Digital Commons Network^™

Operational Planning To Enhance Bhutan Power Grid Resilience In Interconnected Systems, Kelzangla -

Chulalongkorn University Theses and Dissertations (Chula ETD)

The complexity of modern power systems has led to more blackouts in the past 15 years. These blackouts cause significant disruptions and economic impacts. To address this, the IEEE PES taskforce recommended Intentional Controlled Islanding (ICI) via Special Protection Schemes (SPSs). ICI, or controlled system separation, is an adaptive control strategy to prevent widespread blackouts when conventional protection measures fail. It involves quickly identifying and disconnecting specific grid branches to form stable, manageable islands. These islands can be controlled more efficiently, reducing the risk of a total blackout. The three critical aspects of ICI are determining the timing (when), boundaries …

Optimal Scheduling And Sizing Of Battery Energy Storage System In An Industrial Microgrid, Jirawat Wongyai

Chulalongkorn University Theses and Dissertations (Chula ETD)

This project focuses on enhancing operational efficiency by integrating a Battery Energy Storage System (BESS) with a solar power generation system. The primary goal is to design and optimize the scheduling and sizing of the BESS using Rule-Based Algorithm and Particle Swarm Optimization. The analysis includes assessing electricity cost reduction rates, payback periods, and identifying the battery capacity that maximizes cost savings while maintaining an acceptable payback period. Additionally, the project applies the Rule-Based method to the factory's actual electrical system, calculates the optimal timing for BESS investment as costs decrease, and translates the reduced electricity consumption into carbon credits. …

Practical Implementation Of Oscillation Source Detection Using Dissipating Energy Flow Method, Thanapon Jongjarussang

Chulalongkorn University Theses and Dissertations (Chula ETD)

Power grid oscillation with poorly damped performance is a growing problem. The oscillation source needs to be quickly and precisely identified in order to mitigate the oscillation issues to prevent any detrimental conditions that may arise. An incoming of synchrophasor technology enables the use of dissipating energy flow (DEF) method to practically identify the oscillation source. This research thesis aims at validating the DEF-based method and then developing an application tool to identify the oscillation source in a practical power grid. The DEF method was validated through various simulated oscillation cases based on IEEE 39-bus system leading to a promising …

การพัฒนาขั้นตอนวิธีสำหรับการจับคู่ชื่อสินค้าที่มีรูปแบบการตั้งชื่อที่หลากหลายโดยใช้การประมวลผลภาษาธรรมชาติ, สหฤษฎ์ เจียมสกุล

Chulalongkorn University Theses and Dissertations (Chula ETD)

ในขอบเขตของการซื้อขายสินค้าระหว่างองค์กร ความท้าทายที่สำคัญเกิดขึ้นเมื่อต้องจับคู่คำสั่งซื้อของลูกค้ากับชื่อสินค้าในฐานข้อมูล ซึ่งชื่อสินค้าเหล่านี้มีรูปแบบการตั้งชื่อที่หลากหลาย วิทยานิพนธ์นี้จะกล่าวถึงความซับซ้อนของการจับคู่ชื่อสินค้าภายในบริษัท เจนบรรเจิด จำกัด ซึ่งเป็นบริษัทที่เชี่ยวชาญในการขายสินค้าสำหรับธุรกิจบริการ ปัจจุบันวิธีการที่ใช้แก้ปัญหานี้คือการใช้พนักงานเปรียบเทียบคำสั่งซื้อของลูกค้ากับชื่อสินค้าในฐานข้อมูลทีละรายการ ซึ่งเป็นกระบวนการที่สิ้นเปลืองแรงงานและเวลาเป็นอย่างมาก วิทยานิพนธ์นี้จึงนำเสนอการใช้เทคนิคการประมวลผลภาษาธรรมชาติ (NLP) เพื่อแก้ปัญหาดังกล่าว โดยเริ่มจากการใช้ Pointwise Mutual Information (PMI) ในการคัดเลือกคำสำคัญในพจนานุกรมแบบกำหนดเอง เพื่อการตัดคำภาษาไทยที่เหมาะสมกับชุดข้อมูล จากนั้นนำระบบตัดคำที่ปรับปรุงแล้วมาใช้ในการออกแบบขั้นตอนวิธีสำหรับการสกัดคำหลัก รวมถึงการใช้เทคนิคการวิเคราะห์ความหมายแฝง (LSA) เพื่อค้นหาคำที่คล้ายกับคำค้นหา สุดท้ายจึงนำส่วนต่างๆ มารวมเข้ากับการใช้เทคนิคการจับคู่ข้อความโดยประมาณ จนเกิดเป็นขั้นตอนวิธีสำหรับจับคู่รายชื่อสินค้า ขั้นตอนวิธีที่นำเสนอสามารถทำงานได้อย่างมีประสิทธิภาพ โดยมีความแม่นยำในการระบุผลลัพธ์มากถึง 93.80% และมีความครอบคลุมมากถึง 91.67% ในการทดสอบจับคู่กับชุดตัวอย่างคำสั่งซื้อจริงจากลูกค้า

Solving Multi-Depot Open Pickup And Delivery Problem With Capacity And Distance Restrictions By Ant Colony Optimization Algorithm, Teerawat Indravattana

Chulalongkorn University Theses and Dissertations (Chula ETD)

The recently occurring global pandemic caused the mobile delivery service business to grow rapidly. One of the important aspects of this issue is the problem of finding the route of the company’s couriers to reduce the cost of the operation and increase the total gain. This study aims to find a route that has the least cost while the couriers do not carry the packages over their capacity limits or exceed the maximum distance they can travel, and all requests are satisfied. The problem was defined as a Distance-constrained Multi Depot Open Pickup and Delivery Problem (DMDOPDP). A program simulating …

Technical Feasibility Studies Of The Microgrid Pilot Project At Rubesa In Bhutan., Karma Chheki

Chulalongkorn University Theses and Dissertations (Chula ETD)

Over the years, Microgrid integration of hybrid renewable resources has emerged as a game-changing solution, significantly enhancing resilience and sustainability in the global energy landscape. This thesis introduces both isolated and grid-connected microgrid designs tailored to the context of Rubesa, a local community in the western part of Bhutan called Wangduephodrang district. Drawing upon hybrid solar and hydro resources to serve the local demand, the study emphasizes a Technical Feasibility Study of a Resilience-Oriented Utility Microgrid Pilot Project using the Hybrid Optimization Multiple Energy Resources (HOMER Pro) software. Test results demonstrate that a diversified mix of renewable energy sources of …

A Channel And Spatial Attention Feature Extraction Method For Remote Sensing Image Super-Resolution Using Vision Transformer, Naveed Sultan

Chulalongkorn University Theses and Dissertations (Chula ETD)

In recent years, convolution neural networks have achieved a remarkable advancement in remote sensing image super-resolution due to the complexity and variability of textures and structure. Current deep learning-based super-resolution models concentrate less on high-frequency features, which leads to suboptimal performance in capturing contours, texture, and spatial information. State-of-the-art deep learning methods now focus on feature extraction of remote sensing images using attention mechanisms. However, these methods are still incapable of effectively identifying and utilizing key content attention. The existing transformer models do not focus on capturing the spatial information in their encoder and decoder parts. To cover these problems, …

Heterogeneous Capacitated Vehicle Routing By Particle Swarm Optimization, Ye Kyaw

Chulalongkorn University Theses and Dissertations (Chula ETD)

In logistics and transportation sector, heterogenous fixed fleet vehicle routing problem, where there are different types of vehicles and a limited number of vehicles of each type with varying capacities, poses a significant challenge. The primary objective of this study is to minimize the total cost associated with factors such as fuel consumption and distance travelled. The problem is defined as Heterogeneous Fixed Fleet Vehicle Routing Problem with Distance and Capacity Limit. The PSO algorithm will be customized to handle the heterogeneity of the vehicle fleet efficiently, while taking different vehicle capacities and fuel efficiencies into consideration. Substantial computational experiments …

การพัฒนาระบบนับเซลล์เม็ดเลือดขาวที่ผิดปกติผ่านสมาร์ทโฟน โดยใช้โครงข่ายประสาทเทียมชนิดคอนโวลูชัน, ณัทกร เกษมสำราญ

Chulalongkorn University Theses and Dissertations (Chula ETD)

การวินิจฉัยโรคและการวิเคราะห์ความผิดปกติของผู้ป่วยที่เข้ารับการรักษาที่โรงพยาบาลและคลินิค จะต้องมีการตรวจร่างกาย สังเกตอาการ รวมถึงการซักประวัติผู้ป่วย ในบางครั้งแพทย์มีความจำเป็นต้องส่งตรวจทางห้องปฏิบัติการ เช่น การตรวจความสมบูรณ์ของเม็ดเลือด (CBC) ในอดีตแพทย์จะตรวจด้วยการส่องกล้องจุลทรรศ์ถือเป็นมาตรฐาน เนื่องจากในประเทศไทยผู้เชี่ยวชาญอายุรแพทย์โลหิตวิทยามีจำนวนน้อยเมื่อเทียบกับผู้ป่วยโรคเลือด ส่งผลให้คิวรอการนับเซลล์เม็ดเลือดของผู้ป่วยที่มีเซลล์ผิดปกติยาวนานหลายสัปดาห์ ได้มีการพัฒนาเครื่องนับเซลล์อย่างอัตโนมัติ เพื่อเพิ่มประสิทธิภาพการตรวจความสมบูรณ์ของเลือดได้อย่างรวดเร็วมากยิ่งขึ้น ลดภาระงานของผู้เชี่ยวชาญในการส่องกล้องจุลทรรศน์ลง แต่การนำเครื่องนับอย่างอัตโนมัติมาใช้ในโรงพยาบาลในประเทศไทยยังมีข้อจำกัด เนื่องจากราคาต่อเครื่องสูงจึงมีเฉพาะโรงเรียนแพทย์และโรงพยาบาลขนาดใหญ่ที่สามารถจัดซื้อได้ และมีความบกพร่องที่สำคัญเมื่อเลือดของผู้ป่วยมีเซลล์ที่มีความผิดปกติที่พบได้น้อยในภาวะปกติปะปนมา เครื่องอาจจะไม่สามารถตรวจจับเซลล์ดังกล่าวได้ จึงมีการสร้างเกณฑ์การส่งตรวจซ้ำด้วยการส่องกล้องจุลทรรศน์ เพื่อให้ผลการตรวจที่ได้มีความถูกต้องแม่นยำ จึงเกิดแนวคิดที่จะสร้างระบบอัตโนมัติในการจำแนกชนิดของเซลล์เลือดแบบ AI-Assisted web application ด้วยการให้ผู้ใช้สมาร์ทโฟนประกบกับเลนส์ใกล้ตาของกล้องจุลทรรศน์ถ่ายภาพส่งไปให้ระบบตรวจจับเซลล์เม็ดเลือดที่ผิดปกติได้ ซึ่งสามารถแยกเซลล์เม็ดเลือดได้ 12 ชนิด เมื่อระบบได้รับภาพแล้วจะนับเฉพาะเซลล์ดังกล่าวโดยปัญญาประดิษฐ์ที่มีโครงสร้างตาม YOLOv5x และส่งรายงานการนับให้ผู้ใช้ภายในไม่กี่วินาที หลังจากการปรับแต่งหนึ่งในรุ่นของแบบปัญญาประดิษฐ์ให้ค่า mAP@50 ที่ร้อยละ 90 บนชุดทดสอบ ยังพบว่าระบบที่พัฒนาขึ้นช่วยให้ความสามารถของแพทย์ทั่วไปและนักศึกษาแพทย์ชั้นคลินิค ในการระบุตำแหน่งและชนิดของเซลล์เม็ดเลือด ใกล้เคียงกับอาจารย์อายุรแพทย์โลหิตวิทยา และลดระยะเวลาการนับได้ครึ่งนึง

Novel Pricing Structure And Mechanism With Consideration Of Network Usage Charges For Peer-To-Peer Energy Trading In Distribution Systems Of Thailand, Surapad Larbwisuthisaroj

Chulalongkorn University Theses and Dissertations (Chula ETD)

The rise of distributed energy resources has empowered consumers to become prosumers, generating their own electricity. This trend has led to the development of peer-to-peer (P2P) energy trading. This dissertation focuses on two main areas: integrating network charges in P2P energy trading and determining the maximum P2P penetration levels on distribution systems while considering stakeholder benefits. Firstly, a framework for network usage charges (NUCs) and corresponding market clearing mechanisms are proposed. The NUCs comprise two key components: distribution NUCs (DNUCs) and operational NUCs (ONUCs). These charges are designed to recover energy-related and nonenergy-related costs incurred in the distribution system. DNUCs …

Task Assignment And Path Planning Of Multiple Unmanned Aerial Vehicles Using Integer Linear Programming, Imran Saeed Mirza

Chulalongkorn University Theses and Dissertations (Chula ETD)

วิทยานิพนธ์ฉบับนี้นำเสนอสูตรโปรแกรมเชิงเส้นจำนวนเต็มเพื่อการมอบหมายงานและการวางแผนเส้นทางให้กับอากาศยานไร้คนขับหลายลำกลุ่มโดรนจะได้รับมอบหมายให้เยี่ยมภารกิจให้ครบทุกเป้าหมายและเดินทางกลับไปยังตำแหน่งเริ่มต้นโดยมีเป้าหมายให้ได้ผลรวมของระยะทางที่โดรนทุกตัวเดินทางมีค่าน้อยที่สุดในขณะเดียวกันไม่อนุญาตให้มีทัวร์ย่อยใดๆเพื่อให้ได้ผลลัพธ์ที่มีประสิทธิภาพมากที่สุดมีการทดลองทดสอบเพื่อตรวจสอบความถูกต้องของสูตรที่ได้นำเสนอโดยใช้จำนวนโดรนและจำนวนงานที่หลากหลายผลการทดสอบแสดงให้เห็นว่าการเพิ่มจำนวนโดรนโดยทั่วไปสามารถช่วยลดระยะทางรวมและลดระยะเวลาในการทำภารกิจให้เสร็จสิ้นได้ข้อดีของวิธีที่เสนอคือให้ผลเฉลยที่เหมาะสุดแต่ใช้เวลาในการคำนวณเพื่อค้นหาผลเฉลยก็นานด้วยดังนั้นจึงได้ทำการทดลองโดยกำหนดจำนวนโดรนและภาระงานที่ขนาดแตกต่างกันจากการทดสอบโดยใช้คอมพิวเตอร์โน้ตบุ๊กที่มีหน่วยประมวลผลเพนเทียม10หน่วยความจำแรม8GBและหน่วยความจำเอสเอสดีขนาด256GBพบว่าระบบที่มีงานไม่เกิน27การหาผลเฉลยเหมาะสมที่สุดทำได้ภายในไม่กี่นาทีโดยไม่ขึ้นกับจำนวนโดรนที่ใช้งานแต่สำหรับงานจำนวนมากที่เกินขีดจำกัดนี้จะไม่สามารถได้ผลเฉลยแม้ว่าจะใช้เวลาจำลองไปแล้วเกินหนึ่งชั่วโมงก็ตาม

Survey Of Routing Techniques-Based Optimization Of Energy Consumption In Sd-Dcn, Mohammed Nsaif, Gergely Kovásznai, Ali Malik, Ruairí De Fréin

Articles

The increasing power consumption of Data Center Networks (DCN) is becoming a major concern for network operators. The object of this paper is to provide a survey of state-of-the-art methods for reducing energy consumption via (1) enhanced scheduling and (2) enhanced aggregation of traffic flows using Software-Defined Networks (SDN), focusing on the advantages and disadvantages of these approaches. We tackle a gap in the literature for a review of SDN-based energy saving techniques and discuss the limitations of multi-controller solutions in terms of constraints on their performance. The main finding of this survey paper is that the two classes of …

Perceptual Anthropomorphic Walking Robot Platform For Navigation In Unstructured And Undifferentiated Environments, Luige Vladareanu, Mihai Rădulescu, Marius Pandelea, Hongbo Wang, Florentin Smarandache, Yongfei Feng, Ionel-Alexandru Gal, Alexandra C. Ciocîrlan

Branch Mathematics and Statistics Faculty and Staff Publications

This scientific presentation studies the VIPRO Platform for control of Anthropomorphic Walking Robots (AWR), the architecture control system of the SiMeLA MP robot motion, and shows several experimental results.

Static I-V Curve And Aging Test For Pim Characterization In Metallic Contacts, Kalkidan Anjajo

Masters Theses

"Spring clips and fabric-over-foams (FOFs) are widely used in mobile devices for electrical connection purposes. However, the imperfect metallic connections tend to induce passive intermodulation (PIM), resulting in a receiver sensitivity degradation, known as RF desensitization. Due to the complexity of the PIM characterization, there is not yet a way to evaluate PIM performance using a simple setup for environments like factories. In this study, a current-voltage (I-V) behavior-based PIM evaluation method is proposed and validated with various metallic contacts and contact forces. The test results demonstrated the feasibility of the PIM performance evaluation based on the measured static I-V …

Extended Kalman Filter Based Resilient Formation Tracking Control Of Multiple Unmanned Vehicles Via Game-Theoretical Reinforcement Learning, Lei Xue, Bei Ma, Jian Liu, Chaoxu Mu, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

In This Paper, We Discuss the Resilient Formation Tracking Control Problem of Multiple Unmanned Vehicles (MUV). a Dynamic Leader-Follower Distributed Control Structure is Utilized to Optimize the Performance of the Formation Tracking. for the Follower of the MUV, the Leader is a Cooperative Unmanned Vehicle, and the Target of Formation Tracking is a Non-Cooperative Unmanned Vehicle with a Nonlinear Trajectory. Therefore, an Extended Kalman Filter (EKF) Observer is Designed to Estimate the State of the Target. Then the Leader of the MUV is Adjusted Dynamically According to the State of the Target. in Order to Describe the Interactions between the …

Single Image Super Resolution Using Deep Attention Network, Jagrati Talreja

Chulalongkorn University Theses and Dissertations (Chula ETD)

This thesis introduces two innovative frameworks for Single Image Super Resolution (SISR) that enhances image quality while optimizing computational efficiency. The motivation for this research is driven by the need to overcome the limitations of current SISR techniques like capturing long-range dependencies, enhancing multi-scale feature learning, mitigating over-smoothing, and managing computational demands. The choice to incorporate attention mechanisms in both frameworks is motivated by their proven ability to allow the model to focus on the most relevant parts of the image, thereby improving the reconstruction of high-resolution details from low-resolution inputs. By integrating attention mechanisms with inception blocks, the proposed …

Coaxial Cable Sensing: Review And Perspective, Chen Zhu, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

The development of sensors has been a hot research topic in both scientific and industrial communities over the past decades. In recent years, a new sensing technology based on coaxial cables has emerged. Inspired by the fiber Bragg grating and motivated by the demand for structural health monitoring, coaxial cable Bragg gratings were first proposed and demonstrated with superior large strain capability ($>$ 5%). Mimicking the mature sensing modalities in fiber-optic sensors, coaxial cable sensors are developed to be promising alternatives for fiber-optic sensors in harsh-environment applications involving heavy duty, large strains, high pressures, and high temperatures. Over the …

Three-Dimensional Environmentally Sustainable Neuromorphic Computing System Based On Natural Organic Memristor, Jinhui Wang, Feng Zhao, Mohammed Rafeeq Khan, Md Mehedi Hasan Tanim, Zoe Templin

Electrical and Computer Engineering Faculty Research & Creative Works

Three-dimensional environmentally sustainable neuromorphic computing system based on natural organic honey-memristor is proposed in this paper. The experimental results indicate the proposed systems have high inference accuracy over 90 % with device variation and nonlinearity. What is more, four conductance drift scenarios, ADC (Analog-to-Digital Converter) quantization effects, and different algorithms (VGG8 and DenseNet-40) are considered to further verify the proposed systems.

Eeg-Based Spanish Language Proficiency Classification: An Eeg Power Spectrum And Cross-Spectrum Analysis, Blaise Xavier O'Mara, Skyler Baumer

Honors Theses and Capstones

Second language proficiency may be predicted with electrophysiological techniques. In a machine learning application, this electrophysiological data may be used for language instructors and language students to assess their language learning. This study identifies how electroencephalogram (EEG) power spectrum and cross spectrum data of the brain cortex relates to Spanish second language (L2) proficiency of 20 Spanish language students of varying proficiency levels at the University of New Hampshire. The two metrics for assessing cortical power and processing were event-related desynchronization (ERD)—a measure of relative change in power—of the alpha (8-12 Hz) brain frequency band, and alpha and beta (13-30Hz) …

Blockchain And Puf-Based Secure Key Establishment Protocol For Cross-Domain Digital Twins In Industrial Internet Of Things Architecture, Khalid Mahmood, Salman Shamshad, Muhammad Asad Saleem, Rupak Kharel, Ashok Kumar Das, Sachin Shetty, Joel J. P. C. Rodrigues

VMASC Publications

Introduction:: The Industrial Internet of Things (IIoT) is a technology that connects devices to collect data and conduct in-depth analysis to provide value-added services to industries. The integration of the physical and digital domains is crucial for unlocking the full potential of the IIoT, and digital twins can facilitate this integration by providing a virtual representation of real-world entities.

Objectives:: By combining digital twins with the IIoT, industries can simulate, predict, and control physical behaviors, enabling them to achieve broader value and support industry 4.0 and 5.0. Constituents of cooperative IIoT domains tend to interact and collaborate during their complicated …

Development Of Sensing And Programming Activities For Engineering Technology Pathways Using A Virtual Arduino Simulation Platform, Murat Kuzlu, Vukica Jovanovic, Otilia Popescu, Salih Sarp

Engineering Technology Faculty Publications

The Arduino platform has long been an efficient tool in teaching electrical engineering technology, electrical engineering, and computer science concepts in schools and universities and introducing new learners to programming and microcontrollers. Numerous Arduino projects are widely available through the open-source community, and they can help students to have hands-on experience in building circuits and programming electronics with a wide variety of topics that can make learning electrical prototyping fun. The educational fields of electrical engineering and electrical engineering technology need continuous updating to keep up with the continuous evolution of the computer system. Although the traditional Arduino platform has …

Topologically Optimized Electrodes For Electroosmotic Actuation, Jianwen Sun, Jianyu Zhang, Ce Guan, Teng Zhou, Shizhi Qian, Yongbo Deng

Mechanical & Aerospace Engineering Faculty Publications

Electroosmosis is one of the most used actuation mechanisms for the microfluidics in the current active lab-on-chip devices. It is generated on the induced charged microchannel walls in contact with an electrolyte solution. Electrode distribution plays the key role on providing the external electric field for electroosmosis, and determines the performance of electroosmotic microfluidics. Therefore, this paper proposes a topology optimization approach for the electrodes of electroosmotic microfluidics, where the electrode layout on the microchannel wall can be determined to achieve designer desired microfluidic performance. This topology optimization is carried out by implementing the interpolation of electric insulation and electric …

Light Auditor: Power Measurement Can Tell Private Data Leakage Through Iot Covert Channels, Woosub Jung, Kailai Cui, Kenneth Koltermann, Junjie Wang, Chunsheng Xin, Gang Zhou

Electrical & Computer Engineering Faculty Publications

Despite many conveniences of using IoT devices, they have suffered from various attacks due to their weak security. Besides well-known botnet attacks, IoT devices are vulnerable to recent covert-channel attacks. However, no study to date has considered these IoT covert-channel attacks. Among these attacks, researchers have demonstrated exfiltrating users' private data by exploiting the smart bulb's capability of infrared emission.

In this paper, we propose a power-auditing-based system that defends the data exfiltration attack on the smart bulb as a case study. We first implement this infrared-based attack in a lab environment. With a newly-collected power consumption dataset, we pre-process …

Ultrasensitive Tapered Optical Fiber Refractive Index, Erem Ujah, Meimei Lai, Gymama Slaughter

Electrical & Computer Engineering Faculty Publications

Refractive index (RI) sensors are of great interest for label-free optical biosensing. A tapered optical fiber (TOF) RI sensor with micron-sized waist diameters can dramatically enhance sensor sensitivity by reducing the mode volume over a long distance. Here, a simple and fast method is used to fabricate highly sensitive refractive index sensors based on localized surface plasmon resonance (LSPR). Two TOFs (l = 5 mm) with waist diameters of 5 µm and 12 µm demonstrated sensitivity enhancement at λ = 1559 nm for glucose sensing (5-45 wt%) at room temperature. The optical power transmission decreased with increasing glucose concentration due …

Mwirgan: Unsupervised Visible-To Mwir Image Translation With Generative Adversarial Network, Mohammad Shahab Uddin, Chiman Kwan, Jiang Li

Electrical & Computer Engineering Faculty Publications

Unsupervised image-to-image translation techniques have been used in many applications, including visible-to-Long-Wave Infrared (visible-to-LWIR) image translation, but very few papers have explored visible-to-Mid-Wave Infrared (visible-to-MWIR) image translation. In this paper, we investigated unsupervised visible-to-MWIR image translation using generative adversarial networks (GANs). We proposed a new model named MWIRGAN for visible-to-MWIR image translation in a fully unsupervised manner. We utilized a perceptual loss to leverage shape identification and location changes of the objects in the translation. The experimental results showed that MWIRGAN was capable of visible-to-MWIR image translation while preserving the object’s shape with proper enhancement in the translated images and …

View Synthesis With Scene Recognition For Cross-View Image Localization, Uddom Lee, Peng Jiang, Hongyi Wu, Chunsheng Xin

Electrical & Computer Engineering Faculty Publications

Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from a cell phone or vehicle dashcam to a large scale of geo-tagged reference images, such as satellite/aerial images or Google Street Views. However, the problem remains challenging due to the inconsistency between the query images and the large-scale reference datasets regarding various light and weather conditions. To tackle this issue, this work proposes a novel view synthesis framework equipped with deep generative models, which can merge the unique features from the outdated reference dataset with …

The Effect Of The Width Of The Incident Pulse To The Dielectric Transition Layer In The Scattering Of An Electromagnetic Pulse — A Qubit Lattice Algorithm Simulation, George Vahala, Linda Vahala, Abhay K. Ram, Min Soe

Electrical & Computer Engineering Faculty Publications

The effect of the thickness of the dielectric boundary layer that connects a material of refractive index n₁ to another of index n₂is considered for the propagation of an electromagnetic pulse. A qubit lattice algorithm (QLA), which consists of a specially chosen non-commuting sequence of collision and streaming operators acting on a basis set of qubits, is theoretically determined that recovers the Maxwell equations to second-order in a small parameter ϵ. For very thin boundary layer the scattering properties of the pulse mimics that found from the Fresnel jump conditions for a plane wave - except that …

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study, Haben Yhdego, Christopher Paolini, Michel Audette

Electrical & Computer Engineering Faculty Publications

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has …

Class Activation Mapping And Uncertainty Estimation In Multi-Organ Segmentation, Md. Shibly Sadique, Walia Farzana, Ahmed Temtam, Khan Iftekharuddin, Khan Iftekharuddin (Ed.), Weijie Chen (Ed.)

Electrical & Computer Engineering Faculty Publications

Deep learning (DL)-based medical imaging and image segmentation algorithms achieve impressive performance on many benchmarks. Yet the efficacy of deep learning methods for future clinical applications may become questionable due to the lack of ability to reason with uncertainty and interpret probable areas of failures in prediction decisions. Therefore, it is desired that such a deep learning model for segmentation classification is able to reliably predict its confidence measure and map back to the original imaging cases to interpret the prediction decisions. In this work, uncertainty estimation for multiorgan segmentation task is evaluated to interpret the predictive modeling in DL …

Opioid Use Disorder Prediction Using Machine Learning Of Fmri Data, A. Temtam, Liangsuo Ma, F. Gerard Moeller, M. S. Sadique, K. M. Iftekharuddin, Khan M. Iftekharuddin (Ed.), Weijie Chen (Ed.)

Electrical & Computer Engineering Faculty Publications

According to the Centers for Disease Control and Prevention (CDC) more than 932,000 people in the US have died since 1999 from a drug overdose. Just about 75% of drug overdose deaths in 2020 involved Opioid, which suggests that the US is in an Opioid overdose epidemic. Identifying individuals likely to develop Opioid use disorder (OUD) can help public health in planning effective prevention, intervention, drug overdose and recovery policies. Further, a better understanding of prediction of overdose leading to the neurobiology of OUD may lead to new therapeutics. In recent years, very limited work has been done using statistical …