Pest inventory of a field is a way of knowing when the thresholds for pest controlis reached. It is of increasing interest to use machine learning to automate thisprocess, however, many challenges arise with detection of small insects both intraps and on plants.This thesis investigates the prospects of developing an automatic warning system for notifying a user of when certain pests are detected in a trap. For this, sliding window with histogram of oriented gradients based support vector machinewere implemented. Trap detection with neural network models and a check sizefunction were tested for narrowing the detections down to pests of a certain size.The results indicates that with further refinement and more training images thisapproach might hold potential for fungus gnat and rape beetles.Further, this thesis also investigates detection performance of Mask R-CNNand YOLOv5 on different insects in fields for the purpose of automating thedata gathering process. The models showed promise for detection of rape beetles. YOLOv5 also showed promise as a multi-class detector of different insects,where sizes ranged from small rape beetles to larger bumblebees.

<p>Detection of dim point objects plays an important role in many imaging applications such as early warning systems, surveillance, astronomy, and microscopy. In satellite imaging, natural phenomena, such as clouds, can confound object detection methods. We propose an object detection method that uses spatial, spectral, and temporal information to reject detections that are not consistent with a moving object and achieve a high probability of detection with a low false alarm rate. We propose another method for dim object detection using convolutional neural networks (CNN). The method augments a conventional space-based detection processing chain with a lightweight CNN to improve detection performance. For evaluation of the performance of our proposed methods,</p> <p>we used a set of curated satellite images and generated receiver operating characteristics (ROC).</p> <p><br></p> <p>Most satellite images have adequate spatial resolution and signal-to-noise ratio (SNR) for the detection and localization of common large objects, such as buildings. In many applications, the spatial resolution of the imaging system is not enough to localize a point object or two closely-spaced objects (CSOs) that are described by only a few pixels (or less than one pixel). A low signal-to-noise ratio (SNR) increases the difficulty such as when the objects are dim. We describe a method to estimate the objects’ amplitudes and spatial locations with sub-pixel accuracy using non-linear optimization and information from multiple spectral bands. We also propose a machine</p> <p>learning method that minimizes a cost function derived from the maximum likelihood estimation of the observed image to determine an object’s sub-pixel spatial location and amplitude. We derive the Cramer-Rao Lower Bound and compare the proposed estimators’ variance with this bound.</p>

Defects on fiber products have varied appearances and are common in production lines. A reliable system that can classify and identify defects without subjectivity and fatigue can improve a company's quality management. Computer vision systems are crucial for any autonomous system, but accuracy is essential for real-life applications. This study aims to investigate the contribution of computer vision through computer vision and artificial intelligence in detecting defects in formed fiber products. A hand-crafted dataset of four common defects from the production line was created and tested using transfer learning. The system's performance was measured in terms of mean average precision (mAP), precision, and recall, resulting in a performance of 81.8% mAP, 0.84 recall rate, and 0.79 precision rate for the hand-crafted dataset. / Defekter på fiberprodukter har olika framträdanden och är vanliga i produktionslinjer. Ett tillförlitligt system som kan klassificera och identifiera defekter utan subjektivitet och trötthet kan förbättra ett företags kvalitetsledning. Ett datorseende-system är avgörande för alla autonoma system, men noggrannhet är viktigt för tillämpningar i verkliga livet. Denna studie syftar till att undersöka bidraget från datorseende genom datorseende och artificiell intelligens för att upptäcka defekter i formade fiberprodukter. Ett handgjort dataset med fyra vanliga defekter från produktionslinjen skapades och testades med transfer learning. Systemets prestanda mättes i termer av medelvärde av genomsnittlig precision (mAP), precision och återkallelse, vilket resulterade i en prestanda på 81,8% mAP, 0,84 återkallningsfrekvens och 0,79 precision frekvens för det handgjorda datasetet.

No description available.

<p>This dissertation explore two major goals in Deep Learning algorithm design: efficiency and trustworthiness. We motivate these concerns in Chapter 1 and give relevant background in Chapter 2. We then discuss six works to target these two goals. </p> <p>The first of these discusses how to make the model compression methodology more efficient, so it can be done in a single shot. This allows us to create models with reduced size and layers, so we can have faster and more efficient inference, and is covered in Chapter 3. We then extend this to target efficiency in continual learning in Chapter 4, while mitigating the problem of catastrophic forgetting. The method discussed also allows us to circumvent the potential for data leakage by avoiding the need to store any data from the past tasks. Next, we consider brain-inspired computing as an alternative to traditional neural networks to improve compute efficiency of networks. The spiking neural networks discussed however have large inference latency due to the need for accumulating spikes over many timesteps. We tackle this by introducing a new scheme that distributes an image over time by breaking it down into a sum of its ranked sinusoidal bases in Chapter 5. This results in networks that are faster and more efficient to deploy. Chapter 6 targets mitigating both the communication expense and potential for data leakage in federated learning, by distilling the gradients to be communicated in a small number of images that resemble noise. Communicating these images is more efficient, and circumvents the potential for data leakage as they resemble noise. We then explore the applications of studying curvature of loss with respect to input data points in the last two chapters. We first utilize curvature to create performant coresets to reduce the size of datasets, to make training more efficient in Chapter 7. In Chapter 8, we use curvature as a metric for overfitting and use it to expose dataset integrity issues arising from memorization.</p>

Manufacturers can develop next-generation production and service for their customers by the data gathered and analyzed from customers’ usage conditions. In this research, the operating condition of articular haulers is collected and analyzed through machine learning algorithms to predict the type of operational topographies and road surface. To achieve that, elevation data and satellite images, which were gathered from Microsoft Azure Maps, are used as data sources to identify the topography and road surface on which machines operated. In the end, two machine learning models are trained with machines’ inclination records and road roughness records, respectively, to classify the topography and road surface. For the topography classifier, the topography is categorized into four terrain labels, including "Low Hills", "Mountains", "Plains", and "Tablelands &amp; High Hills". The road surface is classified into "Paved" and "Unpaved". A Convolutional Neural Network (CNN) image classification model is built for labeling satellite images instead of labeling manually. The results indicate that the prediction for topography labels "Plains" and "Tablelands &amp; High Hills" has superior performance, which accounts for the majority of the raw dataset; on the contrary, the road surface classifier still needs further improvement in the future. In addition, an analysis and discussion regarding the imbalanced dataset are included, and it shows the limited effect on an extremely imbalanced dataset. Finally, the conclusion and future work are given.

Polyphonic or multiple music instrument detection is a difficult problem compared to detecting single or solo instruments in an audio recording. As music is time series data it be can modelled using sequence learning methods within deep learning. Recently, temporal convolutional networks (TCN) have shown to outperform conventional recurrent neural networks (RNN) on various sequence modelling tasks. Though there have been significant improvements in deep learning methods, data scarcity becomes a problem in training large scale models. Weakly labelled data is an alternative where a clip is annotated for presence or absence of instruments without specifying the times at which an instrument is sounding. This study investigates how TCN model compares to a Long Short-Term Memory (LSTM) model while trained on weakly labelled dataset. The results showed successful training of both models along with generalisation on a separate dataset. The comparison showed that TCN performed better than LSTM, but only marginally. Therefore, from the experiments carried out it could not be explicitly concluded if TCN is convincingly a better choice over LSTM in the context of instrument detection, but definitely a strong alternative. / Polyfonisk eller multipel musikinstrumentdetektering är ett svårt problem jämfört med att detektera enstaka eller soloinstrument i en ljudinspelning. Eftersom musik är tidsseriedata kan den modelleras med hjälp av sekvensinlärningsmetoder inom djup inlärning. Nyligen har ’Temporal Convolutional Network’ (TCN) visat sig överträffa konventionella ’Recurrent Neural Network’ (RNN) på flertalet sekvensmodelleringsuppgifter. Även om det har skett betydande förbättringar i metoder för djup inlärning, blir dataknapphet ett problem vid utbildning av storskaliga modeller. Svagt märkta data är ett alternativ där ett klipp kommenteras för närvaro av frånvaro av instrument utan att ange de tidpunkter då ett instrument låter. Denna studie undersöker hur TCN-modellen jämförs med en ’Long Short-Term Memory’ (LSTM) -modell medan den tränas i svagt märkta datasätt. Resultaten visade framgångsrik utbildning av båda modellerna tillsammans med generalisering i en separat datasats. Jämförelsen visade att TCN presterade bättre än LSTM, men endast marginellt. Därför kan man från de genomförda experimenten inte uttryckligen dra slutsatsen om TCN övertygande är ett bättre val jämfört med LSTM i samband med instrumentdetektering, men definitivt ett starkt alternativ.

Anti-Semitism is still very much alive in the United States and has increased in the pastyears (ADL, 2023). Anti-Semitic rhetoric was brought to light by the world-famousrapper Kanye West, who in the fall of 2022 committed several anti-Semitic acts on hissocial platforms. When a person with great influence on the public sphere expresseshimself anti-Semitic, people can copy the behavior and believe that it is accepted. Thestudy's purpose is to expand the understanding of how American media frames antiSemitic rhetoric depending on their political ideology. This essay examines how KanyeWest was portrayed in American media in the end of 2022, where all articles found inthe timeperiod that included Kanye and antisemitism were collected. A total of 120articles were collected from four different news sources; New York Post and Fow Newthat are righwinged as well as CNN and NBC that are leftwinged. The applied methodis a mixed method with a focus on qualitative thematic content analysis. The methodhas been applied by finding patterns (themes) in the articles to answer the study'squestions: (1) When Kanye expressed anti-Semitic rhetoric, how was he framed inAmerican media? (2) How does the media's political ideological background affect theportrayal? (3) Has Kanye's anti-Semitism influenced the rise of anti-Semitism in theUS? This study does not examine media outside of the United States and no other mediathan written articles by journalists. The limitation gives a clear result of framing in thecontext of politics in one country. Existing research of Entman (1993, 2007, 2010) isused in the study to show the impact that framing has on the public and how it affectspolitics. The result shows that Kanye was framed primarily as an artist but also as ananti-semite and half of the material had negative frames of Kanye. The comparisonbetween the rightwinged and leftwinged media, showed that the left focused more onhow Kanye affected antisemitism in the U.S. and how antisemitism has increased. Thestudy concluded that Kanye had a big part in spreading antisemitism in the U.S

This thesis presents a deep learning tool able to identify ice in radar images fromthe sea-ice environment of the Twhaites glacier outlet. The project is motivatedby the threatening situation of the Thwaites glacier that has been increasingits mass loss rate during the last decade. This is of concern considering thelarge mass of ice held by the glacier, that in case of melting, could increasethe mean sea level by more than +65 cm [1]. The algorithm generated alongthis work is intended to help in the generation of navigation charts and identificationof icebergs in future stages of the project, outside of the scope of this thesis.The data used for this task are ICEYE’s X-band radar images from the Thwaitessea-ice environment, the target area to be studied. The corresponding groundtruth for each of the samples has been manually generated identifying the iceand icebergs present in each image. Additional data processing includes tiling,to increment the number of samples, and augmentation, done by horizontal andvertical flips of a random number of tiles.The proposed tool performs semantic segmentation on radar images classifyingthe class "Ice". It is developed by a deep learning Convolutional Neural Network(CNN) model, trained with prepared ICEYE’s radar images. The model reachesvalues of F1 metric higher than 89% in the images of the target area (Thwaitessea-ice environment) and is able to generalize to different regions of Antarctica,reaching values of F1 = 80 %. A potential alternative version of the algorithm isproposed and discussed. This alternative score F1 values higher than F1 &gt; 95 %for images of the target environment and F1 = 87 % for the image of the differentregion. However, it must not be confirmed as the final algorithm due to the needfor further verification.

<p>Building a robust deep neural network (DNN) framework turns out to be a very difficult task as adaptive attacks are developed that break a robust DNN strategy. In this work we first study the bootstrap distribution of DNN weights and biases. We bootstrap three DNN models: a simple three layer convolutional neural network (CNN), VGG16 with 13 convolutional layers and 3 fully connected layers, and Inception v3 with 42 layers. Both VGG16 and Inception v3 are trained on CIFAR10 in order for bootstrapping networks to converge. We then compare the bootstrap NN parameter distributions with those from training DNN with different random initial seeds. We discover that the bootstrap DNN parameter distributions change as the DNN model size increases. And the bootstrap DNN parameter distributions are very close to those obtained from training with different random initial seeds. The bootstrap DNN parameter distributions are used to create a graybox defense strategy. We randomize a certain percentage of the weights of the first convolutional layers of a DNN model, and create a random ensemble of DNNs. Based on one trained DNN, we have infinitely many random DNN ensembles. The adaptive attacks lose the target. A random DNN ensemble is resilient to the adversarial attacks and maintains performance on clean data.</p>