Engineering Commons^™

An Accurate Real-Time Method For Face Mask Detectionusing Cnn And Svm, Shili Hechmi

Knowledge Engineering and Data Science

Infectious respiratory diseases, including COVID-19, pose a significant challenge to humanity and a potential threat to life due to their severity and rapid spread. Using a surgical mask is among the most significant safety precautions that can help keep this sort of pandemic from spreading, and manual monitoring of large crowds in public places for face masks is problematic. In this research, we suggest a real-time approach for face mask detection. First, we use a multi-scale deep neural network to extract features. As a result, the attributes are better suited for training the detection system. We employ SVM post-processing in …

Indonesian Language Term Extraction Using Multi-Task Neural Network, Joan Santoso, Esther Irawati Setiawan, Fransiskus Xaverius Ferdinandus, Gunawan Gunawan, Leonel Hernandez Collantes

Knowledge Engineering and Data Science

The rapidly expanding size of data makes it difficult to extricate information and store it as computerized knowledge. Relation extraction and term extraction play a crucial role in resolving this issue. Automatically finding a concealed relationship between terms that appear in the text can help people build computer-based knowledge more quickly. Term extraction is required as one of the components because identifying terms that play a significant role in the text is the essential step before determining their relationship. We propose an end-to-end system capable of extracting terms from text to address this Indonesian language issue. Our method combines two …

Adaptive Neuro-Fuzzy Inference System For Waste Prediction, Haviluddin Haviluddin, Herman Santoso Pakpahan, Novianti Puspitasari, Gubtha Mahendra Putra, Rima Yustika Hasnida, Rayner Alfred

Knowledge Engineering and Data Science

The volume of landfills that are increasingly piled up and not handled properly will have a negative impact, such as a decrease in public health. Therefore, predicting the volume of landfills with a high degree of accuracy is needed as a reference for government agencies and the community in making future policies. This study aims to analyze the accuracy of the Adaptive Neuro-Fuzzy Inference System (ANFIS) method. The prediction results' accuracy level is measured by the value of the Mean Absolute Percentage Error (MAPE). The final results of this study were obtained from the best MAPE test results. The best …

Associated Patterns In Open-Ended Concept Maps Within E-Learning, Didik Dwi Prasetya, Tsukasa Hirasama

Knowledge Engineering and Data Science

A concept map is a diagram that visualizes the structure of individual cognitive knowledge. An approach to creating a concept map structure that allows users to contribute concepts and linkages that express their understanding freely is known as an "open-ended concept map." It has been demonstrated that an open-ended concept map accurately depicts student knowledge structures and reveals student differences. However, manually analyzing an open-ended map is difficult, time-consuming, and includes many propositions, especially in a big classroom. Educational data mining could be used to further process and analyze a collection of concept maps. However, many works attempted to employ …

Design And Prototyping Of A Low-Cost High Frequency Antenna For Vicinity Coupling Devices, Benjamin Kommey, Ernest Ofosu Addo, Elvis Tamakloe

Makara Journal of Technology

This paper describes the development of a high frequency (HF) antenna for high output power vicinity coupling devices (VCDs) operating at 13.56 MHz. Key design parameters, such as RF power level, antenna size, and communication protocol, and their link to the antenna features and requirements, have been discussed. For efficient reader interrogation, detection, and recovery of transponder responses, a tuning circuit necessary to adjust the antenna power matching and resonance characteristics was designed and prototyped. The antenna was fed to an industry standard reader and evaluated for read range performance with vicinity cards. The designed antenna on the reader achieved …

Damage Stability Study Of A 500 Dw Ro-Ro Ferry Vessel, Zulfaidah Ariany, Budhi Santoso, Sarwoko Sarwoko, Nauval Abdurrahman Prasetyo

Makara Journal of Technology

The development of the crossing transportation industry is currently increasing in the island areas. The use of Ro-Ro type ferry boats is extremely efficient in moving people, goods, and vehicles. The current research focuses on the damage stability of the 500 DWT Ro-Ro ferry, which aims to meet the needs of the Ro-Ro ferry in the archipelago area. The previously existing initial design of a barge hull with a main size Lpp = 40.15 m, B = 12 m, H = 3.2 m, and T = 2.15 m was used to analyze the damage stability condition further. First, the drawings …

Autonomous Decision-Making In Interdependent Computing Systems Based On Artificial Intelligence, Georgios Fragkos

Electrical and Computer Engineering ETDs

With the advent of Artificial Intelligence (AI), the notion of autonomy, in terms of acting and thinking based on personal experience and judgment, has paved the way towards an autonomous decision-making future. This future can address the complex domain of the interdependent computing systems, whose main challenge is that they interact with each other with unpredictable and often unstable outcomes. It is crucial to envision and design this AI-driven autonomy for the reciprocal computing systems which cover a variety of use-cases ranging from the Internet of Things (IoT) to cybersecurity. This can be achieved by cloning the human decision-making process, …

Application Of Artificial Intelligence To Lithium-Ion Battery Research And Development, Zhen-Wei Zhu, Jing-Yi Qiu, Li Wang, Gao-Ping Cao, Xiang-Ming He, Jing Wang, Hao Zhang

Journal of Electrochemistry

Lithium-ion batteries (LIBs) have become one of the best solutions to the energy storage issue in modern society. However, the battery materials and device development are both complex, and involve multivariable problems. Traditional trial-and-error approach, which relies on researchers to conduct experiments, has encountered bottlenecks in the improvement of the battery performance. Artificial intelligence (AI) is the most potential technology to deal with this issue due to its powerful high-speed and capabilities of processing massive data. In particular, the capability of machine learning (ML) algorithms in assessing multidimensional data variables and discovering patterns in the sets are expected to assist …

Multi-Electron Reaction-Boosted High Energy Density Batteries: Material And System Innovation, Rui-Qi Guo, Feng Wu, Xin-Ran Wang, Ying Bai, Chuan Wu

Journal of Electrochemistry

The continuous development of the global energy structure transformation has put forward higher demands upon the development of batteries. The improvements of the energy density have become one of the important indicators and hot topic for novel secondary batteries. The energy density of existing lithium-ion battery has encountered a bottleneck due to the limitations of material and systems. Herein, this paper introduces the concept and development of multi-electron reaction materials over the past twenty years. Guided by the multi-electron reaction, light weight electrode and multi-ion effect, current development strategies and future trends of high-energy-density batteries are highlighted from the perspective …

Advances On Composite Cathodes For Lithium-Sulfur Batteries, Xi-Yao Li, Chang-Xin Zhao, Bo-Quan Li, Jia-Qi Huang, Qiang Zhang

Journal of Electrochemistry

Lithium-sulfur (Li-S) batteries are deemed as high-promising next-generation energy storage technique due to their ultrahigh theoretical energy density, where the sulfur cathodes with high specific capacity guarantee the energy density advantage and directly determine the battery performances. After decades of exploration, the most promising sulfur cathodes are sulfur/carbon composite (S/C) cathodes and sulfurized polyacrylonitrile (SPAN) cathodes. In this manuscript, recent advances on S/C and SPAN cathodes in Li-S batteries are comprehensively reviewed. The electrochemical reaction circumstances on S/C and SPAN cathodes are firstly introduced and compared to reveal the working mechanisms of the two types of Li-S batteries. The S/C …

Carbon-Al Interface Effect On The Performance Of Ionic Liquid-Based Supercapacitor At 3 V And 65 OC, Zhen-Zhen Ye, Shu-Ting Zhang, Xin-Qi Chen, Jin Wang, Ying Jin, Chao-Jie Cui, Lei Zhang, Lu-Ming Qian, Gang Zhang, Wei-Zhong Qian

Journal of Electrochemistry

Ionic liquid (IL) electrolyte-based supercapacitors (SCs) have advantages of high operating voltage window, high energy density and nonflammability, as compared to conventional acetonitrile-based organic electrolyte SCs, and are typically suitable for the large-scale energy storage in the era of carbon neutrality full of renewable, but unstable electricity. However, current efforts were concentrated on the study with coin-cell type of IL-SCs, and less has been reported on the pouch type of IL-SCs for a long cycling time yet. To fabricate a reliable SC for the life time test or for the accelerated aging test under high temperature, one should concern the …

Preparation Of Highly-Cyclized Sulfurized Polyacrylonitrile For Lithium-Sulfur Batteries, Xuan Ji, Jia-Yu Wang, An-Bang Wang, Wei-Kun Wang, Ming Yao, Ya-Qin Huang

Journal of Electrochemistry

Sulfurized polyacrylonitrile (SPAN) is regarded as an attractive cathode candidate of lithium-sulfur (Li-S) batteries for its non-dissolution mechanism and effective alleviation of polysulfides shuttling issue in Li-S batteries, displaying high utilization of cathode active material, outstanding cycle stability and structural stability. However, the relation between cyclization degree and cycle stability of SPAN is still unveiled. In this work, SPAN-C-V composites were synthesized by co-introduction of CuSO₄ and zinc n-ethyl-n-phenyldithiocarbamate (ZDB) in the co-heating of sulfur and polyacrylonitrile. The co-introduction of CuSO₄ and ZDB reduced the cyclization reaction onset temperature of PAN while increased the C—C/C=C within SPAN-C-V, thus …

Emergence Of Coherent Backscattering From Sparse And Finite Disordered Media, Nooshin M. Estakhri, Nasim Mohammadi Estrakhri, Theodore B. Norris

Engineering Faculty Articles and Research

Coherent backscattering (CBS) arises from complex interactions of a coherent beam with randomly positioned particles, which has been typically studied in media with large numbers of scatterers and high opacity. We develop a first-principles scattering model for scalar waves to study the CBS cone formation in finite-sized and sparse random media with specific geometries. The current study provides insights into the effects of density, volume size, and other relevant parameters on the angular characteristics of the CBS cone emerging from sparse and bounded random media for various types of illumination, with results consistent with well-known CBS studies which are typically …

Weakly-Supervised Learning Method For The Recognition Of Potato Leaf Diseases, Junde Chen, Xiaofang Deng, Yuxin Wen, Weirong Chen, Adnan Zeb, Defu Zhang

Engineering Faculty Articles and Research

As a crucial food crop, potatoes are highly consumed worldwide, while they are also susceptible to being infected by diverse diseases. Early detection and diagnosis can prevent the epidemic of plant diseases and raise crop yields. To this end, this study proposed a weakly-supervised learning approach for the identification of potato plant diseases. The foundation network was applied with the lightweight MobileNet V2, and to enhance the learning ability for minute lesion features, we modified the existing MobileNet-V2 architecture using the fine-tuning approach conducted by transfer learning. Then, the atrous convolution along with the SPP module was embedded into the …

Highly Power Dense Dc To Three-Phase Ac Modular Converters With Tiny Module Capacitors, Wiwin Hartini Lew

Dissertations and Theses

A Modular Multilevel Converter (MMC) is an attractive candidate in high power conversion due to its modularity and scalability. The energy storage element, namely the module capacitance in the MMC submodule circuit, is typically large and when scaled to convert high power, requires very bulky module capacitors. In addition to deteriorating the power density, the design necessitates the use of electrolytic capacitors, which further affects the overall converter efficiency and reliability. This research presents an MMC submodule topology and the accompanying modulation approach that reduces the submodule capacitance requirements significantly compared to conventional MMC topology (few micro-farads versus several milli-farads). …

Application Of Distributed Fiber-Optic Sensing For Pressure Predictions And Multiphase Flow Characterization, Gerald Kelechi Ekechukwu

LSU Doctoral Dissertations

In the oil and gas industry, distributed fiber optics sensing (DFOS) has the potential to revolutionize well and reservoir surveillance applications. Using fiber optic sensors is becoming increasingly common because of its chemically passive and non-magnetic interference properties, the possibility of flexible installations that could be behind the casing, on the tubing, or run on wireline, as well as the potential for densely distributed measurements along the entire length of the fiber. The main objectives of my research are to develop and demonstrate novel signal processing and machine learning computational techniques and workflows on DFOS data for a variety of …

A Horn Microstrip Transmission Line For The Characterization And Investigation Of Multipactor At Various Pressure And Power, Shaho Hamadamin

Electrical and Computer Engineering ETDs

The University of New Mexico is designing, building, and testing a multipactor testbed based on a horn-microstrip transmission line to characterize and investigate the multipactor effect for a range of vacuum pressures and power. A horn-shaped, 50 Ω Al microstrip line is positioned inside a six-way cross stainless-steel chamber that is vacuumed down to low ~10−7 torr. A 100 𝑀𝑀𝑀𝑀𝑀𝑀 sine signal is fed to a rf amplifier with a bandwidth of 250 − 105 𝑀𝑀𝑀𝑀𝑀𝑀, that can reach 120𝑊𝑊 average (CW) power. Two multipacting detection methods, i.e., global, and local methods, are implemented for accurate multipaction detection. The former …

Protection And Control Of Electric Power Grid Under High Penetration Of Ders, Binod Prasad Poudel

Electrical and Computer Engineering ETDs

Modernizing power grids with communication-based technologies has introduced new challenges to the operation of the grid, especially when the communication network experiences failure or data is corrupted during the transfer. This issue is studied in this dissertation from the control and protection perspective. First, the cyber attack detection and mitigation of distributed control of microgrids is addressed when the distributed energy resources (DER) are exposed to false data injection attacks. A cyber-threat detection technique is proposed based on Kullback-Liebler divergence-based criterion. This criterion with a threshold can detect the misbehavior of a compromised DER control unit and, consequently, calculates the …

Digital Platform To Aid Youth Substance Abuse Prevention, Bingxuan Li

Discovery Undergraduate Interdisciplinary Research Internship

Through research and interviews, I discovered that a significant portion of students in Africa become drug addicts and drop out of school. The solution is to prevent youth substance abuse before it happens, so that more students in Africa may continue their education. With the strong motivation of expanding African student involvement in higher education, I participated DURI program to increase higher education rates in the Democratic Republic of the Congo, Africa. The local government is establishing rehabilitation centers to monitor at-risk students and prevent youth substance abuse, but due to extremely limited resources, it is critical to evaluate the …

Towards Multipronged On-Chip Memory And Data Protection From Verification To Design And Test, Senwen Kan, Jennifer Dworak

Computer Science and Engineering Theses and Dissertations

Modern System on Chips (SoCs) generally include embedded memories, and these memories may be vulnerable to malicious attacks such as hardware trojan horses (HTHs), test access port exploitation, and malicious software. This dissertation contributes verification as well as design obfuscation solutions aimed at design level detection of memory HTH circuits as well as obfuscation to prevent HTH triggering for embedded memory during functional operation. For malicious attack vectors stemming from test/debug interfaces, this dissertation presents novel solutions that enhance design verification and securitization of an IJTAG based test access interface. Such solutions can enhance SoC protection by preventing memory test …

An Efficient Integrated Circuit Simulator And Time Domain Adjoint Sensitivity Analysis, Jiahua Li

Electrical Engineering Theses and Dissertations

In this paper, we revisit time-domain adjoint sensitivity with a circuit theoretic approach and an efficient solution is clearly stated in terms of device level. Key is the linearization of the energy storage elements (e.g., capacitance and inductance) and nonlinear memoryless elements (e.g., MOS, BJT DC characteristics) at each time step. Due to the finite precision of computation, numerical errors that accumulate across timesteps can arise in nonlinear elements.

In Band Full Duplex For Wireless Communication, A Medium Access Control Perspective, Yazeed Alkhrijah

Electrical Engineering Theses and Dissertations

In-band full duplex (IBFD) for wireless communication is defined as the ability of a node to send and receive data simultaneously by using the same frequency band. IBFD has the potential to double the spectral efficiency of wireless networks. In addition, IBFD improves security by mystifying any eavesdropper with multiple transmitted signals in a single frequency. Also, IBFD reduces the end-to-end transmission delay and solves the hidden terminal and exposed terminal problems. However, IBFD suffers from self-interference. Canceling self-interference (SI) is the main challenge in enabling IBFD. Another challenge for IBFD is to manage access to the network. IEEE802.11 are …

Novel Locomotion Methods In Magnetic Actuation And Pipe Inspection, Adam Cox

Mechanical Engineering Research Theses and Dissertations

There is much room for improvement in tube network inspections of jet aircraft. Often, these inspections are incomplete and inconsistent. In this paper, we develop a Modular Robotic Inspection System (MoRIS) for jet aircraft tube networks and a corresponding kinematic model. MoRIS consists of a Base Station for user control and communication, and robotic Vertebrae for accessing and inspecting the network. The presented and tested design of MoRIS can travel up to 9 feet in a tube network. The Vertebrae can navigate in all orientations, including smooth vertical tubes. The design is optimized for nominal 1.5" outside diameter tubes. We …

Reinforcement Learning-Based Demand Response Management In Smart Grid Systems With Prosumers, Jenilee Jao

Electrical and Computer Engineering ETDs

In this thesis, we introduce a reinforcement learning-based price-driven Demand Response Management (DRM) mechanism in smart grid systems consisting of prosumers. Our proposed approach accounts for the prosumers behavioral characteristics and models the emerging interactions among all the involved actors in the smart grid system, i.e., prosumers, Energy Management System (EMS) and utility companies. In particular, an off-policy reinforcement learning is introduced enabling the EMS to determine the optimal price that should be announced to the prosumers on an hourly-basis towards minimizing the overall systems cost. In this process, the utility companies hourly-based wholesale price and the prosumers energy generation …

Orbital Angular Momentum Orthogonality-Based Crosstalk Reduction: Theory And Experiment, Unaiza Tariq

Electrical Engineering Theses and Dissertations

Full duplex communication systems allow a single channel to be used for simultaneous two-way communication, increasing spectral efficiency. However, full duplex communication systems suffer from the issue of self-interference between local transmitter and receiver antennas. Analog subtraction and signal processing methods have previously been used to reduce this problem. This dissertation proposes the use of waves carrying orbital angular momentum (OAM) to mitigate the problem of self-interference by offering a means of additional isolation between local antennas.

Orbital angular momentum has been widely studied both in the photonics and radio domain. The theoretically infinite orthogonal states of an OAM signal …

Distribution Network Operation With Solar Photovoltaic And Energy Storage Technology, Mohammad Ramin Feizi

Electrical Engineering Theses and Dissertations

Among distributed energy resources, solar photovoltaic (PV) generation has the largest penetration in the distribution networks. Serving electric vehicles (EV) with renewable resource generation would further reduce the carbon footprint of the energy supply chain for electric vehicles. However, the integration of solar PV and EVs in the unbalanced distribution network introduces several challenges including voltage fluctuations, voltage imbalances, reverse power flow, and protection devices’ malfunctions. The uncertainties associated with solar PV integration and electric vehicles operation require significant effort to develop accurate optimization methodologies in the unbalanced distribution systems operation. In this thesis, in order to cope with the …

Development And Application Of A Design Flow For Photonic Integrated Circuits, Ifeanyi Achu

Electrical Engineering Theses and Dissertations

Silicon photonics allows for the fabrication of many optical elements on a single photonic integrated circuit (PIC). By taking advantage of the established foundry technology used in the CMOS and silicon’s high refractive index, high feature density manufacturing can be achieved in mass quantities. In CMOS fabrication, from conception of an electronic circuit to testing, the process of designing an electronic circuit is dictated by a design flow which has been developed over the course of decades. This flow includes circuit level design and simulation, layout of the circuit, layout and verification of the chip, fabrication, packaging, and testing. Given …

Void-Semiconductor Gaas Photonic Crystal Surface-Emitting Lasers By Epitaxial Regrowth And Single-Epitaxy Methods, Kevin James Reilly

Nanoscience and Microsystems ETDs

Monolithic semiconductor lasers including edge-emitting lasers (EELs) and vertical-cavity surface-emitting lasers (VCSELs) fail to realize simultaneous achievement of both high-power high-quality beams due to intrinsic limitations of their resonant cavity. Photonic crystal surface emitting lasers (PCSELs) address these structural limitations through employment of a two-dimensional photonic crystal (PC) cavity that creates feedback at a single wavelength for laterally scalable devices. This function of the PC allows PCSELs to power scale with area while maintaining single-mode emission required for diffraction-limited beams. In this way, PCSELs fulfill an industry demand for high-power high-quality lasing from a single chip.

Early PCSELs were fabricated …

Cyber-Secure Distributed Control Of Microgrids With Improved Communication And Control Protocols, Jee Won Choi

Mechanical Engineering ETDs

This dissertation proposes a cyber-secure distributed control of microgrids with improved communication and control protocols. The finite-time event-triggered control protocol for islanded AC and DC secondary control is introduced. For AC microgrids, the proposed strategy can effectively perform frequency restoration and voltage regulations while sharing the active and reactive power among the distributed generators (DGs) based on their power ratings. For DC microgrids, the proposed control protocol can provide accurate current sharing and critical bus voltage regulation. The finite-time control enables a system to reach a consensus in a finite period of time enhanced from asymptotic convergence. The event-triggered communication …

Towards Robust Channel Dynamics: Photoionization In Nitrogen And Air, Justin K. Smith

Electrical and Computer Engineering ETDs

In present photoionization models used in computational studies, there is a lack of experimental data and several assumptions pertaining to photo-electron production in the gas. It is widely accepted that wavelengths between 98 nm and 102.5 nm are the primary contributors to photoionization of oxygen in an air plasma. In air, the collisional kinetics of nitrogen provide the photons, which results in the ionization of oxygen. Photoionization rate measurements from a low current corona discharge in synthetic air mixtures are reported to provide new empirical data. In addition, this provides a method to estimate the scaling parameter w/a. Concurrently, vacuum …