Volume measurements of timber loads is done in conjunction with timber trade. When dealing with goods of major economic values such as these, it is important to achieve an impartial and fair assessment when determining price-based volumes. With the help of Saab’s missile targeting technology, CIND AB develops products for digital volume measurement of timber loads. Currently there is a system in operation that automatically reconstructs timber trucks in motion to create measurable images of them. Future iterations of the system is expected to fully automate the scaling by generating a volumetric representation of the timber and calculate its external gross volume. The first challenge towards this development is to separate the timber load from the truck. This thesis aims to evaluate and implement appropriate method for semantic pixel-wise segmentation of timber loads in real time. Image segmentation is a classic but difficult problem in computer vision. To achieve greater robustness, it is therefore important to carefully study and make use of the conditions given by the existing system. Variations in timber type, truck type and packing together create unique combinations that the system must be able to handle. The system must work around the clock in different weather conditions while maintaining high precision and performance.

Deep learning has dominated the computer vision field since 2012, but a common criticism of deep learning methods is their dependence on large amounts of data. To combat this criticism research into data-efficient deep learning is growing. The foremost success in data-efficient deep learning is transfer learning with networks pre-trained on the ImageNet dataset. Pre-trained networks have achieved state-of-the-art performance on many tasks. We consider the pre-trained network method for a new task where we have to collect the data. We hypothesize that the data efficiency of pre-trained networks can be improved through informed data collection. After exhaustive experiments on CaffeNet and VGG16, we conclude that the data efficiency indeed can be improved. Furthermore, we investigate an alternative approach to data-efficient learning, namely adding domain knowledge in the form of a spatial transformer to the pre-trained networks. We find that spatial transformers are difficult to train and seem to not improve data efficiency.

Les modulations à phase continue (CPMs) sont des méthodes de modulations robuste à la noncohérence du canal de propagation. Dans un contexte spatial, les CPM sont utilisées dans la chaîne de transmission de télémesure de la fusée. Depuis les années 70, la modulation la plus usitée dans les systèmes de télémesures est la modulation CPFSK continuous phase frequency shift keying filtrée. Historiquement, ce type de modulation est concaténée avec un code ReedSolomon (RS) afin d'améliorer le processus de décodage. Côté récepteur, les séquences CPM non-cohérentes sont démodulées par un détecteur Viterbi à sortie dure et un décodeur RS. Néanmoins, le gain du code RS n'est pas aussi satisfaisant que des techniques de codage moderne capables d'atteindre la limite de Shannon. Actualiser la chaîne de communication avec des codes atteignant la limite de Shannon tels que les codes en graphe creux, implique deremanier l’architecture du récepteur usuel pour un détecteur à sortie souple. Ainsi, on propose dans cette étude d' élaborer un détecteur treillis à sortie souple pour démoduler les séquences CPM non-cohérentes. Dans un deuxième temps, on concevra des schémas de pré-codages améliorant le comportement asymptotique du récepteur non-cohérent et dans une dernière étape on élabora des codes de parité à faible densité (LDPC) approchant la limite de Shannon. / Continuous phase modulations (CPM) are modulation methods robust to the non-coherency of propagation channels. In a space context, CPMs are used in the communication link between the rocket and the base stations. Since the 70's, the most popular telemetry modulation is the filtered continuous phase frequency shift keying (CPFSK). Traditionally, the CPFSK scheme isconcatenated with a Reed-Solomon (RS) code to enhance the decoding process. At the receiver side, the non-coherent CPM sequences are demodulated through a hard Viterbi detector and a RS decoder. However, the RS's coding gain is no more satisfactory when directly compared to modern coding schemes enable to reach the Shannon limit. Updating the communication link to capacity achieving codes, as sparse graph codes, implies to redesign the receiver architecture to soft detector. In that respect, we propose in this study to design a trellis-based soft detector to demodulate non-coherent CPM sequences. In a second part, we will elaborate precoding schemes to improve the asymptotic behaviour of the non-coherent receiver and in a last step we will build low density parity check codes approaching the Shannon limit.

The influence of Artificial Intelligence (AI) on society is increasing, with applications in highly sensitive and complicated areas. Examples include using Deep Convolutional Neural Networks within healthcare for diagnosing cancer. However, the inner workings of such models are often unknown, limiting the much-needed trust in the models. To combat this, Explainable AI (XAI) methods aim to provide explanations of the models' decision-making. Two such methods, Spectral Relevance Analysis (SpRAy) and Testing with Concept Activation Methods (TCAV), were evaluated on a deep learning model classifying cat and dog images that contained introduced artificial noise. The task was to assess the methods' capabilities to explain the importance of the introduced noise for the learnt model. The task was constructed as an exploratory step, with the future aim of using the methods on models diagnosing oral cancer. In addition to using the TCAV method as introduced by its authors, this study also utilizes the CAV-sensitivity to introduce and perform a sensitivity magnitude analysis. Both methods proved useful in discerning between the model’s two decision-making strategies based on either the animal or the noise. However, greater insight into the intricacies of said strategies is desired. Additionally, the methods provided a deeper understanding of the model’s learning, as the model did not seem to properly distinguish between the noise and the animal conceptually. The methods thus accentuated the limitations of the model, thereby increasing our trust in its abilities. In conclusion, the methods show promise regarding the task of detecting visually distinctive noise in images, which could extend to other distinctive features present in more complex problems. Consequently, more research should be conducted on applying these methods on more complex areas with specialized models and tasks, e.g. oral cancer.

Företag och organisationer som tillhandahåller kundsupport via e-post kommer över tid att samla på sig stora mängder textuella data. Tack vare kontinuerliga framsteg inom Machine Learning ökar ständigt möjligheterna att dra nytta av tidigare insamlat data för att effektivisera organisationens framtida supporthantering. Syftet med denna studie är att analysera och utvärdera hur Deep Learning kan användas för att automatisera processen att klassificera supportärenden. Studien baseras på ett svenskt företags domän där klassificeringarna sker inom företagets fördefinierade kategorier. För att bygga upp ett dataset extraherades supportärenden inkomna via e-post (par av rubrik och meddelande) från företagets supportdatabas, där samtliga ärenden tillhörde en av nio distinkta kategorier. Utvärderingen gjordes genom att analysera skillnaderna i systemets uppmätta precision då olika metoder för datastädning användes, samt då de neurala nätverken byggdes upp med olika arkitekturer. En avgränsning gjordes att endast undersöka olika typer av Convolutional Neural Networks (CNN) samt Recurrent Neural Networks (RNN) i form av både enkel- och dubbelriktade Long Short Time Memory (LSTM) celler. Resultaten från denna studie visar ingen ökning i precision för någon av de undersökta datastädningsmetoderna. Dock visar resultaten att en begränsning av den använda ordlistan heller inte genererar någon negativ effekt. En begränsning av ordlistan kan fortfarande vara användbar för att minimera andra effekter så som exempelvis träningstiden, och eventuellt även minska risken för överanpassning. Av de undersökta nätverksarkitekturerna presterade CNN bättre än RNN på det använda datasetet. Den mest gynnsamma nätverksarkitekturen var ett nätverk med en konvolution per pipeline som för två olika test-set genererade precisioner på 79,3 respektive 75,4 procent. Resultaten visar också att några kategorier är svårare för nätverket att klassificera än andra, eftersom dessa inte är tillräckligt distinkta från resterande kategorier i datasetet. / Companies and organizations providing customer support via email will over time grow a big corpus of text documents. With advances made in Machine Learning the possibilities to use this data to improve the customer support efficiency is steadily increasing. The aim of this study is to analyze and evaluate the use of Deep Learning methods for automizing the process of classifying support errands. This study is based on a Swedish company’s domain where the classification was made within the company’s predefined categories. A dataset was built by obtaining email support errands (subject and body pairs) from the company’s support database. The dataset consisted of data belonging to one of nine separate categories. The evaluation was done by analyzing the alteration in classification accuracy when using different methods for data cleaning and by using different network architectures. A delimitation was set to only examine the effects by using different combinations of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) in the shape of both unidirectional and bidirectional Long Short Time Memory (LSTM) cells. The results of this study show no increase in classification accuracy by any of the examined data cleaning methods. However, a feature reduction of the used vocabulary is proven to neither have any negative impact on the accuracy. A feature reduction might still be beneficial to minimize other side effects such as the time required to train a network, and possibly to help prevent overfitting. Among the examined network architectures CNN were proven to outperform RNN on the used dataset. The most accurate network architecture was a single convolutional network which on two different test sets reached classification rates of 79,3 and 75,4 percent respectively. The results also show some categories to be harder to classify than others, due to them not being distinct enough towards the rest of the categories in the dataset.

This thesis explores multi-task learning for combustion flame characterization i.e to learn different characteristics of the combustion flame. We propose a multi-task convolutional neural network for two tasks i.e. PFR (Pilot fuel ratio) and fuel type classification based on the images of stable combustion. We utilize transfer learning and adopt VGG16 to develop a multi-task convolutional neural network to jointly learn the aforementioned tasks. We also compare the performance of the individual CNN model for two tasks with multi-task CNN which learns these two tasks jointly by sharing visual knowledge among the tasks. We share the effectiveness of our proposed approach to a private company’s dataset. To the best of our knowledge, this is the first work being done for jointly learning different characteristics of the combustion flame. / <p>This wrok as done with Siemens, and we have applied for a patent which is still pending.</p>

Smart wearables, known as emerging paradigms for vital big data capturing, have been attracting intensive attentions. However, one crucial problem is their power-hungriness, i.e., the continuous data streaming consumes energy dramatically and requires devices to be frequently charged. Targeting this obstacle, we propose to investigate the biodynamic patterns in the data and design a data-driven approach for intelligent data compression. We leverage Deep Learning (DL), more specifically, Convolutional Autoencoder (CAE), to learn a sparse representation of the vital big data. The minimized energy need, even taking into consideration the CAE-induced overhead, is tremendously lower than the original energy need. Further, compared with state-of-the-art wavelet compression-based method, our method can compress the data with a dramatically lower error for a similar energy budget. Our experiments and the validated approach are expected to boost the energy efficiency of wearables, and thus greatly advance ubiquitous big data applications in era of smart health.<br><div>In recent years, there has also been a growing interest in edge intelligence for emerging instantaneous big data inference. However, the inference algorithms, especially deep learning, usually require heavy computation requirements, thereby greatly limiting their deployment on the edge. We take special interest in the smart health wearable big data mining and inference. <br></div><div><br></div><div>Targeting the deep learning’s high computational complexity and large memory and energy requirements, new approaches are urged to make the deep learning algorithms ultra-efficient for wearable big data analysis. We propose to leverage knowledge distillation to achieve an ultra-efficient edge-deployable deep learning model. More specifically, through transferring the knowledge from a teacher model to the on-edge student model, the soft target distribution of the teacher model can be effectively learned by the student model. Besides, we propose to further introduce adversarial robustness to the student model, by stimulating the student model to correctly identify inputs that have adversarial perturbation. Experiments demonstrate that the knowledge distillation student model has comparable performance to the heavy teacher model but owns a substantially smaller model size. With adversarial learning, the student model has effectively preserved its robustness. In such a way, we have demonstrated the framework with knowledge distillation and adversarial learning can, not only advance ultra-efficient edge inference, but also preserve the robustness facing the perturbed input.</div>

Maskininlärning nyttjas inom fler och fler områden. Det har potential att ersätta många repetitiva arbetsuppgifter, eller åtminstone förenkla dem. Dokumenthantering inom ekonomisystem är ett område maskininlärning kan hjälpa till med. Det behövs ofta mycket manuell input i olika fält genom att avläsa fakturor eller kvitton. Målet med projektet är att skapa en applikation som nyttjar maskininlärning åt företaget Centsoft AB. Applikationen ska ta emot OCR-tolkad textmassa från en bild på ett kvitto och sedan, med hög säkerhet, kunna avgöra vilken kategori kvittot tillhör. Den här rapporten syftar till att visa utvecklingen av maskininlärningsmodellen i applikationen. Rapporten svarar på frågeställningen: ”Hur kan kvitton klassificeras med hjälp av maskininlärning?”.Undersökningsmetoden fallstudie och projektmetoden MoSCoW tillämpas i projektet. Projektet tar även hänsyn till åtagandetriangeln. Maskininlärningsramverk används för att utvärdera den upptränade modellen. Den tränade modellen klarar av att, med hög säkerhet, tolka kvitton den inte stött på tidigare. För att få en meningsfull tolkning måste kvitton ha i avsikt att tillhöra någon av de åtta tränade kategorierna.Valet av metoder passade bra till projektet för att besvara frågeställningen. Applikationen kan utvecklas vidare och implementeras i fakturahanteringssystemet. Genomförandet av projektet ger kunskap att arbeta med maskininlärningslösningar. Tekniken kan i framtiden appliceras på flera områden. / Machine learning is used in more and more areas. It has the potential to replace many repetitive tasks, or at least simplify them. Document management within financial systems is an area machine learning can help with. A lot of manual input is often needed in different fields by reading invoices or receipts. The goal of the project is to create an application that uses machine learning for the company Centsoft AB. The application should receive OCR-interpreted texts from an image of a receipt and then, with high certainty, be able to determine which category the receipt belongs to. This report aims to show the development of the machine learning model in the application. The report answers the question: "How can receipts be classified using machine learning?".The methodology case study and the research method MoSCoW will be applied during the project. The project also considers the triangle method described by Eklund. Machine learning frameworks are used to evaluate the trained model. The trained model can, with high certainty, interpret receipts it has not encountered before. In order to get a meaningful interpretation, receipts must have the intention of belonging to one of the eight trained categories.The choice of methods suited the project well to answer the question. The application can be further developed and be implemented in the invoice management system. The implementation of the project gives knowledge about how to work with machine learning solutions. In the future, the technology can be applied in several areas.

Fastighetsvärderingar har historiskt sett utförts av mäklare eller experter på området. Med den växande mängden verktyg på internet för värderingar uppstår frågan hur väl verktygen presterar och vad som kan göras för att förbättra dem. Moderna metoder utgår ifrån försäljningsstatistik av liknande objekt när en värdering görs med tekniska verktyg. Detta med hjälp av olika former av metadata, bland annat storlek, läge och byggnations år. Den här studien utforskar möjligheten att använda interiört skick som variabel i värderingar av lägenheter genom att träna Convolutional Neural Networks för att klassificera for lägenheter i Stockholm, samt undersöka sambandet mellan det interiöra skicket och den felterms om Boolis varderingsalgoritm ger upphov till. Klassificeringsmodellerna tränades på insamlad data för skick av lägenhetsägare samt tillhörande visningsbilder 200 stycken bilder som erhållits av Booli. Studien visar ett statistiskt signifikant samband mellan interiört skick och feltermen från värderingar. Värderingar på lägenheter av högt skick tenderar i genomsnitt att vara 3% för låga, och 3% för höga för lägenheter av lågt skick. Resultaten indikerar att interiör som variabel kan användas för att reducera felet i Boolis varderingsalgoritm. Dock lyckades ej experimentet med att reducera feltermen i någon större utsträckning i detta arbete. / Housing evaluations has historically been made in person by real estate agents or other experts. With growing online tools for evaluations, the question arises how well they perform, and what can be done to improve them. Modern approaches use sales data for similar housing when evaluating a certain house or apartment, with variables mainly being different forms of metadata such as living area, location and year or construction. This study explores the possibility to use the interior condition as a variable in housing evaluations by training Convolutional Neural Networks to classify the condition of kitchens and bathrooms for apartments in Stockholm, Sweden and testing the relationship between said conditions and the error of Booli’s evaluation algorithm. The classification models were trained on crowd sourced data of the condition and the advertisement images for 200 images provided by Booli. The study finds that a statistically significant relationship exists between interior condition and the evaluation error, and the evaluations of apartments tends to be 3% too small on high condition apartments, while being on average 3% too large for low condition apartments. The results of the study indicates that including interior as a variable might reduce the error of Booli’s evaluation algorithm. However, the experiment for doing so in this study failed to do so in any sizeable manner.

The structure of the ankle joint complex creates an ideal balance between mobility and stability, which enables gait. If a lesion emerges in the ankle joint complex, the anatomical structure is altered, which may disturb mobility and stability and cause intense pain. A lesion in the articular cartilage on the talus bone, or a lesion in the subchondral bone of the talar dome, is referred to as an Osteochondral Lesion of the Talus (OLT). Replacing the damaged cartilage or bone with an implant is one of the methods that can be applied to treat OLTs. Episurf Medical develops and produces patient-specific implants (Episealers) along with the necessary associated surgical instruments by, inter alia, creating a corresponding 3D model of the ankle (talus, tibial, and fibula bones) based on either a Magnetic Resonance Imaging (MRI) scan or a Computed Tomography (CT) scan. Presently, the3D models based on MRI scans can be created automatically, but the 3Dmodels based on CT scans must be created manually, which can be very time-demanding. In this thesis project, a U-net based Convolutional Neural Network (CNN) was trained to automatically segment 3D models of ankles based on CT images. Furthermore, in order to optimize the quality of the incoming CT images, this thesis project also consisted of an evaluation of the specified parameters in the Episurf CT talus protocol that is being sent out to the clinics. The performance of the CNN was evaluated using the Dice Coefficient (DC) with five-fold cross-validation. The CNN achieved a mean DC of 0.978±0.009 for the talus bone, 0.779±0.174 for the tibial bone, and 0.938±0.091 for the fibula bone. The values for the talus and fibula bones were satisfactory and comparable to results presented in previous researches; however, due to background artefacts in the images, the DC achieved by the network for the segmentation of the tibial bone was lower than the results presented in previous researches. To correct this, a noise-reducing filter will be implemented. / Fotledens komplexa anatomi ger upphov till en ideal balans mellan rörlighetoch stabilitet, vilket i sin tur möjliggör gång. Fotledens anatomi förändras när en skada uppstår, vilket kan påverka rörligheten och stabiliteten samt orsaka intensiv smärta. En skada i talusbenets ledbrosk eller i det subkondrala benet på talusdomen benämns som en Osteochondral Lesion of the Talus(OLT). En metod att behandla OLTs är att ersätta den del brosk eller bensom är skadat med ett implantat. Episurf Medical utvecklar och producerar individanpassade implantat (Episealers) och tillhörande nödvändiga kirurgiska instrument genom att, bland annat, skapa en motsvarande 3D-modell av fotleden (talus-, tibia- och fibula-benen) baserat på en skanning med antingen magnetisk resonanstomografi (MRI) eller datortomografi (CT). I dagsläget kan de 3D-modeller som baseras på MRI-skanningar skapas automatiskt, medan de 3D-modeller som baseras på CT-skanningar måste skapas manuellt - det senare ofta tidskrävande. I detta examensarbete har ett U-net-baserat Convolutional Neuralt Nätverk (CNN) tränats för att automatiskt kunna segmentera 3D-modeller av fotleder baserat på CT-bilder. Vidare har de speciferade parametrarna i Episurfs CT-protokoll för fotleden som skickas ut till klinikerna utvärderats, detta för att optimera bildkvaliteten på de CT-bilder som används för implantatspositionering och design. Det tränade nätverkets prestanda utvärderades med hjälp av Dicekoefficienten (DC) med en fem-delad korsvalidering. Nätverket åstadkom engenomsnittlig DC på 0.978±0.009 för talusbenet, 0.779±0.174 för tibiabenet, och 0.938±0.091 för fibulabenet. Värdena för talus och fibula var adekvata och jämförbara med resultaten presenterade i tidigare forskning. På grund av bakgrundsartefakter i bilderna blev den DC som nätverket åstadkom för sin segmentering av tibiabenet lägre än tidigiare forskningsresultat. För att korrigera för bakgrundsartefakterna kommer ett brusreduceringsfilter implementeras