Advanced Machine Learning Research Articles

Intelligent Wearable Systems: Opportunities and Challenges in Health and Sports

Wearable devices, or wearables, designed to be attached to the human body, can gather personalized real-time data and continuously monitor an individual’s health status and physiological disposition in a non-invasive manner. Intelligent wearables integrate advanced machine learning algorithms to process complex data patterns and provide accurate insights. As a result, intelligent wearables have emerged as a ground-breaking innovation in the fields of sports and health, introducing a new paradigm in kinematic analysis and patient data evaluation. For example, virtual coaches offer feedback on athletes’ performance, whereas virtual physicians assist in customizing medication for patients. This article provides an overview of various types of intelligent wearables and their applications in health and sports, categorizes machine learning algorithms, and introduces the wireless body area sensor network (WBASN) used for communication in wearable sensors. Additionally, we discuss potential challenges and development directions that could shape the future of intelligent wearables and propose effective solutions for their continued enhancement. This article offers valuable insights into the exciting potential of intelligent wearables to transform healthcare and sports.

T49 Style Stock Prediction

Stock market prediction has long been a pursuit of investors seeking to gain insights into the future trajectory of stock prices. Traditionally, analysts relied on fundamental analysis, technical indicators, and market sentiment to forecast stock movements. However, with the advent of machine learning (ML) and artificial intelligence (AI), predictive analytics in the stock market has seen a significant shift. ML algorithms offer the advantage of processing vast amounts of data and identifying complex patterns that might elude human analysts. In the context of stock market prediction, these algorithms can analyze historical stock prices, trading volumes, market indices, news sentiment, and various other factors to generate forecasts. One notable trend in this domain is the utilization of current stock market indices as input features for ML models. By training on historical data of these indices and their corresponding effects on individual stock prices, algorithms can learn to make predictions based on the current state of the market. One common approach is to use techniques like regression, time series analysis, or deep learning models such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs). These models can capture temporal dependencies and nonlinear relationships in the data, allowing for more accurate predictions. Additionally, ensemble methods like random forests or gradient boosting can be employed to combine the strengths of multiple models for enhanced forecasting performance. Keywords: Stock market prediction,, financial stocks, stock market indices

Multi-source precipitation estimation using machine learning: Clarification and benchmarking

Multi-source precipitation estimation techniques, including interpolation, bias correction, and merging, are essential for acquiring high-precision precipitation datasets. Machine learning (ML) methods have achieved inspiring success in this field, but current studies utilizing ML often blur the boundaries of interpolation, bias correction, and merging because of the utilization of uniform input–output frameworks. The ambiguity in classification (interpolation, bias correction and merging) results in inconsistent and inappropriate comparative benchmarking among studies. A widespread example is the tendency to select easy-to-beat benchmarks, which can magnify the relative performance of ML methods. We propose to reclarify ML-based precipitation estimation by conducting a series of experiments with designed feature combinations to unveil the essence of ML-based methods. Our findings suggest that with different feature combinations, there are no essential distinctions between models for merging, bias correction and interpolation. Ground measurements, as the reference in supervised learning, play a more vital role than different features in precipitation estimation. This means that the ML-based multi-source merging or bias correction should be treated as gauge data-based interpolation with various auxiliary predictors. Moreover, the improvements of ML estimates are more significant compared to low-standard benchmarks like individual precipitation datasets and simple merging methods, but less preeminent compared to high-standard benchmarks such as a sophisticated interpolation method (e.g., Geographically Weighted Regression). Therefore, we call for positioning such ML applications as interpolation and adhering to high-standard benchmarks whenever possible, which can illustrate the true potential and promote further advancements of ML in geospatial estimation.

Multiple Authentication Schemes for Sign-In Process

Abstract: In the ever-evolving landscape of digital applications, user authentication plays a vital role in ensuring data security and privacy. Traditional username-password authentication methods may not always suffice, leading to the need for "Alternate Sign-In Methods." This project aims to develop a robust and user-friendly authentication system using advanced Machine Learning (ML) techniques. The system's primary objective is to offer users multiple authentication options beyond the conventional methods, such as Image Authentication, Pattern-based Authentication, Username-Password Authentication, and Fingerprint-based Authentication. Content-based filtering and collaborative filtering approaches will be employed to ensure efficient and relevant authentication options for each user. The project focuses on enhancing user convenience, security, and overall experience in digital platforms by tailoring sign-in methods to individual preferences.

Movie Review Sentiment Analysis and AI-Story Generation Web Application

Abstract: This paper presents a web application designed to enhance the interaction between users and multimedia content through two innovative platforms: "MOVIE REVIEW SENTIMENT ANALYSIS" and "AI-STORY GENERATION." The first platform leverages the Fastai library and LSTM networks to perform sentiment analysis on user-submitted movie reviews, determining their polarity as positive or negative. This analysis directly influences the movie's aggregate rating, with the system capable of processing extensive textual input with high accuracy. Ratings are dynamically updated and stored in JSON format. The second platform, AI-STORY GENERATION, introduces a creative avenue for generating novel stories based on user prompts. It utilizes Natural Language Processing (NLP) techniques and a Generative Pretrained Transformer (GPT-2 Large) model, trained on tokenized movie scripts, to produce coherent and engaging narratives. The Flask web framework supports the application's backend, providing a robust and scalable foundation for user interaction and content delivery. This dual-platform approach not only demonstrates the practical application of advanced machine learning and NLP techniques in enhancing digital entertainment experiences but also showcases the potential for AI-driven tools to foster creative storytelling. The integration of sentiment analysis and story generation within a single application illustrates a novel use case of AI in the context of web-based entertainment, potentially paving the way for more personalized and interactive user experiences

УСПЕХИ В МОНИТОРИНГЕ СОСТОЯНИЯ КОНСТРУКЦИЙ: ОБЗОР ПОДХОДОВ МАШИННОГО ОБУЧЕНИЯ ДЛЯ ОБНАРУЖЕНИЯ И ОЦЕНКИ ПОВРЕЖДЕНИЙ

Structural Health Monitoring (SHM) is a crucial discipline geared towards detecting damage in engineering structures early, aiming to prevent failures and facilitate condition-based maintenance. Traditional SHM methodologies, relying on visual inspections, analytical models, and signal processing, exhibit inherent limitations. The advent of machine learning has introduced data-driven solutions to automate various aspects of SHM, including damage detection, localization, classification, and prognosis.
 This paper provides a comprehensive review of recent studies exploring supervised, unsupervised, and deep learning techniques in vibration-based, image-based, and multi-sensor SHM. Support vector machines, neural networks, deep convolutional neural networks, and other advanced algorithms have demonstrated exceptional performance in assessing damage using real-world structural datasets.
 Despite these successes, practical challenges persist, particularly in addressing variability and deploying machine learning models effectively on full-scale structures. Overcoming these challenges necessitates a more integrated, cross-disciplinary approach, merging mechanical engineering fundamentals with machine learning expertise. This synergy can pave the way for robust field implementation and further enhance the reliability of SHM systems.
 The transformative potential of machine learning in SHM cannot be understated. Beyond merely shifting from time-based maintenance to condition-based strategies, machine learning can automate and continuously evaluate structural integrity, ensuring the longevity of engineering structures. As we delve deeper into the intersection of mechanical engineering and machine learning, the prospect of a future where SHM seamlessly integrates with advanced technologies becomes increasingly tangible.

Multimodal feature fusion in deep learning for comprehensive dental condition classification.

Dental health issues are on the rise, necessitating prompt and precise diagnosis. Automated dental condition classification can support this need. The study aims to evaluate the effectiveness of deep learning methods and multimodal feature fusion techniques in advancing the field of automated dental condition classification. A dataset of 11,653 clinically sourced images representing six prevalent dental conditions-caries, calculus, gingivitis, tooth discoloration, ulcers, and hypodontia-was utilized. Features were extracted using five Convolutional Neural Network (CNN) models, then fused into a matrix. Classification models were constructed using Support Vector Machines (SVM) and Naive Bayes classifiers. Evaluation metrics included accuracy, recall rate, precision, and Kappa index. The SVM classifier integrated with feature fusion demonstrated superior performance with a Kappa index of 0.909 and accuracy of 0.925. This significantly surpassed individual CNN models such as EfficientNetB0, which achieved a Kappa of 0.814 and accuracy of 0.847. The amalgamation of feature fusion with advanced machine learning algorithms can significantly bolster the precision and robustness of dental condition classification systems. Such a method presents a valuable tool for dental professionals, facilitating enhanced diagnostic accuracy and subsequently improved patient outcomes.

The Role of Machine Learning in Detecting and Preventing Data Breaches

Data breaches pose a growing threat to individuals, organizations, and public safety. In response, machine learning (ML) has emerged as a powerful tool for both detecting and preventing these breaches. This research paper analyses the multifaceted role of ML in data security, exploring its strengths, limitations, and potential future directions. Through a comprehensive literature review, this paper examines how different ML models and algorithms can be employed to detect anomalous behavior, predict cyberattacks, and mitigate vulnerabilities. The importance of ethical considerations surrounding privacy and user rights is also addressed, emphasizing responsible data handling practices. Furthermore, the paper investigates the challenges and best practices of integrating ML into existing security infrastructure, providing recommendations for organizations seeking to leverage its benefits. Finally, it assesses the current limitations of ML in data breach detection and prevention, identifying promising research avenues for advancing data security through ML advancements. In conclusion, this research highlights the crucial role of ML in the ongoing battle against data breaches. By effectively utilizing its capabilities while maintaining ethical considerations, organizations can significantly enhance their data security posture and safeguard valuable information in our increasingly digital world.

Attention-Based Models for Snow-Water Equivalent Prediction

Snow Water-Equivalent (SWE)—the amount of water available if snowpack is melted—is a key decision variable used by water management agencies to make irrigation, flood control, power generation, and drought management decisions. SWE values vary spatiotemporally—affected by weather, topography, and other environmental factors. While daily SWE can be measured by Snow Telemetry (SNOTEL) stations with requisite instrumentation, such stations are spatially sparse requiring interpolation techniques to create spatiotemporal complete data. While recent efforts have explored machine learning (ML) for SWE prediction, a number of recent ML advances have yet to be considered. The main contribution of this paper is to explore one such ML advance, attention mechanisms, for SWE prediction. Our hypothesis is that attention has a unique ability to capture and exploit correlations that may exist across locations or the temporal spectrum (or both). We present a generic attention-based modeling framework for SWE prediction and adapt it to capture spatial attention and temporal attention. Our experimental results on 323 SNOTEL stations in the Western U.S. demonstrate that our attention-based models outperform other machine-learning approaches. We also provide key results highlighting the differences between spatial and temporal attention in this context and a roadmap toward deployment for generating spatially-complete SWE maps.

Development of a Probabilistic Boolean network (PBN) to model intraoperative blood pressure management

BackgroundBlood pressure is a vital sign for organ perfusion that anesthesiologists measure and modulate during surgery. However, current decision-making processes rely heavily on clinicians’ experience, which can lead to variability in treatment across surgeries. With the advent of machine learning, we can now create models to predict the outcomes of interventions and guide perioperative decision-making. The first step in this process involves translating the clinical decision-making process into a framework understood by an algorithm. Probabilistic Boolean networks (PBNs) provide an information-rich approach to this problem. A PBN trends toward a steady state, and its decisions are easily understood via its Boolean predictor functions. We hypothesize that a PBN can be developed that corrects hemodynamic instability in patients by selecting clinical interventions to maintain blood pressure within a given range. MethodsData on patients over the age of 65 undergoing surgery with general anesthesia from 2018 to 2020 were drawn from the UF Health PRECEDE data set with IRB approval (IRB201700747). Parameters examined included heart rate, blood pressure, and frequency of medications given 15 min after anesthetic induction and 15 min before awakening. The medication frequency data were truncated into a 66/33 split for the training and validation set used in the PBN. The model was coded using Python 3 and evaluated by comparing the frequency of medications chosen by the program to the values in the testing set via linear regression analysis. ResultsThe network developed successfully models a hemodynamically unstable patient and corrects the imbalance by administering medications. This is evidenced by the model achieving a stable, steady state matrix in all iterations. However, the model's ability to emulate clinical drug selection was variable. It was successful with its use of vasodilator selection but struggled with the appropriate selection of vasopressors. ConclusionsThe PBN has demonstrated the ability to choose appropriate interventions based on a patient's current vitals. Additional work must be done to have the network emulate the frequency at which drugs are selected from in clinical practice. In its current state, the model provides an understanding of how a PBN behaves in the context of correcting hemodynamic instability and can aid in developing more robust models in the future.

BFS2Adv: Black-box adversarial attack towards hard-to-attack short texts

The advent of Machine Learning as a Service (MLaaS) and deep learning applications has increased the susceptibility of models to adversarial textual attacks, particularly in black-box settings. Prior work on black-box adversarial textual attacks generally follows a stable strategy that involves leveraging char-level, world-level, and sentence-level perturbations, as well as using queries to the target model to find adversarial examples in the search space. However, existing approaches prioritize query efficiency by reducing the search space, thereby overlooking hard-to-attack textual instances. To address this issue, we propose BFS2Adv, a brute force algorithm that generates adversarial examples for both easy-to-attack and hard-to-attack textual inputs. BFS2Adv, starting with an original text, employs word-level perturbations and synonym substitution to construct a comprehensive search space, with each node representing a potential adversarial example. The algorithm systematically explores this space through a breadth-first search, combined with queries to the target model, to effectively identify qualified adversarial examples. We implemented and evaluated a prototype of BFS2Adv against renowned models such as ALBERT and BERT, utilizing the SNLI and MR datasets. Our results demonstrate that BFS2Adv outperforms state-of-the-art algorithms and effectively improves the success rate of short-text adversarial attacks. Furthermore, we provide detailed insights into the robustness of BFS2Adv by analyzing those hard-to-attack examples.

Enhancing banking governance: A machine learning-based credit risk classification

<p>Risk management in the banking sector has gained heightened significance following the 2008 Global Financial Crisis. With the advent of Machine Learning (ML) techniques, financial institutions are increasingly turning to Artificial Intelligence (AI) for enhanced risk assessment and management. This paper introduces a systematic protocol for implementing a decision tree classifier tailored for credit risk classification. Additionally, we develop a user-friendly web application utilizing the Flask framework and Python Pickle library. This application offers customers an intuitive interface to input their attributes and receive predictions regarding their credit risk classification. Our empirical findings demonstrate that the Support Vector Machine (SVM) achieves a commendable accuracy of 77% in classifying customers based on their banking data. Furthermore, the web application proves to be an effective means for customers to interact with the ML model, enhancing accessibility and user engagement. These outcomes underscore the substantial benefits that ML techniques can bring to the banking industry, enabling improved risk detection and management while concurrently enhancing customer service delivery.</p>

Abstract 2336: A prototype for a machine-learning assisted image analysis tool for preclinical in vivo studies

Abstract The purpose of this study was to build a software tool to test the feasibility of machine-learning (ML) assisted analysis of in vivo 3D images in oncology research studies. Conventionally, in vivo image segmentations are performed by hand, and are a bottleneck for data analysis, taking time and introducing both inter and intra-user variability. Recently, advances in ML have shown promise in accelerating similar clinical image analysis tasks. Our objective was to work toward making this technology accessible to preclinical cancer researchers. 3D image data across multiple mouse models, organs, modalities, and imaging systems were used. ML segmentation models were trained with user-defined masks on images of mouse bladders (N=134), kidneys (N=131), livers (N=65), and lungs (N=26) from either ultrasound or micro-computed tomography (uCT) scanners. Models were developed using PyTorch/MONAI, hosted in an AWS cloud environment, and served to users via a custom extension for 3D Slicer (www.slicer.org). Performance was assessed as the difference between the human vs. ML organ volumes on a test set unseen by the models during training. Lastly, the functionality of on-the-fly segmentation improvement tools through iterative user feedback was assessed. Results demonstrated that generating segmentations with the prototype ML software took 2-6 seconds per image running on a modern GPU (NVIDIA RTX 3090), compared to 3-7 minutes if performed manually by an expert user (>30x improvement). The Dice scores between the ML generated and human segmentations ranged from 0.81 (liver ultrasound) to 0.84 (bladder ultrasound) but could be improved using ML-based on-the-fly mask improvement tools. Using data from this pilot study, we estimate that the threshold to achieve 90% accuracy on first-pass segmentations is between 200-300 training images, depending on the variance observed in the image data. In summary, the prototype software was able to decrease the manual analysis time across a variety of preclinical in vivo image modalities, which is broadly relevant to preclinical oncology research. The next steps for this project will be to extend the platform to additional orthotopic tumor models (e.g. pancreatic, liver, prostate, etc.) and deploy to the field to enable access to this toolset by preclinical imaging scientists across the world. Citation Format: Adam M. Aji, Thomas M. Kierski, Juan D. Rojas, Hannah Morilak, Olivia J. Kelada, Kathryn H. Gessner, Andrew S. Gdowski, Lucia Kim, William Y. Kim, Ryan C. Gessner, Tomek J. Czernuszewicz. A prototype for a machine-learning assisted image analysis tool for preclinical in vivo studies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2336.

ROLE AND EVOLUTION OF COMPUTER VISION IN MEDICINE

As the technologies evolve, they become more and more applicable to such fields as medicine and sciences. This article explores the transformative role of computer vision in modern medicine. It delves into the evolution and diverse applications of computer vision technology, highlighting its profound impact on medical imaging, diagnostics, and surgical procedures. Through advanced imaging techniques and machine learning algorithms, computer vision enhances diagnostic accuracy, facilitates surgical navigation, and enables real-time analysis of medical data. The article discusses key insights from industry experts and showcases notable advancements in disease detection, foreign body identification, and injury estimation. Moreover, it emphasizes the potential of computer vision to revolutionize healthcare delivery by improving patient outcomes, streamlining workflows, and enhancing clinical decision-making.

Abstract 4911: PAIRWISE: Deep learning-powered personalized medicine approach identifies actionable drug combinations in B cell lymphoma

Abstract Combination drug therapies offer promise for improving cancer treatment. However, identifying actionable drug combinations for specific cancer subtypes and individual patients remains challenging due to the vast number of possibilities. Existing approaches like high-throughput screening (HTS) and rule-based drug additions have limitations in their ability to predict clinically translatable synergistic combinations. Therefore, advanced machine learning focused on patient-centric modelling have the potential to optimize combination therapies. PAIRWISE is a patient-centric deep learning-powered drug combination recommendation platform. Given gene expression along with chemical structures and targets from a set of two drugs being applied, the output is the binary combination outcome. PAIRWISE introduces a new approach of representing tumor genomics using the unsupervised pretraining design on 11K TCGA tumors. The power of PAIRWISE is derived from knowledge-guided transfer learning by learning from in vitro experiments with drug-drug-cell interactions and cellular heterogeneity. PAIRWISE can accurately predict combination synergy with area under the curve (AUC) > 0.85 across 10 tissue types in a large dataset of 200K in vitro drug combinations and significantly outperform all state-of-the-art methods. Diffuse large B cell lymphoma (DLBCL) is the most common B cell non-Hodgkin lymphoma and remains incurable in around 40% of patients. Finding optimal combination therapy for each DLBCL patient is a critical unmet need. As independent validation, we applied PAIRWISE to an external HTS study of Bruton Tyrosine Kinase inhibitor (BTKi) combinations (Griner et al., 2014), confirming the reproducibility and accuracy of high-confidence predictions (AUC = 0.72). PAIRWISE was also applied to transcriptomic data of 29 DLBCL cell lines (Bal et al., 2022) and predicted BTKi-containing combinations across ABC subtypes with higher synergy scores than GCB (P = 0.02). This is consistent with expected better overall efficacy of BTK inhibitors in ABC subtype (Younes et al., 2019; Davis et al., 2010; Wilson et al., 2015). To predict opportunities in DLBCL, PAIRWISE was used to identify BTKi partners for an additional 211 anti-cancer drugs using 562 published ex vivo DLBCL samples (Schmitz et al., 2018). PAIRWISE effectively identified novel DLBCL sub-population with significantly higher response scores for predicted BTKi combinations and favorable survival. Notably, patients predicted as responsive had significantly better outcomes upon first-line chemotherapy treatments than non-responsive ones (P < 0.0001). Collectively, we demonstrate that PAIRWISE is a highly efficient and generalizable framework that enables confident predictions of pairwise drug combinations at disease subtype level, with the potential of informing treatment options and clinical trial design. Citation Format: Chengqi Xu, Jake Cohen-Setton, Zhouyang Shen, Marta Milo, Ilkay US, Ben Sidders, Jude Fitzgibbon, Heng Pan, Olivier Elemento, Krishna Bulusu. PAIRWISE: Deep learning-powered personalized medicine approach identifies actionable drug combinations in B cell lymphoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4911.

Narrative R&D disclosure and bank loans: Evidence from China

By taking advantage of machine learning and textual analysis method to construct narrative R&D disclosures, we investigate the impact of narrative R&D disclosures of China's listed firms on their access to bank financing with the two-way fixed effects model. We found that narrative R&D disclosures lead to an increase in bank financing of listed firms. This conclusion still holds after a series of robustness and endogeneity tests. Additionally, it is found that the enhancement of incremental information and banks' superiorities in processing complicated public information are the mechanisms. Finally, we further find that the positive impact of narrative R&D disclosures on bank loans is mainly manifested in the sample of firms operating in highly competitive industries, non-state-owned in nature and R&D-intensive.

Integrating Machine Learning in Anti-Money Laundering through Crypto: A Comprehensive Performance Review

The integration of machine learning (ML) algorithms in Anti-Money Laundering (AML) practices has garnered significant attention due to its potential to enhance the detection and prevention of illicit activities in the cryptocurrency ecosystem. This systematic literature review analysed the effectiveness of integrating ML algorithms in detecting and preventing crypto laundering activities, identify the most frequently used ML algorithms, examine trends in publication and research methodologies, and discuss key challenges and constraints associated with integrating ML technologies into AML frameworks. A comprehensive search strategy was employed to identify relevant studies, resulting in the inclusion of 52 articles published between 2019 and 2023. The findings reveal a growing interest in the field, with a notable increase in publications in recent years. Traditional ML models such as Logistic Regression, Random Forest, and Support Vector Machine (SVM) remain prevalent, while deep learning models like Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks are gaining popularity. Graph Convolutional Networks (GCNs) have emerged as a significant area of exploration, particularly in the context of graph data analysis in cryptocurrencies. Despite advancements in ML, cryptocurrencies continue to pose a high risk of money laundering due to the practical challenge of implementation ownership of the various ML models. Future research should focus on how these challenges will be addressed to ensure the effective and sustainable use of ML technologies in real-world AML practices.

Application of Long Short-Term Memory (LSTM) in Stock Price Prediction

No doubt, the stock market has been one of the most volatile and this makes it very difficult to carry out forecast or prediction about the movement in share prices. However, the advent of machine learning is gradually changing the narratives as there are a number of neural networks which could be used to develop models to effectively predict the stock prices. This study examined the application of Long Short-Term Memory algorithms in predicting stock prices using time series data on Apple shares from 2017 to 2022. The closing price of the stocks was adopted and the data split into 98% for training and 2% for test because the study only wanted to make prediction for the last 20 days. TensorFlow together with its subset Keras libraries were employed with other libraries like Dropout for regularization and sklearn for normalization. NumPy to build array, pandas for data analysis were also imported with matplotlib for the purpose of plotting the result graph. The LSTM model was trained to learn from the sequential data and predict the share price. The outcome revealed that the machine learnt very effectively and has a predictive ability for share prices. The model was able to predict the trend or pattern in prices almost accurately.

Advanced machine learning algorithm to predict the implication of climate change on groundwater level for protecting aquifer from depletion

Due to the impact of climate change, the groundwater level (GWL) has been declining recently in Malaysia, which is essential to protect the groundwater aquifer against depletion. Therefore, the current study aimed to propose an accurate GWL prediction model using advanced machine learning (ML) algorithms in five populated towns, namely Jenderam, Bangi, Beranang, Kajang, and Paya Indah Wetland which are in Selangor, Malaysia. The models developed, used 11 months of previously recorded daily meteorological data of rainfall, temperature, evaporation, and GWL data from one selected well for each town, to predict 1-day, 3-day, and 5-day horizons GWL. For all five locations, four ML algorithms have been trained, tested, and then evaluated: long short-term memory (LSTM), extreme gradient boost (XGBoost), Artificial Neural Network (ANN), and Support Vector Regression (SVR). Further, the best model among the four proposed models is used to predict daily GWL from January 2030 to December 2039 using projected rainfall and temperature data extracted from the Intercomparison Project Phase 5 (CMIP5) climate model. Applying the same 3 different input combinations for the models, the results showed that all the locations, including the GWL time-series data, improved the prediction accuracy significantly in all four models. Using testing data for 1-day ahead GWL prediction at Paya Indah Wetland as the best-performing location, XGBoost achieved the highest prediction performance with root mean squared error (RMSE) of 0.026 followed by LSTM, ANN, and SVR with RMSE of 0.027, 0.050, and 0.085 respectively. Ultimately, the results obtained in this study serve as a great benchmark for future GWL prediction using LSTM and XGBoost algorithm and give an insight into the influence of climate change on future GWL. Further, the findings can help local water resource managers draft resealable accuracy water resource plans in the state of Selangor for the next decade.

Screening Metabolic Biomarkers in KRAS Mutated Mouse Acinar and Human Pancreatic Cancer Cells via Single-Cell Mass Spectrometry.

Pancreatic cancer is a highly aggressive and rapidly progressing disease, often diagnosed in advanced stages due to the absence of early noticeable symptoms. The KRAS mutation is a hallmark of pancreatic cancer, yet the underlying mechanisms driving pancreatic carcinogenesis remain elusive. Cancer cells display significant metabolic heterogeneity, which is relevant to the pathogenesis of cancer. Population measurements may obscure information about the metabolic heterogeneity among cancer cells. Therefore, it is crucial to analyze metabolites at the single-cell level to gain a more comprehensive understanding of metabolic heterogeneity. In this study, we employed a 3D-printed ionization source for metabolite analysis in both mice and human pancreatic cancer cells at the single-cell level. Using advanced machine learning algorithms and mass spectral feature selection, we successfully identified 23 distinct metabolites that are statistically significantly different in KRAS mutant human pancreatic cancer cells and mouse acinar cells bearing the oncogenic KRAS mutation. These metabolites encompass a variety of chemical classes, including organic nitrogen compounds, organic acids and derivatives, organoheterocyclic compounds, benzenoids, and lipids. These findings shed light on the metabolic remodeling associated with KRAS-driven pancreatic cancer initiation and indicate that the identified metabolites hold promise as potential diagnostic markers for early detection in pancreatic cancer patients.