Physical Sciences and Mathematics Commons^™

Survey On Deep Neural Networks In Speech And Vision Systems, M. Alam, Manar D. Samad, Lasitha Vidyaratne, ‪Alexander Glandon, Khan M. Iftekharuddin

Computer Science Faculty Research

This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in speech and vision applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent speech and vision systems. With availability of vast amounts of sensor data and cloud computing for processing and training of deep neural networks, and with increased sophistication in mobile and embedded technology, the next-generation intelligent systems are poised to revolutionize personal and commercial computing. This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent …

Semiotic Aggregation In Deep Learning, Bogdan Muşat, Răzvan Andonie

All Faculty Scholarship for the College of the Sciences

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In …

Lightweight Deep Learning For Botnet Ddos Detection On Iot Access Networks, Eric A. Mccullough

MSU Graduate Theses

With the proliferation of the Internet of Things (IoT), computer networks have rapidly expanded in size. While Internet of Things Devices (IoTDs) benefit many aspects of life, these devices also introduce security risks in the form of vulnerabilities which give hackers billions of promising new targets. For example, botnets have exploited the security flaws common with IoTDs to gain unauthorized control of hundreds of thousands of hosts, which they then utilize to carry out massively disruptive distributed denial of service (DDoS) attacks. Traditional DDoS defense mechanisms rely on detecting attacks at their target and deploying mitigation strategies toward the attacker …

Acquisition, Processing, And Analysis Of Video, Audio And Meteorological Data In Multi-Sensor Electronic Beehive Monitoring, Sarbajit Mukherjee

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

In recent years, a widespread decline has been seen in honey bee population and this is widely attributed to colony collapse disorder. Hence, it is of utmost importance that a system is designed to gather relevant information. This will allow for a deeper understanding of the possible reasons behind the above phenomenon to aid in the design of suitable countermeasures.

Electronic Beehive Monitoring is one such way of gathering critical information regarding a colony’s health and behavior without invasive beehive inspections. In this dissertation, we have presented an electronic beehive monitoring system called BeePi that can be placed on top …

Visual Sentiment Analysis For Review Images With Item-Oriented And User-Oriented Cnn: Reproducibility Companion Paper, Quoc Tuan Truong, Hady W. Lauw, Martin Aumuller, Naoko Nitta

Research Collection School Of Computing and Information Systems

We revisit our contributions on visual sentiment analysis for online review images published at ACM Multimedia 2017, where we develop item-oriented and user-oriented convolutional neural networks that better capture the interaction of image features with specific expressions of users or items. In this work, we outline the experimental claims as well as describe the procedures to reproduce the results therein. In addition, we provide artifacts including data sets and code to replicate the experiments.

Real-Time Road Hazard Information System, Carlos Pena-Caballero, Dong-Chul Kim, Adolfo Gonzalez, Osvaldo Castellanos, Angel A. Cantu, Jungseok Ho

Computer Science Faculty Publications and Presentations

Infrastructure is a significant factor in economic growth for systems of government. In order to increase economic productivity, maintaining infrastructure quality is essential. One of the elements of infrastructure is roads. Roads are means which help local and national economies be more productive. Furthermore, road damage such as potholes, debris, or cracks is the cause of many on-road accidents that have cost the lives of many drivers. In this paper, we propose a system that uses Convolutional Neural Networks to detect road degradations without data pre-processing. We utilize the state-of-the-art object detection algorithm, YOLO detector for the system. First, we …

Pose Estimation Using Convolutional Neural Network With Synthesis Depth Data, Wang Song, Fuchang Liu, Huang Ji, Weiwei Xu, Hongwei Dong

Journal of System Simulation

Abstract: 3D scenes can be reconstructed more easily and rapidly with depth camera. However, it is difficult to retrieve items in 3D scenes from a single view depth image, especially for the pose estimation. In this paper, we present a method of pose estimation using convolutional neural network with synthesis depth data, which predicts the items' pose in 3D scenes by regression. This is achieved by (i) synthesizing large amount of depth images with different pose for linear regression using 3D model, (ii) designing a class-dependent linear regression framework, which estimates the object's pose from different classes separately, …

Machine Learning-Based Signal Degradation Models For Attenuated Underwater Optical Communication Oam Beams, Patrick L. Neary, Abbie T. Watnik, K. Peter Judd, James R. Lindle, Nicholas S. Flann

Computer Science Faculty and Staff Publications

Signal attenuation in underwater communications is a problem that degrades classification performance. Several novel CNN-based (SMART) models are developed to capture the physics of the attenuation process. One model is built and trained using automatic differentiation and another uses the radon cumulative distribution transform. These models are inserted in the classifier training pipeline. It is shown that including these attenuation models in classifier training significantly improves classification performance when the trained model is tested with environmentally attenuated images. The improved classification accuracy will be important in future OAM underwater optical communication applications.

A Robust Structured Tracker Using Local Deep Features, Mohammadreza Javanmardi, Amir Hossein Farzaneh, Xiaojun Qi

Computer Science Faculty and Staff Publications

Deep features extracted from convolutional neural networks have been recently utilized in visual tracking to obtain a generic and semantic representation of target candidates. In this paper, we propose a robust structured tracker using local deep features (STLDF). This tracker exploits the deep features of local patches inside target candidates and sparsely represents them by a set of templates in the particle filter framework. The proposed STLDF utilizes a new optimization model, which employs a group-sparsity regularization term to adopt local and spatial information of the target candidates and attain the spatial layout structure among them. To solve the optimization …

Choosing The Structure Of Convolutional Neural Networks For Face Recognition, Kabul Khudaybergenov

Bulletin of National University of Uzbekistan: Mathematics and Natural Sciences

Evaluating the number of hidden neurons and hidden layers necessary for solving of face recognition, pattern recognition and classification tasks is one of the key problems in artificial neural networks. In this note, we show that artificial neural network with a two hidden layer feed forward neural network with d inputs, d neurons in the first hidden layer, 2d+2 neurons in the second hidden layer, k outputs and with a sigmoidal infinitely differentiable function can solve face recognition tasks. This result can be applied to design pattern recognition and classification models with optimal structure in the number of hidden neurons …

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

All Faculty Scholarship for the College of the Sciences

Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before learning starts. For a given dataset, we would like to find the optimal combination of hyperparameter values, in a reasonable amount of time. This is a challenging task because of its computational complexity. In previous work, we introduced the Weighted Random Search (WRS) method, a combination of Random Search (RS) and probabilistic greedy heuristic. In the current paper, we …

Higher-Order Representations For Visual Recognition, Tsung-Yu Lin

Doctoral Dissertations

In this thesis, we present a simple and effective architecture called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs generalize classical orderless texture-based image models such as bag-of-visual-words and Fisher vector representations. However, unlike prior work, they can be trained in an end-to-end manner. In the experiments, we demonstrate that these representations generalize well to novel domains by fine-tuning and achieve excellent results on fine-grained, texture and scene recognition tasks. The visualization of fine-tuned convolutional filters …

Learning In The Machine: To Share Or Not To Share?, Jordan Ott, Erik Linstead, Nicholas Lahaye, Pierre Baldi

Engineering Faculty Articles and Research

Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes. However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy raises the fundamental question of whether weight-sharing is necessary. If so, to which degree of precision? If not, what are the alternatives? The goal of this study is to investigate these questions, primarily through simulations where the weight-sharing assumption is relaxed. Taking inspiration from neural circuitry, we explore the use of Free Convolutional Networks and neurons with variable connection patterns. Using Free Convolutional Networks, we show that while weight-sharing is a pragmatic optimization …

Graph Classification With Kernels, Embeddings And Convolutional Neural Networks, Monica Golahalli Seenappa, Katerina Potika, Petros Potikas

Faculty Publications, Computer Science

In the graph classification problem, given is a family of graphs and a group of different categories, and we aim to classify all the graphs (of the family) into the given categories. Earlier approaches, such as graph kernels and graph embedding techniques have focused on extracting certain features by processing the entire graph. However, real world graphs are complex and noisy and these traditional approaches are computationally intensive. With the introduction of the deep learning framework, there have been numerous attempts to create more efficient classification approaches. We modify a kernel graph convolutional neural network approach, that extracts subgraphs (patches) …

Underwater Gesture Recognition Using Classical Computer Vision And Deep Learning Techniques, Mygel Andrei M. Martija, Jakov Ivan S. Dumbrique, Prospero C. Naval Jr.

Mathematics Faculty Publications

Underwater Gesture Recognition is a challenging task since conditions which are normally not an issue in gesture recognition on land must be considered. Such issues include low visibility, low contrast, and unequal spectral propagation. In this work, we explore the underwater gesture recognition problem by taking on the recently released Cognitive Autonomous Diving Buddy Underwater Gestures dataset. The contributions of this paper are as follows: (1) Use traditional computer vision techniques along with classical machine learning to perform gesture recognition on the CADDY dataset; (2) Apply deep learning using a convolutional neural network to solve the same problem; (3) Perform …

Improving The Efficiency Of Dnn Hardware Accelerator By Replacing Digitalfeature Extractor With An Imprecise Neuromorphic Hardware, Majid Mohammadi Rad, Omid Sojodishijani

Turkish Journal of Electrical Engineering and Computer Sciences

Mixed-signal in-memory computation can drastically improve the efficiency of the hardware implementing machine learning (ML) algorithms by (i) removing the need to fetch neural network parameters from internal or external memory and (ii) performing a large number of multiply-accumulate operations in parallel. However, this boost in efficiency comes with some disadvantages. Among them, the inability to precisely program nonvolatile memory devices (NVM) with neural network parameters and sensitivity to noise prevent the mixed-signal hardware to perform a precise and deterministic computation. Unfortunately, these hardware-specific errors can get magnified while propagating along with the layers of the deep neural network. In …

Detection Of Hand Osteoarthritis From Hand Radiographs Using Convolutionalneural Networks With Transfer Learning, Kemal Üreten, Hasan Erbay, Hadi̇ Hakan Maraş

Turkish Journal of Electrical Engineering and Computer Sciences

Osteoarthritis is the most common type of arthritis. Hand osteoarthritis leads to specific structural changes in the joints, such as asymmetric joint space narrowing and osteophytes (bone spurs). Conventional radiography has traditionally been the primary method of visualizing these structural changes and diagnosing osteoarthritis. We aimed to develop a computerized method that is capable of determining the structural changes seen in radiography of the hand and to assist practitioners in interpreting radiographic changes and diagnosing the disease. In this retrospective study, transfer-learning-based convolutional neural networks were trained on a randomly selected dataset containing 332 radiography images of hands from an …

Efficient Turkish Tweet Classification System For Crisis Response, Saed Alqaraleh, Merve Işik

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a convolutional neural networks Turkish tweet classification system for crisis response. This system has the ability to classify the present information before or during any crisis. In addition, a preprocessing model was also implemented and integrated as a part of the developed system. This paper presents the first ever Turkish tweet dataset for crisis response, which can be widely used and improve similar studies. This dataset has been carefully preprocessed, annotated, and well organized. It is suitable to be used by all the well-known natural language processing tools. Extensive experimental work, using our produced Turkish tweet dataset …

Filter Design For Small Target Detection On Infrared Imagery Using Normalized-Cross-Correlation Layer, Hüseyi̇n Seçki̇n Demi̇r, Erdem Akagündüz

Turkish Journal of Electrical Engineering and Computer Sciences

n this paper, we introduce a machine learning approach to the problem of infrared small target detection filter design. For this purpose, similar to a convolutional layer of a neural network, the normalized-cross-correlational (NCC) layer, which we utilize for designing a target detection/recognition filter bank, is proposed. By employing the NCC layer in a neural network structure, we introduce a framework, in which supervised training is used to calculate the optimal filter shape and the optimum number of filters required for a specific target detection/recognition task on infrared images. We also propose the mean-absolute-deviation NCC (MAD-NCC) layer, an efficient implementation …

Context-Aware System For Glycemic Control In Diabetic Patients Using Neural Networks, Owais Bhat, Dawood A. Khan

Turkish Journal of Electrical Engineering and Computer Sciences

Diabetic patients are quite hesitant in engaging in normal physiological activities due to difficulties associated with diabetes management. Over the last few decades, there have been advancements in the computational power of embedded systems and glucose sensing technologies. These advancements have attracted the attention of researchers around the globe developing automatic insulin delivery systems. In this paper, a method of closed-loop control of diabetes based on neural networks is proposed. These neural networks are used for making predictions based on the clinical data of a patient. A neural network feedback controller is also designed to provide a glycemic response by …

Applying Deep Learning Models To Structural Mri For Stage Prediction Of Alzheimer's Disease, Altuğ Yi̇ği̇t, Zerri̇n Işik

Turkish Journal of Electrical Engineering and Computer Sciences

Alzheimer's disease is a brain disease that causes impaired cognitive abilities in memory, concentration, planning, and speaking. Alzheimer's disease is defined as the most common cause of dementia and changes different parts of the brain. Neuroimaging, cerebrospinal fluid, and some protein abnormalities are commonly used as clinical diagnostic biomarkers. In this study, neuroimaging biomarkers were applied for the diagnosis of Alzheimer's disease and dementia as a noninvasive method. Structural magnetic resonance (MR) brain images were used as input of the predictive model. T1 weighted volumetric MR images were reduced to two-dimensional space by several preprocessing methods for three different projections. …

Quantifying Seagrass Distribution In Coastal Water With Deep Learning Models, Daniel Perez, Kazi Islam, Victoria Hill, Richard Zimmerman, Blake Schaeffer, Yuzhong Shen, Jiang Li

OES Faculty Publications

Coastal ecosystems are critically affected by seagrass, both economically and ecologically. However, reliable seagrass distribution information is lacking in nearly all parts of the world because of the excessive costs associated with its assessment. In this paper, we develop two deep learning models for automatic seagrass distribution quantification based on 8-band satellite imagery. Specifically, we implemented a deep capsule network (DCN) and a deep convolutional neural network (CNN) to assess seagrass distribution through regression. The DCN model first determines whether seagrass is presented in the image through classification. Second, if seagrass is presented in the image, it quantifies the seagrass …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …