdrop of law s tacit dimension that is, the power-relations between law, domination and normalisation allows one to see more. In the general field of power, the function of law is exactly to maintain the constant possibility of change. Whereas domination and normalisation would stabilise society, the law makes it move. The European individual has a reality as a problem. What is a problem? A problem is something that allows entry into the field of thought, said Foucault. To be a problem, it is necessary for certain number of factors to have made it uncertain, to have made it lose familiarity, or to have provoked a certain number of difficulties around it . Entering the field of thought through problematisations of the European individual human forms, power and knowledge one is able to glimpse the historical backgrounds of our present being. These were produced, and then again buried, in intersections between practices of power and games of truth. In the problem of the European individual one has suitable circumstances that bring to light forces that have passed through the individual through centuries.