Computer Sciences Commons^™

Enhancing Project Based Learning With Unsupervised Learning Of Project Reflections, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Natural Language Processing (NLP) is an area of research and application that uses computers to analyze human text. It has seen wide adoption within several industries but few studies have investigated it for use in evaluating the effectiveness of educational interventions and pedagogies. Pedagogies such as Project based learning (PBL) centers on learners solving an authentic problem or challenge which leads to knowledge creation and higher engagement. PBL also lends itself well in plugging the gap between what is taught in classrooms and applying the knowledge gained to the real working environment. In this study, we seek to investigate how …

Quantum Computing For Supply Chain Finance, Paul R. Griffin, Ritesh Sampat

Research Collection School Of Computing and Information Systems

Applying quantum computing to real world applications to assess the potential efficacy is a daunting task for non-quantum specialists. This paper shows an implementation of two quantum optimization algorithms applied to portfolios of trade finance portfolios and compares the selections to those chosen by experienced underwriters and a classical optimizer. The method used is to map the financial risk and returns for a trade finance portfolio to an optimization function of a quantum algorithm developed in a Qiskit tutorial. The results show that whilst there is no advantage seen by using the quantum algorithms, the performance of the quantum algorithms …

A Learning And Optimization Framework For Collaborative Urban Delivery Problems With Alliances, Jingfeng Yang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

The emergence of e-Commerce imposes a tremendous strain on urban logistics which in turn raises concerns on environmental sustainability if not performed efficiently. While large logistics service providers (LSPs) can perform fulfillment sustainably as they operate extensive logistic networks, last-mile logistics are typically performed by small LSPs who need to form alliances to reduce delivery costs and improve efficiency, and to compete with large players. In this paper, we consider a multi-alliance multi-depot pickup and delivery problem with time windows (MAD-PDPTW) and formulate it as a mixed-integer programming (MIP) model. To cope with large-scale problem instances, we propose a two-stage …

Injecting Descriptive Meta-Information Into Pre-Trained Language Models With Hypernetworks, Wenying Duan, Xiaoxi He, Zimu Zhou, Hong Rao, Lothar Thiele

Research Collection School Of Computing and Information Systems

Pre-trained language models have been widely adopted as backbones in various natural language processing tasks. However, existing pre-trained language models ignore the descriptive meta-information in the text such as the distinction between the title and the mainbody, leading to over-weighted attention to insignificant text. In this paper, we propose a hypernetwork-based architecture to model the descriptive meta-information and integrate it into pre-trained language models. Evaluations on three natural language processing tasks show that our method notably improves the performance of pre-trained language models and achieves the state-of-the-art results on keyphrase extraction.

Exploring The Personality Of Virtual Tutors In Conversational Foreign Language Practice, Johanna Dobbriner, Cathy Ennis, Robert J. Ross

Conference papers

Fluid interaction between virtual agents and humans requires the understanding of many issues of conversational pragmatics. One such issue is the interaction between communication strategy and personality. As a step towards developing models of personality driven pragmatics policies, in this paper, we present our initial experiment to explore differences in user interaction with two contrasting avatar personalities. Each user saw a single personality in a video-call setting and gave feedback on the interaction. Our expectations, that a more extroverted outgoing positive personality would be a more successful tutor, were only partially confirmed. While this personality did induce longer conversations in …

Evaluation Of Wind Data Reliability By Using Logarithmic And Power Laws: A Case Study In Southern Iraq, Ahmed B. Khamees, Saif F. Yaseen, Khalid S. Heni, Mudar Ahmed Abdulsattar

Karbala International Journal of Modern Science

In this study, two sites were investigated in the southern region of Iraq: Ali AL-Gharbi and AL-Salman in Mesan and AL-Muthana provinces, respectively. A theoretical extrapolation between wind speed and height was carried out for both locations each month using the Logarithmic Law. Power Law was also applied to achieve calculations of wind shear coefficient (α) by using the actual data collected from the meteorological mast installed in each site at three levels of 10 m, 30 m, and 50 m, at an interval of ten minutes. To compare the effects of each law, two laws are employed.

Polystyrene Molecular Weight Determination Of Submicron Particles Shell, Airat Z. Sakhabutdinov, Safaa.M.R.H. Hussein, Alsu R. Ibragimova Ph.D., Vladimir Kuklin Ph.D., Maxim Petrovich Danilaev, L.Y. Zaharova

Karbala International Journal of Modern Science

The method of determination of the molecular weight of the polystyrene, which is formed as the shell on the surfaces of submicron aluminum oxide particles is considered in the paper. This method is based on the sedimentation of submicron particles, covered by polymer molecules, in a solvent for polystyrene. It is shown that the average polystyrene molecular weight is 39500±11250 amu, when the polymer shells on the surfaces of submicron particles (Al2O3) are formed by the vapor-phase method.

Adaptive Reconstruction Of The Heterogeneous Scan Line Etm+ Correction Technique, Heba Kh. Abbas, Salema S. Salman, Rash Awad Abtan, Anwar H. Al-Saleh, Ali A. Al-Zuky

Karbala International Journal of Modern Science

ETM+ is a land-imaging sensor with great and wide use in many fields, however, after May 2003, because of a technical defect in the sensor´s system scan line corrector SLC, it started giving images of earth containing black gap lines at a 22% rate. These gaps made the process of analyzing and extracting accurate information from these images difficult and complicated. Therefore, scientists have developed many techniques to remove the gap lines from all ETM+ band-images and complete the missing data. In this study, three different ETM+ time images with a 16-day interval between them were used to fill gap …

Two-Dimensional Quantitative Profiling Of Cell Morphology With Serous Effusion By Unsupervised Machine Learning Analysis, Safaa Al-Qaysi Ph.D., Ding Dai Md Ph.D., Heng Hong Md Ph.D., Yuhua Wen Ph.D., X.H. Hu Ph.D.

Karbala International Journal of Modern Science

Cytological evaluation of serous effusion specimens is an important part of cancer diagnosis. In this study we performed two-dimensional (2D) morphometric features and clustering analysis for development of useful techniques for identification and differentiation of malignant and begin cells in serous effusion specimens extracted from ten patients with clinical symptoms of pleural and peritoneal effusion. Our findings show that the two-dimensional (2D) morphometric features and clustering analysis are useful techniques for identification and differentiation of malignant and begin cells in serous effusion specimens, which can lead to development of new methods for rapid cells profiling in clinical application.

Stability-Delay Efficient Cluster-Based Routing Protocol For Vanet, Ahmed Jawad Kadhim Al-Shaibany Ph.D

Karbala International Journal of Modern Science

Vehicular Ad hoc Network (VANET) can be used in safety applications to transfer information about some events (e.g. accidents) with minimum time. Sending this information is achieved by using a routing algorithm. A large number of cluster-based routing schemes were presented for VANET. Unfortunately, the mobility of vehicles in unexpected directions negatively affects the performance of these schemes, destroys the network links, and decreases the routes' stability. This problem leads to repeat route discovery and maintenance operations and, as a result increases the overhead and delay. Thus, they are not an optimal selection for safety applications. Moreover, the cluster-based policies …

A New Chaotic Image Cryptosystem Based On Plaintext-Associated Mechanism And Integrated Confusion-Diffusion Operation, Ahmed Kareem Shibeeb, Mohammed Hussein Ahmed, Ahmed Hashim Mohammed

Karbala International Journal of Modern Science

In modern chaotic image cryptosystems, the initial values generated for the chaotic system are carried out based on the hash function or summation result of the image pixels. Also, the confusion-diffusion structure is often typically split into two different components. However, it decreases the cryptosystem security because the independent structure can be cryptanalysis separately. A practical chaotic image cryptosystem based on plaintext-associated mechanism and integrated confusion-diffusion operation has been developed in this research paper to enhance the encryption reliability. The initial values of the four-dimensional chaotic system are updated by using the pixel values and locations to increase the sensitivity …

Editorial Board

Karbala International Journal of Modern Science

No abstract provided.

An Empirical Study Of Thermal Attacks On Edge Platforms, Tyler Holmes

Symposium of Student Scholars

Cloud-edge systems are vulnerable to thermal attacks as the increased energy consumption may remain undetected, while occurring alongside normal, CPU-intensive applications. The purpose of our research is to study thermal effects on modern edge systems. We also analyze how performance is affected from the increased heat and identify preventative measures. We speculate that due to the technology being a recent innovation, research on cloud-edge devices and thermal attacks is scarce. Other research focuses on server systems rather than edge platforms. In our paper, we use a Raspberry Pi 4 and a CPU-intensive application to represent thermal attacks on cloud-edge systems. …

Molecular Vibrations Of Symmetric Molecules: Raman Scattering Driven Molecular Dynamics Method, Martina Kaledin, Dominick Pierre-Jacques, Ciara Tyler, Jason Dyke

Symposium of Student Scholars

This project focuses on developing a novel computational technique to study molecular vibrations through infrared (IR) and Raman scattering Driven Molecular Dynamics (DMD) method. While the main criterion for IR absorption is a net change in the dipole moment in a molecule as it vibrates, presently we wish to predict and analyze vibrational spectra to study symmetric vibrational modes that are IR inactive or weakly active while strongly Raman active. A newly developed method was tested on CO₂, H₂O, CH₄, and C₂₀ molecules. Students optimized the molecular structures, obtained vibrational frequencies, and IR …

Learning Environment Containerization Of Machine Learning For Cybersecurity, Hao Zhang

Symposium of Student Scholars

Machine learning plays a critical role in detecting and preventing in the field of cybersecurity. However, many students have difficulties on configuring the appropriate coding environment and retrieving datasets on their own computers, which, to some extent, wastes valuable time for learning core contents of machine learning and cybersecurity. In this paper, we propose an approach with learning environment containerization of machine learning algorithm and dataset. This will help students focus more on learning contents and have valuable hand-on experience through Docker container and get rid of the trouble of configuration coding environment and retrieve dataset. This paper provides an …

Spam Email Detection: Comparison Between Naïve Bayes And Neural Network, Zhuolin Li

Symposium of Student Scholars

Classification is an important technique to deal with cybersecurity threats. In this paper, we detect spam emails from publicly available dataset using Naive Bayes and Neural Network (NN). The results from experiments show that for data sets with more balanced for classification, the accuracy of Naive Bayes is better than NN

Finding Similar Stocks By Detecting Cliques In Market Graphs, Sudhashree Sayenju

Symposium of Student Scholars

The stock market provides an abundant source of data. However, when the amount of raw data becomes overwhelming it grows increasingly difficult to know how the stocks interact with each other. Stock data visualization as a market graph serves as one of the most popular way of summarizing important information. When modelling the data as a graph, vertices correspond to stocks and edges correspond to strong correlation in their pricing in a certain period of time. This project presents a technique to find stocks that behave very similarly. Such information helps investors make decisions on which stocks to purchase next. …

Probing Structure And Energetics Of Proton-Bound Complexes N2…Hco+ And N2h+…Oc Using Computational Chemistry Methods, Antonio Barrios, Dalton Boutwell, Onyi Okere, Monique Olocha, Oluwaseun Omodemi, Alexander Toledo, Antonio Barrios

Symposium of Student Scholars

N₂…HCO⁺ and N₂H⁺…OC are predicted to exist in interstellar clouds. These complexes involve HCO⁺ and N₂H⁺ fragments that are bound to N₂ and CO, respectively using hydrogen-bonded interaction. The reason these molecules are important is that the existence of nitrogen can be measured indirectly through ion-molecular complexes studied in this work. The measured vibrational spectra of molecules is an excellent way to characterize and detect molecules. We used B3LYP, MP2, and CCSD(T) computational methods to predict the structure and vibrational frequencies of N₂…HCO⁺ and N …

Theoretical Study On The Isomerization And Detection Of N2h+…Oc Complex In Interstellar Clouds, Dalton Boutwell, Martina Kaledin

Symposium of Student Scholars

In this study, we characterize N₂H⁺…OC linear complex using Driven Molecular Dynamics (DMD) and Vibrational Self-Consistent Field Theory (VSCF) methods due to its relevance in astrochemistry. A central challenge is the detection of the molecular complex in interstellar media (ISM). Computational chemistry approaches can predict vibrational spectra, hence facilitate prediction of its existence and stability in the ISM. N₂H⁺…OC involves the proton transfer process via hydrogen bonding interaction. Proton motion is highly anharmonic, therefore facing a significant challenge to characterize it accurately. Quantum mechanical variational methods are popular among many theoretical chemists …

Energy Saving On Edges: State-Of-The-Art And Future Directions, Kousalya Banka

Symposium of Student Scholars

Internet of Things (IoT) comprises a set of devices that are interconnected ranging from our daily used objects to advanced networked devices. It is a constantly evolving phenomenon as the number of devices owned by the regular user is increasing at a rapid rate. These devices are used for various reasons such as social networking, monitoring, performing complex operations and with the increase of advanced technologies, they demand more energy to perform such tasks. Cloud computing enables these communications to seamlessly perform complex tasks in a cloud environment but utilizing these resources properly to perform at the best is the …

On Non-Linear Network Embedding Methods, Huong Yen Le

Dissertations

As a linear method, spectral clustering is the only network embedding algorithm that offers both a provably fast computation and an advanced theoretical understanding. The accuracy of spectral clustering depends on the Cheeger ratio defined as the ratio between the graph conductance and the 2nd smallest eigenvalue of its normalizedLaplacian. In several graph families whose Cheeger ratio reaches its upper bound of Theta(n), the approximation power of spectral clustering is proven to perform poorly. Moreover, recent non-linear network embedding methods have surpassed spectral clustering by state-of-the-art performance with little to no theoretical understanding to back them.

The dissertation includes work …

Exploring, Understanding, Then Designing: Twitter Users’ Sharing Behavior For Minor Safety Incidents, Mashael Yousef Almoqbel

Dissertations

Social media has become an integral part of human lives. Social media users resort to these platforms for various reasons. Users of these platforms spend a lot of time creating, reading, and sharing content, therefore, providing a wealth of available information for everyone to use. The research community has taken advantage of this and produced many publications that allow us to better understand human behavior. An important subject that is sometimes discussed and shared on social media is public safety. In the past, Twitter users have used the platform to share incidents, share information about incidents, victims and perpetrators, and …

Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue

Dissertations

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …

Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie

Dissertations

This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.

In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.

In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …

Data-Driven Learning For Robot Physical Intelligence, Leidi Zhao

Dissertations

The physical intelligence, which emphasizes physical capabilities such as dexterous manipulation and dynamic mobility, is essential for robots to physically coexist with humans. Much research on robot physical intelligence has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this dissertation, a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation is proposed. This method tackles …

Participatory Learning: Measuring Learning And Educational Technology Acceptance, Erick Sanchez Suasnabar

Dissertations

Participatory Learning (PL) integrates several learning approaches, engaging students throughout the entire assignment process for both online and face-to-face courses. Beyond simply providing a solution, students also craft a problem (problem-based learning), grade each other (peer assessment and feedback), evaluate themselves (self-assessment), and can view others’ work (learning by example). This dissertation research explores the resulting learning effects. Contributions to both educational and Information Systems research include extending an early PL model and experiments that applied the PL approach to examinations, by validating and testing new constructs based on user activity and critical thinking. In addition, the study explores a …

Designing Collaborative Lifelogging To Facilitate Learning In Collaborative Physical-Recreation Communities, Sayed Mousa Ahmadi Olounabadi

Dissertations

Since the 1940s, researchers have envisioned lifelogging as the systematic capture and utilization of lived experiences for augmenting learning, performance, and community Unfortunately, this vision was never actualized since few, if any, systems support lifelogging in the term's original sense. Technologies that emerged through the Quantified-Self (QS) movement allowed users to monitor and track almost every life aspect. However, the decontextualized self-tracking data QS systems produced are unsuitable for supporting learning and community engagement, and therefore have not made lifelogging a reality yet. Central to this dissertation is understanding how to augment learning and community through lifelogging. This is particularly …

Reserve Price Optimization In Display Advertising, Achir Kalra

Dissertations

Display advertising is the main type of online advertising, and it comes in the form of banner ads and rich media on publishers' websites. Publishers sell ad impressions, where an impression is one display of an ad in a web page. A common way to sell ad impressions is through real-time bidding (RTB). In 2019, advertisers in the United States spent nearly 60 billion U.S. dollars on programmatic digital display advertising. By 2022, expenditures are expected to increase to nearly 95 billion U.S. dollars. In general, the remaining impressions are sold directly by the publishers. The only way for publishers …

Advances In Deep Learning With Applications To Computer Vision And Astronomy, Zhihang Hu

Dissertations

Deep Learning has spanned a variety of applications in computer vision as well as computational astronomy. These two aspects obtained similar data structure, therefore, their solutions can be transferable between each other. This dissertation look into two video-related tasks in computer vision and propose a novel problem in computational astronomy.

Specifically, acquiring an in-depth understanding of videos has been a cornerstone problem in computer vision. This problem has been studied by various researchers from different perspectives, among which video prediction has attracted much attention. Video prediction aims to generate the pixels of future frames given a sequence of context frames. …

Novel Statistical Modeling Methods For Traffic Video Analysis, Hang Shi

Dissertations

Video analysis is an active and rapidly expanding research area in computer vision and artificial intelligence due to its broad applications in modern society. Many methods have been proposed to analyze the videos, but many challenging factors remain untackled. In this dissertation, four statistical modeling methods are proposed to address some challenging traffic video analysis problems under adverse illumination and weather conditions.

First, a new foreground detection method is presented to detect the foreground objects in videos. A novel Global Foreground Modeling (GFM) method, which estimates a global probability density function for the foreground and applies the Bayes decision rule …