No description available.

In the most recent years, many deep learning models have been used to identify and classify diseases of plant leaves by inputting plant leaf images as input to the model. However, there is still a gap in research on how to improve the accuracy of the deep learning models of plant leaf diseases. This thesis is about investigating various techniques for improving the MobileNetV2 model's accuracy for plant disease detection in leaves and classification. These techniques involved adjusting the learning rate, adding additional layers, and various data-augmented operations. The results of this thesis have shown that these techniques can significantly improve the accuracy of the model, and the best results can be achieved by using random rotation and crop data augmentation. After adding random rotation and crop data augmentation to the model, it achieved an accuracy of 94%, a precision of 91%, a recall of 96%, and an F1-score of 95%. This shows that the proposed techniques can be used to improve the accuracy of plant leaf disease detection and classification models, which can help farmers identify and treat plant diseases.

No description available.

Modern state-of-the-art object detection models are based on convolutional neural networks and can be divided into single-shot detectors and two-stage detectors. Two-stage detectors exhibit impressive detection performance but their complex pipelines make them slow. Single-shot detectors are not as accurate as two-stage detectors, but are faster and can be used for real-time object detection. Despite the fact that single-shot detectors are faster, a large number of calculations are still required to produce a prediction that not many embedded devices are capable of doing in a reasonable time. Therefore, it is natural to ask if single-shot detectors could become faster even. Pruning is a technique to reduce the size of neural networks. The main idea behind network pruning is that some model parameters are redundant and do not contribute to the final output. By removing those redundant parameters, fewer computations are needed to produce predictions, which may lead to a faster inference and since the parameters are redundant, the model accuracy should not be affected. This thesis investigates two approaches for pruning the SSD-MobileNet- V2 single-shot detector. The first approach prunes the single-shot detector by a large portion and retrains the remaining parameters only once. In the other approach, a smaller portion is pruned, but pruning and retraining are done in an iterative fashion, where pruning and retraining constitute one iteration. Beyond comparing two pruning approaches, the thesis also studies the tradeoff between model accuracy and inference speed that pruning induces. The results from the experiments suggest that the iterative pruning approach preserves the accuracy of the original model better than the other approach where pruning and finetuning are performed once. For all four pruning levels that the two approaches are compared iterative pruning yields more accurate results. In addition, an inference evaluation indicates that iterative pruning is a good compression method for SSD-MobileNet-V2, finding models that both are faster and more accurate than the original model. The thesis findings could be used to guide future pruning research on SSD-MobileNet- V2, but also on other single-shot detectors such as RetinaNet and the YOLO models. / Moderna modeller för objektsdetektering bygger på konvolutionella neurala nätverk och kan delas in i ensteg- och tvåstegsdetektorer. Tvåstegsdetektorer uppvisar imponerande detektionsprestanda, men deras komplexa pipelines gör dem långsamma. Enstegsdetektorer uppvisar oftast inte lika bra detektionsprestanda som tvåstegsdetektorer, men de är snabbare och kan användas för objektdetektering i realtid. Trots att enstegsdetektorer är snabbare krävs det fortfarande ett stort antal beräkningar för att få fram en prediktering, vilket inte många inbyggda enheter kan göra på rimlig tid. Därför är det naturligt att fråga sig om enstegsdetektorer kan bli ännu snabbare. Nätverksbeskärning är en teknik för att minska storleken på neurala nätverk. Huvudtanken bakom nätverksbeskärning är att vissa modellparametrar är överflödiga och inte bidrar till det slutliga resultatet. Genom att ta bort dessa överflödiga parametrar krävs färre beräkningar för att producera en prediktering, vilket kan leda till att nätverket blir snabbare och eftersom parametrarna är överflödiga bör modellens detektionsprestanda inte påverkas. I den här masteruppsatsen undersöks två metoder för att beskära enstegsdetektorn SSD-MobileNet-V2. Det första tillvägagångssättet går ut på att en stor del av detektorn vikter beskärs och att de återstående parametrarna endast finjusteras en gång. I det andra tillvägagångssättet beskärs en mindre del, men beskärning och finjustering sker på ett iterativt sätt, där beskärning och finjustering utgör en iteration. Förutom att jämföra två metoder för beskärning studeras i masteruppsatsen också den kompromiss mellan modellens detektionsprestanda och inferenshastighet som beskärningen medför. Resultaten från experimenten tyder på att den iterativa beskärningsmetoden bevarar den ursprungliga modellens detektionsprestanda bättre än den andra metoden där beskärning och finjustering utförs en gång. För alla fyra beskärningsnivåer som de två metoderna jämförs ger iterativ beskärning mer exakta resultat. Dessutom visar en hastighetsutvärdering att iterativ beskärning är en bra komprimeringsmetod för SSD-MobileNet-V2, eftersom modeller som både snabbare och mer exakta än den ursprungliga modellen går att hitta. Masteruppsatsens resultat kan användas för att vägleda framtida forskning om beskärning av SSD-MobileNet-V2, men även av andra enstegsdetektorer, t.ex. RetinaNet och YOLO-modellerna.

This report presents a deep learning based approach for segmenting and characterizing tumor cell deaths using images provided by the Önfelt lab, which contain NK cells and HL60 leukemia cells. We explore the efficiency of convolutional neural networks (CNNs) in distinguishing between live and dead tumor cells, as well as different classes of cell death. Three CNN architectures: MobileNetV2, ResNet-18, and ResNet-50 were employed, utilizing transfer learning to optimize performance given the limited size of available datasets. The networks were trained using two loss functions: weighted cross-entropy and generalized dice loss and two optimizers: Adaptive moment estimation (Adam) and stochastic gradient descent with momentum (SGDM), with performance evaluations based on metrics such as mean accuracy, intersection over union (IoU), and BF score. Our results indicate that MobileNetV2 with cross-entropy loss and the Adam optimizer outperformed other configurations, demonstrating high mean accuracy. Challenges such as class imbalance, annotation bias, and dataset limitations are discussed, alongside potential future directions to enhance model robustness and accuracy. The successful training of networks capable of classifying all identified types of cell death, demonstrates the potential for a deep learning approach to identify different types of cell deaths as a tool for analyzing immunotherapeutic strategies and enhance understanding of NK cell behaviors in cancer treatment.