As people across the globe are becoming more interested in watching their weight, eating more healthily, and avoiding obesity, a system that can measure calories and nutrition in everyday meals can be very useful. Recently, there has been an increase in the usage of personal mobile technology such as smartphones or tablets, which users carry with them practically all the time. In this paper, we proposed a food calorie and nutrition measurement system that can help patients and dieticians to measure and manage daily food intake. Our system is built on food image processing and uses nutritional fact tables. Via a special calibration technique, our system uses the built-in camera of such mobile devices and records a photo of the food before and after eating it in order to measure the consumption of calorie and nutrient components. The proposed algorithm used color, texture and contour segmentation and extracted important features such as shape, color, size and texture. Using various combinations of these features and applying a support vector machine as a classifier, a good classification was achieved and simulation results show that the algorithm recognizes food categories with an accuracy rate of 92.2%, on average.

As people across the globe are becoming more interested in watching their weight, eating more healthily, and avoiding obesity, a system that can measure calories and nutrition in everyday meals can be very useful. Recently, there has been an increase in the usage of personal mobile technology such as smartphones or tablets, which users carry with them practically all the time. In this paper, we proposed a food calorie and nutrition measurement system that can help patients and dieticians to measure and manage daily food intake. Our system is built on food image processing and uses nutritional fact tables. Via a special calibration technique, our system uses the built-in camera of such mobile devices and records a photo of the food before and after eating it in order to measure the consumption of calorie and nutrient components. The proposed algorithm used color, texture and contour segmentation and extracted important features such as shape, color, size and texture. Using various combinations of these features and applying a support vector machine as a classifier, a good classification was achieved and simulation results show that the algorithm recognizes food categories with an accuracy rate of 92.2%, on average.

As people across the globe are becoming more interested in watching their weight, eating more healthily, and avoiding obesity, a system that can measure calories and nutrition in everyday meals can be very useful. Recently, there has been an increase in the usage of personal mobile technology such as smartphones or tablets, which users carry with them practically all the time. In this paper, we proposed a food calorie and nutrition measurement system that can help patients and dieticians to measure and manage daily food intake. Our system is built on food image processing and uses nutritional fact tables. Via a special calibration technique, our system uses the built-in camera of such mobile devices and records a photo of the food before and after eating it in order to measure the consumption of calorie and nutrient components. The proposed algorithm used color, texture and contour segmentation and extracted important features such as shape, color, size and texture. Using various combinations of these features and applying a support vector machine as a classifier, a good classification was achieved and simulation results show that the algorithm recognizes food categories with an accuracy rate of 92.2%, on average.

<p>The finance industry has been rather slow adopting a customer oriented approach and instead had more of a transaction oriented approach having largely undifferentiated markets. During the last two decades the world’s finance industry has been undergoing a process of transformation set off by the deregulations, internationalisation and technological change. The effects from these changes have made the companies providing financial services, such as banks, face new challenges regarding their role in the economy. Swedbank, one of the largest banks in Sweden, is now looking at how to segment their market in the best possible way in an attempt to find segments that they can serve better and in that way become more competitive. One potential new segment they have found is the increasingly more common franchise systems. This has lead to the following problem statement and purpose for this thesis:</p><p>How do banks work with market segmentation?</p><p>The main purpose with this study has been to develop a deeper understanding of how banks work with market segmentation by studying the example of the potential segment of franchisees and their franchisors. The subordinate purposes include learning what franchisees think about their situation and relation with banks, clarifying the market potential of franchise segment for banks, and to give suggestions of aspects that might be valuable to consider for banks when examining the potential for a new segment of franchisees and their franchisors.</p><p>My aim was to create a better understanding of the phenomenon studied by interpretations and therefore chose a qualitative data collection and analysis method to be able to answer the problem statement and purposes for this study. Nine in-depth interviews, eight interviews with different franchisees and one interview with a respondent from Swedbank, was carried out.</p><p>What I have found with this study is that up till now the segmentation by banks has not been very fine tuned using rather simple variables and methods. But seen that as the bank market is starting to adopt more of a relationship marketing perspective the banks’ view of segmentation might also be starting to change and develop. As this study of Swedbank’s work with establishing whether franchise systems can be a new segment for them show that banks seem to be moving from their simple break-down approach with size and industry variables towards more of a build-up approach seeing their customers as different and unique building up the segments. Still though, segmentation is not very natural and prioritised as it is for many other companies.</p><p>Other conclusions that can be drawn from this study are that if banks are to create a segment with franchise systems and trying to attract them with various marketing packages they have to be aware that relationships seem to be very important for customers and something that might make them not changing bank even if being offered good solutions. Although not having much contact with their banks customers can be satisfied since relationships can be in either a passive or active relational mode. Consequently if wanting to be able to get good penetration with a package of bank products and services I believe it is important that the banks are offering these packages to the franchise systems already early in the franchisees’ start-up phase, either when new franchisees are added to the existing franchise system or when the whole franchise system is completely new otherwise it will be more difficult to attract franchisees with such a package offering.</p><p>Another conclusion that can be made is that banks seem to have problems with spreading good solutions throughout the whole bank. By looking over their market segmentation banks might become better at this, as well as becoming more knowledgeable about the different segments.</p><p>Lastly, the market potential for franchise segments for banks seems to be rather good since even though franchisees do not see themselves as different from other small companies having different needs some prerequisites makes them different and interesting.</p>

The finance industry has been rather slow adopting a customer oriented approach and instead had more of a transaction oriented approach having largely undifferentiated markets. During the last two decades the world’s finance industry has been undergoing a process of transformation set off by the deregulations, internationalisation and technological change. The effects from these changes have made the companies providing financial services, such as banks, face new challenges regarding their role in the economy. Swedbank, one of the largest banks in Sweden, is now looking at how to segment their market in the best possible way in an attempt to find segments that they can serve better and in that way become more competitive. One potential new segment they have found is the increasingly more common franchise systems. This has lead to the following problem statement and purpose for this thesis: How do banks work with market segmentation? The main purpose with this study has been to develop a deeper understanding of how banks work with market segmentation by studying the example of the potential segment of franchisees and their franchisors. The subordinate purposes include learning what franchisees think about their situation and relation with banks, clarifying the market potential of franchise segment for banks, and to give suggestions of aspects that might be valuable to consider for banks when examining the potential for a new segment of franchisees and their franchisors. My aim was to create a better understanding of the phenomenon studied by interpretations and therefore chose a qualitative data collection and analysis method to be able to answer the problem statement and purposes for this study. Nine in-depth interviews, eight interviews with different franchisees and one interview with a respondent from Swedbank, was carried out. What I have found with this study is that up till now the segmentation by banks has not been very fine tuned using rather simple variables and methods. But seen that as the bank market is starting to adopt more of a relationship marketing perspective the banks’ view of segmentation might also be starting to change and develop. As this study of Swedbank’s work with establishing whether franchise systems can be a new segment for them show that banks seem to be moving from their simple break-down approach with size and industry variables towards more of a build-up approach seeing their customers as different and unique building up the segments. Still though, segmentation is not very natural and prioritised as it is for many other companies. Other conclusions that can be drawn from this study are that if banks are to create a segment with franchise systems and trying to attract them with various marketing packages they have to be aware that relationships seem to be very important for customers and something that might make them not changing bank even if being offered good solutions. Although not having much contact with their banks customers can be satisfied since relationships can be in either a passive or active relational mode. Consequently if wanting to be able to get good penetration with a package of bank products and services I believe it is important that the banks are offering these packages to the franchise systems already early in the franchisees’ start-up phase, either when new franchisees are added to the existing franchise system or when the whole franchise system is completely new otherwise it will be more difficult to attract franchisees with such a package offering. Another conclusion that can be made is that banks seem to have problems with spreading good solutions throughout the whole bank. By looking over their market segmentation banks might become better at this, as well as becoming more knowledgeable about the different segments. Lastly, the market potential for franchise segments for banks seems to be rather good since even though franchisees do not see themselves as different from other small companies having different needs some prerequisites makes them different and interesting.

<p>Unmanned Aerial Systems (UAS) have been an essential tool for field scouting, nutrient applications, and farm management. However, assessing the aerial images captured by UAS is labor-intensive, and human assessment can be misleading, introducing bias. Deep learning based image segmentation has been proposed to assist in segmenting different areas of interest in the field, but it usually requires significant pixel-level annotated data. To address this, we propose a semi-supervised learning algorithm, AgSemSeg, to train a robust image segmentation</p> <p>model with less annotated data. Semi-supervised semantic segmentation aims to predict accurate pixel-level segmentation results via incorporating unlabeled images. Existing methods rely on computing the consistency loss on the output predictions between pseudo-labels and unlabeled images. In AgSemSeg, we exploit the intermediate feature representations rather than only using the output predictions to improve the overall performance of the</p> <p>model. Specifically, we add a projection layer on the output of the backbone encoder, and inject consistency loss between intermediate feature representations with Sliced-Wasserstein distance. We evaluate AgSemSeg using Agriculture-Vision dataset and outperform the supervised baseline by up to 9.71%. We also evaluate AgSemSeg on benchmark datasets such as PASCAL VOC 2012 and Cityscapes datasets, and it outperforms supervised baselines by up to 24.6% and 7.5% mIoU, respectively. We also perform extensive ablation studies to show that our proposed components are key to the performance improvements of our method. </p>

Die vorliegende Arbeit widmet sich den aktuellen Problemen der Branche für Blumen und Pflanzen und hat zum Ziel, eine lebensstilbasierte Kundensegmentierung im Blumen- und Pflanzeneinzelhandel in Deutschland zu erstellen. Da diesbezüglich kaum auf bereits vorhandene Forschungsarbeiten zurückgegriffen werden konnte, werden grundsätzliche Theorien diskutiert und miteinander in Verbindung gebracht. So werden einerseits die aktuellen Gegebenheiten des Marktes für BuP bestimmt, sozialwissenschaftliche Theorien über Lebensstile diskutiert und die Theorien des Marketings, insbesondere die der Marktsegmentierung und die der zur Verfügung stehenden Marketinginstrumente, berücksichtigt. Basierend auf diesen Theorien wird ein interdisziplinäres Modell entwickelt, das die Kaufmotive der Konsumenten für BuP erforscht. Ziel ist es, Rückschlüsse über das Zustandekommen von Kaufentscheidungen zu erhalten, was es im Umkehrschluss ermöglicht, Handlungsempfehlungen für die Marktangebotsseite abzuleiten. Dazu werden in einer empirischen Erhebung 880 Konsumenten befragt und deren Antwortverhalten ausgewertet. Dabei finden eine Faktorenanalyse, eine Clusteranalyse und eine multinominale logistische Regressionsanalyse Anwendung. Die Ergebnisse zeigen auf, dass sich die Konsumenten in sechs verschiedene Zielsegmente differenzieren lassen. Des Weiteren zeigen die Beschreibungen der sechs Segmente Möglichkeiten für einen möglichst effizienten Einsatz der Marketinginstrumente auf. Die Diskussion über deren Einsatz erfolgt anhand ausgewählter Situationen aus der Unternehmenspraxis.