RNAs are involved in different facets of biological processes; including but not limited to controlling and inhibiting gene expressions, enabling transcription and translation from DNA to proteins, in processes involving diseases such as cancer, and virus-host interactions. As such, there are useful applications that may arise from studies and analyses involving RNAs, such as detecting cancer by measuring the abundance of specific RNAs, detecting and identifying infections involving RNA viruses, identifying the origins of and relationships between RNA viruses, and identifying potential targets when designing novel drugs. Extracting sequences from RNA samples is usually not a major limitation anymore thanks to sequencing technologies such as RNA-Seq. However, accurately identifying and analyzing the extracted sequences is often still the bottleneck when it comes to developing RNA-based applications. Like proteins, functional RNAs are able to fold into complex structures in order to perform specific functions throughout their lifecycle. This suggests that structural information can be used to identify or classify RNA sequences, in addition to the sequence information of the RNA itself. Furthermore, a strand of RNA may have more than one possible structural conformations it can fold into, and it is also possible for a strand to form different structures in vivo and in vitro. However, past studies that utilized secondary structure information for RNA identification purposes have relied on one predicted secondary structure for each RNA sequence, despite the possible one-to-many relationship between a strand of RNA and the possible secondary structures. Therefore, we hypothesized that using a representation that includes the multiple possible secondary structures of an RNA for classification purposes may improve the classification performance. We proposed and built a pipeline that produces secondary structure fingerprints given a sequence of RNA, that takes into account the aforementioned multiple possible secondary structures for a single RNA. Using this pipeline, we explored and developed different types of secondary structure fingerprints in our studies. A type of fingerprints serves as high-level topological representations of the RNA structure, while another type represents matches with common known RNA secondary structure motifs we have curated from databases and the literature. Next, to test our hypothesis, the different fingerprints are then used with deep learning and with different datasets, alone and together with various sequence-based features, to investigate how the secondary structure fingerprints affect the classification performance. Finally, by analyzing our findings, we also propose approaches that can be adopted by future studies to further improve our secondary structure fingerprints and classification performance.

fMRI imaging is considered key on the understanding of the brain and the mind, for this reason has been the subject of tremendous research connecting different disciplines. The intrinsic complexity of this 4-D type of data processing and analysis has been approached with every single computational perspective, lately increasing the trend to include artificial intelligence. One step critical on the fMRI pipeline is image registration. A model of Deep Networks based on Fully Convolutional Neural Networks, spatial transformation neural networks with a self-learning strategy was proposed for the implementation of a Fully deformable model image registration algorithm. Publicly available fMRI datasets with images from real-life subjects were used for training, testing and validating the model. The model performance was measured in comparison with ANTs deformable registration method with good results suggesting that Deep Learning can be used successfully for the development of the field using the basic strategy of studying the brain using the brain-self strategies.

The advancements of AI methodologies and computing power enables automation and propels the Industry 4.0 phenomenon. Information and data are digitized more than ever, millions of documents are being processed every day, they are fueled by the growth in institutions, organizations, and their supply chains. Processing documents is a time consuming laborious task. Therefore automating data processing is a highly important task for optimizing supply chains efficiency across all industries. Document analysis for data extraction is an impactful field, this thesis aims to achieve the vital steps in an ideal data extraction pipeline. Data is often stored in tables since it is a structured formats and the user can easily associate values and attributes. Tables can contain vital information from specifications, dimensions, cost etc. Therefore focusing on table analysis and recognition in documents is a cornerstone to data extraction. This thesis applies deep learning methodologies for automating the two main problems within table analysis for data extraction; table detection and table structure detection. Table detection is identifying and localizing the boundaries of the table. The output of the table detection model will be inputted into the table structure detection model for structure format analysis. Therefore the output of the table detection model must have high localization performance otherwise it would affect the rest of the data extraction pipeline. Our table detection improves bounding box localization performance by incorporating a Kullback–Leibler loss function that calculates the divergence between the probabilistic distribution between ground truth and predicted bounding boxes. As well as adding a voting procedure into the non-maximum suppression step to produce better localized merged bounding box proposals. This model improved precision of tabular detection by 1.2% while achieving the same recall as other state-of-the-art models on the public ICDAR2013 dataset. While also achieving state-of-the-art results of 99.8% precision on the ICDAR2017 dataset. Furthermore, our model showed huge improvements espcially at higher intersection over union (IoU) thresholds; at 95% IoU an improvement of 10.9% can be seen for ICDAR2013 dataset and an improvement of 8.4% can be seen for ICDAR2017 dataset. Table structure detection is recognizing the internal layout of a table. Often times researchers approach this through detecting the rows and columns. However, in order for correct mapping of each individual cell data location in the semantic extraction step the rows and columns would have to be combined and form a matrix, this introduces additional degrees of error. Alternatively we propose a model that directly detects each individual cell. Our model is an ensemble of state-of-the-art models; Hybird Task Cascade as the detector and dual ResNeXt101 backbones arranged in a CBNet architecture. There is a lack of quality labeled data for table cell structure detection, therefore we hand labeled the ICDAR2013 dataset, and we wish to establish a strong baseline for this dataset. Our model was compared with other state-of-the-art models that excelled at table or table structure detection. Our model yielded a precision of 89.2% and recall of 98.7% on the ICDAR2013 cell structure dataset.

Robust and timely perception of the environment is an essential requirement of all autonomous and semi-autonomous systems. This necessity has been the main factor behind the rapid growth and adoption of LiDAR sensors within the ADAS sensor suite. In this thesis, we develop a fast and accurate 3D object detector that converts raw point clouds collected by LiDARs into sparse occupancy cuboids to detect cars and other road users using deep convolutional neural networks. The proposed pipeline reduces the runtime of PointPillars by 43% and performs on par with other state-of-the-art models. We do not gain improvements in speed by compromising the network's complexity and learning capacity but rather through the use of an efficient input encoding procedure. In addition to rigorous profiling on three different platforms, we conduct a comprehensive error analysis and recognize principal sources of error among the predicted attributes. Even though point clouds adequately capture the 3D structure of the physical world, they lack the rich texture information present in color images. In light of this, we explore the possibility of fusing the two modalities with the intent of improving detection accuracy. We present a late fusion strategy that merges the classification head of our LiDAR-based object detector with semantic segmentation maps inferred from images. Extensive experiments on the KITTI 3D object detection benchmark demonstrate the validity of the proposed fusion scheme.

High Dynamic Range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this thesis, we propose a joint design for snapshot HDR imaging by devising a spatially varying modulation mask in the hardware combined with a deep learning algorithm to reconstruct the HDR image. In this approach, we achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware-software solution offers a flexible, yet robust, way to modulate per-pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparative analysis demonstrated that our method outperforms the state-of-the-art in terms of visual perception quality. We leverage transfer learning to overcome the lack of sufficiently large HDR datasets available. We show how transferring from a different large scale task (image classification on ImageNet) leads to considerable improvements in HDR reconstruction

Deep Neural Networks (DNNs) are ubiquitous and span a variety of applications ranging from image classification and facial recognition to medical image analysis and real-time object detection. As DNN models become more sophisticated and complex, the computational cost of training these models becomes a burden. For this reason, outsourcing the training process has been the go-to option for many DNN users. Unfortunately, this comes at the cost of vulnerability to backdoor attacks. These attacks aim at establishing hidden backdoors in the DNN such that it performs well on clean samples but outputs a particular target label when a trigger is applied to the input. Current backdoor attacks generate triggers in the spatial domain; however, as we show in this work, it is not the only domain to exploit and one should always "check the other doors". To the best of our knowledge, this work is the first to propose a pipeline for generating a spatially dynamic (changing) and invisible (low norm) backdoor attack in the frequency domain. We show the advantages of utilizing the frequency domain for creating undetectable and powerful backdoor attacks through extensive experiments on various datasets and network architectures. Unlike most spatial domain attacks, frequency-based backdoor attacks can achieve high attack success rates with low poisoning rates and little to no drop in performance while remaining imperceptible to the human eye. Moreover, we show that the backdoored models (poisoned by our attacks) are resistant to various state-of-the-art (SOTA) defenses, and so we contribute two possible defenses that can successfully evade the attack. We conclude the work with some remarks regarding a network’s learning capacity and the capability of embedding a backdoor attack in the model.

As deep learning continues to push the boundaries with applications previously thought impossible, it has become more important than ever to reduce the associated resource costs. Data is not always abundant, labelling costs valuable human time, and deep models are demanding of computer hardware. In this dissertation, I will examine questions of minimalism in deep learning. I will show that deep learning can learn with fewer measurements, fewer weights, and less information. With minimalism, deep learning can become even more ubiquitous, succeeding in more applications and on more everyday devices.

Prediction of initial velocity of artillery system is a feature that is hard to determine with statistical and analytical models. Machine learning is therefore to be tested, in order to achieve a higher accuracy than the current method (baseline). An ensemble approach will be explored in this paper, centered around feed forward deep neural network and random forest regression. Furthermore, collinearity of features and their importance will be investigated. The impact of the measured error on the range of the projectile will also be derived by finding a numerical solution with Newton Raphsons method. For the five systemstest data was used on, the mean absolute errors were 26, 9.33, 8.72 and 9.06 for deep neural networks,random forest regression, ensemble learning and conventional method, respectively. For future works,more models should be tested with ensemble learning, as well as investigation on the feature space for the input data.

Indiana University-Purdue University Indianapolis (IUPUI) / Textual emotion classification is a task in affective AI that branches from sentiment analysis and focuses on identifying emotions expressed in a given text excerpt. It has a wide variety of applications that improve human-computer interactions, particularly to empower computers to understand subjective human language better. Significant research has been done on this task, but very little of that research leverages one of the most emotion-bearing symbols we have used in modern communication: Emojis. In this thesis, we propose several transformer-based models for emotion classification that processes emojis as input tokens and leverages pretrained models and uses them , a model that processes Emojis as textual inputs and leverages DeepMoji to generate affective feature vectors used as reference when aggregating different modalities of text encoding. To evaluate ReferEmo, we experimented on the SemEval 2018 and GoEmotions datasets, two benchmark datasets for emotion classification, and achieved competitive performance compared to state-of-the-art models tested on these datasets. Notably, our model performs better on the underrepresented classes of each dataset.

No description available.