Because of Machine Learning, machines have become extremely good at image classification in near real time. With using significant training data, powerful machines can be trained to recognize images as good as any human would. Till now the norm has been to have pictures sent to a server and have the server recognize them. With increasing number of sensors the trend is moving towards edge computing to curb the increasing rate of data transfer and communication bottlenecks. The idea is to do the processing locally or as close to the sensor as possible and then only transmit actionable data to the server. While, this does solve plethora of communication problems, specially in industrial settings, it creates a new problem. The sensors need to do this computationally intensive image classification which is a challenge for embedded/wearable devices, due to their resource constrained nature. This thesis analyzes Machine Learning algorithms and libraries from the motivation of porting image classifiers to embedded devices. This includes, comparing different supervised Machine Learning approaches to image classification and figuring out which are most suited for being ported to embedded devices. Taking a step forward in making the process of testing and implementing Machine Learning algorithms as easy as their desktop counterparts. The goal is to ease the process of porting new image recognition and classification algorithms on a host of different embedded devices and to provide motivations behind design decisions. The final proposal goes through all design considerations and implements a prototype that is hardware independent. Which can be used as a reference for designing and then later porting of Machine Learning classifiers to embedded devices. / Maskiner har blivit extremt bra på bildklassificering i nära realtid. På grund av maskininlärning med kraftig träningsdata, kan kraftfulla maskiner utbildas för att känna igen bilder så bra som alla människor skulle. Hittills har trenden varit att få bilderna skickade till en server och sedan få servern att känna igen bilderna. Men eftersom sensorerna ökar i antal, går trenden mot så kallad "edge computing" för att stryka den ökande graden av dataöverföring och kommunikationsflaskhalsar. Tanken är att göra bearbetningen lokalt eller så nära sensorn som möjligt och sedan bara överföra aktiv data till servern. Samtidigt som detta löser överflöd av kommunikationsproblem, speciellt i industriella inställningar, skapar det ett nytt problem. Sensorerna måste kunna göra denna beräkningsintensiva bildklassificering ombord vilket speciellt är en utmaning för inbyggda system och bärbara enheter, på grund av sin resursbegränsade natur. Denna avhandling analyserar maskininlärningsalgoritmer och biblioteken från motivationen att portera generiska bildklassificatorer till inbyggda system. Att jämföra olika övervakade maskininlärningsmetoder för bildklassificering, utreda vilka som är mest lämpade för att bli porterade till inbyggda system, för att göra processen att testa och implementera maskininlärningsalgoritmer lika enkelt som sina skrivbordsmodeller. Målet är att underlätta processen för att portera nya bildigenkännings och klassificeringsalgoritmer på en mängd olika inbyggda system och att ge motivation bakom designbeslut som tagits och för att beskriva det snabbaste sättet att skapa en prototyp med "embedded vision design". Det slutliga förslaget går igenom all hänsyn till konstruktion och implementerar en prototyp som är maskinvaruoberoende och kan användas för snabb framtagning av prototyper och sedan senare överföring av maskininlärningsklassificatorer till inbyggda system.

Identifying Low-head dams (LHD) and creating an inventory become a priority as fatalities continue to occur at these structures. Because obstruction inventories do not specifically identify LHDs, and they are not assigned a hazard classification, there is not an official inventory of LHD. However, there is a multi-agency taskforce that is creating an inventory of LHD. All efforts have been performed by manually identifying LHD on Google Earth Pro (GE Pro). The purpose of this paper is to assess whether a machine learning approach can accelerate the national inventory. We used a machine learning approach to implement a high-resolution remote sensing data and a Convolutional Neural Network (CNN) architecture. The model achieved 76% accuracy on identifying LHD (true positive) and 95% accuracy identifying NLHD (true negative) on the validation set. We deployed the trained model into the National Hydrologic Geospatial Fabric (Hydrofabric) flowlines on the Provo River watershed. The results showed a high number of false positives and low accuracy in identifying LHD due to the mismatch between Hydrofabric flowlines and actual waterways. We recommend improving the accuracy of the Hydrofabric waterway tracing algorithms to increase the percentage of correctly classified LHD.

Corneal diseases are one of the major causes of visual impairment and blindness worldwide. Used for diagnoses, a laser confocal microscope provides a sequence of images, at incremental depths, of the various corneal layers and structures. From these, ophthalmologists can extract clinical information on the state of health of a patient’s cornea. However, many factors impede ophthalmologists in forming diagnoses starting with the large number and variable quality of the individual images (blurring, non-uniform illumination within images, variable illumination between images and noise), and there are also difficulties posed for automatic processing caused by eye movements in both lateral and axial directions during the scanning process. Aiding ophthalmologists working with long sequences of corneal image requires the development of new algorithms which enhance, correctly order and register the corneal images within a sequence. The novel algorithms devised for this purpose and presented in this thesis are divided into four main categories. The first is enhancement to reduce the problems within individual images. The second is automatic image classification to identify which part of the cornea each image belongs to, when they may not be in the correct sequence. The third is automatic reordering of the images to place the images in the right sequence. The fourth is automatic registration of the images with each other. A flexible application called CORNEASYS has been developed and implemented using MATLAB and the C language to provide and run all the algorithms and methods presented in this thesis. CORNEASYS offers users a collection of all the proposed approaches and algorithms in this thesis in one platform package. CORNEASYS also provides a facility to help the research team and Ophthalmologists, who are in discussions to determine future system requirements which meet clinicians’ needs. / The data and image files accompanying this thesis are not available online.

Abstract Predicting Location and Training Effectiveness (PLATE) Erik Bruenner Physical activity and exercise have been shown to have an enormous impact on many areas of human health and can reduce the risk of many chronic diseases. In order to better understand how exercise may affect the body, current kinesiology studies are designed to track human movements over large intervals of time. Procedures used in these studies provide a way for researchers to quantify an individual’s activity level over time, along with tracking various types of activities that individuals may engage in. Movement data of research subjects is often collected through various sensors, such as accelerometers. Data from these specialized sensors may be fed into a deep learning model which can accurately predict what movements a person is making based on aggregated sensor data. However, in order for prediction models to produce accurate classifications of activities, they must be ‘trained’. Training occurs through the process of supervised learning on large amounts of data where movements are already known. These training data sets are also known as ‘validation’ data or ‘ground truth’. Currently, generation of these ground truth sets is very labor-intensive. To generate these labeled data sets, research assistants must analyze many hours of video footage with research subjects. These research assistants painstakingly categorize each video, second by second, with a description of the activity the subject was engaging in. Using only labeled video, the PLATE project facilitates the generation of ground truth data by developing an artificial intelligence (AI) that predicts video quality labels, along with labels that denote the physical location that these activities occurred in. The PLATE project builds on previous work by a former graduate student, Roxanne Miller. Miller developed a classification system to categorize subject activities into groups such as ‘Stand’, ‘Sit’, ‘Walk’, ‘Run’, etc. The PLATE project focuses instead on development of AI to generate ground truth training in order to accurately detect and identify the quality of video data, and the location of the video data. In the context of the PLATE project, video quality refers to whether or not a test subject is visible in the frame. Location classifications include categorizing ‘indoors’, ‘outdoors’, and ‘traveling’. More specifically, indoor categories are further identified as ‘house’, ‘office’, ‘school’, ‘store’ or ‘commercial’ space. Outdoor locations are further classified as ‘commercial space’, ‘park/greenspace’, ‘residential’ or ‘neighborhood’. The nature of our location classification problem lends itself particularly well to a hierarchical classification approach, where general indoor, outdoor, or travel categories are predicted, then separate models predict the subclassifications of these categories. The PLATE project uses three convolutional neural networks in its hierarchical location prediction pipeline, and one convolutional neural network to predict if video frames are high or low quality. Results from the PLATE project demonstrate that quality can be predicted with an accuracy of 96%, general location with an accuracy of 75%, and specific locations with an accuracy of 31%. The findings and model produced by the PLATE project are utilized in the PathML project as part of a ground truth prediction software for activity monitoring studies. PathML is a project funded by the NIH as part of a Small Business Research Initiative. Cal Poly partnered with Sentimetrix Inc, a data analytics/machine learning company, to build a methodology for automated labeling of human physical activity. The partnership aims to utilize this methodology to develop a software tool that performs automatic labeling and facilitates the subsequent human inspection. Phase I (proof of concept) of the project took place from September 2021 to August 2022, Phase II (final software production) is pending. This thesis is part of the research that took place during Phase I lifetime, and continues to support Phase II development.

No description available.

No description available.

Available computing resources play a large part in enabling the training of modern deep neural networks to complete complex computer vision tasks. Improving the efficiency with which this computational power is utilized is highly important for enterprises to improve their networks rapidly. The first few training iterations over the data set often result in substantial gradients from seeing the samples and quick improvements in the network. At later stages, most of the training time is spent on samples that produce tiny gradient updates and are already properly handled. To make neural network training more efficient, researchers have used methods that give more attention to the samples that still produce relatively large gradient updates for the network. The methods used are called ''Importance Sampling''. When used, it reduces the variance in sampling and concentrates the training on the more informative examples. This thesis contributes to the studies on importance sampling by investigating its effectiveness in different contexts. In comparison to other studies, we more extensively examine image classification by exploring different network architectures over a wide range of parameter counts. Similar to earlier studies, we apply several ways of doing importance sampling across several datasets. While most previous research on importance sampling strategies applies it to image classification, our research aims at generalizing the results by applying it to object detection problems on top of image classification. Our research on image classification tasks conclusively suggests that importance sampling can speed up the training of deep neural networks. When performance in convergence is the vital metric, our importance sampling methods show mixed results. For the object detection tasks, preliminary experiments have been conducted. However, the findings lack enough data to demonstrate the effectiveness of importance sampling in object detection conclusively.

A conversational robot will in many cases have todeal with multi-party spoken interaction in which one or morepeople could be speaking simultaneously. To do this, the robotmust be able to identify the speakers in order to attend to them.Our project has approached this problem from a visual pointof view where a Convolutional Neural Network (CNN) wasimplemented and trained using video stream input containingone or more faces from an already existing data set (AVA-Speech). The goal for the network has then been to for eachface, and in each point in time, detect the probability of thatperson speaking. Our best result using an added Optical Flowfunction was 0.753 while we reached 0.781 using another pre-processing method of the data. These numbers correspondedsurprisingly well with the existing scientific literature in thearea where 0.77 proved to be an appropriate benchmark level. / En social robot kommer i många fall tvingasatt hantera konversationer med flera interlokutörer och därolika personer pratar samtidigt. För att uppnå detta är detviktigt att roboten kan identifiera talaren för att i nästa ledkunna bistå eller interagera med denna. Detta projekt harundersökt problemet med en visuell utgångspunkt där ettFaltningsnätverk (CNN) implementerades och tränades medvideo-input från ett redan befintligt dataset (AVA-Speech).Målet för nätverket har varit att för varje ansikte, och i varjetidpunkt, detektera sannolikheten att den personen talar. Vårtbästa resultat vid användning av Optical Flow var 0,753 medanvi lyckades nå 0,781 med en annan typ av förprocessering avdatan. Dessa resultat motsvarade den existerande vetenskapligalitteraturen på området förvånansvärt bra där 0,77 har visatsig vara ett lämpligt jämförelsevärde. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm

Traditional multi-class classification problems assume that each instance is associated with a single label from category set Y where |Y| > 2. Multi-label classification generalizes multi-class classification by allowing each instance to be associated with multiple labels from Y. In many real world data analysis problems, data objects can be assigned into multiple categories and hence produce multi-label classification problems. For example, an image for object categorization can be labeled as 'desk' and 'chair' simultaneously if it contains both objects. A news article talking about the effect of Olympic games on tourism industry might belong to multiple categories such as 'sports', 'economy', and 'travel', since it may cover multiple topics. Regardless of the approach used, multi-label learning in general requires a sufficient amount of labeled data to recover high quality classification models. However due to the label sparsity, i.e. each instance only carries a small number of labels among the label set Y, it is difficult to prepare sufficient well-labeled data for each class. Many approaches have been developed in the literature to overcome such challenge by exploiting label correlation or label dependency. In this dissertation, we propose a probabilistic model to capture the pairwise interaction between labels so as to alleviate the label sparsity. Besides of the traditional setting that assumes training data is fully labeled, we also study multi-label learning under other scenarios. For instance, training data can be unreliable due to missing values. A conditional Restricted Boltzmann Machine (CRBM) is proposed to take care of such challenge. Furthermore, labeled training data can be very scarce due to the cost of labeling but unlabeled data are redundant. We proposed two novel multi-label learning algorithms under active setting to relieve the pain, one for standard single level problem and one for hierarchical problem. Our empirical results on multiple multi-label data sets demonstrate the efficacy of the proposed methods. / Computer and Information Science

<p dir="ltr">This dissertation encompasses three studies in distinct yet impactful domains: B2B marketing, real-time video super-resolution (VSR), and smart office document routing systems. In the B2B marketing sphere, the study addresses the extended buying cycle by developing an algorithm for customer data aggregation and employing a CatBoost model to predict potential purchases with 91% accuracy. This approach enables the identification of high-potential<br>customers for targeted marketing campaigns, crucial for optimizing marketing efforts.<br>Transitioning to multimedia enhancement, the dissertation presents a lightweight recurrent network for real-time VSR. Developed for applications requiring high-quality video with low latency, such as video conferencing and media playback, this model integrates an optical flow estimation network for motion compensation and leverages a hidden space for the propagation of long-term information. The model demonstrates high efficiency in VSR. A<br>comparative analysis of motion estimation techniques underscores the importance of minimizing information loss.<br>The evolution towards smart office environments underscores the importance of an efficient document routing system, conceptualized as an online class-incremental image classification challenge. This research introduces a one-versus-rest parametric classifier, complemented by two updating algorithms based on passive-aggressiveness, and adaptive thresholding methods to manage low-confidence predictions. Tested on 710 labeled real document<br>images, the method reports a cumulative accuracy rate of approximately 97%, showcasing the effectiveness of the chosen aggressiveness parameter through various experiments.</p>