Digital Commons Network^™

Topsis Approach For Madm Based On Quadripartitioned Single Valued Neutrosophic Refined Hamacher Aggregation Operations, Arokia Pratheesha S V, Annapoorna M S, Radha R, Parul Arora, Ritika Wason, Divya Baliga B

Neutrosophic Sets and Systems

Hamacher operators are extensively utilized in multicriteria attribute group decision-making (MAGDM) problems due to their remarkable adaptability provided by an adjustable parameter. Here, the Hamacher T-norm and T-conorm operations for two QSVNRNs are formulated.Using these Hamacher op erations, we present the quadripartitioned single-valued neutrosophic refined Hamacher weighted averaging (QSVNRHWA) operators within the QSVNR framework and analyze their properties.Finally, we explore a TOPSIS-based approach for multi-attribute decision-making problems that employs the QSVNRHWA opera tors, demonstrating its application in evaluating practical scenarios related to converting solid waste into energy.

Single-Valued Neutrosophic Graph With Heptapartitioend Structure, Hanaa Fathi, M. Myvizhi, Ahmed Abdelhafeez, Mohamed Refaat Abdellah, Mohamed Eassa, Mohamed S. Sawah, Hussam Elbehiery

Neutrosophic Sets and Systems

This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neutrosophic Graphs (SVHNG) and investigate their characteristics through comprehensive proofs and illustrative examples.

Pharmacodynamics Of Aspirin Through Gestation: Predictors Of Aspirin Response And Association With Pregnancy Outcome, A Prospective Cohort Study, Rupsa C. Boelig, Emily Foecke Munden, Tingting Zhan, Steven E. Mckenzie, Walter K. Kraft

Department of Pharmacology, Physiology, and Cancer Biology Faculty Papers

Low-dose aspirin is recommended for prevention of hypertensive disorders of pregnancy (HDP) and preterm birth (PTB) in high-risk pregnancies. There is limited data on factors impacting aspirin response in pregnancy. We aimed to evaluate predictors of aspirin response and association with pregnancy outcome with a prospective study of high-risk pregnancies taking 81 mg aspirin daily. Aspirin response was evaluated with Platelet Function Assay-100 (PFA-100) epinephrine closure time at baseline (< 16 weeks' gestation), follow-up 1 (2-4 weeks after aspirin initiation), and follow-up 2 (28-32 weeks gestation). Multivariable regression was used to identify factors associated with PFA-100 at each visit, and results presented with beta coefficient (B) and confidence interval. The median difference (MD) in PFA-100 in those with and without HDP or PTB was compared. Results included 108 who completed follow-up 1 and 96 who completed both visits with > 75% adherence. PFA-100 was increased from baseline at follow-ups 1 and 2 (MD 37 (27-49); MD 26 (15.5-38.5) respectively). At follow-up 1, obesity (B = -30 (-53 to -7) seconds), …

Altered Thermal Preference By Preoptic Estrogen Receptor Alpha Neurons In Postpartum Females, Nan Zhang, Meng Yu, Qianru Zhao, Bing Feng, Yue Deng, Jonathan C Bean, Qingzhuo Liu, Benjamin P Eappen, Yang He, Kristine M Conde, Hailan Liu, Yongjie Yang, Longlong Tu, Mengjie Wang, Yongxiang Li, Na Yin, Hesong Liu, Junying Han, Darah Ave Threat, Nathan Xu, Taylor Smiley, Pingwen Xu, Lulu Chen, Tianshu Zeng, Yanlin He, Chunmei Wang

Faculty, Staff and Students Publications

OBJECTIVE: This study aims to investigate how reproductive experience (RE) alters thermal preference and thermoregulation in female mice, with a focus on estrogen receptor alpha (ERα)-expressing neurons in the preoptic area (POA).

METHODS: Thermal preference and body temperature were measured in female mice with and without RE, and virgin female mice with selective deletion of ERα from the POA (ERα

RESULTS: We showed that female mice prefer a cooler environment starting from late pregnancy and persisting long term postpartum. Female mice with RE (>4 weeks post-weaning) displayed lower body temperature and a lower thermal preferred temperature, and lost preference …

Arteriovenous Malformation Presenting As A Disfigured And Throbbing Face: Case Report, Abrar Shamim Dds, Steven Halepas Dmd, Md, Alfonso Salcines Dmd, Md, Sidney B. Eisig Dds, Facs

The New York State Dental Journal

Maxillofacial arteriovenous malformations (AVMs) are a rare condition in which arteries and veins are in continuity without a capillary bed in between, which poses a significant risk of severe bleeding. Intraosseous AVMs can lead to cortical bone expansion and facial deformity. Dental procedures may result in life-threatening bleeding risk if this condition is not recognized. This report describes a patient experiencing pain in the lower right side of the mouth, along with a taste of blood in the mornings and a tingling sensation in the chin and lower lip. The patient had a history of uncontrolled bleeding following a dental …

Bright Ideas: How Leaf Cells Shape The Way Plants Capture Light, Nicola Trozzi, Janlo M. Robil

Biology Faculty Publications

No abstract provided.

A World-Threatening Feeling: Grief, Moral Injury, And Institutional Loss In Rural Courts, Michele Statz

Fordham Law Review

No abstract provided.

Microbial Communities Associated With Endangered West Texas Springsnails And Their Potential Roles In Conservation, Russell L. Minton, Kathryn E. Perez

School of Integrative Biological & Chemical Sciences Faculty Publications

Desert springs are one of the most threatened ecosystems globally. Those in Southwestern North America support high numbers of threatened and endemic species. Human activities present the greatest threats to springs and the organisms they support. Freshwater snails in the genera Pyrgulopsis and Tryonia are two groups of such organisms, representing diverse and threatened groups of springsnails in the Southwestern United States. Desert springs also harbour unique microbial diversity that faces similar threats from water usage and freshwater habitat degradation. Understanding springsnails and the bacteria they host represent potential exemplars for interdisciplinary conservation efforts. We studied the bacterial communities associated …

Crystal Structure And Hirshfeld-Surface Analysis Of The Pesticide Etoxazole, Chaluvarangaiah Sowbhagya, Thaluru M.Mohan Kumar, Hemmige S. Yathirajan, Sean Parkin

Chemistry Faculty Publications

Etoxazole (C21H23F2NO2), systematic name 4-(4-tert-butyl-2-ethoxyphenyl)-2- (2,6-difluorophenyl)-4,5-dihydro-1,3-oxazole, is a fluorinated insecticide and acaricide that inhibits chitin biosynthesis, disrupting insect development by preventing proper exoskeleton formation. Widely used in agriculture since 1998, it is readily absorbed by plant tissues and translocates within leaves. Metabolic studies have identified several oxidative degradation products, while toxicological assessments have examined potential effects, including oxidative stress. This study presents a detailed crystallographic and Hirshfeld surface analysis of etoxazole. The molecule consists of a central dihydro-oxazole ring flanked by 2,6-difluorophenyl and 4-tert-butyl-2-ethoxyphenyl groups, each twisted relative to the oxazole core. The dihydro-oxazole ring is nearly planar, with the …

The Relationship Between Food Insecurity And Emotional Eating During The Coronavirus Pandemic In Northern California, Andreza S.B. Souza, Marcelle M. Dougan, Giselle A.P. Pignotti

Faculty Research, Scholarly, and Creative Activity

Objectives: This cross-sectional study examined the association between food insecurity and emotional eating and explored correlations between emotional eating and dietary behavior in the U.S during the pandemic. Methods: Participants (N = 515, 77.1 % female, 44.1 ± 14.7 years old) completed a validated online survey between August and November of 2020 including questions about food security and eating behaviors. A multivariable linear regression model was used to evaluate the association between food insecurity and emotional eating. Pearson correlations were calculated to assess the relationship between emotional eating and dietary behavior Results: Overall, 31.3 % of the participants experienced food …

Navigating Your Us Bioscience Career Into The 2030s, Peter J Hotez

Center for Medical Ethics and Health Policy Staff Publications

The coming decade might see major cuts to the United States Government funding for biomedicine and the mainstreaming of pseudoscience. But your biosciences PhD gives you the problem-solving skills to navigate this maelstrom, especially if you maintain flexibility, optimism, and enthusiasm for uncharted paths.

Increasing A-Type Co32− Substitution Decreases The Modulus Of Apatite Nanocrystals, Stephanie Wong, Abigail Eaton, Christina Krywka, Arun Nair, Christophe Drouet, Alix Deymier

Faculty Publications

Biological apatite mineral is highly substituted with carbonate (CO₃²⁻). CO₃²⁻ can exchange for either phosphate, known as B-type, or hydroxyl groups, known as A-type. Although the former has been extensively studied, A-type CO₃²⁻ substituted apatites are poorly understood. Therefore, A-type CO₃²⁻ apatites with biologically relevant levels of CO32− (1.7–5.8 wt%) were prepared and characterized. The addition of A-type CO₃²⁻ into the apatite structure caused the predicted expansion of the a-axis and contraction of the c-axis in the unit cell. This was accompanied by a significant modification in the atomic …

Patient Consent And The Right To Notice And Explanation Of Ai Systems Used In Health Care, Meghan E Hurley, Benjamin H Lang, Kristin Marie Kostick-Quenet, Jared N Smith, Jennifer Blumenthal-Barby

Center for Medical Ethics and Health Policy Staff Publications

Given the need for enforceable guardrails for artificial intelligence (AI) that protect the public and allow for innovation, the U.S. Government recently issued a Blueprint for an AI Bill of Rights which outlines five principles of safe AI design, use, and implementation. One in particular, the right to notice and explanation, requires accurately informing the public about the use of AI that impacts them in ways that are easy to understand. Yet, in the healthcare setting, it is unclear what goal the right to notice and explanation serves, and the moral importance of patient-level disclosure. We propose three normative functions …

Experiences Among Parents Caring For Children With Juvenile Idiopathic Arthritis At A Tertiary Referral Hospital In Kenya, Hassan Silim, Susan Wamithi, Roselyter Riang’A, Angela Migowa

Paediatrics and Child Health, East Africa

Background: Juvenile idiopathic arthritis (JIA) is the most common rheumatic disease in childhood. Despite the availability of effective treatment strategies such as disease-modifying antirheumatic drugs (DMARDs), JIA is reported to have a negative impact on the quality of life of the patients and their caregivers. Ascertaining the perceptions of the parents will help facilitate more effective management strategies and improve outcomes for these patients. This study aimed to ascertain parental experiences and perceptions of caring for children with juvenile idiopathic arthritis (JIA).

Methods: This was a single-center facility-based qualitative study. An in-depth interview guide was used to collect …

A Wave-Optics Bsdf For Correlated Scatterers, Ruomai Yang

Dartmouth College Master’s Theses

In this project, we present a wave optics bidirectional scattering distribution function(BSDF) for the material with a collection of scatterers, such as certain fabrics with pores or foggy glass, where the corona effect can be observed under strong light sources. This effect arises from the diffraction of individual scatterers and the interference between them. To describe this effect, we treat each scatterer as an aperture to calculate diffraction, while using a pair correlation function to represent their spatial relationships and calculate the interference. This two-level decomposition allows us to derive a BSDF that can control both the individual diffraction function …

Family Genetic Risk Communication And Reverse Cascade Testing In The Babyseq Project, Melissa K Uveges, Hadley Stevens Smith, Stacey Pereira, Casie Genetti, Amy L Mcguire, Alan H Beggs, Robert C Green, Ingrid A Holm

Center for Medical Ethics and Health Policy Staff Publications

Purpose: Genomic sequencing of newborns can initiate disease surveillance and therapy for children and may identify at-risk relatives through reverse cascade testing. We explored genetic risk communication and reverse cascade testing among families of newborns who underwent exome sequencing and were identified as having a risk for an autosomal dominant disease.

Methods: We conducted semistructured interviews with parents of newborns enrolled in the BabySeq Project who had a pathogenic or likely pathogenic variant associated with an autosomal dominant childhood- and/or adult-onset disease returned. We used directed content analysis to derive themes.

Results: From 11 families, all first-degree relatives (n = …

"Insanity" As An American Empire: The Canton Insane Asylum For American Indians, 1902-1934, Thanh Chi Nguyen

Dartmouth College Master’s Theses

This graduate thesis involves a retelling of the history of the now defunct Canton Insane Asylum, built in the early 20th century located in Canton, South Dakota. It was America’s first federal psychiatric facility dedicated exclusively for American Indians. The Canton Insane Asylum for American Indians is a touchstone whose microhistory reflects larger political and economic sentiments in both the state of South Dakota and in the United States writ large. Conceiving South Dakota, as first and foremost a white settler society erected on land forcibly wrested from American Indian people, the asylum played an important economic development role and …

A High-Lipid Diet Leads To Greater Pathology And Lower Tolerance During Infection, Weston Gerald Perrine, Erin Sauer, Ashley C. Love, Ashley Morris, Johnathan Novotny, Sarah Durant

Biological Sciences Faculty Publications and Presentations

Altered food landscapes contribute importantly to wildlife disease dynamics and may play a critical role in host heterogeneity in disease outcomes through changes in host diet composition. We explored the effects of dietary macronutrient composition on disease pathology and feeding behavior of canaries (Serinus canaria domestica) infected with Mycoplasma gallisepticum (MG). In the first experiment, we provided canaries with isocaloric diets composed of identical ingredients that varied in macronutrient content (high protein or high lipid) then MG- or sham-inoculated birds. In the second experiment, we offered both diets to canaries before and after MG or sham inoculation. In experiment one, …

On Explicit Solutions For Coupled Reaction-Diffusion And Burgers-Type Equations With Variable Coefficients Through A Riccati System, Jose M. Escorcia, Erwin Suazo

School of Mathematical & Statistical Sciences Faculty Publications

This work is concerned with the study of explicit solutions for generalized coupled reaction-diffusion and Burgers-type systems with variable coefficients. Including nonlinear models with variable coefficients such as the diffusive Lotka-Volterra model, the Gray-Scott model, the Burgers equations. The equations' integrability (via the explicit formulation of the solutions) is accomplished by using similarity transformations and requiring that the coefficients fulfill a Riccati system. We present traveling wave-type solutions as well as solutions with more complex dynamics and relevant features such as bending. A Mathematica file has been prepared as supplementary material, verifying the Riccati systems used in the construction of …

Comparison Of Deep Learning And Traditional Machine Learning Models For Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers, Kesheng Wang, Donald A. Adjeroh, Wei Fang, Suzy M. Walter, Danqing Xiao, Ubolrat Piamjariyakul, Chun Xu

Health & Biomedical Sciences Faculty Publications

Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer’s disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor …

The Cross-Sectional Association Between Lifestyle Behaviors And Breast And Cervical Cancer Screening Among Hispanic Women Along The Texas-Mexico Border, Paul Gerardo Yeh, Audrey C Choh, Susan P Fisher-Hoch, Joseph B Mccormick, David R Lairson, Belinda M Reininger

Faculty, Staff and Student Publications

Objective: Lifestyle behaviors may influence timely cancer screening, but their relationship is unknown among Hispanic women who have low cancer screening rates.

Methods: We used Cameron County Hispanic Cohort data from 2014 to 2022 to evaluate the relationship between lifestyle and compliance with mammography and Papanicolaou (Pap) screening guidelines ("up-to-date") among Hispanic women along the Texas-Mexico border. The 2018 World Cancer Research Fund scoring system characterized cancer-preventive lifestyle adherence. Multivariable logistic regression assessed the association between lifestyle behaviors and mammography and, separately, Pap screening.

Results: Among 385 age-eligible women for mammography and 412 age-eligible women for Pap test screening, up-to-date …

Training Protocol And Calibration Of The International Caries Detection And Assessment System In A School-Based Clinical Trial Of Elementary School-Age Children, Jose-Miguel Yamal, Dania Mofleh, Ru-Jye Chuang, Mengxi Wang, Kila Johnson, Alejandra Garcia-Quintana, Tolulope Titiloye, Suchitra Nelson, Shreela V Sharma

Faculty, Staff and Student Publications

Objectives: This paper demonstrates International Caries Detection and Assessment System (ICDAS) training procedures and inter/intra-examiner reliability for lesion severity, activity, and filling criteria in an elementary school setting.

Methods: ICDAS training was conducted in December 2021 prior to a school-based cluster-randomized controlled trial. A total of 59 children (6-8 years old) in grades 1-2 from one school in Houston, Texas were recruited. Two licensed dentists received a 5-day training from an ICDAS trainer at the participating school. Thirty-eight children were evaluated at least once by each dental trainee, and 18 had repeat examinations. The ICDAS criteria were used to classify …

Predicting Fatal Opioid-Involved Overdoses: A Social-Ecological Framework Matched To A Linked-Data Warehouse, Ric Bayly, Jack Cordes, Dana Bernson, Leland K Ackerson, Marc R Larochelle, Ghada H Hassan, Cici X Bauer, Thomas J Stopka

Faculty, Staff and Student Publications

Background: An estimated 60 million people used opioids non-medically worldwide in 2021. In 2019, opioid use disorder caused the loss of over 12.5 million healthy years of life due to disability and premature deaths, including those resulting from opioid-involved overdoses. Factors associated with opioid-involved overdoses are numerous, multi-layered, and interrelated. Using the social-ecological model as a foundation, we sought to comprehensively identify risk and preventive factors of fatal opioid-involved overdoses and operationalize them with quantifiable measures.

Methods: With our Community Advisory Board, investigators' expertise, and an examination of the literature, we created an expansive, opioid-overdose specific social-ecological model structured as …

Sequencing In Over 50,000 Cases Identifies Coding And Structural Variation Underlying Atrial Fibrillation Risk, Seung Hoan Choi, Sean J Jurgens, Ling Xiao, Matthew C Hill, Christopher M Haggerty, Garðar Sveinbjörnsson, Valerie N Morrill, Nicholas A Marston, Lu-Chen Weng, James P Pirruccello, David O Arnar, Daniel Fannar Gudbjartsson, Helene Mantineo, Aenne S Von Falkenhausen, Andrea Natale, Arnljot Tveit, Bastiaan Geelhoed, Carolina Roselli, David R Van Wagoner, Dawood Darbar, Doreen Haase, Elsayed Z Soliman, Giovanni E Davogustto, Goo Jun, Hugh Calkins, Jeffrey L Anderson, Jennifer A Brody, Jennifer L Halford, John Barnard, John E Hokanson, Jonathan D Smith, Joshua C Bis, Kendra Young, Linda S B Johnson, Lorenz Risch, Lorne J Gula, Lydia Coulter Kwee, Mark D Chaffin, Michael Kühne, Michael Preuss, Namrata Gupta, Navid A Nafissi, Nicholas L Smith, Peter M Nilsson, Pim Van Der Harst, Quinn S Wells, Renae L Judy, Renate B Schnabel, Renee Johnson, Roelof A J Smit, Stacey Gabriel, Stacey Knight, Tetsushi Furukawa, Thomas W Blackwell, Victor Nauffal, Xin Wang, Yuan-I Min, Zachary T Yoneda, Zachary W M Laksman, Connie R Bezzina, Alvaro Alonso, Bruce M Psaty, Christine M Albert, Dan E Arking, Dan M Roden, Daniel I Chasman, Daniel J Rader, David Conen, David D Mcmanus, Diane Fatkin, Emelia J Benjamin, Eric Boerwinkle, Gregory M Marcus, Ingrid E Christophersen, J Gustav Smith, Jason D Roberts, Laura M Raffield, M Benjamin Shoemaker, Michael H Cho, Michael J Cutler, Michiel Rienstra, Mina K Chung, Morten S Olesen, Moritz F Sinner, Nona Sotoodehnia, Paulus Kirchhof, Ruth J F Loos, Saman Nazarian, Sanghamitra Mohanty, Scott M Damrauer, Stefan Kaab, Susan R Heckbert, Susan Redline, Svati H Shah, Toshihiro Tanaka, Yusuke Ebana, Hilma Holm, Kari Stefansson, Christian T Ruff, Marc S Sabatine, Kathryn L Lunetta, Steven A Lubitz, Patrick T Ellinor

Faculty, Staff and Student Publications

Atrial fibrillation (AF) is a prevalent and morbid abnormality of the heart rhythm with a strong genetic component. Here, we meta-analyzed genome and exome sequencing data from 36 studies that included 52,416 AF cases and 277,762 controls. In burden tests of rare coding variation, we identified novel associations between AF and the genes MYBPC3, LMNA, PKP2, FAM189A2 and KDM5B. We further identified associations between AF and rare structural variants owing to deletions in CTNNA3 and duplications of GATA4. We broadly replicated our findings in independent samples from MyCode, deCODE and UK Biobank. Finally, we found that CRISPR knockout of KDM5B …

Functional Investigation Of A Putative Calcium-Binding Site Involved In The Inhibition Of Inositol 1,4, 5-Trisphosphate Receptor Activity, Vikas Arige, Larry E Wagner, Sundeep Malik, Mariah R Baker, Guizhen Fan, Irina I Serysheva, David I Yule

Faculty, Staff and Student Publications

The regulation of inositol 1,4,5-trisphosphate (IP3) receptor (IP3R) activity is thought to define the spatiotemporal patterns of Ca2+ signals necessary for the appropriate activation of downstream effectors. The binding of both IP3 and Ca2+ is obligatory for IP3R channel opening. Ca2+ however regulates IP3R activity in a biphasic manner. Ca2+ binding to a high-affinity pocket formed by the third armadillo repeat domain and linker domain promotes IP3R channel opening without altering the Ca2+ dependency for channel inactivation. These data suggest that a distinct low-affinity Ca2+-binding site is responsible for the reduction in IP3R activity at higher [Ca2+]. We mutated a …

Pilot Screening For Prodromal Parkinson’S Disease In Post-9/11 Veterans With Probable Rapid Eye Movement Sleep Behavior Disorder, Melissa B Jones, Dakota Broadway, Taryn White, George R Jackson, Supriya Singh, Ruosha Li, Erik K St Louis, Laura E Marsh, Ricardo E Jorge

Faculty, Staff and Students Publications

This pilot examined prodromal markers in post-9/11 Veterans with TBI and probable REM sleep behavior disorder (N = 12). RBD was confirmed in 5 of 10 (50 %) participants with polysomnography. Veterans with subthreshold parkinsonism had lower olfactory scores. Future studies should quantify REM sleep without atonia and include broader markers.

Disrupting Tymp-Mediated Pathways To Block Lymph Node Metastasis In Ovarian Cancer, Emine Bayraktar

Dissertations and Theses (Open Access)

Historically, ovarian cancer (OC) was thought to metastasize by surface-to-surface spread, but recent developments have yielded a new understanding of the paths of metastatic spread. In epithelial ovarian cancer, the mechanisms driving lymph node (LN) metastasis are poorly understood, and it remains unclear whether omental metastasis occurs in parallel with LN metastasis. Utilizing comparative transcriptomic and proteomic profiling of primary tumors, LN metastases, and omental metastases, we identified significant upregulation of thymidine phosphorylase (TYMP) in LN metastases compared to primary and omental tumor sites. Functional studies in murine models demonstrated that TYMP silencing significantly suppressed LN metastasis, underscoring TYMP as …

Community Engagement Approaches And Lessons Learned: A Case Study Of The Precise Pregnancy Cohort Study In Kenya, Onesmus Wanje, Angela Koech, Maggie Woo Kinshella, Grace Mwashigadi, Alice Kombo, Grace Maitha, Nathan Barreh, Hiten D. Mistry, Marianne Vidler, Rachel Craik

Centre of Excellence in Women and Child Health

Community engagement (CE) has been recommended as an important ethical consideration for health research to enhance informed consent and exchange knowledge between researchers and community members. The purpose of this paper is to describe how CE was developed and delivered for the PRECISE prospective pregnancy cohort study in Kenya. PRECISE enrolled pregnant women in antenatal care, followed them up to the postpartum period, and collected data and biological samples to enable the study of placental disorders in sub-Saharan Africa. Initially CE was aimed at informing the community about the study, establishing communitywide acceptance of the research and addressing concerns about …

Explainable Neural Networks With Guarantee: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

Dr. Tongue: Sign-Oriented Multi-Label Detection For Remote Tongue Diagnosis, Yiliang Chen, Steven S. C. Ho, Cheng Xu, Yao Jie Xie, Wing Fai Yeung, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Tongue diagnosis is a vital tool in Western and Traditional Chinese Medicine, providing key insights into a patient's health by analyzing tongue attributes. The COVID-19 pandemic has heightened the need for accurate remote medical assessments, emphasizing the importance of precise tongue attribute recognition via telehealth. To address this, we propose a Sign-Oriented multi-label Attributes Detection framework. Our approach begins with an adaptive tongue feature extraction module that standardizes tongue images and mitigates environmental factors. This is followed by a Sign-oriented Network (SignNet) that identifies specific tongue attributes, emulating the diagnostic process of experienced practitioners and enabling comprehensive health evaluations. To …