Digital Commons Network^™

Maximum Marginal Relevance And Vector Space Model For Summarizing Students' Final Project Abstracts, Gunawan Gunawan, Fitria Fitria, Esther Irawati Setiawan, Kimiya Fujisawa

Knowledge Engineering and Data Science

Automatic summarization is reducing a text document with a computer program to create a summary that retains the essential parts of the original document. Automatic summarization is necessary to deal with information overload, and the amount of data is increasing. A summary is needed to get the contents of the article briefly. A summary is an effective way to present extended information in a concise form of the main contents of an article, and the aim is to tell the reader the essence of a central idea. The simple concept of a summary is to take an essential part of …

K-Means Clustering And Multilayer Perceptron For Categorizing Student Business Groups, Miftahul Walid, Norfiah Lailatin Nispi Sahbaniya, Hozairi Hozairi, Fajar Baskoro, Arya Yudhi Wijaya

Knowledge Engineering and Data Science

The research conducted in this study was driven by the East Java provincial government's requirement to assess the transaction levels of the Student Business Group (KUS) in the SMA Double Track program. These transaction levels are a basis for allocating supplementary financial aid to each business group. The system's primary objective is to assist the provincial government of East Java in making well-informed choices pertaining to the distribution of supplementary capital to the KUS. The classification technique employed in this study is the multilayer perceptron. However, the K-Means Clustering method is utilised to generate target data due to the limited …

Round-Robin Algorithm In Load Balancing For National Data Centers, I Kadek Wahyu Sudiatmika, Gede Indrawan, Sariyasa Sariyasa

Knowledge Engineering and Data Science

The Provincial Government of Bali assumes a crucial role in administering various public service applications to meet the requirements of its community, traditional villages, and regional apparatus. Nevertheless, the escalating magnitude of traffic and uneven distribution of requests have resulted in substantial server burdens, which may jeopardize the operation of applications and heighten the likelihood of downtime. Ensuring efficient load distribution is of utmost importance in tackling these difficulties, and the Round Robin algorithm is often utilized for this purpose. However, the current body of research has not extensively examined the distinct circumstances surrounding on-premise servers in the Bali Provincial …

Long-Term Traffic Prediction Based On Stacked Gcn Model, Atkia Akila Karim, Naushin Nower

Knowledge Engineering and Data Science

With the recent surge in road traffic within major cities, the need for both short and long-term traffic flow forecasting has become paramount for city authorities. Previous research efforts have predominantly focused on short-term traffic flow estimations for specific road segments and paths. However, applications of paramount importance, such as traffic management and schedule routing planning, demand a deep understanding of long-term traffic flow predictions. However, due to the intricate interplay of underlying factors, there exists a scarcity of studies dedicated to long-term traffic prediction. Previous research has also highlighted the challenge of lower accuracy in long-term predictions owing to …

Optimizing Random Forest Algorithm To Classify Player's Memorisation Via In-Game Data, Akmal Vrisna Alzuhdi, Harits Ar Rosyid, Mohammad Yasser Chuttur, Shah Nazir

Knowledge Engineering and Data Science

Assessment of a player's knowledge in game education has been around for some time. Traditional evaluation in and around a gaming session may disrupt the players' immersion. This research uses an optimized Random Forest to construct a non-invasive prediction of a game education player's Memorization via in-game data. Firstly, we obtained the dataset from a 3-month survey to record in-game data of 50 players who play 4-15 game stages of the Chem Fight (a test case game). Next, we generated three variants of datasets via the preprocessing stages: resampling method (SMOTE), normalization (min-max), and a combination of resampling and normalization. …

Asset Cueing Nuclear Radiation Anomaly Detection Using An Embedded Neural Network Resource, April Inamura

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

Nuclear radiation detection is inherently a challenging task, coupled with a high background variation or increase in anomalies, the accuracy for detection can plummet. A key factor in the success of nuclear detection hinges on the sensor’s ability to generalize its model and directly leads to the model’s robustness. The goal of this project is to develop algorithms suitable for use on the University of Nebraska-Lincoln’s Pingora chip, a low-power, system-on-chip device with an active neural processing unit (NPU) made for nuclear radiation detection. The thesis aims to improve Pingora’s overall generalization ability in nuclear radiation source detection. A multiphase …

Fusion Of Microgrid Control With Model-Free Reinforcement Learning: Review And Vision, Buxin She, Fangxing Li, Hantao Cui, Jingqiu Zhang, Rui Bo

Electrical and Computer Engineering Faculty Research & Creative Works

Challenges and opportunities coexist in microgrids as a result of emerging large-scale distributed energy resources (DERs) and advanced control techniques. In this paper, a comprehensive review of microgrid control is presented with its fusion of model-free reinforcement learning (MFRL). A high-level research map of microgrid control is developed from six distinct perspectives, followed by bottom-level modularized control blocks illustrating the configurations of grid-following (GFL) and grid-forming (GFM) inverters. Then, mainstream MFRL algorithms are introduced with an explanation of how MFRL can be integrated into the existing control framework. Next, the application guideline of MFRL is summarized with a discussion of …

On The Use Of Wireless Technologies For Wildlife Monitoring: Wireless Sensor Network Routing Protocols, Lilian Mutalemwa

Tanzania Journal of Engineering and Technology (TJET)

Traditional methods for wildlife monitoring are labor-intensive and time-consuming. Therefore, advanced technologies and remote monitoring methods are becoming increasingly popular. This paper presents a study on wireless technologies for wildlife monitoring. In the study, a review of the literature was done to identify the most commonly used wireless technologies. Various technologies were explored including unmanned aerial vehicles (UAVs), Internet of Things (IoT), wireless sensor networks (WSNs), artificial intelligence (AI), global positioning system (GPS), and very high frequency (VHF) radio. Then, a more detailed study was done on WSN technology. Investigations were done to observe the performance of routing protocols in …

Optimization Techniques For Machine Learning Inference And Near Memory Image Processing In Hardware For Highly Constrained Iot Edge Nodes, Rajeev Joshi

USF Tampa Graduate Theses and Dissertations

The growing demand for fast and energy-efficient hardware for resource-constrained Internet of Things (IoT) edge devices has highlighted the limitations of conventional computing architectures. This research focuses on addressing the demand for fast, optimized, and energy-efficient machine learning inference engines as well as image processing in IoT edge applications. In this work, we address three challenging research problems and devise efficient solutions. Our investigation involved comprehensive exploration and analysis, leading to the proposal of effective approaches for overcoming these demanding issues. Through our work, we contribute novel solutions that offer improved efficiency and effectiveness in handling these research problems.

First, …

Enhancing Smart Grid Security And Reliability Through Graph Signal Processing And Energy Data Analytics, Md Abul Hasnat

USF Tampa Graduate Theses and Dissertations

Situational awareness in a large, dynamic, and complex cyber-physical critical infrastructure, such as a smart grid, is vital for ensuring its smooth and uninterrupted operation. With the evolving realities of the modern-day smart grids, new challenges associated with the situational awareness of these systems are emerging that demand intelligent and efficient solutions. This dissertation intends to address several problems for enhancing situational awareness by studying the dynamic interaction among the components of the smart grids through energy data analytics using various data-driven, machine learning, and graph signal processing (GSP) techniques. The presented work provides valuable insight into the data-driven analysis …

Performance Evaluation Of Full Array, Sub-Array And Overlapped Sub-Array Hybrid Beamforming Architectures For Massive Mimo Systems, Godwin Mruma Gadiel

Tanzania Journal of Engineering and Technology (TJET)

The technological advancement in wireless communication, promises high data rate for end users. This has led to the possibility of smart cities, inter connected vehicles, and virtual reality applications. One of the recent technologies in wireless communication is massive MIMO where large number of antennas are deployed at the transmitter or receiver. This is possible due to the use of mmWave in wireless communication. With massive MIMO, beamforming technique can be employed in the communication system. Beamforming is the ability of communication system to direct power to the intended users and to cancel power at non-intended users and thus significantly …

Smart Grid In Tanzania: Research Opportunities, Aviti Thadei Mushi

Tanzania Journal of Engineering and Technology (TJET)

reinvigorated its power generation capacity significantly to ensure smooth execution of its industrialization agenda and cope with the fourth industrial revolution. To ensure reliable availability of power to sustain its growing economy, Tanzania embarked on a deliberated measure to forge an energy mix. This deliberate measure encompasses the use of renewable energy technologies such as wind, solar, biomass, wastes, and micro hydro; natural gas; and other energy sources which are locally available including coal and geothermal. To effectively and efficiently manage such a growing power system and make electricity accessible to all for higher levels of industrial investment and services, …

Adaptive Plasmonic Metasurfaces For Radiative Cooling And Passive Thermoregulation, Azadeh Didari-Bader, Nooshin M. Estakhri, Nasim Mohammadi Estrakhri

Engineering Faculty Articles and Research

In this work, we investigate a class of planar photonic structures operating as passive thermoregulators. The radiative cooling process is adjusted through the incorporation of a phase change material (Vanadium Dioxide, VO₂) in conjunction with a layer of transparent conductive oxide (Aluminum-doped Zinc Oxide, AZO). VO₂ is known to undergo a phase transition from the “dielectric” phase to the “plasmonic” or “metallic” phase at a critical temperature close to 68°C. In addition, AZO shows plasmonic properties at the long-wave infrared spectrum, which, combined with VO₂, provides a rich platform to achieve low reflections across the …

Topological Interpolation Method For Modeling Dynamic Systems, Isamiddin Xakimovich Siddikov, Dilnoza Maxamadjanovna Umurzakova

Chemical Technology, Control and Management

The method of simulation structural-complex continuous-discrete control systems is discussed. For simulation and calculation of dynamic processes in continuous-discrete systems topological interpolation method is proposed, based on application of hybrid methods of space of state variables and interpolation of signals. The essence of the method is that the dynamics of the investigated system, considered at the final interval, is broken down into subintervals, on each of which the processes are described by linear ordinary system differential equations. The computational efficiency of the proposed method was evaluated by comparison with standard methods such as the Runge-Kutta-Merson method. The use of this …

Modeling And Dynamic Correction Of The Thermal Radiation Fluxes Measuring System, Olexander Alekseevich Sytnik, Fatima Mirazizovna Sagatova

Chemical Technology, Control and Management

Temperature measurements are currently an integral part of modern production, in particular, energy, aviation, instrumentation, etc. Therefore, the need to improve the accuracy of measurement, control and regulation of temperature largely determines the technical and economic efficiency of production. The development of reliable methods for temperature control under various conditions and the creation of specific devices is one of the most important tasks of modern instrumentation. The article deals with the issues of solving the problems of modeling and correcting the dynamic characteristics of a system for measuring thermal radiation fluxes using the integral method of signal recovery. For computer …

Investigation Of Magnetic Circuits Of Differential Transformer Displacement Sensors, Sulton Fayzullaevich Amirov, Absaid Khurramovich Sulliev, Shukhrat Azamatovich Sharapov

Chemical Technology, Control and Management

The article examines the magnetic circuits of both existing and developed differential transformer displacement sensors for large linear displacements. These circuits are characterized by a specific distribution structure of magnetic resistance parameters in long ferromagnetic cores and the magnetic capacitance between them. It is shown that in the existing sensor, the distribution of working magnetic flux along the length of the ferromagnetic cores has a nonlinear nature, resulting in a nonlinear relationship between the output signal in the form of electromotive force and the input linear displacement of the sensor. It has been established that by selecting the law of …

Synthesis Of Control Systems With Multilayer Neural Networks Based On Velocity Gradient Methods, Oxunjon Boborayimov, Okyay Kaynak

Chemical Technology, Control and Management

In this manuscripts, the synthesis of control systems with multilayer neural networks based on the speed gradient methods is given. For adjusting the weight coefficients of the base processor element, the gradient method of minimizing the learning criterion is used. A procedure for the synthesis of neural network control systems based on the velocity gradient methods has been developed. This guarantees the stabilization of the system under external limited disturbances that are inaccessible to direct measurement. Taking into account the state vector of the control object in the network learning function ensures the consistency of the processes of setting the …

Scanning Photoelectrochemical Microscopic Study In Photoinduced Electron Transfer Of Supramolecular Sensitizers-Tio2 Thin Films Systems, Sheng-Ya Zhang, Min Yao, Ze Wang, Tian-Jiao Liu, Rong-Fang Zhan, Hui-Qin Ye, Yan-Jun Feng, Xiao-Quan Lu

Journal of Electrochemistry

Crafting charge transfer channels at titanium dioxide (TiO₂) based photoanodes remain a pressing bottleneck in solar-to-chemical conversion technology. Despite the tremendous attempts, TiO₂ as the promising photoanode material still suffers from sluggish charge transport kinetics. Herein, we propose an assembly strategy that involves the axial coordination grafting metalloporphyrin-based photosensitizer molecules (MP) onto the surface-modified TiO₂ nanorods (NRs) photoanode, forming the composite MP/TiO₂ NRs photoelectrode. As expected, the resulted unique MP_B/TiO₂ NRs photoelectrode displays significantly improved photocurrent density as compared to TiO₂ NRs alone and MP_A/TiO₂ NRs photoelectrode. Scanning …

Deep Learning Enhancement And Privacy-Preserving Deep Learning: A Data-Centric Approach, Hung S. Nguyen

USF Tampa Graduate Theses and Dissertations

Deep Learning and its applications have become attractive to a lot of research recentlybecause of its capability to capture important information from large amounts of data. While most of the work focuses on finding the best model parameters, improving machine learning performance from data perspective still needs more attention. In this work, we propose techniques to enhance the robustness of deep learning classification by tackling data issue. Specifically, our data processing proposals aim to alleviate the impacts of class-imbalanced data and non- IID data in deep learning classification and federated learning scenarios. In addition, data pre-processing strategies such that dimensionality …

A Comprehensive Review Of Dc-Dc Converters For Ev Applications, Shayan Hosseinzad, Amin Mirzaei

Emirates Journal for Engineering Research

DC-DC converters in Electric vehicles (EVs) have the role of interfacing power sources to the DC-link and the DC-link to the required voltage levels for usage of different systems in EVs like DC drive, electric traction, entertainment, safety and etc. Improvement of gain and performance in these converters has a huge impact on the overall performance and future of EVs. So, different configurations have been suggested by many researches. In this paper, bidirectional DC-DC converters (BDCs) are divided into four categories as isolated-soft, isolated-hard, non-isolated-soft and non-isolated-hard depending on the isolation and type of switching. Moreover, the control strategies, comparative …

Optimal Estimation Inversion Of Ionospheric Electron Density From Gnss-Pod Limb Measurements: Part I-Algorithm And Morphology, Dong L. Wu, Nimalan Swarnalingam, Cornelius C. J. H. Salinas, Daniel J. Emmons, Tyler C. Summers, Robert Gardiner-Garden

Faculty Publications

GNSS-LEO radio links from Precise Orbital Determination (POD) and Radio Occultation (RO) antennas have been used increasingly in characterizing the global 3D distribution and variability of ionospheric electron density (Ne). In this study, we developed an optimal estimation (OE) method to retrieve Ne profiles from the slant total electron content (hTEC) measurements acquired by the GNSS-POD links at negative elevation angles (ε < 0°). Although both OE and onion-peeling (OP) methods use the Abel weighting function in the Ne inversion, they are significantly different in terms of performance in the lower ionosphere. The new OE results can overcome the large Ne oscillations, sometimes negative values, seen in the OP retrievals in the E-region ionosphere. In the companion paper in this Special Issue, the HmF2 and NmF2 from the OE retrieval are validated against ground-based ionosondes and radar observations, showing generally good agreements in NmF2 from all sites. Nighttime hmF2 measurements tend to agree better than the daytime when the ionosonde heights tend to be slightly lower. The OE algorithm has been applied to all GNSS-POD data acquired from the COSMIC-1 (2006–2019), COSMIC-2 (2019–present), and Spire (2019–present) constellations, showing a consistent ionospheric Ne morphology. The unprecedented spatiotemporal sampling of the ionosphere from these constellations now allows a detailed analysis of the frequency–wavenumber spectra for the Ne variability at different heights. In the lower ionosphere (~150 km), we found significant spectral power in DE1, DW6, DW4, SW5, and SE4 wave components, in addition to well-known DW1, SW2, and DE3 waves. In the upper ionosphere (~450 km), additional wave components are still present, including DE4, DW4, DW6, SE4, and SW4. The co-existence of eastward- and westward-propagating wave4 components implies the presence of a stationary wave4 (SPW4), as suggested by other earlier studies. Further improvements to the OE method are proposed, including a tomographic inversion technique that leverages the asymmetric sampling about the tangent point associated with GNSS-LEO links.

How Did The Landscape Of Student Belonging Shift During Covid-19?, Shruti Misra, Neha Kardam, Jennifer Vanantwerp, Denise Wilson

University Faculty Publications and Creative Works

The goal of this study is to understand if and how emergency remote teaching (ERT) used during the COVID-19 pandemic changed the ways in which instructional support and interactions were linked to belonging among engineering students. Belonging is a fundamental human motivation associated with a wide range of positive psychological, educational, social, and job outcomes. Frequent and predominantly conflict-free interactions within a stable, relational framework of caring are required to facilitate belonging. To better understand potential shifts in belonging that occurred from prepandemic to mid-pandemic, this study used survey data from a cross-sectional dataset at a single, large institution comprised …

Stochastic Worst-Case Test Vectors For Asic Devices In Single Event Environment, Mostafa Hemeda

Theses and Dissertations

Charged particles and energetic particles can impact the integrated circuit, referred to as single event effects (SEE). Nuclear reactors and space radiation can produce these particles. These effects can negatively affect the reliability and performance of electronics. When SEE occurs, a transient current is created, which can cause electronic devices to have incorrect outputs and ultimately fail. As a result, ensuring the reliability of ASIC circuits is a significant concern.

This thesis discusses the different fault types, then discuss the soft error and, in particular, the Single Event Transient (SET) and its causes and models. Then, this thesis proposes a …

Characterizing Controversiality Of Topics Utilizing Eccentricity Of Opinions, Sriniwas Pandey, Hiroki Sayama

Northeast Journal of Complex Systems (NEJCS)

Access to abundant biased information in echo chambers and social bubbles often intensifies opinions to the extremes. The extremization of opinions results in several topics becoming controversial. However, it is very difficult to measure the degree of controversiality of a topic objectively since the controversiality of any topic is subjective and perceived differently from different communities. The absence of an objective measure of controversiality has been a major hindrance in understanding the causes and effects of it. In this work we propose a method to quantify controversiality of a topic by utilizing eccentricity of opinions on that topic. The eccentricity …

Experimental Evaluation Of Smart Electric Meters’ Resilience Under Cyber Security Attacks, Harsh Kumar, Oscar A. Alvarez, Sanjeev Kumar

Electrical and Computer Engineering Faculty Publications

For the first time, commercial grade smart meters have been subjected to cyber security attacks to understand their operation and security resilience under different attack scenarios. Cyber security is a matter of top concern for utility companies installing smart meters for remote collection of power usage data from customer premises. Keeping power-usage data secure and to maintain system’s resiliency under cyber security attacks is very important. In Smart electric grids, the power usage data from smart meters are periodically reported to the utility company. Reporting and remote monitoring of power usage data requires the use of data network protocols, which …

Model-Driven Analysis Of Ecg Using Reinforcement Learning, Christian O'Reilly, Sai Durga Rithvik Oruganti, Deepa Tilwani, Jessica Bradshaw

Publications

Modeling is essential to better understand the generative mechanisms responsible for experimental observations gathered from complex systems. In this work, we are using such an approach to analyze the electrocardiogram (ECG). We present a systematic framework to decompose ECG signals into sums of overlapping lognormal components. We use reinforcement learning to train a deep neural network to estimate the modeling parameters from an ECG recorded in babies from 1 to 24 months of age. We demonstrate this model-driven approach by showing how the extracted parameters vary with age. From the 751,510 PQRST complexes modeled, 82.7% provided a signal-to-noise ratio that …

Adversary Aware Continual Learning, Muhammad Umer

Theses and Dissertations

Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In this dissertation, we have demonstrated that continual learning approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific class at test time. We then propose a novel defensive framework to counter …

Design Of Hybrid Inverters Using Wideband Gap Semiconductors For Microgrid Application, Luca Gacy

Electronic Theses and Dissertations

As the world becomes more reliant on renewable energy sources such as solar and wind power, the need for high efficiency high power inverters connected to homes is more relevant than ever. Connecting these renewable energy sources (RES) coupled with an energy storage system (ESS) to the grid through a hybrid inverter, with the highest efficiency and grid stability, is quickly becoming a necessity for the near future. This thesis explores the integration of wide band gap semiconductors for the power stage in these systems, along with the analysis of hybrid inverter topologies and structures. The goal of this thesis …

Tank Level Controller Plc Lab, Siddhi Upadhyaya, Teghvir Grewal

Electrical Engineering

The California Polytechnic State University San Luis Obispo’s Electrical Engineering Department is currently developing lab experiments for the new EE435 (Industrial Power Control and Automation) class. In order to support these efforts, fourth year Cal Poly students are expected to develop laboratory experiments that will be conducted during this new class for the semester system. The lab experiment focused on in this project is called the Tank Level Controller. This experiment will introduce EE 435 students to Schneider Electric Programmable Logic Controller (PLC) hardware and software, which is prominent in the automation industry.
This experiment will require students to develop …

Current Source Dc-Dc Converter For Undersea Fiber Optic Sensors, Richard Anthony Esplana Kwan, John Charles Rodinec, Andrew Armstrong

Electrical Engineering

Today, there are nearly 400 cable networks spanning roughly 750,000 miles to connect our world together. With thousands of miles of cable already lying on the ocean floor, with thousands more to come, many have recognized a unique opportunity in using this cable infrastructure as an attachment point for sensors to help study and monitor the ocean. Placing sensors onto a submarine cable is not a simple task; the sensors will require power that they receive from a transmission cable, from a battery, or from the submarine cable itself. Unfortunately, the existing power feed configuration for submarine cables typically only …