Computer Engineering Commons^™

Forecasting Pedestrian Trajectory Using Deep Learning, Arsal Syed

UNLV Theses, Dissertations, Professional Papers, and Capstones

In this dissertation we develop different methods for forecasting pedestrian trajectories. Complete understanding of pedestrian motion is essential for autonomous agents and social robots to make realistic and safe decisions. Current trajectory prediction methods rely on incorporating historic motion, scene features and social interaction to model pedestrian behaviors. Our focus is to accurately understand scene semantics to better forecast trajectories. In order to do so, we leverage semantic segmentation to encode static scene features such as walkable paths, entry/exits, static obstacles etc. We further evaluate the effectiveness of using semantic maps on different datasets and compare its performance with already …

Analysis Of Microscopic Objects Using Computer Vision Methods, Yuan Dao

UNLV Theses, Dissertations, Professional Papers, and Capstones

As an essential and powerful tool to observe living organisms, three-dimensional fluorescence microscopy is widely used in biological research and diagnosis. The 4D fluorescence microscopy data can be obtained using time-lapsed videos of 3D images. To analyze and extract useful information from the increasingly large and complex biological image dataset, efficient and effective computational tools are in need but still lagging behind. In analyzing biological data, two major challenges are faced. First, time-lapsed fluorescence microscopic images typically have a low SNR. Second, biological objects often change their morphology and internal structure frequently. As such, conventional image processing methods may not …

Distributed Neural Network Based Architecture For Dddos Detection In Vehicular Communication Systems, Nicholas Jaton

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

With the continued development of modern vehicular communication systems, there is an ever growing need for cutting edge security in these systems. A misbehavior detection systems (MDS) is a tool developed to determine if a vehicle is being attacked so that the vehicle can take steps to mitigate harm from the attacker. Some attacks such as distributed denial of service (DDoS) attacks are a concern for vehicular communication systems. During a DDoS attack, multiple nodes are used to flood the target with an overwhelming amount of communication packets. In this thesis, we investigated the current MDS literature and how it …

Designing Blended Experiences: Laugh Traders Design Fiction, Brian J. Okeefe

Frameless

The increasing ubiquity of interactions that involve complementary digital content, physical objects, and spaces, brings about new challenges for designers. There is a need to embed designs in legacy systems, whether those are existing physical structures or existing digital platforms. Traditional approaches to product design, interaction design, and user experience design often do not take this new context into account. Many systems do not consider how designers produce new digital and physical experiences that work harmoniously, while supporting new interactions and relationships with people (Imaz and Benyon 2007; Jetter, Geyer, Schwarz & Reiterer 2012). To address this, we propose the …

An Efficient Multi-Message And Multi-Receiver Signcryption Scheme For Heterogeneous Smart Mobile Iot, Jianying Qiu, Kai Fan, Kuan Zhang, Qiang Pan, Hui Li, Yintang Yang

Department of Electrical and Computer Engineering: Faculty Publications

The Internet of Things (IoT) is developing towards smart and mobile Internet of Things (SM-IoT), which has made great progress. Due to the inherent heterogeneity, distribution, intensive communication, and resource constraints of SM-IoT, efficient security and privacy communication protocols become a particularly critical challenge. Signcryption has received considerable attention. Various signcryption schemes have been proposed to solve secure communication. However, most of them are low in efficiency, without the consideration of characteristics of the SM-IoT. In this paper, we propose a signcryption scheme to achieve efficient secure multi-message and multi-receiver communication for the heterogeneous and distributed SM-IoT. We develop Identity-based …

Review Of Data Mining Techniques For Detecting Churners In The Telecommunication Industry, Mahmoud Ewieda, Mohamed Ismail Roushdy, Essam Shaaban

Future Computing and Informatics Journal

The telecommunication sector has been developed rapidly and with large amounts of data obtained as a result of increasing in the number of subscribers, modern techniques, data-based applications, and services. As well as better awareness of customer requirements and excellent quality that meets their satisfaction. This satisfaction raises rivalry between firms to maintain the quality of their services and upgrade them. These data can be helpfully extracted for analysis and used for predicting churners. Researchers around the world have conducted important research to understand the uses of Data mining (DM) that can be used to predict customers' churn. This …

Airborne Counter-Uncrewed Systems With Runtime Assurance Control, Isaac J. Seslar

Mechanical Engineering ETDs

This thesis develops a response to the increase in the availability of the commercially available uncrewed aerial systems and is dedicated to the detection, classification, and tracking required to successfully neutralize when determined malicious. A requirement of actively avoiding obstacles using runtime assurance is addressed and designed to keep the hardware safe in potentially dangerous situations. This work will elaborate on the several components the test bed is comprised of, specifically the hardware and software portions that successfully solve the problem. The software encompasses the simulation, the multiple algorithms required for the tracking, and the machine learning required for detection …

Dynamic Planning Networks, Norman Tasfi, Miriam A M Capretz

Electrical and Computer Engineering Publications

We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. DPN learns to efficiently form plans by expanding a single action conditional state transition at a time instead of exhaustively evaluating each action, reducing the number of state-transitions used during planning. We observe emergent planning patterns in our agent, including classical search methods such as breadth-first and depth-first search. DPN shows improved …

Computational Frameworks For Multi-Robot Cooperative 3d Printing And Planning, Laxmi Prasad Poudel

Graduate Theses and Dissertations

This dissertation proposes a novel cooperative 3D printing (C3DP) approach for multi-robot additive manufacturing (AM) and presents scheduling and planning strategies that enable multi-robot cooperation in the manufacturing environment. C3DP is the first step towards achieving the overarching goal of swarm manufacturing (SM). SM is a paradigm for distributed manufacturing that envisions networks of micro-factories, each of which employs thousands of mobile robots that can manufacture different products on demand. SM breaks down the complicated supply chain used to deliver a product from a large production facility from one part of the world to another. Instead, it establishes a network …

Bayesian Adaptive Path Allocation Techniques For Intra-Datacenter Workloads, Ali Malik, Ruairí De Fréin, Chih-Heng Ke, Hasanen Alyasiri, Obinna Izima

Conference papers

Data center networks (DCNs) are the backbone of many cloud and Internet services. They are vulnerable to link failures, that occur on a daily basis, with a high frequency. Service disruption due to link failure may incur financial losses, compliance breaches and reputation damage. Performance metrics such as packet loss and routing flaps are negatively affected by these failure events. We propose a new Bayesian learning approach towards adaptive path allocation that aims to improve DCN performance by reducing both packet loss and routing flaps ratios. The proposed approach incorporates historical information about link failure and usage probabilities into its …

Forecasting Stock Exchange Data Using Group Method Of Data Handling Neural Network Approach, Marzieh Faridi Masouleh, Ahmad Bagheri

Knowledge Engineering and Data Science

The increasing uncertainty of the natural world has motivated computer scientists to seek out the best approach to technological problems. Nature-inspired problem solving approaches include meta-heuristic methods that are focused on evolutionary computation and swarm intelligence. One of these problems significantly impacting information is forecasting exchange index, which is a serious concern with the growth and decline of stock as there are many reports on loss of financial resources or profitability. When the exchange includes an extensive set of diverse stock, particular concepts and mechanisms for physical security, network security, encryption, and permissions should guarantee and predict its future needs. …

Backpropagation Neural Network With Combination Of Activation Functions For Inbound Traffic Prediction, Purnawansyah Purnawansyah, Haviluddin Haviluddin, Herdianti Darwis, Huzain Azis, Yulita Salim

Knowledge Engineering and Data Science

Predicting network traffic is crucial for preventing congestion and gaining superior quality of network services. This research aims to use backpropagation to predict the inbound level to understand and determine internet usage. The architecture consists of one input layer, two hidden layers, and one output layer. The study compares three activation functions: sigmoid, rectified linear unit (ReLU), and hyperbolic Tangent (tanh). Three learning rates: 0.1, 0.5, and 0.9 represent low, moderate, and high rates, respectively. Based on the result, in terms of a single form of activation function, although sigmoid provides the least RMSE and MSE values, the ReLu function …

Do Missing Link Community Smell Affect Developers Productivity: An Empirical Study, Toukir Ahammed, Sumon Ahmed, Mohammed Shafiul Alam Khan

Knowledge Engineering and Data Science

Missing link smell occurs when developers contribute to the same source code without communicating with each other. Existing studies have analyzed the relationship of missing link smells with code smell and developer contribution. However, the productivity of developers involved in missing link smell has not been explored yet. This study investigates how productivity differs between smelly and non-smelly developers. For this purpose, the productivity of smelly and non-smelly developers of seven open-source projects are analyzed. The result shows that the developers not involved in missing link smell have more productivity than the developers involved in smells. The observed difference is …

Indonesian Sentence Boundary Detection Using Deep Learning Approaches, Joan Santoso, Esther Irawati Setiawan, Christian Nathaniel Purwanto, Fachrul Kurniawan

Knowledge Engineering and Data Science

Detecting the sentence boundary is one of the crucial pre-processing steps in natural language processing. It can define the boundary of a sentence since the border between a sentence, and another sentence might be ambiguous. Because there are multiple separators and dynamic sentence patterns, using a full stop at the end of a sentence is sometimes inappropriate. This research uses a deep learning approach to split each sentence from an Indonesian news document. Hence, there is no need to define any handcrafted features or rules. In Part of Speech Tagging and Named Entity Recognition, we use sequence labeling to determine …

Face Images Classification Using Vgg-Cnn, I Nyoman Gede Arya Astawa, Made Leo Radhitya, I Wayan Raka Ardana, Felix Andika Dwiyanto

Knowledge Engineering and Data Science

Image classification is a fundamental problem in computer vision. In facial recognition, image classification can speed up the training process and also significantly improve accuracy. The use of deep learning methods in facial recognition has been commonly used. One of them is the Convolutional Neural Network (CNN) method which has high accuracy. Furthermore, this study aims to combine CNN for facial recognition and VGG for the classification process. The process begins by input the face image. Then, the preprocessor feature extractor method is used for transfer learning. This study uses a VGG-face model as an optimization model of transfer learning …

Detection Of Disease And Pest Of Kenaf Plant Based On Image Recognition With Vggnet19, Diny Melsye Nurul Fajri, Wayan Firdaus Mahmudy, Titiek Yulianti

Knowledge Engineering and Data Science

One of the advantages of Kenaf fiber as an environmental management product that is currently in the center of attention is the use of Kenaf fiber for luxury car interiors with environmentally friendly plastic materials. The opportunity to export Kenaf fiber raw material will provide significant benefits, especially in the agricultural sector in Indonesia. However, there are problems in several areas of Kenaf's garden, namely plants that are attacked by diseases and pests, which cause reduced yields and even death. This problem is caused by the lack of expertise and working hours of extension workers as well as farmers' knowledge …

Towards Semantic Integration Of Machine Vision Systems To Aid Manufacturing Event Understanding, Kaishu Xia, Clint Saidy, Max Kirkpatrick, Noble Anumbe, Amit Sheth, Ramy Harik

Publications

A manufacturing paradigm shift from conventional control pyramids to decentralized, service-oriented, and cyber-physical systems (CPSs) is taking place in today’s 4th industrial revolution. Generally accepted roles and implementation recipes of cyber systems are expected to be standardized in the future of manufacturing industry. The authors intend to develop a novel CPS-enabled control architecture that accommodates: (1) intelligent information systems involving domain knowledge, empirical model, and simulation; (2) fast and secured industrial communication networks; (3) cognitive automation by rapid signal analytics and machine learning (ML) based feature extraction; (4) interoperability between machine and human. Semantic integration of process indicators is fundamental …

A Quantitative Validation Of Multi-Modal Image Fusion And Segmentation For Object Detection And Tracking, Nicholas Lahaye, Michael J. Garay, Brian D. Bue, Hesham El-Askary, Erik Linstead

Mathematics, Physics, and Computer Science Faculty Articles and Research

In previous works, we have shown the efficacy of using Deep Belief Networks, paired with clustering, to identify distinct classes of objects within remotely sensed data via cluster analysis and qualitative analysis of the output data in comparison with reference data. In this paper, we quantitatively validate the methodology against datasets currently being generated and used within the remote sensing community, as well as show the capabilities and benefits of the data fusion methodologies used. The experiments run take the output of our unsupervised fusion and segmentation methodology and map them to various labeled datasets at different levels of global …

Mac For Machine-Type Communications In Industrial Iot—Part I: Protocol Design And Analysis, Jie Gao, Weihua Zhuang, Mushu Li, Xuemin Shen, Xu Li

Electrical and Computer Engineering Faculty Research and Publications

In this two-part paper, we propose a novel medium access control (MAC) protocol for machine-type communications in the Industrial Internet of Things. The considered use case features a limited geographical area and a massive number of devices with sporadic data traffic and different priority types. We target supporting the devices while satisfying their Quality-of-Service (QoS) requirements with a single access point and a single channel, which necessitates a customized design that can significantly improve the MAC performance. In Part I of this paper, we present the MAC protocol that comprises a new slot structure, corresponding channel access procedure, and mechanisms …

Mac For Machine-Type Communications In Industrial Iot—Part Ii: Scheduling And Numerical Results, Jie Gao, Mushu Li, Weihua Zhuang, Xuemin Shen, Xu Li

Electrical and Computer Engineering Faculty Research and Publications

In the second part of this article, we develop a centralized packet transmission scheduling scheme to pair with the protocol designed in Part I and complete our medium access control (MAC) design for machine-type communications in the industrial Internet of Things. For the networking scenario, fine-grained scheduling that attends to each device becomes necessary, given stringent Quality-of-Service (QoS) requirements and diversified service types, but prohibitively complex for a large number of devices. To address this challenge, we propose a scheduling solution in two steps. First, we develop algorithms for device assignment based on the analytical results from Part I, when …

Personalized Digital Phenotype Score, Healthcare Management And Intervention Strategies Using Knowledge Enabled Digital Health Framework For Pediatric Asthma, Utkarshani Jaimini, Amit Sheth

Publications

Asthma is a personalized, and multi-trigger respiratory condition which requires continuous monitoring and management of symptoms and medication adherence. We developed kHealth: Knowledge-enabled Digital Healthcare Framework to monitor and manage the asthma symptoms, medication adherence, lung function, daily activity, sleep quality, indoor, and outdoor environmental triggers of pediatric asthma patients. The kHealth framework collects up to 1852 data points per patient per day. It is practically impossible for the clinicians, parents, and the patient to analyze this vast amount of multimodal data collected from the kHealth framework. In this chapter, we describe the personalized scores, clinically relevant asthma categorization using …

Crossroad - Avoid Crowd Intelligence, Xukun Zhang, Yuzheng Wu, Haochen Zhang

Interdisciplinary Design Senior Theses

Nowadays, waiting takes big chunks of daily-life activity. People may always find themselves facing long queues, waiting in a crowded facility, even when they have tried to avoid peak hours. Heading to a highly populated public area may have felt like heading to a battlefield. Without access to the real-time information of the facility, people start to discover that waiting starts to become an unpredictable event that can sometimes delay their schedule or even worse. This project serves as a solution to tackle this lack of transparency. Crossroad aims to combine facilities’ cameras with micro-controller to see the engagement of …

Jamming Attack Workaround Study, Soren Madsen, Jack Schoen

Interdisciplinary Design Senior Theses

The Internet of Things (IoT) is a fast growing industry with strong footholds in the smart home market featuring devices such as the Amazon Echo, Ring security cameras, smart TVs, and much more. However, it doesn’t stop there; the industrial sector has begun using smart devices for measurement, automated tasks, and time sensitive communication. Many of these devices have become reliant on WiFi technology and are vulnerable to attacks on the security of the protocols involved.

In this paper, we discuss the details of the deauthentication attack on WPA and WPA2 systems and propose a solution for detection and recovery …

Pier Ocean Pier, Brandon J. Nowak

Computer Engineering

Pier Ocean Peer is a weatherproof box containing a Jetson Nano, connected to a cell modem and camera, and powered by a Lithium Iron Phosphate battery charged by a 50W solar panel. This system can currently provide photos to monitor the harbor seal population that likes to haul out at the base of the Cal Poly Pier, but more importantly it provides a platform for future expansion by other students either though adding new sensors directly to the Jetson Nano or by connecting to the jetson nano remotely through a wireless protocol of their choice.

Towards Enabling Unmanned Aerial Vehicles As A Service For Heterogeneous Applications, Farid Nait-Abdesselam, Ahmad Alsharoa, Mohamed Y. Selim, Daji Qiao, Ahmed E. Kamal

Electrical and Computer Engineering Faculty Research & Creative Works

The increasing use of unmanned aerial vehicles (UAVs) in various commercial applications, such as precision agriculture and aerial remote sensing, is fast contributing to a significant growth in the UAV market. Also, it is crucial to provide continuous coverage after failures of wireless network components or additional bandwidth in high traffic situations. By introducing the concept of UAVs as a service (UaaS), we propose a novel framework, dubbed D3S, consisting of four phases: Demand, decision, deployment, and service. The main objective of this framework is to provide a realistic and streamlined approach to support the implementation of the UaaS paradigm. …

Bibliometric Review On Iot Based System For Remote Downloading On Microcontroller, Arundhati Bandopadhyaya Ms., Diya Dodwad Ms., Diviyanshi Gupta Ms., Surya Koyyana Mr., Parag Narkhede Mr., Shripad Deshpande Mr.

Library Philosophy and Practice (e-journal)

Working with sensors has become an area of expertise within the domain of electronic engineering. On a day to day basis, thousands of sensors are put to use around us, for instance, in smoke alarms, speedometers, motors, computers, radiators etc. to accumulate sensor data, cables that connect the sensors to the bottom station after which the information is worked on. But cabling is often expensive especially when handling large scale industrial applications ^[5]. For an equivalent reason, low-cost wireless networks came into the picture recently and are in high demand. A research paper we found during our review of …

Online Laboratory Course Using Low Tech Supplies To Introduce Digital Logic Design Concepts, Dhanya Nair

Engineering Faculty Articles and Research

This paper describes a Digital Logic Design Laboratory Course developed to engage students with hardware systems within an online setting. This is a junior level core course for students from Computer Science (CS), Computer Engineering (CE) and Electrical Engineering (EE). Hence, the laboratories are designed to provide the hands-on experience of breadboarding, testing and debugging essential to CE and EE while accommodating CS students with no prior hardware experience. Commercially available low-cost electronic trainers (portable workstations) are loaned to the students in addition to basic electronic components. To ensure a strong foundation in debugging, prior to utilizing these workstations, students …

Cyber Social Threats 2021: Ai, Covid-19 Vaccine, Detection And Countering Strategies, Ugur Kursuncu, Jeremy Blackburn, Yelena Mejova, Megan Squire, Amit Sheth

Publications

In recent years, online platforms have been utilized for promoting harmful content and behavior such as extremism, harassment, mis/disinformation, human trafficking, genderbased violence among others affecting our society, often leading to real-world events. Such content and behaviors are inherently complex, making the recognition of these narratives challenging for researchers as well as social media companies. The Cyber Social Threats (CySoc) Workshop 2021 aimed to facilitate a rich forum for researchers and practitioners from both academia and industry in the areas of computing and social science, to discuss novel avenues for research on interdisciplinary aspects of harmful communications on social media, …

Requirements Metrics - A Working List, William L. Honig

Computer Science: Faculty Publications and Other Works

A working set of metrics for review of requirements materials including documents.

Real-Time Machine Learning For Quickest Detection, Yongxin Liu

Doctoral Dissertations and Master's Theses

Safety-critical Cyber-Physical Systems (CPS) require real-time machine learning for control and decision making. One promising solution is to use deep learning to discover useful patterns for event detection from heterogeneous data. However, deep learning algorithms encounter challenges in CPS with assurability requirements: 1) Decision explainability, 2) Real-time and quickest event detection, and 3) Time-eficient incremental learning.

To address these obstacles, I developed a real-time Machine Learning Framework for Quickest Detection (MLQD). To be specific, I first propose the zero-bias neural network, which removes decision bias and preferabilities from regular neural networks and provides an interpretable decision process. Second, I discover …