Data Science Commons^™

Anomaly Detection On Small Wind Turbine Blades Using Deep Learning Algorithms, Bridger Altice, Edwin Nazario, Mason Davis, Mohammad Shekaramiz, Todd K. Moon, Mohammad A. S. Masoum

Electrical and Computer Engineering Faculty Publications

Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and …

The Fuxi Farm: Practice Exploration And Reflection On Integrated Innovation Of Smart Agriculture Technology, Yucheng Zhang, Xiaobo Zhang, Shuqin Gao, Congcong Zheng, Jingyao Zhang, Ya Wen, Lujun Li, Zhuo Wang, Tie Li, Honglong Zhao

Bulletin of Chinese Academy of Sciences (Chinese Version)

Smart agriculture plays a pivotal role in enhancing food security by optimizing resource use and improving crop yields through the application of AI technologies. The establishment of smart farms is critical to rapidly integrating AI into agricultural production, offering platforms for both the deployment and testing of AI solutions and equipment. This paper examines the development of smart farms, with a focus on practices from developed countries, and assesses the current status of smart farming in China. We then focus on exploring the content, pathways, and practices for constructing a smart agricultural production system in China through the establishment of …

Accelerate Innovation Of Forage Intelligent Breeding Technology: Reflection And Suggestions, Haichun Jing, Weijuan Hu, Jingbo Jin, Jingyu Zhang, Yao Zhou, Yue Gong, Gang Yao, Lei Wang, Kang Chong

Bulletin of Chinese Academy of Sciences (Chinese Version)

The world is facing unprecedented changes today, with continuous population growth intensifying the pressure on food demand. The shift towards diversified dietary structures has increased the demand for feed grains, while climate change further threatens China’s food security by affecting agricultural productivity and carbon sequestration economy. At present, China has entered a new era of food supply and feed. As the food supply for animals, forage is the core component of feed, and its industrial development has profound strategic significance for ensuring national food security. This study analyzes the current situation of China’s forage seed industry, summarizes the cutting-edge achievements …

Rapid Soil Detection Technology Aids In Assessing Soil Nutrients In China, Wei Wu, Xiaoyong Liao, Xiaopeng Li, Yuntao Wu, Huixian Lu, Yucheng Zhang, Jiabao Zhang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Soil quality is the core issue for ensuring China’s food security, and soil health is the top priority of soil quality. Comprehensive, rapid and accurate acquisition of soil background data is the prerequisite for achieving homogeneous soil management and formulating balanced fertilization strategies, which will play a key role in improving non-point source pollution caused by unreasonable fertilization and achieving balanced grain yield increase. This study reviews rapid soil testing methods both domestically and internationally. Based on previous research, it proposes a technical approach to rapidly detect soil nutrient concentrations by calculating the gamma quanta released during the decay of …

Hillside Agricultural Machinery And Agricultural Intelligence Driven By New Technologies, Hong Qiao, Yanfeng Lyu, Enhao Zheng

Bulletin of Chinese Academy of Sciences (Chinese Version)

Hilly and mountainous areas play a crucial role in China’s agricultural production. However, the low level of comprehensive mechanization for crop cultivation, planting, and harvesting in these regions severely hampers the modernization of agriculture. The complex terrain and diverse cropping patterns in hilly areas necessitate the development of specialized agricultural machinery and robots tailored to these unique landscapes. To advance this process, the Chinese government has introduced a series of policies in recent years to support the research and development of agricultural machinery for hilly regions, providing strong backing for the advancement of agricultural technology in these areas. Against this …

Artificial Intelligence Innovation For Smart Plant Factory To Diversify Its Big Food Production Functions, Huaqin Gong, Haichun Jing, Xin Tan, Xianhui Wang, Yucheng Zhang, Rongcheng Lin, Mingyu Yang, Shuang Lin, Hualing Xie, Yanping Yang, Shitang Ye, Peng Li, Tingyun Kuang

Bulletin of Chinese Academy of Sciences (Chinese Version)

China’s food security is facing more and more severe and complex challenges, such as tight balance between food demand and supply, the upgrading of consumption structure, and resource constraints. The plant factory is an advanced scenario in agricultural production, a diversified food production system that gets rid of the constraints of “ask for food from the mother nature” and respond to disasters and wars, and is oriented to space. Nevertheless, the high cost greatly limits the application and development of plant factories. The rapid development of artificial intelligence will bring new opportunities for the innovative development and expansion of plant …

Data And Intelligent Driven Space Science Experimental Research: New Exploration Under Ai4s Paradigm, Shengyang Li, Kang Liu, Yunfei Liu, Chufan Lai

Bulletin of Chinese Academy of Sciences (Chinese Version)

As artificial intelligence (AI) technology continues to advance, it is revolutionizing various scientific fields, giving rise to a new research paradigm known as AI for Science (AI4S). This study highlights the unique multidisciplinary advantages of AI in space science experiments conducted under microgravity conditions. It provides a comprehensive analysis of AI-driven approaches to multimodal space science experiment data pattern mining, domain knowledge extraction, interdisciplinary knowledge integration, and cognitive intelligence. The study reveals AI’s substantial potential to enhance intelligent scientific research, cognition, and discovery within the realm of space science experiments. The findings suggest that data-driven space science research, as a …

The Pathogenicity Of Vancomycin-Resistant Enterococcus Faecalis To Colon Cancer Cells, Fangyu Wang, Wei Yu

Faculty, Staff and Student Publications

BACKGROUND: The aim of this study was to investigate the pathogenicity of vancomycin-resistant Enterococcus faecalis (VREs) to human colon cells in vitro.

METHODS: Three E. faecalis isolates (2 VREs and E. faecalis ATCC 29212) were cocultured with NCM460, HT-29 and HCT116 cells. Changes in cell morphology and bacterial adhesion were assessed at different time points. Interleukin-8 (IL-8) and vascular endothelial growth factor A (VEGFA) expression were measured via RT-qPCR and enzyme-linked immunosorbent assay (ELISA), respectively. Cell migration and human umbilical vein endothelial cells (HUVECs) tube formation assays were used for angiogenesis studies. The activity of PI3K/AKT/mTOR signaling pathway was measured …

Mortality Outcomes In A Large Population With And Without Covert Cerebrovascular Disease, Ellen M Vickery, Lester Y Leung, Patrick H Luetmer, David F Kallmes, Sunyang Fu, Chengyi Zheng, Hongfang Liu, David M Kent

Faculty, Staff and Student Publications

Covert cerebrovascular disease (CCD) is frequently reported on neuroimaging and associates with increased dementia and stroke risk. We aimed to determine how incidentally-discovered CCD during clinical neuroimaging in a large population associates with mortality. We screened CT and MRI reports of adults aged ≥50 in the Kaiser Permanente Southern California health system who underwent neuroimaging for a non-stroke clinical indication from 2009-2019. Natural language processing identified incidental covert brain infarcts (CBI) and/or white matter hyperintensities (WMH), grading WMH as mild/moderate/severe. Models adjusted for age, sex, ethnicity, multimorbidity, vascular risks, depression, exercise, and imaging modality. Of n=241,028, the mean age was …

Cancergpt For Few Shot Drug Pair Synergy Prediction Using Large Pretrained Language Models, Xiaoqian Jiang, Ying Ding, Yejin Kim

Faculty, Staff and Student Publications

Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. …

Strategies To Combine 3d Vasculature And Brain Cta With Deep Neural Networks: Application To Lvo, Luca Giancardo

Faculty, Staff and Student Publications

Automated tools to detect large vessel occlusion (LVO) in acute ischemic stroke patients using brain computed tomography angiography (CTA) have been shown to reduce the time for treatment, leading to better clinical outcomes. There is a lot of information in a single CTA and deep learning models do not have an obvious way of being conditioned on areas most relevant for LVO detection, i.e., the vasculature structure. In this work, we compare and contrast strategies to make convolutional neural networks focus on the vasculature without discarding context information of the brain parenchyma and propose an attention-inspired strategy to encourage this. …

Generalizable Pipeline For Constructing Hiv Risk Prediction Models Across Electronic Health Record Systems

Faculty, Staff and Student Publications

OBJECTIVE: The HIV epidemic remains a significant public health issue in the United States. HIV risk prediction models could be beneficial for reducing HIV transmission by helping clinicians identify patients at high risk for infection and refer them for testing. This would facilitate initiation on treatment for those unaware of their status and pre-exposure prophylaxis for those uninfected but at high risk. Existing HIV risk prediction algorithms rely on manual construction of features and are limited in their application across diverse electronic health record systems. Furthermore, the accuracy of these models in predicting HIV in females has thus far been …

The Il6/Jak/Stat3 Signaling Axis Is A Therapeutic Vulnerability In Smarcb1-Deficient Bladder Cancer, Danthasinghe Waduge Badrajee Piyarathna, Lacey Elizabeth Dobrolecki, David J H Shih, Zhongcheng Shi, Jun Xu, Shixia Huang, Matthew J Ellis, Andrea B Apolo, Leomar Y Ballester, Jianjun Gao, Donna E Hansel, Yair Lotan, H Courtney Hodges, Seth P Lerner, Chad J Creighton, Arun Sreekumar, W Jim Zheng, Pavlos Msaouel, Shyam M Kavuri, Nagireddy Putluri

Faculty, Staff and Student Publications

SMARCB1 loss has long been observed in many solid tumors. However, there is a need to elucidate targetable pathways driving growth and metastasis in SMARCB1-deficient tumors. Here, we demonstrate that SMARCB1 deficiency, defined as genomic SMARCB1 copy number loss associated with reduced mRNA, drives disease progression in patients with bladder cancer by engaging STAT3. SMARCB1 loss increases the chromatin accessibility of the STAT3 locus in vitro. Orthotopically implanted SMARCB1 knockout (KO) cell lines exhibit increased tumor growth and metastasis. SMARCB1-deficient tumors show an increased IL6/JAK/STAT3 signaling axis in in vivo models and patients. Furthermore, a pSTAT3 selective inhibitor, TTI-101, reduces …

Sox On Tumors, A Comfort Or A Constraint?, Zerui Zhang, Yijun Wang, Siwen Li, Dian Hu, Jiaqian Zhang, Zhangfan Wu, Xiaoping Chen, Bixiang Zhang, Xiao Xu, Shuai Wang, Shengjun Xu, Wenjie Huang, Limin Xia

Faculty, Staff and Student Publications

The sex-determining region Y (SRY)-related high-mobility group (HMG) box (SOX) family, composed of 20 transcription factors, is a conserved family with a highly homologous HMG domain. Due to their crucial role in determining cell fate, the dysregulation of SOX family members is closely associated with tumorigenesis, including tumor invasion, metastasis, proliferation, apoptosis, epithelial-mesenchymal transition, stemness and drug resistance. Despite considerable research to investigate the mechanisms and functions of the SOX family, confusion remains regarding aspects such as the role of the SOX family in tumor immune microenvironment (TIME) and contradictory impacts the SOX family exerts on tumors. This review summarizes …

Transfer Learning In The Era Of Foundational Models: Application To Diagnosis In Rheumatology, Prashant Shekhar

Math Department Colloquium Series

Problems with current synovitis grading procedures

• There has been a lack of reliability in grading these images in the medical community due to a lack of universally accepted diagnostic criteria [Momtazmanesh et al., 2022]
• The human/machine variability creates an additional challenge in an efficient automated scoring system [Ranganath et al., 2022]
• There is a lack of consistency between doctors in grading these images [Momtazmanesh et al., 2022]

The Hsp90-Myc-Cdk9 Network Drives Therapeutic Resistance In Mantle Cell Lymphoma, Yang Liu, Qingsong Cai, Yu Xue, Yijing Li, Joseph Mcintosh, Zhihong Chen, Jovanny Vargas, Lei Nie, Yixin Yao, Heng-Huan Lee, Wei Wang, Johnnelson R Bigcal, Maria Badillo, Jitendra Meena, Christopher Flowers, Jia Zhou, Zhongming Zhao, Lukas M Simon, Michael Wang

Faculty, Staff and Student Publications

Brexucabtagene autoleucel CAR-T therapy is highly efficacious in overcoming resistance to Bruton's tyrosine kinase inhibitors (BTKi) in mantle cell lymphoma. However, many patients relapse post CAR-T therapy with dismal outcomes. To dissect the underlying mechanisms of sequential resistance to BTKi and CAR-T therapy, we performed single-cell RNA sequencing analysis for 66 samples from 25 patients treated with BTKi and/or CAR-T therapy and conducted in-depth bioinformatics™ analysis. Our analysis revealed that MYC activity progressively increased with sequential resistance. HSP90AB1 (Heat shock protein 90 alpha family class B member 1), a MYC target, was identified as early driver of CAR-T resistance. CDK9 …

Transcription Factor Bach1 In Cancer: Roles, Mechanisms, And Prospects For Targeted Therapy, Junqing Jiang, Jiaqian Zhang, Zhangfan Wu, Yijun Wang, Mengyu Sun, Xiaoping Chen, Bixiang Zhang, Xiao Xu, Shuai Wang, Shengjun Xu, Yufei Wang, Wenjie Huang, Limin Xia

Faculty, Staff and Student Publications

Transcription factor BTB domain and CNC homology 1 (BACH1) belongs to the Cap 'n' Collar and basic region Leucine Zipper (CNC-bZIP) family. BACH1 is widely expressed in mammalian tissues, where it regulates epigenetic modifications, heme homeostasis, and oxidative stress. Additionally, it is involved in immune system development. More importantly, BACH1 is highly expressed in and plays a key role in numerous malignant tumors, affecting cellular metabolism, tumor invasion and metastasis, proliferation, different cell death pathways, drug resistance, and the tumor microenvironment. However, few articles systematically summarized the roles of BACH1 in cancer. This review aims to highlight the research status …

Patient And Dentist Perspectives On Collecting Patient Reported Outcomes After Painful Dental Procedures In The National Dental Pbrn, Rahma Mungia, Alfa-Ibrahim Yansane, David Holmes, Kim Funkhouser, Ana M Ibarra-Noriega, Janelle Urata, D Brad Rindal, Heiko Spallek, Joel White, Muhammad F Walji

Faculty, Staff and Student Publications

BACKGROUND: Dental Patient Reported Outcomes (PROs) relate to a dental patient's subjective experience of their oral health. How practitioners and patients value PROs influences their successful use in practice.

METHODS: Semi-structured interviews were conducted with 22 practitioners and 32 patients who provided feedback on using a mobile health (mHealth) platform to collect the pain experience after dental procedures. A themes analysis was conducted to identify implementation barriers and facilitators.

RESULTS: Five themes were uncovered: (1) Sense of Better Care. (2) Tailored Follow-up based on the dental procedure and patient's pain experience. (3) Effective Messaging and Alerts. (4) Usable Digital Platform. …

Session 8: Machine Learning Based Behavior Of Non-Opec Global Supply In Crude Oil Price Determinism, Mofe Jeje

SDSU Data Science Symposium

Abstract

While studies on global oil price variability, occasioned by OPEC crude oil supply, is well documented in energy literature; the impact assessment of non-OPEC global oil supply on price variability, on the other hand, has not received commensurate attention. Given this gap, the primary objective of this study, therefore, is to estimate the magnitude of oil price determinism that is explained by the share of non-OPEC’s global crude oil supply. Using secondary sources of data collection method, data for target variable will be collected from the US Federal Reserve, as it relates to annual crude oil price variability, while …

Principal Component Analysis With Application To Credit Card Data, Eleanor Cain, Semhar Michael, Gary Hatfield

SDSU Data Science Symposium

Principal Component Analysis (PCA) is a type of dimension reduction technique used in data analysis to process the data before making a model. In general, dimension reduction allows analysts to make conclusions about large data sets by reducing the number of variables while retaining as much information as possible. Using the numerical variables from a data set, PCA aims to compute a smaller set of uncorrelated variables, called principal components, that account for a majority of the variability from the data. The purpose of this poster is to understand PCA as well as perform PCA on a large sample credit …