Physical Sciences and Mathematics Commons^™

Deep Reinforcement Learning-Based Portfolio Management, Nitin Kanwar

Computer Science and Engineering Theses - Archive

Machine Learning is at the forefront of every field today. The subfields of Machine Learning called Reinforcement Learning and Deep Learning, when combined have given rise to advanced algorithms which have been successful at reaching or surpassing the human-level performance at playing Atari games to defeating multiple times champion at Go. These successes of Machine Learning have attracted the interest of the financial community and have raised the question if these techniques could also be applied in detecting patterns in the financial markets. Until recently, mathematical formulations of dynamical systems in the context of Signal Processing and Control Theory have …

Ultra-Context: Maximizing The Context For Better Image Caption Generation, Ankit Khare

Computer Science and Engineering Theses - Archive

Several combinations of visual and semantic attention have been geared towards developing better image captioning architectures. In this work we introduce a novel combination of word-level semantic context with image feature-level visual context, which provides a more holistic overall context for image caption generation. This approach does not require training any explicit network structure, using any external resource for training semantic attributes, or supervision during any training step. The proposed architecture addresses the significance of learning to find context at three levels to achieve a better trade-off as well as a balance between the two lines of attentiveness (word-level and …

From Body To Brain: Using Artificial Intelligence To Identify User Skills & Intentions In Interactive Scenarios, Michalis Papakostas

Computer Science and Engineering Dissertations - Archive

Artificial Intelligence has probably been the most rapidly evolving field of science during the last decade. Its numerous real-life applications have radically altered the way we experience daily-living with great impact in some of the most basic aspects of human lives including but not limited to health and well-being, communication and interaction, education, driving, daily, and entertainment. Human-Computer Interaction (HCI) is the field of Computer Science lying in the epicenter of this evolution and is responsible for transforming rudimentary research findings and theoretical principles into intuitive tools, responsible for enhancing human performance, increasing productivity and ensuring safety. Two of the …

Patchnet: A Tool For Deep Patch Classification, Thong Hoang, Julia Lawall, Richard J. Oentaryo, Yuan Tian, David Lo

Research Collection School Of Computing and Information Systems

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of a code change, differentiating it from the existing deep learning models on source code. PatchNet provides several options allowing users to selectparameters for the training process. The tool has been validated in the context of automatic identification of stable-relevant patches in the Linux kernel and is potentially applicable to automate other software engineering tasks that can be formulated as patch classification problems. …

Patchnet: A Tool For Deep Patch Classification, Thong Hoang, Julia Lawall, Richard J. Oentaryo, Yuan Tian, David Lo

Research Collection School Of Computing and Information Systems

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of a code change, differentiating it from the existing deep learning models on source code. PatchNet provides several options allowing users to select parameters for the training process. The tool has been validated in the context of automatic identification of stable-relevant patches in the Linux kernel and is potentially applicable to automate other software engineering tasks that can be formulated as patch classification …

Deep Learning Vs Markov Model In Music Generation, Jeffrey Cruz

Honors College Theses

Artificial intelligence is one of the fastest growing fields at the moment in Computer Science. This is mainly due to the recent advances in machine learning and deep learning algorithms. As a result of these advances, deep learning has been used extensively in applications related to computerized audio/music generation. The main body of this thesis is an experiment. This experiment was based on a similar experiment done by Mike Kayser of Stanford University in 2013 for his thesis “Generative Models of Music” where he used Hidden Markov Models and tested the quality/accuracy of the music he generated using a music …

Deepjit: An End-To-End Deep Learning Framework For Just-In-Time Defect Prediction, Thong Hoang, Hoa Khanh Dam, Yasutaka Kamei, David Lo, Naoyasu Ubayashi

Research Collection School Of Computing and Information Systems

Software quality assurance efforts often focus on identifying defective code. To find likely defective code early, change-level defect prediction – aka. Just-In-Time (JIT) defect prediction – has been proposed. JIT defect prediction models identify likely defective changes and they are trained using machine learning techniques with the assumption that historical changes are similar to future ones. Most existing JIT defect prediction approaches make use of manually engineered features. Unlike those approaches, in this paper, we propose an end-to-end deep learning framework, named DeepJIT, that automatically extracts features from commit messages and code changes and use them to identify defects. Experiments …

Triplet Loss Network For Unsupervised Domain Adaptation, Imad Eddine Ibrahim Bekkouch, Youssef Youssry, Rustam Gafarov, Adil Khan, Asad Masood Khattak

All Works

© 2019 by the authors. Domain adaptation is a sub-field of transfer learning that aims at bridging the dissimilarity gap between different domains by transferring and re-using the knowledge obtained in the source domain to the target domain. Many methods have been proposed to resolve this problem, using techniques such as generative adversarial networks (GAN), but the complexity of such methods makes it hard to use them in different problems, as fine-tuning such networks is usually a time-consuming task. In this paper, we propose a method for unsupervised domain adaptation that is both simple and effective. Our model (referred to …

Softmax And Mcfadden's Discrete Choice Under Interval (And Other) Uncertainty, Bartłomiej Jacek Kubica, Laxman Bokati, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

One of the important steps in deep learning is softmax, when we select one of the alternatives with a probability depending on its expected gain. A similar formula describes human decision making: somewhat surprisingly, when presented with several choices with different expected equivalent monetary gain, we do not just select the alternative with the largest gain; instead, we make a random choice, with probability decreasing with the gain -- so that it is possible that we will select second highest and even third highest value. Both formulas assume that we know the exact value of the expected gain for each …

Weighted Random Search For Hyperparameter Optimization, Adrian-Cǎtǎlin Florea, Rǎzvan Andonie

All Faculty Scholarship for the College of the Sciences

We introduce an improved version of Random Search (RS), used here for hyperparameter optimization of machine learning algorithms. Unlike the standard RS, which generates for each trial new values for all hyperparameters, we generate new values for each hyperparameter with a probability of change. The intuition behind our approach is that a value that already triggered a good result is a good candidate for the next step, and should be tested in new combinations of hyperparameter values. Within the same computational budget, our method yields better results than the standard RS. Our theoretical results prove this statement. We test our …

Highly Accurate Fragment Library For Protein Fold Recognition, Wessam Elhefnawy

Computer Science Theses & Dissertations

Proteins play a crucial role in living organisms as they perform many vital tasks in every living cell. Knowledge of protein folding has a deep impact on understanding the heterogeneity and molecular functions of proteins. Such information leads to crucial advances in drug design and disease understanding. Fold recognition is a key step in the protein structure discovery process, especially when traditional computational methods fail to yield convincing structural homologies. In this work, we present a new protein fold recognition approach using machine learning and data mining methodologies.

First, we identify a protein structural fragment library (Frag-K) composed of a …

Deep Learning For Document Image Analysis, Christopher Alan Tensmeyer

Theses and Dissertations

Automatic machine understanding of documents from image inputs enables many applications in modern document workflows, digital archives of historical documents, and general machine intelligence, among others. Together, the techniques for understanding document images comprise the field of Document Image Analysis (DIA). Within DIA, the research community has identified several sub-problems, such as page segmentation and Optical Character Recognition (OCR). As the field has matured, there has been a trend of moving away from heuristic-based methods, designed for particular tasks and domains of documents, and moving towards machine learning methods that learn to solve tasks from examples of input/output pairs. Within …

Transnfcm: Translation-Based Neural Fashion Compatibility Modeling, Xun Yang, Yunshan Ma, Lizi Liao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Identifying mix-and-match relationships between fashion items is an urgent task in a fashion e-commerce recommender system. It will significantly enhance user experience and satisfaction. However, due to the challenges of inferring the rich yet complicated set of compatibility patterns in a large e-commerce corpus of fashion items, this task is still underexplored. Inspired by the recent advances in multi-relational knowledge representation learning and deep neural networks, this paper proposes a novel Translation-based Neural Fashion Compatibility Modeling (TransNFCM) framework, which jointly optimizes fashion item embeddings and category-specific complementary relations in a unified space via an end-to-end learning manner. TransNFCM places items …

Deep Learning Method For Hyperspectral Remote Sensing Images With Small Samples, Xiangbin Shi, Zhong Jian, Cuiwei Liu, Liu Fang, Deyuan Zhang

Journal of System Simulation

Abstract: In order to solve the problem of large information dimension and fewer labeled training samples of hyperspectral remote sensing images, this paper proposes a hyperspectral remote sensing image classification framework HSI-CNN, which reduces the number of model parameters while maintaining the depth of neural network. Image pattern invariance and spectral channel contribution rate are analyzed, and the spectral redundancy information is reduced by principal component analysis. A full convolution neural network structure suitable for small sample hyperspectral remote sensing images is designed and the amount of network parameters is effectively reduced. Three kinds of HSI-CNN structures are proposed …

Video Action Recognition Based On Key-Frame, Mingxiao Li, Qichuan Geng, Mo Hong, Wu Wei, Zhou Zhong

Journal of System Simulation

Abstract: Video action recognition is an important part of intelligent video analysis. In recent years, deep learning methods, especially the two-stream convolutional neural network achieved the state-of-the-art performance. However, most methods simply use uniform sampling to get frames, which may cause the loss of information in sampling interval. We propose a segmentation method and a key-frame extraction method for video action recognition, and combine them with a multi-temporal-scale two-stream network. Our framework achieves a 94.2% accuracy at UCF101 split1, which is the same as the state-of-the-art method’s performance.

A Horizon Detection Method Based On Deep Learning And Random Forest, Jihua Ye, Shuxia Shi, Hanxi Li, Jiali Zuo, Shimin Wang

Journal of System Simulation

Abstract: The detection effect of existing horizon line detection methods is greatly affected by the environment, and the computational complexity is high. Aiming at the problem of horizon line detection in complex road scene in real-life, a horizon line detection method based on deep learning and random forest is proposed. The deep learning model is used to extract the depth features, then the obtained depth features are used for random forest training. The results of horizon line detection are obtained by random forest regression-voting. The simulation results show that this method has good detection effect. The detection results are not …

Traffic Flow Prediction Based On Deep Learning, Mingyu Liu, Jianping Wu, Yubo Wang, He Lei

Journal of System Simulation

Abstract: Traffic flow prediction is an important component of urban intelligent transportation system. With the development of machine learning and artificial intelligence, deep learning has been applied in traffic engineering area. Gated recurrent unit (GRU) neural network is selected to predict urban traffic flow. Cross-validation method is used to explore the optimal number of gated recurrent units. The GRU model is compared with other three predictors such as support vector regression and evaluated in different performance measurements. The results show that GRU model has better performance in traffic flow prediction than the other three models.

Research On Evaluation Framework Of Coa Based On Wargaming, Haiyang Liu, Yubo Tang, Xiaofeng Hu, Guangpeng Qiao

Journal of System Simulation

Abstract: Aiming at the evaluation problem of COA (course of action) level indicators in joint operation, an evaluation framework of COA based on wargaming was proposed. By multidimensional analysis of wargaming data, an evaluation feature space was constructed from basic features generated by data cube models and SoS (system of systems) features based on complex network. Wargaming experiments were used to generate small batch metrics results of COA level indicators, and the corresponding result labels of evaluation feature space data were generated by data fitting method. Two-phase correlation analysis was used for dimensionality reduction of high dimensional evaluation features. …

Visual Object Tracking Algorithm Based On Deep Denoising Autoencoder Over Rgb-D Data, Mingxin Jiang, Zhigeng Pan, Lanfang Wang, Taoxin Hu

Journal of System Simulation

Abstract: A visual object tracking algorithm based on cross-modality features deep learning over RGB-D data is proposed. A sparse denoising autoencoder deep learning network is constructed, which can extract cross-modal features of the samples in RGB-D video data. The cross-modal features of the samples are input to the logistic regression classifier, the observation likelihood model is established according to the confidence score of the classifier, and the reasonable state transition model is established. The object tracking results over RGB-D data are obtained using particle filtering algorithm. Experimental results show that the proposed method has strong robustness to abnormal changes. …

A Model For Battlefield Situation Change Rate Prediction Based On Deep Learning, Jiuyang Tao, Wu Lin, Wang Chi, Junda Chu, Liao Ying, Zhu Feng

Journal of System Simulation

Abstract: To measure and estimate the uncertainty of the battlefield situation is of great significance for the commanders to plan the reconnaissance mission and reduce the risk of decision-making. Based on Shannon's information theory, firstly, methods and a model on measurement of situation change rate are proposed. Secondly, a scene with two-dimensional grid elements maneuvering is established, based on deep learning, the prediction method for maneuvering trend is explored. It is proved that cross entropy is equivalent to situation change rate. Finally, with the increase of the objective uncertainty, situation change rate and the accuracy of the forecast is …

Multi-Sensory Deep Learning Architectures For Slam Dunk Scene Classification, Paul Minogue

Dissertations

Basketball teams at all levels of the game invest a considerable amount of time and effort into collecting, segmenting, and analysing footage from their upcoming opponents previous games. This analysis helps teams identify and exploit the potential weaknesses of their opponents and is commonly cited as one of the key elements required to achieve success in the modern game. The growing importance of this type of analysis has prompted research into the application of computer vision and audio classification techniques to help teams classify scoring sequences and key events using game footage. However, this research tends to focus on classifying …

Applied Machine Learning For Classification Of Musculoskeletal Inference Using Neural Networks And Component Analysis, Shaswat Sharma

Electronic Theses and Dissertations

Artificial Intelligence (AI) is acquiring more recognition than ever by researchers and machine learning practitioners. AI has found significance in many applications like biomedical research for cancer diagnosis using image analysis, pharmaceutical research, and, diagnosis and prognosis of diseases based on knowledge about patients' previous conditions. Due to the increased computational power of modern computers implementing AI, there has been an increase in the feasibility of performing more complex research.

Within the field of orthopedic biomechanics, this research considers complex time-series dataset of the "sit-to-stand" motion of 48 Total Hip Arthroplasty (THA) patients that was collected by the Human Dynamics …

Cyber Intrusion Detection By Using Deep Neural Networks With Attack-Sharing Loss, Boxiang Dong, Hui Wendy Wang, Aparna S. Varde, Dawei Li, Bharath K. Samanthula, Weifeng Sun, Liang Zhao

Department of Computer Science Faculty Scholarship and Creative Works

Cyber attacks pose crucial threats to computer system security, and put digital treasuries at excessive risks. This leads to an urgent call for an effective intrusion detection system that can identify the intrusion attacks with high accuracy. It is challenging to classify the intrusion events due to the wide variety of attacks. Furthermore, in a normal network environment, a majority of the connections are initiated by benign behaviors. The class imbalance issue in intrusion detection forces the classifier to be biased toward the majority/benign class, thus leave many attack incidents undetected. Spurred by the success of deep neural networks in …

Elimination Of Useless Images From Raw Camera-Trap Data, Ulaş Tekeli̇, Yalin Baştanlar

Turkish Journal of Electrical Engineering and Computer Sciences

Camera-traps are motion triggered cameras that are used to observe animals in nature. The number of images collected from camera-traps has increased significantly with the widening use of camera-traps thanks to advances in digital technology. A great workload is required for wild-life researchers to group and label these images. We propose a system to decrease the amount of time spent by the researchers by eliminating useless images from raw camera-trap data. These images are too bright, too dark, blurred, or they contain no animals. To eliminate bright, dark, and blurred images we employ techniques based on image histograms and fast …

Enhancing Face Pose Normalization With Deep Learning, Anil Çeli̇k, Nafi̇z Arica

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we propose a hybrid method for face pose normalization, which combines the 3-D model-based method with stacked denoising autoencoder (SDAE) deep network. Instead of applying a mirroring operation for the invisible face parts of the posed image, SDAE learns how to fill in those regions by a large set of training samples. In the performance evaluation, we compare the proposed method to four different pose normalization methods and investigate their effects on facial emotion recognition and verification problems in addition to visual quality tests. Methods evaluated in the experiments include 2-D alignment, 3-D model-based method, pure SDAE-based …

Improving Word Embeddings Projection For Turkish Hypernym Extraction, Savaş Yildirim

Turkish Journal of Electrical Engineering and Computer Sciences

Corpus-driven approaches can automatically explore is-a relations between the word pairs from corpus. This problem is also called hypernym extraction. Formerly, lexico-syntactic patterns have been used to solve hypernym relations. The language-specific syntactic rules have been manually crafted to build the patterns. On the other hand, recent studies have applied distributional approaches to word semantics. They extracted the semantic relations relying on the idea that similar words share similar contexts. Former distributional approaches have applied one-hot bag-of-word (BOW) encoding. The dimensionality problem of BOW has been solved by various neural network approaches, which represent words in very short and dense …

Facial Re-Enactment, Speech Synthesis And The Rise Of The Deepfake, Nicholas Gardiner

Theses : Honours

Emergent technologies in the fields of audio speech synthesis and video facial manipulation have the potential to drastically impact our societal patterns of multimedia consumption. At a time when social media and internet culture is plagued by misinformation, propaganda and “fake news”, their latent misuse represents a possible looming threat to fragile systems of information sharing and social democratic discourse. It has thus become increasingly recognised in both academic and mainstream journalism that the ramifications of these tools must be examined to determine what they are and how their widespread availability can be managed.

This research project seeks to examine …

Image-Based Roadway Assessment Using Convolutional Neural Networks, Weilian Song

Theses and Dissertations--Computer Science

Road crashes are one of the main causes of death in the United States. To reduce the number of accidents, roadway assessment programs take a proactive approach, collecting data and identifying high-risk roads before crashes occur. However, the cost of data acquisition and manual annotation has restricted the effect of these programs. In this thesis, we propose methods to automate the task of roadway safety assessment using deep learning. Specifically, we trained convolutional neural networks on publicly available roadway images to predict safety-related metrics: the star rating score and free-flow speed. Inference speeds for our methods are mere milliseconds, enabling …

Determining Political Inclination In Tweets Using Transfer Learning, Mehtab Iqbal

College of Graduate Studies: Theses & Dissertations

Last few years have seen tremendous development in neural language modeling for transfer learning and downstream applications. In this research, I used Howard and Ruder’s Universal Language Model Fine Tuning (ULMFiT) pipeline to develop a classifier that can determine whether a tweet is politically left leaning or right leaning by likening the content to tweets posted by @TheDemocrats or @GOP accounts on Twitter. We achieved 87.7% accuracy in predicting political ideological inclination.

Lung Segmentation In Chest Radiographs Using Fully Convolutional Networks, Rahul Hooda, Ajay Mittal, Sanjeev Sofat

Turkish Journal of Electrical Engineering and Computer Sciences

Automated segmentation of medical images that aims at extracting anatomical boundaries is a fundamental step in any computer-aided diagnosis (CAD) system. Chest radiographic CAD systems, which are used to detect pulmonary diseases, first segment the lung field to precisely define the region-of-interest from which radiographic patterns are sought. In this paper, a deep learning-based method for segmenting lung fields from chest radiographs has been proposed. Several modifications in the fully convolutional network, which is used for segmenting natural images to date, have been attempted and evaluated to finally evolve a network fine-tuned for segmenting lung fields. The testing accuracy and …