Physical Sciences and Mathematics Commons^™

An Empirical Study On Data Distribution-Aware Test Selection For Deep Learning Enhancement, Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Lei Ma, Mike Papadakis, Yves Le Traon

Research Collection School Of Computing and Information Systems

Similar to traditional software that is constantly under evolution, deep neural networks need to evolve upon the rapid growth of test data for continuous enhancement (e.g., adapting to distribution shift in a new environment for deployment). However, it is labor intensive to manually label all of the collected test data. Test selection solves this problem by strategically choosing a small set to label. Via retraining with the selected set, deep neural networks will achieve competitive accuracy. Unfortunately, existing selection metrics involve three main limitations: (1) using different retraining processes, (2) ignoring data distribution shifts, and (3) being insufficiently evaluated. To …

Ai-Enabled Adaptive Learning Using Automated Topic Alignment And Doubt Detection, Kar Way Tan, Siaw Ling Lo, Eng Lieh Ouh, Wei Leng Neo

Research Collection School Of Computing and Information Systems

Implementing adaptive learning is often a challenging task at higher learning institutions where the students come from diverse backgrounds and disciplines. In this work, we collected informal learning journals from learners. Using the journals, we trained two machine learning models, an automated topic alignment and a doubt detection model to identify areas of adjustment required for teaching and students who require additional attention. The models form the baseline for a quiz recommender tool to dynamically generate personalized quizzes for each learner as practices to reinforce learning. Our pilot deployment of our AI-enabled Adaptive Learning System showed that our approach delivers …

Structured And Natural Responses Co-Generation For Conversational Search, Chenchen Ye, Lizi Liao, Fuli Feng, Wei Ji, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Generating fluent and informative natural responses while maintaining representative internal states for search optimization is critical for conversational search systems. Existing approaches either 1) predict structured dialog acts first and then generate natural response; or 2) map conversation context to natural responses directly in an end-to-end manner. Both kinds of approaches have shortcomings. The former suffers from error accumulation while the semantic associations between structured acts and natural responses are confined in single direction. The latter emphasizes generating natural responses but fails to predict structured acts. Therefore, we propose a neural co-generation model that generates the two concurrently. The key …

Reflection As An Agile Course Evaluation Tool, Siaw Ling Lo, Pei Hua Cher, Fernando Bello

Research Collection School Of Computing and Information Systems

Reflection is often used as a tool to analyse student learning, be it for internalizing of acquired knowledge or as a form of seeking help through expression of doubts or misconceptions. However, it can be a challenge to extract relevant information from the free-form reflection text. Often times the workload of manually analyzing the reflection text can be a form of deterrence instead of providing insights in the course delivery for instructors, let alone improving the learning experience. In this paper, we review the current usage of reflection and propose an automated reflection framework, together with an end-to-end analysis of …

A3gan: Attribute-Aware Anonymization Networks For Face De-Identification, Liming Zhai, Qing Guo, Xiaofei Xie, Lei Ma, Yi Estelle Wang, Yang Liu

Research Collection School Of Computing and Information Systems

Face de-identification (De-ID) removes face identity information in face images to avoid personal privacy leakage. Existing face De-ID breaks the raw identity by cutting out the face regions and recovering the corrupted regions via deep generators, which inevitably affect the generation quality and cannot control generation results according to subsequent intelligent tasks (e.g., facial expression recognition). In this work, for the first attempt, we think the face De-ID from the perspective of attribute editing and propose an attribute-aware anonymization network (A3GAN) by formulating face De-ID as a joint task of semantic suppression and controllable attribute injection. Intuitively, the semantic suppression …

Cosm2ic: Optimizing Real-Time Multi-Modal Instruction Comprehension, Weerakoon Mudiyanselage Dulanga Kaveesha Weerakoon, Vigneshwaran Subbaraju, Minh Anh Tuan Tran, Archan Misra

Research Collection School Of Computing and Information Systems

Supporting real-time, on-device execution of multi-modal referring instruction comprehension models is an important challenge to be tackled in embodied Human-Robot Interaction. However, state-of-the-art deep learning models are resource-intensive and unsuitable for real-time execution on embedded devices. While model compression can achieve a reduction in computational resources up to a certain point, further optimizations result in a severe drop in accuracy. To minimize this loss in accuracy, we propose the COSM2IC framework, with a lightweight Task Complexity Predictor, that uses multiple sensor inputs to assess the instructional complexity and thereby dynamically switch between a set of models of varying computational intensity …

Using Constraint Programming And Graph Representation Learning For Generating Interpretable Cloud Security Policies, Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar

Research Collection School Of Computing and Information Systems

Modern software systems rely on mining insights from business sensitive data stored in public clouds. A data breach usually incurs signifcant (monetary) loss for a commercial organization. Conceptually, cloud security heavily relies on Identity Access Management (IAM) policies that IT admins need to properly confgure and periodically update. Security negligence and human errors often lead to misconfguring IAM policies which may open a backdoor for attackers. To address these challenges, frst, we develop a novel framework that encodes generating optimal IAM policies using constraint programming (CP). We identify reducing dormant permissions of cloud users as an optimality criterion, which intuitively …

Techniques To Enhance A Qubo Solver For Permutation-Based Combinatorial Optimization, Siong Thye Goh, Jianyuan Bo, Sabrish Gopalakrishnan, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Many combinatorial optimization problems can be formulated as a problem to determine the order of sequence or to find a corresponding mapping of the objects. We call such problems permutation-based optimization problems. Many such problems can be formulated as a quadratic unconstrained binary optimization (QUBO) or Ising model by introducing a penalty coefficient to the permutation constraint terms. While classical and quantum annealing approaches have been proposed to solve QUBOs to date, they face issues with optimality and feasibility. Here we treat a given QUBO solver as a black box and propose techniques to enhance its performance. First, to ensure …

A Mean-Field Markov Decision Process Model For Spatial Temporal Subsidies In Ride-Sourcing Markets, Zheng Zhu, Jintao Ke, Hai Wang

Research Collection School Of Computing and Information Systems

Ride-sourcing services are increasingly popular because of their ability to accommodate on-demand travel needs. A critical issue faced by ride-sourcing platforms is the supply-demand imbalance, as a result of which drivers may spend substantial time on idle cruising and picking up remote passengers. Some platforms attempt to mitigate the imbalance by providing relocation guidance for idle drivers who may have their own self-relocation strategies and decline to follow the suggestions. Platforms then seek to induce drivers to system-desirable locations by offering them subsidies. This paper proposes a mean-field Markov decision process (MF-MDP) model to depict the dynamics in ride-sourcing markets …

Actor-Critic Reinforcement Learning For Bidding In Bilateral Negotiation, Furkan Arslan, Reyhan Aydoğan

Turkish Journal of Electrical Engineering and Computer Sciences

Designing an effective and intelligent bidding strategy is one of the most compelling research challenges in automated negotiation, where software agents negotiate with each other to find a mutual agreement when there is a conflict of interests. Instead of designing a hand-crafted decision-making module, this work proposes a novel bidding strategy adopting an actor-critic reinforcement learning approach, which learns what to offer in a bilateral negotiation. An entropy reinforcement learning framework called Soft Actor-Critic (SAC) is applied to the bidding problem, and a self-play approach is employed to train the model. Our model learns to produce the target utility of …

A Novel Hybrid Algorithm For Morphological Analysis: Artificial Neural-Net-Xmor, Ayla Kayabaş, Ahmet Ercan Topcu, Özkan Kiliç

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we present a novel algorithm that combines a rule-based approach and an artificial neural network-based approach in morphological analysis. The usage of hybrid models including both techniques is evaluated for performance improvements. The proposed hybrid algorithm is based on the idea of the dynamic generation of an artificial neural network according to two-level phonological rules. In this study, the combination of linguistic parsing, a neural network-based error correction model, and statistical filtering is utilized to increase the coverage of pure morphological analysis. We experimented hybrid algorithm applying rule-based and long short-term memory-based (LSTM-based) techniques, and the results …

Content Loss And Conditional Space Relationship In Conditional Generative Adversarial Networks, Enes Eken

Turkish Journal of Electrical Engineering and Computer Sciences

In the machine learning community, generative models, especially generative adversarial networks (GANs) continue to be an attractive yet challenging research topic. Right after the invention of GAN, many GAN models have been proposed by the researchers with the same goal: creating better images. The first and foremost feature that a GAN model should have is that creating realistic images that cannot be distinguished from genuine ones. A large portion of the GAN models proposed to this end have a common approach which can be defined as factoring the image generation process into multiple states for decomposing the difficult task into …

Using A Static Naming Approach To Implement Remote Scope Promotion, Ayşe Yilmazer

Turkish Journal of Electrical Engineering and Computer Sciences

GPUs employ simple coherence mechanisms and require explicit use of costly synchronization operations for data integrity. Local-scoped synchronization can be utilized to lower the performance penalty of synchronization when sharing is within a subgroup of threads. Unfortunately, in asymmetric sharing (which is an important dynamic sharing pattern), it is necessary to use global-scoped synchronization due to possible accesses by remote sharers. Remote Scope Promotion (RSP) was introduced to take advantage of local-scoped synchronization at regular accesses while using scope promotion at occasional remote accesses. First implementation of RSP makes use of a simple approach that performs costly cache operations on …

Development Of A Hybrid System Based On Abc Algorithm For Selection Of Appropriate Parameters For Disease Diagnosis From Ecg Signals, Ersi̇n Ersoy, Gazi̇ Erkan Bostanci, Mehmet Serdar Güzel

Turkish Journal of Electrical Engineering and Computer Sciences

The number of people who die due to cardiovascular diseases is quite high. In our study, ECG (electrocar-diogram) signals were divided into segments and waves based on temporal boundaries. Signal similarity methods such as convolution, correlation, covariance, signal peak to noise ratio (PNRS), structural similarity index (SSIM), one of the basic statistical parameters, arithmetic mean and entropy were applied to each of these sections. In addition, a square error-based new approach was applied and the difference of the signs from the mean sign was taken and used as a feature vector. The obtained feature vectors are used in the artificial …

Automatic Keyword Assignment System For Medical Research Articles Using Nearest-Neighbor Searches, Fati̇h Di̇lmaç, Adi̇l Alpkoçak

Turkish Journal of Electrical Engineering and Computer Sciences

Assigning accurate keywords to research articles is increasingly important concern. Keywords should be selected meticulously to describe the article well since keywords play an important role in matching readers with research articles in order to reach a bigger audience. So, improper selection of keywords may result in less attraction to readers which results in degradation in its audience. Hence, we designed and developed an automatic keyword assignment system (AKAS) for research articles based on k-nearest neighbor (k-NN) and threshold-nearest neighbor (t-NN) accompanied with information retrieval systems (IRS), which is a corpus-based method by utilizing IRS using the Medline dataset in …

Analysis Of Tissue Electrical Properties On Bio-Impedance Variation Of Upper Limps, Enver Salkim

Turkish Journal of Electrical Engineering and Computer Sciences

Upper limb loss has a significant impact on individual socioeconomic life. Human-machine interface (HMI) using surface electromyography (sEMG) establishes a link between the user and a hand prosthesis to recognize hand gestures and motions which allows the control of robotic machines and prostheses to perform dexterous tasks. Numerous methods aimed to enhance hand gesture and motion recognition toward an HMI. Bio-impedance analysis (BIA) is a noninvasive way of assessing body compositions and has been recently used for hand motion interpretation using `brute force? pattern recognition. The impedance variation in the body mostly depends on the precise stimulation using appropriate electrical …

Degree-Based Random Walk Approach For Graph Embedding, Sarmad N. Mohammed, Semra Gündüç

Turkish Journal of Electrical Engineering and Computer Sciences

Graph embedding, representing local and global neighbourhood information by numerical vectors, is a crucial part of the mathematical modeling of a wide range of real-world systems. Among the embedding algorithms, random walk-based algorithms have proven to be very successful. These algorithms collect information by creating numerous random walks with a predefined number of steps. Creating random walks is the most demanding part of the embedding process. The computation demand increases with the size of the network. Moreover, for real-world networks, considering all nodes on the same footing, the abundance of low-degree nodes creates an imbalanced data problem. In this work, …

Generating Ad Creatives Using Deep Learning For Search Advertising, Kevser Nur Çoğalmiş, Ahmet Bulut

Turkish Journal of Electrical Engineering and Computer Sciences

We generated advertisement creatives programmatically using deep neural networks. A landing page contains relevant text data, which can be used for generating advertisement creatives, i.e. ads. We treated the ad generation task as a text summarization problem and built a sequence to sequence model. In order to assess the validity of our approach, we conducted experiments on four datasets. Our empirical results showed that our model generated relevant ads on a template-based dataset with moderate hyperparameters. Training the model with more content increased the performance of the model, which we attributed to rigorous hyperparameter tune-up. The choice of word embedding …

Learning Term Weights By Overfitting Pairwise Ranking Loss, Ömer Şahi̇n, İlyas Çi̇çekli̇, Gönenç Ercan

Turkish Journal of Electrical Engineering and Computer Sciences

A search engine strikes a balance between effectiveness and efficiency to retrieve the best documents in a scalable way. Recent deep learning-based ranker methods are proving to be effective and improving the state-of-the-art in relevancy metrics. However, as opposed to index-based retrieval methods, neural rankers like bidirectional encoder representations from transformers (BERT) do not scale to large datasets. In this article, we propose a query term weighting method that can be used with a standard inverted index without modifying it. Query term weights are learned using relevant and irrelevant document pairs for each query, using a pairwise ranking loss. The …

Prediction Of Broken Rotor Bar In Induction Motor Using Spectral Entropy Features And Tlbo Optimized Svm, Sudip Halder, Sunil Bhat, Bimal Dora

Turkish Journal of Electrical Engineering and Computer Sciences

The information of the fault frequency characteristics is of great importance for all associated fault diag nostics. This requires a high-resolution spectrum analysis to achieve efficient monitoring of machinery faults, especially while diagnosing rotor bar breakage under light load conditions, because the fault frequencies almost overlap with the fundamental. In this context, rather than looking for frequencies associated with rotor faults, several frequency bands are observed separately in terms of the entropy contained within these bands. First, the motor current signal has been divided into several frequency bands using the continuous wavelet transform (CWT), and the spectral entropy is calculated …

A Deep Learning Based System For Real-Time Detection And Sorting Of Earthworm Cocoons, Ali̇ Çeli̇k, Si̇nan Uğuz

Turkish Journal of Electrical Engineering and Computer Sciences

Vermicompost, created by earthworms after eating and digesting organic waste, plays an important role as an organic fertiliser in sustainable agriculture. In this study, a deep learning-based smart system was developed to separate earthworm cocoons used in the production of vermicompost from the compost and return it to production. In the first stage of the study, a dataset containing 1000 images of cocoons was created. The cocoons in each image were labeled and training was performed using a deep learning architecture, one-stage and two-stage models. The models were trained over 2000 epochs with a learning rate of 0.01. From the …

The Potential Of Citizen Science Data To Complement Satellite And Airborne Lidar Tree Height Measurements: Lessons From The Globe Program, Josh Enterkine, Brian A. Campbell, Holli Kohl, Nancy F. Glenn, Kristen Weaver, David Overoye, Deanna Danke

Geosciences Faculty Publications and Presentations

The Global Learning and Observations to Benefit the Environment (GLOBE) Program is an international science, citizen science, and education program through which volunteers in participating countries collect environmental data in support of Earth system science. Using the program's software application, GLOBE Observer (GO), volunteers measure tree height and optional tree circumference, which may support the interpretation of NASA and other space-based satellite data such as tree height data from the Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) and Global Ecosystem Dynamics Investigation instrument. This paper describes tree heights data collected through the GO application and identifies sources of error in …

Efficiency In The Upper Deschutes Basin: Understanding The Hydrosocial Implications Of Irrigation Canal Piping, Rebecca Anderson

Dissertations and Theses

In response to water scarcity, irrigation efficiency projects aim to conserve water for in-stream flow and agricultural use. Piping irrigation canals is a common irrigation efficiency method which reduces the loss of incidental recharge, resulting in trade-offs within a hydrosocial system. Few studies have focused on the consequences of canal piping and none have integrated a critical analysis of the social factors involved in deciding what constitutes 'efficient' water use. This study seeks to fill this gap by combining natural and social science to give attention to the scales and perspectives involved in irrigation efficiency canal piping and the material …

Precision Determination Of The Neutral Weak Form Factor Of ^48ca, D. Adhikari, (...), David S. Armstrong, Et Al.

Arts & Sciences Articles

We report a precise measurement of the parity-violating (PV) asymmetry APV in the elastic scattering of longitudinally polarized electrons from 48Ca. We measure APV=2668±106(stat)±40(syst) parts per billion, leading to an extraction of the neutral weak form factor FW(q=0.8733  fm−1)=0.1304±0.0052(stat)±0.0020(syst) and the charge minus the weak form factor Fch−FW=0.0277±0.0055. The resulting neutron skin thickness Rn−Rp=0.121±0.026(exp)±0.024(model)  fm is relatively thin yet consistent with many model calculations. The combined CREX and PREX results will have implications for future energy density functional calculations and on the density dependence of the symmetry energy of nuclear matter.

Population Genetics Of Transposable Element Load: A Mechanistic Account Of Observed Overdispersion, Gregory Conradi Smith, Ron D. Smith, Joshua Puzey

Arts & Sciences Articles

In an empirical analysis of transposable element (TE) abundance within natural populations of Mimulus guttatus and Drosophila melanogaster, we found a surprisingly high variance of TE count (e.g., variance-to-mean ratio on the order of 10 to 300). To obtain insight regarding the evolutionary genetic mechanisms that underlie the overdispersed population distributions of TE abundance, we developed a mathematical model of TE population genetics that includes the dynamics of element proliferation and purifying selection on TE load. The modeling approach begins with a master equation for a birth-death process and extends the predictions of the classical theory of TE dynamics in …

Complex Functional Joint Models For Longitudinal Electronic Health Record, Siyuan Guo

Theses and Dissertations

Longitudinal measurements are important components in electronic health record (EHR) data. In practice, using longitudinal EHR history is expected to improve the estimation or prediction performance when studying some outcomes of interest, such as binary outcome or time to event outcome. However, the longitudinal observations in EHR data is complex due to irregular and sparse EHR visits. Therefore, modelling longitudinal data and further incorporating them with different types of outcomes is challenge. In this dissertation, we aim to develop methodology to first, describe the pattern of the longitudinal predictors with continuous or binary observations, and second, model the longitudinal predictors …

Cybersecurity Of Critical Infrastructures: Challenges And Solutions, Leandros Maglaras, Helge Janicke, Mohamed Amine Ferrag

Research outputs 2022 to 2026

People’s lives are becoming more and more dependent on information and computer technology. This is accomplished by the enormous benefits that the ICT offers for everyday life. Digital technology creates an avenue for communication and networking, which is characterized by the exchange of data, some of which are considered sensitive or private. There have been many reports recently of data being hijacked or leaked, often for malicious purposes. Maintaining security and privacy of information and systems has become a herculean task. It is therefore imperative to understand how an individual’s or organization’s personal data can be protected. Moreover, critical infrastructures …

Adversarial Activity Detection And Prediction Using Behavioral Biometrics, Amin Fallahi

Dissertations - ALL

Behavioral biometrics can be used in different security applications like authentication, identification, etc. One of the trending applications is predicting future activities of people and guessing whether they will engage in malicious activities in the future. In this research, we study the possibility of predicting future activities and propose novel methods for near-future activity prediction.

First, we study gait signals captured using smartphone accelerometer sensor and build a model to predict a future gait signal. Activity recognition using body movements captured from mobile phone sensors has been a major point of interest in recent research. Data that is being continuously …

Evaluation Of The Energetic Factors In Crystalline Pharmaceuticals Using Solid-State Density Functional Theory And Low-Frequency Vibrational Spectroscopy, Margaret P. Davis

Dissertations - ALL

Due to the importance of maintaining stable and effective pharmaceutical solid doses, it is critical to study the variety of solid forms that active pharmaceutical ingredients can adopt including polymorphs, hydrates, and cocrystals. In this work, low-frequency vibrational spectroscopies and rigorous quantum mechanical simulations are combined to provide a new technique for characterizing and investigating pharmaceutically relevant polymorphs, hydrates, and cocrystals as well as a series of model cocrystals. Low-frequency spectra in the sub-200 cm-1 range provide not only unique and characteristic spectra for all of the systems explored here but, along with X-ray structural parameters, they offer a way …

Campus Nature Rx: How Investing In Nature Interventions Benefits College Students, Donald A. Rakow, Dorothy C. Ibes

Arts & Sciences Articles

Excerpt from article: "The college experience is a time of discovery, learning, and personal growth. However, many U.S. college students report unprecedentedly high levels of mental health problems during these formative years. According to the 2021 National Collegiate Health Assessment, over 30 percent of students received psychological or mental health services in the previous 12 months..."