Digital Commons Network^™

Prediction Of Brain Metastases Development In Patients With Lung Cancer By Explainable Artificial Intelligence From Electronic Health Records, Degui Zhi, Ping Zhu, Antonio Dono, Xiaoqian Jiang, Hua Xu, Yoshua Esquenazi, W Jim Zheng

Faculty, Staff and Student Publications

PURPOSE: Early detection of brain metastases (BMs) is critical for prompt treatment and optimal control of the disease. In this study, we seek to predict the risk of developing BM among patients diagnosed with lung cancer on the basis of electronic health record (EHR) data and to understand what factors are important for the model to predict BM development through explainable artificial intelligence approaches accurately.

MATERIALS AND METHODS: We trained a recurrent neural network model, REverse Time AttentIoN (RETAIN), to predict the risk of developing BM using structured EHR data. To interpret the model's decision process, we analyzed the attention …

Interconnectedness And Financial Stability In The Era Of Artificial Intelligence, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

This chapter explains AI use cases may amplify some threats to the stability of the financial system. It argues that lack of a consistent approach to AI Governance by financial regulators and limited oversight on some AI models in terms of systemic risks need to be addressed to preserve the stability of the financial system. To illustrate the problem and propose specific policy recommendations, the chapter first explains how the widespread use AI in finance impacts systemic risk in the financial sector. Then, it explains why trustworthiness of AI encompasses not only the typical ethical principles about transparency, explainability, fairness, …

Informational Content Of Factor Structures In Simultaneous Discrete Response Models, Shakeeb Khan, Arnaud Maurel, Yichong Zhang

Research Collection School Of Economics

We study the informational content of factor structures in discrete triangular systems. Factor structures have been employed in a variety of settings in cross sectional and panel data models, and in this paper we attempt to formally quantify their informational content in a bivariate system often employed in the treatment effects literature. Our main findings are that under the factor structures often imposed in the literature, point identification of parameters of interest, such as both the treatment effect and the factor load, is attainable under weaker assumptions than usually required in these systems. For example, we show is that an …

A Multi-Species Simulation Of Mosquito Disease Vector Development In Temperate Australian Tidal Wetlands Using Publicly Available Data, Kerry Staples, Steven Richardson, Peter J. Neville, Jacques Oosthuizen

Research outputs 2022 to 2026

Worldwide, mosquito monitoring and control programs consume large amounts of resources in the effort to minimise mosquito-borne disease incidence. On-site larval monitoring is highly effective but time consuming. A number of mechanistic models of mosquito development have been developed to reduce the reliance on larval monitoring, but none for Ross River virus, the most commonly occurring mosquito-borne disease in Australia. This research modifies existing mechanistic models for malaria vectors and applies it to a wetland field site in Southwest, Western Australia. Environmental monitoring data were applied to an enzyme kinetic model of larval mosquito development to simulate timing of adult …

Developing Resilient Cyber-Physical Systems: A Review Of State-Of-The-Art Malware Detection Approaches, Gaps, And Future Directions, M. Imran Malik, Ahmed Ibrahim, Peter Hannay, Leslie F. Sikos

Research outputs 2022 to 2026

Cyber-physical systems (CPSes) are rapidly evolving in critical infrastructure (CI) domains such as smart grid, healthcare, the military, and telecommunication. These systems are continually threatened by malicious software (malware) attacks by adversaries due to their improvised tactics and attack methods. A minor configuration change in a CPS through malware has devastating effects, which the world has seen in Stuxnet, BlackEnergy, Industroyer, and Triton. This paper is a comprehensive review of malware analysis practices currently being used and their limitations and efficacy in securing CPSes. Using well-known real-world incidents, we have covered the significant impacts when a CPS is compromised. In …

Machine Learning Methods For Inferring The Number Of Uav Emitters Via Massive Mimo Receive Array, Yifan Li, Feng Shu, Jinsong Hu, Shihao Yan, Haiwei Song, Weiqiang Zhu, Da Tian, Yaoliang Song, Jiangzhou Wang

Research outputs 2022 to 2026

To provide important prior knowledge for the direction of arrival (DOA) estimation of UAV emitters in future wireless networks, we present a complete DOA preprocessing system for inferring the number of emitters via a massive multiple-input multiple-output (MIMO) receive array. Firstly, in order to eliminate the noise signals, two high-precision signal detectors, the square root of the maximum eigenvalue times the minimum eigenvalue (SR-MME) and the geometric mean (GM), are proposed. Compared to other detectors, SR-MME and GM can achieve a high detection probability while maintaining extremely low false alarm probability. Secondly, if the existence of emitters is determined by …

Regulating Artificial Intelligence In International Investment Law, Mark Mclaughlin

Research Collection Yong Pung How School Of Law

The interaction between artificial intelligence (AI) and international investment treaties is an uncharted territory of international law. Concerns over the national security, safety, and privacy implications of AI are spurring regulators into action around the world. States have imposed restrictions on data transfer, utilised automated decision-making, mandated algorithmic transparency, and limited market access. This article explores the interaction between AI regulation and standards of investment protection. It is argued that the current framework provides an unpredictable legal environment in which to adjudicate the contested norms and ethics of AI. Treaties should be recalibrated to reinforce their anti-protectionist origins, embed human-centric …

Insights Into Accuracy Of Social Scientists' Forecasts Of Societal Change, Igor Grossma, Andree Hartanto, Nadyanna M. Majeed, Et Al See Comments For Full List Of Authors

Research Collection School of Social Sciences

How well can social scientists predict societal change, and what processes underlie their predictions? To answer these questions, we ran two forecasting tournaments testing accuracy of predictions of societal change in domains commonly studied in the social sciences: ideological preferences, political polarization, life satisfaction, sentiment on social media, and gender-career and racial bias. Following provision of historical trend data on the domain, social scientists submitted pre-registered monthly forecasts for a year (Tournament 1; N=86 teams/359 forecasts), with an opportunity to update forecasts based on new data six months later (Tournament 2; N=120 teams/546 forecasts). Benchmarking forecasting accuracy revealed that social …

Arousing Motives Or Eliciting Stories? On The Role Of Pictures In A Picture–Story Exercise, Philipp Schäpers, Stefan Krumm, Filip Lievens, Nikola Stenzel

Research Collection Lee Kong Chian School Of Business

Picture–story exercises (PSE) form a popular measurement approach that has been widely used for the assessment of implicit motives. However, current theorizing offers two diverging perspectives on the role of pictures in PSEs: either to elicit stories or to arouse motives. In the current study, we tested these perspectives in an experimental design. We administered a PSE either with or without pictures. Results from N = 281 participants revealed that the experimental manipulation had a medium to large effect for the affiliation and power motive domains, but no effect for the achievement motive domain. We conclude that the herein chosen …

Engaging Students Through Conversational Chatbots And Digital Content: A Climate Action Perspective, Thomas Menkhoff, Benjamin Gan

Research Collection Lee Kong Chian School Of Business

In this case study, we report experiences deploying a conversational chatbot as a pre-class and post-class engagement tool for undergraduate students enrolled in sustainability-related courses aimed at educating them about the severity of climate change and the importance of climate action by offsetting one’s carbon footprint (e.g, by planting trees or mangroves in SEA). The intitiative supports the university’s sustainability efforts in general and our new sustainability major in particular aimed at helping students to achieve sustainability-related learning outcomes with reference to climate change and climate action (SDG 13), one of the 17 Sustainable Development Goals established by the United …

Knowledge, Skills, And Workforce Development: Commentary On Ackerman, Frederick L. Oswald, Karyssa A. Courey, Zihan Liu

Research Collection Lee Kong Chian School Of Business

Ackerman (2023) proposed incorporating a more comprehensive range of knowledge and skills into the conceptualization and operationalization of intelligence beyond traditional assessments. In agreeing with and extending this proposition, the current commentary focuses on the specific context of workforce development and highlights three critical considerations: (a) the development of knowledge and skills at different life stages of education and work, (b) the role of social contexts in knowledge and skill acquisition, and (c) quantitative and qualitative approaches to understanding and assessing a broader set of knowledge and skills in light of ongoing changes in the workplace. Overall, we encourage greater …

Phage Peptide Technology To Characterize Extracellular Vesicles In The Brain Tumors, Jadelynn Rudolf

Undergraduate Research Conference

Extracellular vesicles (EV) are lipid-bound containers derived from the endosomal membrane network or from the extracellular membrane of cells. They can carry proteins, lipids, miRNAs, and other molecules, and may be involved in intercellular communication via membrane-associated proteins. Glioblastomas (GBM) are aggressive cancers of the brain and spinal cord derived from astrocytes. Extracellular vesicles derived from glioblastomas can make their way through the blood brain barrier and find their way to different bodily fluids, and so could serve as biomarkers for this cancer. We have isolated phage-display peptides from a commercial library of random phage-displayed peptides that will bind glioblastoma …

Computational Evaluation Of Bioactive Compounds From Vaccinium Vitis-Idaea L (Ligonberry) For Treating Kras-Associated Lung Cancer, Ayooluwa Ilesanmi, Gbenga Dairo, Toheeb Balogun, Bibiire Awoyale

Undergraduate Research Conference

Lung cancer is the cancer of the lung's epithelial cells typically characterized by difficult breathing, chest pain, blood-stained coughs, headache, and weight loss. If left unmanaged, lung cancer can spread to other body parts. While several treatment methods exist for managing lung cancer, exploring natural plant sources for developing therapeutics offers great potential in complementing different treatment approaches. In this study, we concentrated on inhibiting the mutated Kirsten rat sarcoma viral oncogene homolog (KRAS) by targeting an associated protein (Phosphodiesterase 6δ) to which KRAS form complexes. We evaluated bioactive compounds from Lingonberry (Vaccinium vitis-idaea L), adopting computational approaches such as …

Triazole Compounds – Potentials In The Treatment Of Cystic Fibrosis, Maggie Taylor

Undergraduate Research Conference

Cystic Fibrosis (CF) is a genetic disease that affects the respiratory and digestive system and is most common among Caucasians of Northern European origin. CF is caused by mutations in a membrane protein CFTR (Cystic Fibrosis Transmembrane-conductance Regulator). This mutation impairs the membrane protein’s chloride ion channel function. One of the most common CFTR mutations is the DF508 mutation that affects over 70% of CF cases. Our research has shown that the DF508-CFTR mutation can be partially reversed by physical and chemical means [Heda & Marino, BBRC, 271:659-664, 2000]. In cell lines expressing DF508-CFTR, synthetic anion carriers have shown to …

How Technology May Be Used For Future Disease Prediction: A Systematic Literature Review, Rich P. Manprisio, Mohammed Salam

Research Days

Exasperated by the current pandemic, our healthcare system continues to struggle with the accuracy and effectiveness of disease treatments. However, despite these growing challenges, technological advancements have aided potential disease prediction. There has been a positive correlation between utilizing technologies and leveraging them for disease predictions. Thanks to our continued reliance and technological advancement, current research shows that it has many viable options to aid the healthcare field. This systematic review looks at the current state of how technologies have been and can be used to improve healthcare.

Bm-02 Spartanburg Methodist College: Evaluation Of Classroom Space Efficiency, Kahleag D. Terry, Drake A. Taber, Christina King-Johnson

SC Upstate Research Symposium

Spartanburg Methodist College: Evaluation of Classroom Space Efficiency

In 2019, Spartanburg Methodist College converted from a two-year to a four-year institution. As the college grows, more classrooms are needed to satisfy the course requirements for students. A research study was conducted to answer the following question: What is the best option to implement additional class times/locations for traditional undergraduate students for both student and faculty.

Through out the semester, the student researchers analyzed various types of data address the problems of space and later class time allocation opportunities. An evaluation of the last eight semesters class location and times were …

Pc-01 Synthesis Of Zinc Glycoconjugated Phthalocyanines As A Potential Phototherapeutic, Jessica A. Silva-Conejo, Katrina Mccarter, Tessa Greene, Joshua V. Ruppel

SC Upstate Research Symposium

Photodynamic Therapy (PDT) uses photosensitizers that are activated by light to produce singlet oxygen that can cause cell damage and potential cell death. Phthalocyanines are promising photosensitizers due to their absorption at clinically relevant wavelengths, meaning that they absorb at a wavelength that can penetrate deeper into tissues.

One challenge with using Phthalocyanines is that they have very low solubility in biological media. One potential approach to increase solubility is through glycoconjugation. Glycoconjugation can also be used as a strategy to increase selectivity toward targeted tissues. Glycoconjugated phthalocyanines can be synthesized using a copper catalyzed azide-alkyne cycloaddition reaction, otherwise known …

Foliar Expression Of Candidate Genes Involved In Condensed Tannin Biosynthesis In White Clover (Trifolium Repens), Stephen N. Panter, J. Simmonds, A. Winkworth, A. Mouradov, G. C. Spangenberg

IGC Proceedings (1977-2023)

Bloat disease in cattle and sheep is caused by the rapid microbial degradation of protein-rich fodder in the rumen. This leads to the production of protein foams that trap gases, causing bloat, a condition that is often fatal to livestock and costly to farmers. Condensed tannins (CTs) are phenolic polymers produced by the phenylpropanoid pathway of plants (Figure 1). CTs bind to proteins under acidic to neutral conditions, such as those present in the rumen, slowing their breakdown. A diet with a CT content of between 2% and 4% by dry weight, which is provided by some pasture legumes (e.g. …

Discovery, Isolation And Characterisation Of Promoters In White Clover (Trifolium Repens), C. M. Labandera, Y. H. Lin, E. Ludlow, M. Emmerling, U. John, P. W. Sale, C. Pallaghy, G. C. Spangenberg

IGC Proceedings (1977-2023)

The availability of a suite of promoters with a range of spatial, temporal and inducible expression patterns is of significant importance to control targeted expression of genes for molecular breeding in forage species. A range of resources and tools have been developed for promoter isolation and characterisation in white clover (Trifolium repens L.), including a comprehensive BAC library and a 15K unigene microarray.

Novel Genotypes Of The Subtropical Grass Eragrostis Curvula For The Analysis Of Apomixis (Diplospory), S. Cardone, P. Polci, J. P. Selva, M. Mecchia, S. C. Pessino, P. Voigt, G. C. Spangenberg, V. Echenique

IGC Proceedings (1977-2023)

Eragrostis curvula (Schrad.) Nees is a variable grass native to Southern Africa. Its several forms, known as lovegrasses, were introduced to Australia, USA and Argentina as forage perennial grasses. Apomixis is a common trait in the genus Eragrostis, with diplospory being the most frequent type. Sexual reproduction also occurs in Eragrostis, although not frequently. Since most tetraploid Eragrostis lines are apomictic, the generation of a sexual tetraploid strain is a requirement for linkage analysis of the gene(s) governing the apomictic character. Furthermore, isogenic lines of the same ploidy, reproducing alternatively by sexuality or apomixes, represent an ideal system …

Isolation And Characterisation Of Genes Encoding Malate Synthesis And Transport Determinants In The Aluminum-Tolerant Australian Weeping-Grass (Microlaena Stipoides), R. M. Polotnianka, E. Ribarev, L. Mackin, K. A. Sivakumaran, G. D. Nugent, U. P. John, G. C. Spangenberg

IGC Proceedings (1977-2023)

Acid soils cover some 40% of the Earth’s arable land where they represent a major limitation to plant production. Plant growth on acid soils is primarily limited due to aluminium (Al) solubilized by acidity into toxic Al³⁺ cations which will inhibit root growth resulting in poor uptake of water and nutrients. Many important pasture species lack sufficient Al tolerance within their germplasm to allow effective breeding for this character.

Development And Use Of A Tool For Automated Alignments Of Genes In The Rice Bac's Genbank Card Against Other Species, P. Barre, G. Darrieutort, J. Auzanneau, B. Julier

IGC Proceedings (1977-2023)

In many cases, the analysis of the genetic bases of any trait requires molecular markers and if possible co-dominant PCR-based ones. In perennial fodder species, the number of publicly available markers (microsatellites and Sequence Tagged Site (STS)) is limited. Our goal is to use sequences from model grass species, i.e. rice, wheat, maize, barley, in L. perenne in order to develop STS markers in interesting regions such as under a QTL (Quantitative Trait Loci) or around a candidate gene,. As the genome sequence of rice is now available, the objective was to use the sequences of genes included in the …

Application Of Molecular Markers Derived From Medicago Truncatula In White Clover (Trifolium Repens L.), C. Jones, M. T. Abberton

IGC Proceedings (1977-2023)

White clover is the major forage legume of temperate areas. Genome maps have been produced recently (Jones et al., 2003; Barrett et al., 2004) and the location of QTL for important agricultural traits reported (Abberton et al., 2004). White clover is closely related to the model legume Medicago truncatula and there is likely to be considerable benefit in applying genomic resources from model to crop. However, the extent of synteny between the species must be established. Here we present preliminary results detailing progress towards this goal.

Screening Of Perennial Grasses And A Mutant Maize Collection By Fourier-Transformed Infrared (Ftir) Spectroscopy For Improved Biofuel Traits, S. C. Thain, P. Morris, S. Hawkins, C. Morris, I. S. Donnison

IGC Proceedings (1977-2023)

Currently the potential of biomass crops, including grasses, is limited because most species have not been bred for this purpose. However traits such as lignification, phenolic cross-linking and carbohydrate accessibility, which are also important for nutritive quality in forage grasses, can affect potential biofuel quality in applications such as combustion, fast-pyrolysis or fermentation. A collection of Lolium and Festuca species known to exhibit a range of lignin, cell wall phenolic and carbohydrate concentrations have been used to test optimum characteristics for biofuel processing. This collection formed a “calibration” set for subsequent high through-put FTIR chemical screening of additional plant lines: …

A Proposal For An International Transcriptome Initiative For Forage And Turf: Microarray Tools For Expression Profiling In Ryegrass, Clover And Grass Endophytes, T. Webster, N. Nguyen, C. Rhodes, S. A. Felitti, R. Chapman, D. Edwards, G. C. Spangenberg

IGC Proceedings (1977-2023)

Knowledge of the expression pattern of genes provides a valuable insight into gene function and role in determining the observed heritable phenotype. High–density cDNA and oligonucleotide microarrays represent powerful tools for transcriptome analysis to gain an understanding of gene expression patterns for thousands of genes. Internationally coordinated efforts in transcriptome analyses and sharing of microarray resources will benefit the advancement of our understanding of gene function in forage and turf species.

Effects Of Various Dietary Carbohydrate Sources On The Growth Performance And Body Composition Of The Dog Conch, Laevistrombus Canarium, Jen-Hong Chu

Journal of Marine Science and Technology–Taiwan

This study investigates the effects of dietary supplementation with various carbohydrate sources on the growth and dietary nutrient utilization efficiency of a 0.72-g dog conch, Laevistrombus canarium. Five treatment diets had supplementation with alpha-starch (Sta), dextrin (Dex), pullulan gum (Pg), xanthan gum (Xg), and carboxymethyl cellulose (CMC). At the end of the feeding trial, the best growth performance (weight gain, 442.23%) and diet efficiency (protein efficiency ratio, 1.25, and feed conversion ratio [FCR], 2.04) were exhibited by the dog conch fed the Sta diet, whereas the lowest growth performance was observed in the dog conch fed the Xg and CMC …

Cost Advantages Of Far East/Europe Trunk Route Deployment With Port Selection In East Asia, Tai Hui-Huang, Chang Chin-Wei

Journal of Marine Science and Technology–Taiwan

To cater to the gradually increasing sizes of ships, several traditional container ports in East Asia built deep-water wharves to attract shipping carriers to berth, a decision that is considered highly reasonable because it allows for shipping carriers to gain a cost advantage. For traditional Far East/Europe (F/E) trunk routes, shipping carriers must deploy vessels that are large enough at hub ports to maintain low transshipment costs. However, for a port to attract shipping carriers, it should be able to first meet the cargo demand of these carriers. The port would also need to improve the loading ratio to enjoy …

Influence Of Vacuum Condition On Rapid Chloride Migration (Rcm) Test For Chloride Penetration Resistance Of Concrete, Chih-Yen Lin, Chun-Fu Chang, Chung-Chia Yang

Journal of Marine Science and Technology–Taiwan

NT Build 492 regulates that the pressure be set at 7.5–37.5 torr and be maintained for 3 h for vacuum processing. This large range of acceptable vacuum pressure is awkward for research, and 3 h of pump-down time may be excessive. In this study, vacuum conditions were divided into vacuum pressure and pump-down time groups: various vacuum pressures and pump-down times were used to preprocess specimens to explore the effect of vacuum conditions on the RCM test. The salt ponding test was also conducted to identify the optimal vacuum conditions. It is shown that the relationship between vacuum pressure and …

Exhaust Noise Elimination Using Silencers Fortified With Perforated Tubes, Extended Tubes, Penetrable Resin Inlet And Orifice Plate, Min-Chie Chiu, Ho-Chih Cheng

Journal of Marine Science and Technology–Taiwan

Pneumatic equipment in marine diesel engine and associated piping system often emit extremely high level of noises when releasing pressure. Concerning the crew’s hearing health, discovering an efficient noise silencing device becomes essential. A silencer fortified with extended tubes, perforated tubes, orifice plate, and penetrable resin inlet is presented in order to competently dampen the blown-up noises. A simplified objective function by means of FEM, Artificial Neural Networks (ANNs), and a Genetic Algorithm (GA) is established to enable the numerical calculation when using a finite element method. Three silencer designs, silencer A (with element A, a penetrable resin inlet), B …

Deep Learning–Based, Oceantdlx Sea Ice Detection Model For Sar Image, Liu Lin, Li Wanwu, Li Hang, Sun Yi

Journal of Marine Science and Technology–Taiwan

This study constructs four deep-learning OceanTDLx series models and uses a WinR-AdaGrad gradient descent algorithm to train and optimize the constructed models. Through an analysis of the loss, accuracy, and time consumption of the four models (i.e., OceanTDL2, OceanTDL3, OceanTDL5 and OceanTDL8), we reveal that the models’ performance does not improve when the number of layers is increased and that OceanTDL5 provides the optimal performance. OceanTDL5 is compared with OceanTDA9 (a model that we previously constructed), and the curves for training loss_batch and training accuracy_batch indicate that OceanTDL5 is more suitable than OceanTDA9 for detecting distributed targets, particularly semi-melted sea …