Engineering Commons^™

Learning Deep Time-Index Models For Time Series Forecasting, Jiale Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Research Collection School Of Computing and Information Systems

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a …

Imitation Improvement Learning For Large-Scale Capacitated Vehicle Routing Problems, The Viet Bui, Tien Mai

Research Collection School Of Computing and Information Systems

Recent works using deep reinforcement learning (RL) to solve routing problems such as the capacitated vehicle routing problem (CVRP) have focused on improvement learning-based methods, which involve improving a given solution until it becomes near-optimal. Although adequate solutions can be achieved for small problem instances, their efficiency degrades for large-scale ones. In this work, we propose a newimprovement learning-based framework based on imitation learning where classical heuristics serve as experts to encourage the policy model to mimic and produce similar or better solutions. Moreover, to improve scalability, we propose Clockwise Clustering, a novel augmented framework for decomposing large-scale CVRP into …

Estimation Of Recursive Route Choice Models With Incomplete Trip Observations, Tien Mai, The Viet Bui, Quoc Phong Nguyen, Tho V. Le

Research Collection School Of Computing and Information Systems

This work concerns the estimation of recursive route choice models in the situation that the trip observations are incomplete, i.e., there are unconnected links (or nodes) in the observations. A direct approach to handle this issue could be intractable because enumerating all paths between unconnected links (or nodes) in a real network is typically not possible. We exploit an expectation–maximization (EM) method that allows dealing with the missing-data issue by alternatively performing two steps of sampling the missing segments in the observations and solving maximum likelihood estimation problems. Moreover, observing that the EM method could be expensive, we propose a …

Lightweight Deep Neural Network Models For Electromyography Signal Recognition For Prosthetic Control, Ahmet Mert

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, lightweight deep learning methods are proposed to recognize multichannel electromyography (EMG) signals against varying contraction levels. The classical machine learning, and signal processing methods namely, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), root mean square (RMS), and waveform length (WL) are adopted to convolutional neural network (CNN), and long short-term memory neural network (LSTM). Eight-channel recordings of nine amputees from a publicly available dataset are used for training and testing the proposed models considering prosthetic control strategies. Six class hand movements with three contraction levels are applied to WL and RMS-based feature extraction. After that, they …

A Practical Framework For Early Detection Of Diabetes Using Ensemble Machine Learning Models, Qusay Saihood, Emrullah Sonuç

Turkish Journal of Electrical Engineering and Computer Sciences

The diagnosis of diabetes, a prevalent global health condition, is crucial for preventing severe complications. In recent years, there has been a growing effort to develop intelligent diagnostic systems for diabetes utilizing machine learning (ML) algorithms. Despite these efforts, achieving high accuracy rates using such systems remains a significant challenge. Recent advancements in ensemble ML methods offer promising opportunities for early detection of diabetes, as they are known to be faster and more cost-effective than traditional approaches. Therefore, this study proposes a practical framework for diagnosing diabetes that involves three stages. The data preprocessing stage encompasses several crucial tasks, including …

Improving Unet Segmentation Performance Using An Ensemble Model In Images Containing Railway Lines, Mehmet Sevi̇, İlhan Aydin

Turkish Journal of Electrical Engineering and Computer Sciences

This study aims to make sense of the autonomous system and the railway environment for railway vehicles. For this purpose, by determining the railway line, information about the general condition of the line can be obtained along the way. In addition, objects such as pedestrian crossings, people, cars, and traffic signs on the line will be extracted. The rails and the rail environment in the images will be segmented with a semantic segmentation network. In order to ensure the safety of rail transport, computer vision, and deep learning-based methods are increasingly used to inspect railway tracks and surrounding objects. In …

Cu2o Heterojunction Solar Cell With Photovoltaic Properties Enhanced By A Ti Buffer Layer, Binghao Wang, Zhiqiang Chen, Feng Zhao

Center for Electron Microscopy and Nanofabrication Publications and Presentations

In this study, semiconductor oxide cuprite (Cu2O) and indium tin oxide (ITO) heterojunction solar cells with and without a 10 nm thick titanium (Ti) thin film as the buffer layer were fabricated and characterized for comparison. The Cu2O film was formed by low-cost electrodeposition, and Ti and ITO layers were deposited on a glass substrate by sputtering. The interfacial microstructures, surface topology, and electrical and photovoltaic properties of both solar cells were investigated. The test results showed that the Ti buffer layer changed the surface morphology, resistivity, and contact potential of the electrodeposited Cu2O film. With these changes, the photovoltaic …

An Empirical Investigation Of The Behavior And Cognition Of Engineering Designers While Describing Domains Of Design Problems, John Kochenberger

Theses and Dissertations

This thesis presents a protocol study that examines the behavioral and cognitive patterns in human designers when they describe a problem domain of engineering interest through constructing concept maps. Understanding various design problem domains usually comes in design projects before the start of the formal design process and is crucial for discovering the pain points of given scenarios and identifying opportunities for creating value to improve them. Thus, this activity relies on the entrepreneurial aspects of engineering design that leads to identifying the right design problem to solve. While concept maps have been used to examine various research questions in …

Design Of A Burst Mode Ultra High-Speed Low-Noise Cmos Image Sensor, Xin Yue

Dartmouth College Ph.D Dissertations

Ultra-high-speed (UHS) image sensors are of interest for studying fast scientific phenomena and may also be useful in medicine. Several published studies have recently achieved frame rates of up to millions of frames per second (Mfps) using advanced processes and/or customized processes.

This thesis presents a burst-mode (108 frames) UHS low-noise CMOS image sensor (CIS) based on charge-sweep transfer gates in an unmodified, standard 180 nm front-side-illuminated CIS process. By optimizing the photodiode geometry, the 52.8 μm pitch pixels with 20x20 μm^2 of active area, achieve a charge-transfer time of less than 10 ns. A proof-of-concept CIS was designed and …

Domain Restriction Zones: An Evolution Of The Military Exclusion Zone, Cole M. Mooty, Robert A. Bettinger, Mark G. Reith

Faculty Publications

Since the early part of the twenty-first century, US adversaries have expanded their military capabilities within and their access to new warfighting domains. When faced with the growth of adversaries’ asymmetric capabilities, the means, tactics, and strategies previously used by the US military lose their proportional effectiveness. To avoid such degradation of capability, the operational concept of the military exclusion zone (MEZ) should be revised to suit the modern battlespace while also addressing the shifts in national policy that encourage diplomacy over military force. The concept and development of domain restriction zones (DRZs) increase the relevancy of traditional MEZs in …

A Case For An Independent Cyber Force, Ian C. Heffron, Mark Reith, James W. Dean

Faculty Publications

Although cyberspace is considered the newest warfighting domain, military analysts and scholars have opined the United States remains woefully behind its peers in cyberspace and have called for the creation of a separate cyber service component. Yet a cohesive and robust discussion on this topic has yet to emerge. This article proposes a general framework that builds on the Joint doctrine, organization, training, materiel, leadership and education, personnel, facilities, and policy (DOTMLPF-P) analysis to address questions of sufficiency and necessity. Such analysis reveals DoD cyber operations do not maximize the United States’ ability to fight a cyber war, especially when …

Accurate Covariance Estimation For Pose Data From Iterative Closest Point Algorithm, Rick H. Yuan, Clark N. Taylor, Scott L. Nykl

Faculty Publications

One of the fundamental problems of robotics and navigation is the estimation of the relative pose of an external object with respect to the observer. A common method for computing the relative pose is the iterative closest point (ICP) algorithm, where a reference point cloud of a known object is registered against a sensed point cloud to determine relative pose. To use this computed pose information in downstream processing algorithms, it is necessary to estimate the uncertainty of the ICP output, typically represented as a covariance matrix. In this paper, a novel method for estimating uncertainty from sensed data is …

Mitochondrial Transfer From Cancer-Associated Fibroblasts Increases Migration In Aggressive Breast Cancer, Kevin F. Gwolas, Sarah Libring, Emily Berestesky, Shayan Gholizadeh, Samantha C. Schwager, Andra R. Frost, Thomas R. Gaborski, Jian Zhang, Cynthia A. Reinhart-King

Biomedical Engineering Faculty Publications and Presentations

Cancer-associated fibroblasts (CAFs) have distinct roles within the tumor microenvironment, which can impact the mode and efficacy of tumor cell migration. CAFs are known to increase invasion of less-aggressive breast cancer cells through matrix remodeling and leader–follower dynamics. Here, we demonstrate that CAFs communicate with breast cancer cells through the formation of contact-dependent tunneling nanotubes (TNTs), which allow for the exchange of cargo between cell types. CAF mitochondria are an integral cargo component and are sufficient to increase the 3D migration of cancer cells. This cargo transfer results in an increase in mitochondrial ATP production in cancer cells, whereas it …

Co-Activation Of The Diaphragm And External Intercostal Muscles Through An Adaptive Closed-Loop Respiratory Pacing Controller, Rabeya Zinnat Adury, Ricardo Siu, Ranu Jung

Biomedical Engineering Faculty Publications and Presentations

Introduction: Respiratory pacing is a promising alternative to traditional mechanical ventilation that has been shown to significantly increase the survival and quality of life after the neural control of the respiratory system has been compromised. However, current pacing approaches to achieve adequate ventilation tend to target only the diaphragm without pacing external intercostal muscles that are also activated during normal inspiration. Furthermore, the pacing paradigms do not allow for intermittent sighing, which carries an important physiological role. We hypothesized that simultaneous activation of the diaphragm and external intercostal muscles would improve the efficiency of respiratory pacing compared to diaphragm stimulation …

Recognizing The Potential To Reduce Ghg Emissions Through Air Transportation Electrification, Julio Roa, Joseph Oldham, Marina Lima

Mineta Transportation Institute

California is aggressively moving forward with efforts to deploy zero-emission transportation technology to fight climate change, especially the Greenhouse Gas (GHG) emissions from the high-impact transportation sector. However, to date, the investments California has made with Cap-and-Trade funding have focused on ground transportation and some marine sources and not the aircraft at the over 140 airports in the state. Through a California-focused comprehensive GHG emissions analysis, this research project seeks to determine how RAM using electric/hybrid electric aircraft can provide new high-speed transportation for high-priority passenger and cargo movement within Fresno County and connections to coastal urban centers. Using VISION, …

Cost Estimation Trends For Major Defense Acquisition Programs, Sammantha Jones, Edward D. White, Jonathan D. Ritschel, Shawn M. Valentine

Faculty Publications

The authors use both descriptive and inferential techniques to investigate average and standard deviation trends in cost estimates for major defense acquisition programs (MDAPs) grouped into decades from the 1970s to 2010s. For total program-cost-growth factors (CGFs), the 2010s exhibited lower CGFs compared to the 1990s. For the program-acquisition-unit cost (PAUC) CGFs, the 2010s appear lower than the 1990s and borderline lower than the 1970s. A statistically significant decreasing trend in the standard deviations of total program CGFs throughout the decades was identified. This lowering variability trend also appeared for PAUC CGFs from the 1980s onward. This finding appears to …

The Influence Of Bio-Inhibitor On The Corrosion Resistance Of Reinforced Concrete Beams Containing Mswi-Ba As A Partial Sand Replacement, Jamal Khatib, Israa Amer, Ghanem Hassan, Adel Elkordi

BAU Journal - Science and Technology

In this paper, the corrosion behavior of reinforced concrete beams containing municipal solid waste incineration bottom ash (MSWI-BA) as a partial sand replacement and Ceratonia siliqua extract as a green corrosion inhibitor was investigated. Four mixes were prepared: (0 and 20% replacement of sand by MSWI-BA with and without Ceratonia siliqua extract). Tests conducted were UPV, compressive strength, split tensile strength, and elastic modulus. RC beams were prepared for determining the flexural performance. Eight beams were casted. Four beams were exposed to accelerated corrosion test and four beams were kept at room temperature. It was found that the compressive strength, …

Analysis Of Evolution And Morphology Of Urban And Road Networks: Case Study Lebanon-Nabatiyeh Area, Amal Al Ghorayeb, Adel Elkordi, Ghaleb Faour, Zeinab Jaber, Youssef Attallah

BAU Journal - Science and Technology

This study examines the morphology and evolution of urban and road networks and their relationship with topography in the Lebanon-Nabatiyeh area, by using GIS and remote sensing data. and calculate the annual urban growth percentage rate. The results reveal a clear relationship between the morphology of urban and road networks and their evolution over four periods, as well as the influence of the surrounding topography on their configuration. The study recommends that urban areas should be developed in areas with a slope range of 15º or more to improve the urban structure and infrastructure surrounding them. Understanding the evolution and …

Neurocomputing And Interfacing Digital Tasting System: Research, Design, And Evaluation, Amira J. Zaylaa, Ahmad El Hajj

BAU Journal - Science and Technology

The continuous evolution in computing and interfacing has been extended to develop multi-sensory experiences in many domains such as neurological, auditory, vision, and haptic domains. So far, only a few remarkable system approaches have been approved to be serving the taste sensation digitally. Although taste sensation is linked to the brain, there is a lack of optimal neurocomputing digital taste sensation systems. Our study provides a new neurocomputing method to digitally stimulate the sense of taste by electrical stimulation on the human tongue. We aim to link chemical stimulation and electrical stimulation in order to design an electronic interface for …

Methods And Surface Materials Repair For Concrete Structures – A Review, Lelian W. Elkhatib, Adel Elkordi, Jamal Khatib

BAU Journal - Science and Technology

Concrete is a very critical material that may require maintenance and possible repair periodically, especially in important structure such as bridges. In general, concrete in structures (e.g. reinforced concrete) may be subjected to cracks due to a variety of reasons. These include, design and external environments such as the ingress of harmful ions into the concrete, unexpected extra loads including earthquakes. These cracks can affect not only the appearance of the structure but more importantly the structural performance of concrete and the integrity of the concrete structure. Therefore, when cracks occur a proper repair method should be selected, based on …

Mechanical And Durability Properties Of Fly Ash Geopolymer Concrete – A Review, Ali Shebli, Jamal Khatib, Adel Elkordi

BAU Journal - Science and Technology

Geopolymers have emerged as a promising alternative for Ordinary portland cement (OPC) in construction industry, due to their potential to minimize the emissions of carbon dioxide (CO₂) and improve the efficiency of waste recycling. This paper aims to study the fresh and hardened properties of fly ash geopolymer concrete (GPC), as well as to review the raw materials used in the production of geopolymers. Several factors impact the mechanical and durability properties of fly ash GPC, including the specific type of fly ash utilized, the curing temperature, the alkaline activator (AA) concentration, and the type of AA used. …

Localized Surface Plasmon Resonance Of Palladium Parallelepiped Nanoparticles, Salem Marhaba, Nourhan El Kawni

BAU Journal - Science and Technology

Localized surface plasmon resonance (LSPR) of palladium parallelepiped nanoparticle have been investigated using Finite Element Method (FEM) in the frame of COMSOL Multiphysics Software. Spectral characteristics (magnitude, peak position and width) of LSPR of a single Pd nanoparticle having the shape of a parallelepiped are investigated in two different cases. The first case studied the size effect on LSPR by fixing the height with varying both length and width. However, the second case studied the shape effect on the LSPR by rounding the corners of the parallelepiped for different radii while fixing its dimensions. The extinction cross-section spectra of these …

Algorithms For The Generalized Inverse Solution And Direct Solution: Using An Algebra Computer-Based System To Obtain Meridian Arc Length, Wei-Kuo Tseng, King-Cheng Tsai, Chian Liou, Jiunn-Liang Guo, Yi-Jia Sun

Journal of Marine Science and Technology–Taiwan

In this study, the idea employed in the article of [1] to treat the problem of the arc-length of meridian is applied to the arc-length determined by the third flattening (n) instead of the eccentricity (e) of an Earth-reference ellipsoid . With WGS 84 ellipsoid datum used in modern navigation, the meridian arc-length is a crucial factor for map projections and geodetic and distance calculations such as Mercator charts, the universal transverse Mercator, great circle (ellipse), rhumb line, and geodesic. Because navigation software lacks officially standardized calculation methods, these “black box solutions” used in navigational systems are unknown. Therefore members …

Three-Dimensional Higher-Order Compressive Sensing For Raypath Separation In An Acoustic Waveguide, Fengyan Zhong

Journal of Marine Science and Technology–Taiwan

In an acoustic waveguide, the separation of multiple raypaths, especially close raypaths, is a challenging task in the presence of colored noise due to interference in the acoustic eld. In this paper, a three-dimensional higher-order compressive sensing method for raypath separation is proposed. The method is applied on an array-to-array experimental conguration where both emitter and reception arrays are used. With the array-to-array conguration, the raypaths are characterized by three parameters including arrival direction, departure direction, and arrival time. Furthermore, the performance of the proposed algorithm is illustrated by simulations and experiments. The numerical results based on simulation illustrate that …

Projection Of Sea Surface Temperature Based On Empirical Mode Decomposition And Its Application In Typhoon Number Forecast, Wen-Cheng Huang, Jung-Chen Lee

Journal of Marine Science and Technology–Taiwan

The primary objective of this paper is to demonstrate the applicability of empirical mode decomposition (EMD) in projecting non-stationary daily sea surface temperature (SST) series, and the other is to apply the projected series of SST to estimate the number of typhoons. The study focuses on an area ranging from 5°N~25°N and 110°E~170°E, collecting daily sea temperature data and typhoons records within this region. The findings conclusively indicate that the EMD-based data generation method proposed in this paper can effectively addresses the limitations of previous hydrological models in generating non-stationary series, signifying a significant advancement in hydrological time series modeling …

Final Report - Hyperspectral Imaging Analysis For Mechanical And Chemical Properties Of Concrete And Steel Surfaces, Genda Chen, Hongyan Ma, Pengfei Ma, Liang Fan, Abdullah Alhaj

Project SN-5

This project aims to develop a hyperspectral imaging approach for characterizing the mechanical and chemical properties of concrete and steel surfaces. A dual-sensor camera is used to collect images for mortar classification, mortar compressive strength assessment, Cl- concentration determination, and steel rebar and plate corrosion evaluation. Each pixel in an image includes spectral features ranging from 400 nm to 2500 nm in wavelength. For mortar samples, reflectance intensities at a wavelength of 1920 nm to 1980 nm, associated with the O-H chemical bond, were extracted and averaged to classify the types of mortars with K-Nearest Neighbors (KNN) and Support Vector …

Neutrosophic Decision Making Model For Investment Portfolios Selection And Optimizing Based On Wide Variety Of Investment Opportunities And Many Criteria In Market, Ayman H. Abdel-Aziem, Hoda K. Mohamed, Ahmed Abdelhafeez

Neutrosophic Systems with Applications

Investment portfolio selection is a difficult subject due to the presence of competing factors. Choosing a portfolio for one's investments is a major choice that may have far-reaching effects on one's financial well-being. Risk tolerance, time horizon, investing objectives, asset allocation, and investment selection are only a few of the factors that will be studied in this article. The Stable Preference Ordering Towards Ideal Solution (SPOTIS) technique is the basis for our proposed integrated multi-criteria decision-making (MCDM) model. This paper used the single-valued neutrosophic set as a framework to deal with uncertain data. The purpose of the suggested SPOTIS–Neutrosophic model …

Hybrid Electric Vehicles - A Review, Marothu Polaram Saichand Mr., Lakshman Rao S. Paragond Dr., Bindu S Dr., Athulya Jyothi V Ms.

Manipal Journal of Science and Technology

A hybrid vehicle was first patented by William H Patton in 1889. With the development of technology, hybrid electric vehicles are now stepping up to contribute to reducing fossil fuel dependency. This ultimately contributes to climate change. Hybrid vehicles, due to their advanced technology allow flexibility in choosing any of the available fuel choices. A hybrid electric vehicle (HEV) is a kind of hybrid vehicle which combines an internal combustion engine (ICE) system with electricity for propulsion (also known as a hybrid vehicle drivetrain). This is to achieve more efficient and cheaper fuel consumption with better performance. There are various …

Construction And Preliminary Application Of The Carbon-Based Spatial Governance Performance Evaluation System ——Taking Zhejiang Province As An Example, Lin Qu, Ganlin Xia, Cunkuan Bao Prof.

CSID Journal of Infrastructure Development

Carbon is generated through human socio-economic activities, with territorial space serving as the medium for these activities. Variations in spatial governance result in differences in the scale, intensity and efficiency of social and economic activities, as well as energy and resource consumption and carbon emissions across diverse functional spaces. Consequently, spatial governance performance should be evaluated using carbon-related indicators. This study initially established a theoretical model for assessing spatial governance performance based on carbon and an evaluation method encompassing three dimensions or indices "level-progress-gap". Zhejiang Province and its 11 prefecture-level cities were selected as the research area for preliminary application …

Chitosan-Based Green And Sustainable Hybrid Composites, Shilpa Sunil, Kashmitha Muthamma, Jaideep J P, Suhas Yeshwant Nayak Dr., Tejaswini Pralhad Bedekar Ms., Dhanya Sunil Dr.

Manipal Journal of Science and Technology

In recent years, there has been much effort to provide eco-friendly and biodegradable materials for the next-generation composite products owing to global environmental concerns and increased awareness of renewable green resources. In this context, the present study reports the preparation of green composite materials from natural, biocompatible, and biodegradable chitosan films reinforced with seashells and waste glass using a solution-casting method. The surface morphological features and chemical interactions of the composite films were studied using SEM, EDS, FTIR, and XRD techniques. The swelling degree (SD) and hardness properties of composites with various reinforcement weight proportions are compared to those of …