Deep Temporal Convolutional Networks For Short-Term Traffic Flow Forecasting, Wentian Zhao, Yanyun Gao, Tingxiang Ji, Xili Wan, Feng Ye, Guangwei Bai

Electrical and Computer Engineering Faculty Publications

To reduce the increasingly congestion in cities, it is essential for intelligent transportation system (ITS) to accurately forecast the short-term traffic flow to identify the potential congestion sites. In recent years, the emerging deep learning method has been introduced to design traffic flow predictors, such as recurrent neural network (RNN) and long short-term memory (LSTM), which has demonstrated its promising results. In this paper, different from existing work, we study the temporal convolutional network (TCN) and propose a deep learning framework based on TCN model for short-term city-wide traffic forecast to accurately capture the temporal and spatial evolution of traffic …

Recurrent Residual U-Net For Medical Image Segmentation, Md Zahangir Alom, Christopher Yakopcic, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep …

A Survey Of Techniques For Mobile Service Encrypted Traffic Classification Using Deep Learning, Pan Wang, Xuejiao Chen, Feng Ye, Zhixin Sun

Electrical and Computer Engineering Faculty Publications

The rapid adoption of mobile devices has dramatically changed the access to various net- working services and led to the explosion of mobile service traffic. Mobile service traffic classification has been a crucial task that attracts strong interest in mobile network management and security as well as machine learning communities for past decades. However, with more and more adoptions of encryption over mobile services, it brings a lot of challenges about mobile traffic classification. Although classical machine learning approaches can solve many issues that port and payload-based methods cannot solve, it still has some limitations, such as time-consuming, costly handcrafted …

Smart Garage Opener, Jacob Wasson

Williams Honors College, Honors Research Projects

The purpose of this research project was to design an anti-theft device that interfaces with a standard garage door opener to allow packages to easily be delivered into a garage in a safe and secure manner. Primary functionality of the device is to use a package’s tracking number and corresponding barcode to open and close a garage door to a preset height so that a package can be delivered inside the garage before it closes. My contribution to the project revolved around the programming and board design of the microcontroller circuit that controls the input and output signals of the …

Ict-Enabled Control And Energy Management Of Community Microgrids For Resilient Smart Grid Operation, Mahmoud Saleh

Dissertations and Theses

Our research has focused on developing novel controllers and algorithms to enhance the resilience of the power grid and increase its readiness level against major disturbances.

The U.S. power grid currently encounters two main challenges: (1) the massive and extended blackouts caused by natural disasters, such as hurricane Sandy. These blackouts have raised a national call to explore innovative approaches for enhanced grid resiliency. Scrutinizing how previous blackouts initiated and propagated throughout the power grid, the major reasons are lack of situational awareness, lack of real-time monitoring and control, underdeveloped controllers at both the transmission and distribution levels, and lack …

Danger-Aware Resource Management In V2x Network, Tsigigenet Dessalgn

College of Graduate Studies: Theses & Dissertations

IEEE 802.11p is one of the key technologies that enable dedicated short-range communications (DSRC) in intelligent transportation system (ITS) for safety on the road. The main challenge in vehicular communication is the large amount of data to be processed. As vehicle density and velocity increases, the data to be transmitted also increases. We proposed a protocol that reduces the number of data to be transmitted at every second according to the level of danger that the transmitter vehicle experiences. The proposed protocol measures inter-vehicle distance, as the representative of the danger of a vehicle, to determine the priority for transmission. …

Effect Of Wireless Communication Delay On Dc Microgrids Performance, Mahmoud Saleh, Yusef Esa, Ahmed Mohamed

Publications and Research

This paper investigates the effect of wireless communication technologies latency on the converters and the bus voltage of centrally communication based controlled DC microgrids (MGs) during islanding. A DC microgrid with its communication based control scheme was modeled to show the impact of latency. Simulation results show that the impact may be severe depending on the design, and the operational condition of the microgrid before latency occurs.

Impact Of Communication Latency On The Bus Voltage Of Centrally Controlled Dc Microgrid During Islanding, Mahmoud Saleh, Yusef Esa, Ahmed Mohamed

Publications and Research

Maintaining a sustainable and reliable source of energy to supply critical loads within a renewable energy based microgrid (MG) during blackouts is directly related to its bus voltage variations. For example, voltage variation might trigger protection devices and disconnect DERs within the MG. Centrally controlled MGs (CCMGs) type is dependent on communication. Therefore, it is very important to analyze the impact of communication networks performance degradation, such as latency, on the bus voltage of CCMGs. This paper investigates the effect of wireless communication technologies latency on the bus voltage and performance of centralized DC MGs. Two mathematical models were developed …

Investigating The Effect Of Detecting And Mitigating A Ring Oscillator-Based Hardware Trojan, Lakshmi Ramakrishnan

Electrical Engineering Theses and Dissertations

The outsourcing of the manufacturing process of integrated circuits to fabrications plants all over the world has exposed these chips to several security threats, especially at the hardware level. There have been instances of malicious circuitry, such as backdoors, being added to circuits without the knowledge of the chip designers or vendors. Such threats could be immensely powerful and dangerous against confidentiality, among other vulnerabilities.

Defense mechanisms against such attacks have been probed and defense techniques have been developed. But with the passage of time, attack techniques have improved immensely as well. From directly observing the inputs or outputs, adversaries …

Cmos Radioactive Isotope Identification With Multichannel Analyzer And Embedded Neural Network, Samuel Murray

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

A radiation detection and identification system is designed and implemented to perform gamma ray spectroscopy on radioactive sources and identify which isotopes are present in the sources. A multichannel analyzer is implemented on an ASIC to process the signal produced from gamma rays detected by a scintillator and photomultiplier tube and to quantize the gamma ray energies to build a histogram. A fast, low memory embedded neural network is implemented on a microcontroller ASIC to identify the isotopes present in the gamma ray histogram produced by the multichannel analyzer in real time.

Advisors: Sina Balkir and Michael W. Hoffman

Electric Upgrades - Supercapacitor Electric Bicycle, John Chen, Wilson Fletcher, Spencer Esparza

Electrical Engineering

Supercapacitors provide high current capabilities compared to conventional lithium-ion batteries, allowing for fast charging and discharging of electrical energy. This project seeks to test the benefits of supercapacitors in an electric bicycle unit in order to gain higher regenerative energy. The main components of the bicycle are its regenerative motor, supercapacitor array, and motor controller. Developing the project will provide data on the feasibility of using alternative battery storage and charging.

Command Validation For Cybersecure Power Router, Isaac M. Kroger

Electrical Engineering Undergraduate Honors Theses

For grid-connected homes equipped with solar panels, power electronics are necessary to manage and convert power between the solar panels, battery storage, grid, and residential load. A power router can be used to manage these power electronics and govern power generation, storage, and distribution within the household. This level of control makes power routers that do not employ cybersecurity a target for external attacks. The use of command validation is an effective way to prevent unauthorized commands from maliciously altering the state of a home’s power router. The purpose of this thesis is to describe the development of the command …

Image Processing Applications In Real Life: 2d Fragmented Image And Document Reassembly And Frequency Division Multiplexed Imaging, Houman Kamran Habibkhani

LSU Doctoral Dissertations

In this era of modern technology, image processing is one the most studied disciplines of signal processing and its applications can be found in every aspect of our daily life. In this work three main applications for image processing has been studied.

In chapter 1, frequency division multiplexed imaging (FDMI), a novel idea in the field of computational photography, has been introduced. Using FDMI, multiple images are captured simultaneously in a single shot and can later be extracted from the multiplexed image. This is achieved by spatially modulating the images so that they are placed at different locations in the …

Datanet: Deep Learning Based Encrypted Network Traffic Classification In Sdn Home Gateway, Pan Wang, Feng Ye, Xuejiao Chen, And Yi Qian

Electrical and Computer Engineering Faculty Publications

A smart home network will support various smart devices and applications, e.g., home automation devices, E-health devices, regular computing devices, and so on. Most devices in a smart home access the Internet through a home gateway (HGW). In this paper, we propose a software-defined- network (SDN)-HGW framework to better manage distributed smart home networks and support the SDN controller of the core network. The SDN controller enables efficient network quality-of-service management based on real-time traffic monitoring and resource allocation of the core network. However, it cannot provide network management in distributed smart homes. Our proposed SDN-HGW extends the control to …

Handwritten Bangla Character Recognition Using The State-Of-The-Art Deep Convolutional Neural Networks, Md Zahangir Alom, Paheding Sidike, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

In spite of advances in object recognition technology, handwritten Bangla character recognition (HBCR) remains largely unsolved due to the presence of many ambiguous handwritten characters and excessively cursive Bangla handwritings. Even many advanced existing methods do not lead to satisfactory performance in practice that related to HBCR. In this paper, a set of the state-of-the-art deep convolutional neural networks (DCNNs) is discussed and their performance on the application of HBCR is systematically evaluated. The main advantage of DCNN approaches is that they can extract discriminative features from raw data and represent them with a high degree of invariance to object …

Soil Moisture Sensor, Jaclyn Miller, Derek Bitecofer, Seung Jun Lee

Williams Honors College, Honors Research Projects

Since water is an important resource and not all communities around the world can afford to be liberal with their water needs; it has become important to use available water as efficiently as possible, especially in agriculture. For the purpose of reducing the overwatering of crops, an unattended ground moisture sensor can be implemented to measure the moisture level in the soil surrounding the plants. This will allow a farmer to know when to water or stop watering crops. For convenience, the moisture data information should be transmitted wirelessly to the user. The design of an unattended ground moisture sensor …

Cyber-Based Contingency Analysis And Insurance Implications Of Power Grid, Zhiyuan Yang

Dissertations, Master's Theses and Master's Reports

Cybersecurity for power communication infrastructure is a serious subject that has been discussed for a decade since the first North American Electric Reliability Corporation (NERC) critical infrastructure protection (CIP) initiative in 2006. Its credibility on plausibility has been evidenced by attack events in the recent past. Although this is a "very high impact, rare probability" event, the establishment of quantitative measures would help asset owners in making a series of investment decisions. First, this dissertation tackles attackers' strategies based on the current communication architecture between remote IP-based (unmanned) power substations and energy control centers. Hypothetically, the identification of intrusion paths …

Designing And Testing 3-D Printed Wafer-Box With Embedded Pzt Sensors To Identify The Shape Effect On Energy Harvesting, Ahmad Jami Safayet

College of Graduate Studies: Theses & Dissertations

Piezoelectric energy has been recently paid attention in the field of alternative energy. Day by day the traditional energy sources including Coal tar and oils are becoming scarce. People are heading to an alternative energy source to meet the future energy demand. Piezoelectric energy is one of the competitive energy sources compared to the conventional renewable energy sources including solar, wind, and geothermal power and so on. This energy production method bears enormous research potential because it can be used as the roadway for a new method of power generation. This research project aimed to identify which shaped wafer-box produced …

Recursive Non-Local Means Filter For Video Denoising, Redha A. Ali, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

In this paper, we propose a computationally efficient algorithm for video denoising that exploits temporal and spatial redundancy. The proposed method is based on non-local means (NLM). NLM methods have been applied successfully in various image denoising applications. In the single-frame NLM method, each output pixel is formed as a weighted sum of the center pixels of neighboring patches, within a given search window.

The weights are based on the patch intensity vector distances. The process requires computing vector distances for all of the patches in the search window. Direct extension of this method from 2D to 3D, for video …

Design And Simulation Of An 8-Bit Successive Approximation Register Charge-Redistribution Analog-To-Digital Converter, Sumit K. Verma

Electrical Engineering Theses

The thesis initially investigates the history of the monolithic ADCs. The next chapter explores the different types of ADCs available in the market today. Next, the operation of a 4-bit SAR ADC has been studied. Based on this analysis, an 8-bit charge-redistribution SAR ADC has been designed and simulated with Multisim (National Instruments, Austin, TX). The design is divided into different blocks which are individually implemented and tested. Level-1 SPICE MOSFET models representative of 5μm devices were used wherever individual MOSFETs were used in the design. Finally, the power dissipation during the conversion period was also estimated. The supply voltage …

Hardware Based Testing Of Communication Based Control For Dc Microgrid, Mahmoud Saleh, Yusef Esa, Ahmed Mohamed

Publications and Research

This paper further describes our work presented in Industry Application Society 2016 Conference, with more details related to the control and operation of the microgrid. The DC microgrid facility was custom designed and implemented at CCNY with minimal off-the-shelf components to enable flexibility and reconfiguration capability. The design steps, requirements, and experimental results of the developed testbed were discussed. As a case study, a central controller for energy management algorithm was developed and tested under several operational scenarios. The experimental results verify the applicability of the developed testbed for validating DC microgrid controllers.

Quantitative Analysis Of Regenerative Energy In Electric Rail Traction Systems, Mahmoud Saleh, Oindrilla Dutta, Yusef Esa, Ahmed Mohamed

Publications and Research

This paper aims at determining the influential factors affecting regenerative braking energy in DC rail transit systems. This has been achieved by quantitatively evaluating the dependence of regenerative energy on various parameters, such as vehicle dynamics, train scheduling, ground inclination and efficiency of the electrical devices. The recuperated power and energy have been presented by a mathematical model, comprising of a set of empirical forms, which allows for thorough analysis. A detailed simulation model of a typical DC-traction system has been developed to validate the developed empirical forms. The results verified the validity of the proposed mathematical model, and demonstrated …

Optimal Microgrids Placement In Electric Distribution Systems Using Complex Network Framework, Mahmoud Saleh, Yusef Esa, Nwabueze Onuorah, Ahmed Mohamed

Publications and Research

This paper provides a new approach to find the optimal location for Microgrids (MGs) in electric distribution systems using complex network analysis. An optimal location in this paper refers to a location that would result in increased grid resilience, reduced power losses, less line loading, higher voltage stability and secured supply to critical loads during power outage. The criteria used to find the optimal placement of MGs were based on the centrality analysis adopted from complex network theory, the center of mass concept used in physics, and the controlled delivery grid (CDG) concept. An IEEE 30-bus system was used as …

Energy Management Algorithm For Resilient Controlled Delivery Grids, Mahmoud Saleh, Yusef Esa, Ahmed Mohamed, Haim Grebel, Roberto Rojas-Cessa

Publications and Research

Resilience of the power grid is most challenged at power blackouts since the issues that led to it may not be fully resolved by the time the power is back. In this paper, a Real-Time Energy Management Algorithm (RTEMA) has been developed to increase the resilience of power systems based on the controlled delivery grid (CDG) concept. In a CDG, loads communicate with a central controller, periodically sending requests for power. The central controller runs an algorithm, based on which it may decide whether to grant the requested energy fully or partially. Therefore, the CDG limits loads discretionary access to …

On-Chip Training Of Memristor Crossbar Based Multi-Layer Neural Networks, Raqibul Hasan, Tarek M. Taha, Christopher Yakopcic

Electrical and Computer Engineering Faculty Publications

Memristor crossbar arrays carry out multiply-add operations in parallel in the analog domain, and so can enable neuromorphic systems with high throughput at low energy and area consumption. On-chip training of these systems have the significant advantage of being able to get around device variability and faults. This paper presents on-chip training circuits for multi-layer neural networks implemented using a single crossbar per layer and two memristors per synapse. Using two memristors per synapse provides double the synaptic weight precision when compared to a design that uses only one memristor per synapse. Proposed on-chip training system utilizes the back propagation …

Design & Evaluation Of A Hybrid Switched Capacitor Circuit With Wide-Bandgap Devices For Dc Grid Applications, Joshua L. Stewart

Electrical and Computer Engineering ETDs

ABSTRACT

As technologies advance, the rate at which renewable power sources, such as solar photovoltaic (PV) and wind, are being added to the power grid is increasing. Typically, PV power plants require large inverters for direct current to alternating current (DC-AC) power conversion, as well as large transformers to step up voltages to the grid voltage. Offshore wind farms and large PV power plants in remote locations often aggregate power on a DC bus in order to improve efficiency and reduce the cost of power conversion hardware within the energy complex. However, the power must still be converted to AC …

A Hardware One-Time Pad Prototype Generator For Localising Cloud Security, Paul Tobin, Lee Tobin, Michael Mckeever, Jonathan Blackledge

Conference papers

In this paper, we examine a system for encrypting data before storing in the Cloud. Adopting this system gives excellent security to stored data and complete control for accessing data by the client at different locations. The motivation for developing this personal encryption came about because of poor Cloud security and doubts over the safety of public encryption algorithms which might contain backdoors. However, side-channel attacks and other unwanted third-party interventions in Cloud security, probably contribute more to the poor security record history. These factors led to the development of a prototype for personalising security locally which defeats cryptanalysis. The …

Chaos-Based Cryptography For Cloud Computing, Paul Tobin, Lee Tobin, Michael Mckeever, Jonathan Blackledge

Conference papers

Cloud computing and poor security issues have quadrupled over the last six years and with the alleged presence of backdoors in common encryption ciphers, has created a need for personalising the encryption process by the client. In 2007, two Microsoft employees gave a presentation ``On the Possibility of a backdoor in the NIST SP800-90 Dual Elliptic Curve Pseudo Random Number Generators'' and was linked in 2013 by the New York Times with notes leaked by Edward Snowden. This confirmed backdoors were placed, allegedly, in a number of encryption systems by the National Security Agency, which if true creates an urgent …

Wireless Window Blinds, Cooper Laone, Niraj Morar, Zachary Malig, Jake Phillips

Electrical Engineering

The Internet of Things asserts that there exists a global need for all objects to connect easily and accessibly. Today, smartphones, tablets, laptops and smart watches makeup just a few of the interconnected devices by the greater population. As a result a growing need for wireless connection between personal devices like phones, and computers to everyday appliances exists. This idea extends directly to households, businesses and buildings, where a growing need for smart home or smart-business appliances has taken root. Many companies like Nest, ADT and Apple make products for automated home security and in home media control. The Wireless …

An Exact Analysis For Four-Order Acousto-Optic Bragg Diffraction Which Incorporates Both Incident Light Angle And Sound Frequency Dependencies, Adeyinka Sunday Ademola

Electrical Engineering Theses

This thesis extends the prior work which produced an exact solution to the four-order acousto-optic (AO) Bragg cell with assumed fixed center frequency and with exact Bragg angle incident light. The extension predicts the model that incorporates the dependencies of both the input angle of light and the sound frequency. Specifically, a generalized 4^th order linear differential equation (DE), is developed from a simultaneous analysis of four coupled AO system of DEs. Through standard methods, the characteristic roots, which requires solving a quartic equation, is produced. Subsequently, a derived system of homogeneous solutions, which absorbs the roots obtained using …