No description available.

Title: Cover Song Identification using Music Harmony Features, Model and Complexity Analysis Author: Ladislav Maršík Department: Department of Software Engineering Supervisor: Prof. RNDr. Jaroslav Pokorný, CSc., Department of Software Engineering Abstract: Analysis of digital music and its retrieval based on the audio fe- atures is one of the popular topics within the music information retrieval (MIR) field. Every musical piece has its characteristic harmony structure, but harmony analysis is seldom used for retrieval. Retrieval systems that do not focus on similarities in harmony progressions may consider two versions of the same song different, even though they differ only in instrumentation or a singing voice. This thesis takes various paths in exploring, how music harmony can be used in MIR, and in particular, the cover song identification (CSI) task. We first create a music harmony model based on the knowledge of music theory. We define novel concepts: a harmonic complexity of a mu- sical piece, as well as the chord and chroma distance features. We show how these concepts can be used for retrieval, complexity analysis, and how they compare with the state-of-the-art of music harmony modeling. An extensive comparison of harmony features is then performed, using both the novel fe- atures and the...

The goal of this project is to investigate any correlation between marketing emails and their receivers using machine learning and only a limited amount of initial data. The data consists of roughly 1200 emails and 98.000 receivers of these. Initially, the emails are grouped together based on their content using text clustering. They contain no information regarding prior labeling or categorization which creates a need for an unsupervised learning approach using solely the raw text based content as data. The project investigates state-of-the-art concepts like bag-of-words for calculating term importance and the gap statistic for determining an optimal number of clusters. The data is vectorized using term frequency - inverse document frequency to determine the importance of terms relative to the document and to all documents combined. An inherit problem of this approach is high dimensionality which is reduced using latent semantic analysis in conjunction with singular value decomposition. Once the resulting clusters have been obtained, the most frequently occurring terms for each cluster are analyzed and compared. Due to the absence of initial labeling an alternative approach is required to evaluate the clusters validity. To do this, the receivers of all emails in each cluster who actively opened an email is collected and investigated. Each receiver have different attributes regarding their purpose of using the service and some personal information. Once gathered and analyzed, conclusions could be drawn that it is possible to find distinguishable connections between the resulting email clusters and their receivers but to a limited extent. The receivers from the same cluster did show similar attributes as each other which were distinguishable from the receivers of other clusters. Hence, the resulting email clusters and their receivers are specific enough to distinguish themselves from each other but too general to handle more detailed information. With more data, this could become a useful tool for determining which users of a service should receive a particular email to increase the conversion rate and thereby reach out to more relevant people based on previous trends. / Målet med detta projekt att undersöka eventuella samband mellan marknadsföringsemail och dess mottagare med hjälp av oövervakad maskininlärning på en brgränsad mängd data. Datan består av ca 1200 email meddelanden med 98.000 mottagare. Initialt så gruperas alla meddelanden baserat på innehåll via text klustering. Meddelandena innehåller ingen information angående tidigare gruppering eller kategorisering vilket skapar ett behov för ett oövervakat tillvägagångssätt för inlärning där enbart det råa textbaserade meddelandet används som indata. Projektet undersöker moderna tekniker så som bag-of-words för att avgöra termers relevans och the gap statistic för att finna ett optimalt antal kluster. Datan vektoriseras med hjälp av term frequency - inverse document frequency för att avgöra relevansen av termer relativt dokumentet samt alla dokument kombinerat. Ett fundamentalt problem som uppstår via detta tillvägagångssätt är hög dimensionalitet, vilket reduceras med latent semantic analysis tillsammans med singular value decomposition. Då alla kluster har erhållits så analyseras de mest förekommande termerna i vardera kluster och jämförs. Eftersom en initial kategorisering av meddelandena saknas så krävs ett alternativt tillvägagångssätt för evaluering av klustrens validitet. För att göra detta så hämtas och analyseras alla mottagare för vardera kluster som öppnat något av dess meddelanden. Mottagarna har olika attribut angående deras syfte med att använda produkten samt personlig information. När de har hämtats och undersökts kan slutsatser dras kring hurvida samband kan hittas. Det finns ett klart samband mellan vardera kluster och dess mottagare, men till viss utsträckning. Mottagarna från samma kluster visade likartade attribut som var urskiljbara gentemot mottagare från andra kluster. Därav kan det sägas att de resulterande klustren samt dess mottagare är specifika nog att urskilja sig från varandra men för generella för att kunna handera mer detaljerad information. Med mer data kan detta bli ett användbart verktyg för att bestämma mottagare av specifika emailutskick för att på sikt kunna öka öppningsfrekvensen och därmed nå ut till mer relevanta mottagare baserat på tidigare resultat.

Facial expression recognition (FER) is still a challenging concept, and machines struggle to comprehend effectively the dynamic shifts in facial expressions of human emotions. The existing systems, which have proven to be effective, consist of deeper network structures that need powerful and expensive hardware. The deeper the network is, the longer the training and the testing. Many systems use expensive GPUs to make the process faster. To remedy the above challenges while maintaining the main goal of improving the accuracy rate of the recognition, we create a generic hierarchical structure with variable settings. This generic structure has a hierarchy of three convolutional blocks, two dropout blocks and one fully connected block. From this generic structure we derived four different network structures to be investigated according to their performances. From each network structure case, we again derived six network structures in relation to the variable parameters. The variable parameters under analysis are the size of the filters of the convolutional maps and the max-pooling as well as the number of convolutional maps. In total, we have 24 network structures to investigate, and six network structures per case. After simulations, the results achieved after many repeated experiments showed in the group of case 1; case 1a emerged as the top performer of that group, and case 2a, case 3c and case 4c outperformed others in their respective groups. The comparison of the winners of the 4 groups indicates that case 2a is the optimal structure with optimal parameters; case 2a network structure outperformed other group winners. Considerations were done when choosing the best network structure, considerations were; minimum accuracy, average accuracy and maximum accuracy after 15 times of repeated training and analysis of results. All 24 proposed network structures were tested using two of the most used FER datasets, the CK+ and the JAFFE. After repeated simulations the results demonstrate that our inexpensive optimal network architecture achieved 98.11 % accuracy using the CK+ dataset. We also tested our optimal network architecture with the JAFFE dataset, the experimental results show 84.38 % by using just a standard CPU and easier procedures. We also compared the four group winners with other existing FER models performances recorded recently in two studies. These FER models used the same two datasets, the CK+ and the JAFFE. Three of our four group winners (case 1a, case 2a and case 4c) recorded only 1.22 % less than the accuracy of the top performer model when using the CK+ dataset, and two of our network structures, case 2a and case 3c came in third, beating other models when using the JAFFE dataset. / Electrical and Mining Engineering

Background: Glioblastoma (GBM) is the most common and malignant primary brain tumor. It is a rapidly progressing tumor that infiltrates the adjacent healthy brain tissue and is difficult to treat. Despite modern treatment including surgical resection followed by radiochemotherapy and adjuvant chemotherapy, the outcome remains poor. The median overall survival is 10-12 months. Neuroimaging is the most important diagnostic tool in the assessment of GBMs and the current imaging standard is contrast-enhanced magnetic resonance imaging (MRI). Positron emission tomography (PET) has been recommended as a complementary imaging modality. PET provides additional information to MRI, in biological behavior and aggressiveness of the tumor. This study aims to investigate if the combination of PET and MRI can improve the diagnostic assessment of these tumors. Patients and methods: In this study, 22 patients fulfilled the inclusion criteria, diagnosed with GBM, and participated in all four 18F-fluorothymidine (FLT)-PET/MR examinations. FLT-PET/MR examinations were performed preoperative (baseline), before the start of the oncological therapy, at two and six weeks into therapy. Optimization of an adaptive thresholding algorithm, a batch processing pipeline, and image feature extraction algorithms were developed and implemented in MATLAB and the analyzing tool imlook4d. Results: There was a significant difference in radiochemotherapy treatment response between long-term and short-term survivors’ tumor volume in MRI (p<0.05), and marginally significant (p<0.10) for maximum standard uptake value (SUVmax), PET tumor volume, and total lesion activity (TLA). Preoperative short-term survivors had on average larger tumor volume, higher SUV, and total lesion activity (TLA). The overall trend seen was that long-term survivors had a better treatment response in both MRI and PET than short-term survivors.  During radiochemotherapy, long-term survivors displayed shrinking MR tumor volume after two weeks, and almost no remaining tumor volume was left after six weeks; the short-term survivors display marginal tumor volume reduction during radiochemotherapy. In PET, long-term survivors mean tumor volumes start to decrease two weeks into radiochemotherapy. Short-term survivors do not show any PET volume reduction two and six weeks into radiochemotherapy. For patients with more or less than 200 days progression-free survival, PET volume and TLA were significantly different, and MR volume only marginally significant, suggesting that PET possibly could have added value. Conclusion: The combination of PET and MRI can be used to predict radiochemotherapy response between two and six weeks, predicting overall survival and progression-free survival using MR and PET volume, SUVmax, and TLA. This study is limited by small sample size and further research with greater number of participants is recommended.

Práce pojednává o využití support vector machines v detekci řečové aktivity. V první části jsou zkoumány různé druhy příznaků, jejich extrakce a zpracování a je nalezena jejich optimální kombinace, která podává nejlepší výsledky. Druhá část představuje samotný systém pro detekci řečové aktivity a ladění jeho parametrů. Nakonec jsou výsledky porovnány s dvěma dalšími systémy, založenými na odlišných principech. Pro testování a ladění byla použita ERT broadcast news databáze. Porovnání mezi systémy bylo pak provedeno na databázi z NIST06 Rich Test Evaluations.

Master thesis is related to the problematics of automatic speech recognition on systems with restricted hardware resources - embedded systems. The object of this work was to design and implement speech recognition system on embedded systems, that do not contain floating-point processing units. First objective was to choose proper hardware architecture. Based on the knowledge of available HW resources, the recognition system design was made. During the system development, optimalization was made on constituent elements so they could be mounted on chosen HW. The result of the the project is successful recognition of Czech numerals on embedded system.

Feature selection or variable selection is an important step in different machine learning tasks. In a traditional approach, users specify the amount of features, which shall be selected. Afterwards, algorithm select features by using scores like the Joint Mutual Information (JMI). If users do not know the exact amount of features to select, they need to evaluate the full learning chain for different feature counts in order to determine, which amount leads to the lowest training error. To overcome this drawback, we extend the JMI score and mitigate the flaw by introducing a stopping criterion to the selection algorithm that can be specified depending on the learning task. With this, we enable developers to carry out the feature selection task before the actual learning is done. We call our new score Historical Joint Mutual Information (HJMI). Additionally, we compare our new algorithm, using the novel HJMI score, against traditional algorithms, which use the JMI score. With this, we demonstrate that the HJMI-based algorithm is able to automatically select a reasonable amount of features: Our approach delivers results as good as traditional approaches and sometimes even outperforms them, as it is not limited to a certain step size for feature evaluation.

Muscle fatigue is a severe problem for elite athletes, and this is due to the long resting times, which can vary. Various mechanisms can cause muscle fatigue which signifies that the specific muscle has reached its maximum force and cannot continue the task. This thesis was about surveying and exploring state-of-the-art methods and systematically, theoretically, and practically testing the applicability and performance of more recent machine learning methods on an existing EMG to muscle fatigue pipeline. Several challenges within the EMG domain exist, such as inadequate data, finding the most suitable model, and how they should be addressed to achieve reliable prediction. This required approaches for addressing these problems by combining and comparing various state-of-the-art methodologies, such as data augmentation techniques for upsampling, spectrogram methods for signal processing, and transfer learning to gain a reliable prediction by various pre-trained CNN models. The approach during this study was to conduct seven experiments consisting of a classification task that aims to predict muscle fatigue in various stages. These stages are divided into 7 classes from 0-6, and higher classes represent a fatigued muscle. In the tabular part of the experiments, the Decision Tree, Random Forest, and Support Vector Machine (SVM) were trained, and the accuracy was determined. A similar approach was made for the spectrogram part, where the signals were converted to spectrogram images, and with a combination of traditional- and intelligent data augmentation techniques, such as noise and DCGAN, the limited dataset was increased. A comparison between the performance of AlexNet, VGG16, DenseNet, and InceptionV3 pre-trained CNN models was made to predict differences in jump heights. The result was evaluated by implementing baseline classifiers on tabular data and pre-trained CNN model classifiers for CWT and STFT spectrograms with and without data augmentation. The evaluation of various state-of-the-art methodologies for a classification problem showed that DenseNet and VGG16 gave a reliable accuracy of 89.8 % on intelligent data augmented CWT images. The intelligent data augmentation applied on CWT images allows the pre-trained CNN models to learn features that can generalize unseen data. Proving that the combination of state-of-the-art methods can be introduced and address the challenges within the EMG domain.

his project aims to find a method that will help fill the information gaps in electroencephalography (EEG) brain-computer interfaces (BCI) research, by creating a pipeline method that allows for quicker research iterations than current state-of-the-art methods. The pipeline method is a multi-step processstarting from the recording EEG data from a subject performing a thought paradigm action, continuing with processing and decoding of the data, and ending with visualization and analysis the decoded results. Thought paradigms are in this project defined as different ways that the subject can think, with different words and different ways of thinking of those words. The pipeline will utilize various machine learning methods to be able to reach the two main goals of quickly being able to analyze and compare different paradigms and methods. Regarding the accuracy of the models, a minimum level of higher than random chance accuracies is needed if the pipeline should be considered to be useful for analyzing and comparing paradigms and methods, while a higher level of having accuracies comparable with state-of-the-art methods will allow for comparisons with paradigms and methods from other research methods as well. In the pipeline, various simple feature extraction methods are tested, such as the Fourier transform (FT) and low pass filtering. As well as features based on covariance between channels and data gradients. A specific way to baseline correct the features is also proposed and tested. The results of the project show that the pipeline method is a viable way of quickly testing and comparing paradigms and methods. With results that are comparable to state of the art methods. While also allowing for quick iteration and comparison. Future possibilities using this method are discussed