The automation in the aquaculture is proving to be more and more effective these days. The economic drain on the aquaculture farmers due to the high mortality of the shrimps can be reduced by ensuring the welfare of the animals. The health of shrimps can decline with even barest of changes in the conditions in the farm. This is the result of increase in stress. As shrimps are quite sensitive to the changes, even small changes can increase the stress in the animals which results in the decline of health. This severely dampens the mortality rate in the animals. Also, human interference while feeding the shrimps severely induces the stress on the shrimps and thereby affecting the shrimp’s mortality. So, to ensure the optimum efficiency of the farm, the feeding of the shrimps is made automated. The underfeeding and overfeeding also affects the growth of shrimps. To determine the right amount of food to provide for shrimps, Biomass is a very helpful parameter. The use of artificial intelligence (AI) to calculate the farm's biomass is the project's primary area of interest. This model uses the cameras mounted on top of the tank at densely populated areas. These cameras monitor the farm, and our model detects the biomass. By doing so, it is possible to estimate how much food should be distributed at that particular area. Biomass of the shrimps can be calculated with the help of the number of shrimps and the average lengths of the shrimps detected. With the reduced human interference in calculating the biomass, the health of the animals improves and thereby making the process sustainable and economical.

Applying machine learning to various applications has gained significant momentum in recent years. However, the increasing complexity of networks introduces challenges such as a larger memory footprint and decreased throughput. This thesis aims to address these challenges by exploring the use of 8-bit floating-point numbers for machine learning. The numerical accuracy was evaluated empirically by implementing software models of the arithmetic and running experiments on a neural network provided by MediaTek. While the initial findings revealed poor accuracy when performing computations solely with 8-bit floating-point arithmetic, a significant improvement could be achieved by using a higher-precision accumulator register. The hardware cost was evaluated using a synthesis tool by measuring the increase in silicon area and impact on clock frequency after four new vector instructions had been implemented. A large increase in area was measured for the functional blocks, but the hardware cost for interconnect and instruction decoding were negligible. A slight decrease in system clock frequency was observed, although marginally. Ideas that likely could improve the accuracy of inference calculations and decrease the hardware cost are proposed in the section for future work.

No description available.

Common Objects in Context for bridge inspection (COCO-Bridge) was introduced for use by unmanned aircraft systems (UAS) to assist in GPS denied environments, flight-planning, and detail identification and contextualization, but has far-reaching applications such as augmented reality (AR) and other artificial intelligence (AI) platforms. COCO-Bridge is an annotated dataset which can be trained using a convolutional neural network (CNN) to identify specific structural details. Many annotated datasets have been developed to detect regions of interest in images for a wide variety of applications and industries. While some annotated datasets of structural defects (primarily cracks) have been developed, most efforts are individualized and focus on a small niche of the industry. This effort initiated a benchmark dataset with a focus on structural details. This research investigated the required parameters for detail identification and evaluated performance enhancements on the annotation process. The image dataset consisted of four structural details which are commonly reviewed and rated during bridge inspections: bearings, cover plate terminations, gusset plate connections, and out of plane stiffeners. This initial version of COCO-Bridge includes a total of 774 images; 10% for evaluation and 90% for training. Several models were used with the dataset to evaluate model overfitting and performance enhancements from augmentation and number of iteration steps. Methods to economize the predictive capabilities of the model without the addition of unique data were investigated to reduce the required number of training images. Results from model tests indicated the following: additional images, mirrored along the vertical-axis, provided precision and accuracy enhancements; increasing computational step iterations improved predictive precision and accuracy, and the optimal confidence threshold for operation was 25%. Annotation recommendations and improvements were also discovered and documented as a result of the research. / MS / Common Objects in Context for bridge inspection (COCO-Bridge) was introduced to improve a drone-conducted bridge inspection process. Drones are a great tool for bridge inspectors because they bring flexibility and access to the inspection. However, drones have a notoriously difficult time operating near bridges, because the signal can be lost between the operator and the drone. COCO-Bridge is an imagebased dataset that uses Artificial Intelligence (AI) as a solution to this particular problem, but has applications in other facets of the inspection as well. This effort initiated a dataset with a focus on identifying specific parts of a bridge or structural bridge elements. This would allow a drone to fly without explicit direction if the signal was lost, and also has the potential to extend its flight time. Extending flight time and operating autonomously are great advantagesfor drone operators and bridge inspectors. The output from COCO-Bridge would also help the inspectors identify areas that are prone to defects by highlighting regions that require inspection. The image dataset consisted of 774 images to detect four structural bridge elements which are commonly reviewed and rated during bridge inspections. The goal is to continue to increase the number of images and encompass more structural bridge elements in the dataset so that it may be used for all types of bridges. Methods to reduce the required number of images were investigated, because gathering images of structural bridge elements is challenging,. The results from model tests helped build a roadmap for the expansion and best-practices for developing a dataset of this type.

<p dir="ltr">Impaired cerebral vasoregulation is one of the most common post-ischemic stroke effects. Diagnosis and prevention of this condition is often invasive, costly and in-effective. This impairment restricts the cerebral blood vessels to properly regulate blood flow, which is very important for normal brain functioning. Developing accurate, non-invasive and efficient methods to detect this condition aids in better stroke diagnosis and prevention. </p><p dir="ltr">The aim of this thesis is to develop deep learning techniques for the purpose of detection of cerebral vasoregulation impairments by analyzing physiological signals. This research employs various Deep learning techniques like Convolution Neural Networks (CNN), MobileNet, and Long-Short-Term Memory (LSTM) to determine variety of physiological signals from the PhysioNet database like Electrocardio-gram (ECG), Transcranial Doppler (TCD), Electromyogram (EMG), and Blood Pressure(BP) as stroke or non-stroke subjects. The effectiveness of these algorithms is demonstrated by a classification accuracy of 90\% for the combination of ECG and EMG signals. </p><p dir="ltr">Furthermore, this research explores the importance of analyzing dynamic physiological activities in determining the impairment. The dynamic activities include Sit-stand, Sit-stand-balance, Head-up-tilt, and Walk dataset from the PhysioNet website. CNN and MobileNetV3 are employed in classification purposes of these signals, attempting to identify cerebral health. The accuracy of the model and robustness of these methods is greatly enhanced when multiple signals are integrated. </p><p dir="ltr">Overall, this study highlights the potential of deep multimodal physiological learning in the development of precision brain medicine further enhancing stroke diagnosis. The results pave the way for the development of advanced diagnostic tools to determine cerebral health. </p>

<p dir="ltr"> The widespread adoption of Convolutional Neural Networks (CNNs) in real-world applications, particularly on resource-constrained devices, is hindered by their computational complexity and memory requirements. This research investigates the application of pruning and quantization techniques to optimize CNNs for arrhythmia classification using the MIT-BIH Arrhythmia Database. By combining magnitude-based pruning, regularization-based pruning, filter map-based pruning, and quantization at different bit-widths (4-bit, 8-bit, 2-bit, and 1-bit), the study aims to develop a more compact and efficient CNN model while maintaining high accuracy. The experimental results demonstrate that these techniques effectively reduce model size, improve inference speed, and maintain accuracy, adapting them for use on devices with limited resources. The findings highlight the potential of these optimization techniques for real-time applications in mobile health monitoring and edge computing, paving the way for broader adoption of deep learning in resource-limited environments.</p>

Cellular network traffic prediction is a critical challenge for communication providers, which is important for use cases such as traffic steering and base station resources management. Traditional prediction methods mostly rely on historical time-series data to predict traffic load, which often fail to model the real world and capture surrounding environment conditions. In this work, we propose a multi-modal deep learning model for 4G/5G Cellular Network Traffic prediction by considering external data sources such as satellite imagery and weather data. Specifically, our proposed model consists of three components (1) temporal component (modeling correlations between traffic load values with historical data points via LSTM) (2) computer vision component (using embeddings to capture correlations between geographic regions that share similar landscape patterns using satellite imagery data and state of the art CNN models), and (3) weather component (modeling correlations between weather measurements and traffic patterns). Furthermore, we study the effects and limitations of using such contextual datasets on time series learning process. Our experiments show that such hybrid models do not always lead to better performance, and LSTM model is capable of modeling complex sequential interactions. However, there is a potential for classifying or labelling regions by their urban landscape and the network traffic. / Förutsägelse av mobilnätstrafik är en kritisk utmaning för kommunikation leverantörer, där användningsområden inkluderar trafikstyrning och hantering av basstationsresurser. Traditionella förutsägelsesmetoder förlitar sig främst på historisk tidsseriedata för att förutsäga trafikbelastning, detta misslyckas ofta med att modellera den verkliga världen och fånga omgivande miljö. Det här arbetet föreslår en multimodal modell med djupinlärning förutsägelse av 4G/5G nätverkstrafik genom att beakta externa datakällor som satellitbilder och väderdata. Specifikt består vår föreslagna modell av tre komponenter (1) temporal komponent (korrelationsmodellering mellan trafikbelastningsvärden med historiska datapunkter via LSTM) (2) datorseende komponent (med inbäddningar för att fånga korrelationer mellan geografiska regioner som delar liknande landskapsmönster med hjälp av satelitbilddata och state-of-the-art CNN modeller), och (3) väderkomponent (modellerande korrelationer mellan vädermätningar och trafikmönster). Dessutom studerar vi effekterna och begränsningarna av att använda sådana kontextuella datamängder på tidsserieinlärningsprocessen. Våra experiment visar att hybridmodeller inte alltid leder till bättre prestanda och att LSTM-modellen är kapabel att modellera komplexa sekventiella interaktioner. Det finns dock en potential att klassificera eller märka regioner efter deras stadslandskap och nättrafiken. / La prévision du trafic sur les réseaux cellulaires est un défi crucial pour les fournisseurs de communication, ce qui est important pour les cas d’utilisation tels que la direction du trafic et la gestion des ressources des stations de base. Les méthodes de prédiction traditionnelles reposent principalement sur des données historiques de séries chronologiques pour prédire la charge de trafic, qui échouent souvent à modéliser le monde réel et à capturer les conditions de l’environnement environnant. Dans ce travail, nous proposons un modèle d’apprentissage profond multimodal pour la prédiction du trafic des réseaux cellulaires 4G/5G en considérant des sources de données externes telles que l’imagerie satellitaire et les données météorologiques. Plus précisément, notre modèle proposé se compose de trois composants (1) composant temporel (modélisation des corrélations entre les valeurs de charge de trafic avec des points de données historiques via LSTM) (2) composant de vision par ordinateur (utilisant des incorporations pour capturer les corrélations entre les régions géographiques qui partagent des modèles de paysage similaires à l’aide de données d’imagerie satellitaire et de modèles CNN de pointe) et (3) composante météorologique (modélisation des corrélations entre les mesures météorologiques et les modèles de trafic). De plus, nous étudions les effets et les limites de l’utilisation de tels ensembles de données contextuelles sur le processus d’apprentissage des séries chronologiques. Nos expériences montrent que de tels modèles hybrides ne conduisent pas toujours à de meilleures performances, et le modèle LSTM est capable de modéliser des interactions séquentielles complexes. Cependant, il est possible de classer ou d’étiqueter les régions en fonction de leur paysage urbain et du trafic du réseau.

This thesis analyses how three television stations - Czech ČT24, Russian RT and American CNN - informed about the Crimean crisis which took place in Ukraine in 2014. The first part of the thesis presents theoretical approach and mentions previous similar studies, which focused on examining of medial coverage and framing of war conflicts. Next chapter describes the history of Ukraine briefly and underlines events which could have caused the Crimean crisis. Thereafter the thesis introduces the timeline of the Crimean crisis. In the next part the thesis analyses sources, topics and keywords which appeared in the news of ČT24, RT and CNN. It also describes how particular people and events were visually covered. In the final chapter the approach of the three examined television channels is compared.

There are many clinical situations where magnetic resonance imaging (MRI) is preferable over other imaging modalities, while the major disadvantage is the relatively long scan time. Due to limited resources, this means that not all patients can be offered an MRI scan, even though it could provide crucial information. It can even be deemed unsafe for a critically ill patient to undergo the examination. In MRI, there is a trade-off between resolution, signal-to-noise ratio (SNR) and the time spent gathering data. When time is of utmost importance, we seek other methods to increase the resolution while preserving SNR and imaging time. In this work, I have studied one of the most promising methods for this task. Namely, constructing super-resolution algorithms to learn the mapping from a low resolution image to a high resolution image using convolutional neural networks. More specifically, I constructed networks capable of transferring high frequency (HF) content, responsible for details in an image, from one kind of image to another. In this context, contrast or weight is used to describe what kind of image we look at. This work only explores the possibility of transferring HF content from T1-weighted images, which can be obtained quite quickly, to T2-weighted images, which would take much longer for similar quality. By doing so, the hope is to contribute to increased efficacy of MRI, and reduce the problems associated with the long scan times. At first, a relatively simple network was implemented to show that transferring HF content between contrasts is possible, as a proof of concept. Next, a much more complex network was proposed, to successfully increase the resolution of MR images better than the commonly used bicubic interpolation method. This is a conclusion drawn from a test where 12 participants were asked to rate the two methods (p=0.0016) Both visual comparisons and quality measures, such as PSNR and SSIM, indicate that the proposed network outperforms a similar network that only utilizes images of one contrast. This suggests that HF content was successfully transferred between images of different contrasts, which improves the reconstruction process. Thus, it could be argued that the proposed multi-contrast model could decrease scan time even further than what its single-contrast counterpart would. Hence, this way of performing multi-contrast super-resolution has the potential to increase the efficacy of MRI.

Traffic sign recognition is an important problem for autonomous cars and driver assistance systems. With recent developments in the field of machine learning, high performance can be achieved, but typically at a large computational cost. This thesis aims to investigate the relation between classification accuracy and computational complexity for the visual recognition problem of classifying traffic signs. In particular, the benefits of partitioning the classification problem into smaller sub-problems using prior knowledge in the form of shape or current region are investigated. In the experiments, the convolutional neural network (CNN) architecture MobileNetV2 is used, as it is specifically designed to be computationally efficient. To incorporate prior knowledge, separate CNNs are used for the different subsets generated when partitioning the dataset based on region or shape. The separate CNNs are trained from scratch or initialized by pre-training on the full dataset. The results support the intuitive idea that performance initially increases with network size and indicate a network size where the improvement stops. Including shape information using the two investigated methods does not result in a significant improvement. Including region information using pretrained separate classifiers results in a small improvement for small complexities, for one of the regions in the experiments. In the end, none of the investigated methods of including prior knowledge are considered to yield an improvement large enough to justify the added implementational complexity. However, some other methods are suggested, which would be interesting to study in future work.