Supervised Learning Algorithms Research Articles

Amharic spoken digits recognition using convolutional neural network

Spoken digits recognition (SDR) is a type of supervised automatic speech recognition, which is required in various human–machine interaction applications. It is utilized in phone-based services like dialing systems, certain bank operations, airline reservation systems, and price extraction. However, the design of SDR is a challenging task that requires the development of labeled audio data, the proper choice of feature extraction method, and the development of the best performing model. Even if several works have been done for various languages, such as English, Arabic, Urdu, etc., there is no developed Amharic spoken digits dataset (AmSDD) to build Amharic spoken digits recognition (AmSDR) model for the Amharic language, which is the official working language of the government of Ethiopia. Therefore, in this study, we developed a new AmSDD that contains 12,000 utterances of 0 (Zaero) to 9 (zet’enyi) digits which were recorded from 120 volunteer speakers of different age groups, genders, and dialects who repeated each digit ten times. Mel frequency cepstral coefficients (MFCCs) and Mel-Spectrogram feature extraction methods were used to extract trainable features from the speech signal. We conducted different experiments on the development of the AmSDR model using the AmSDD and classical supervised learning algorithms such as Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) as the baseline. To further improve the performance recognition of AmSDR, we propose a three layers Convolutional Neural Network (CNN) architecture with Batch normalization. The results of our experiments show that the proposed CNN model outperforms the baseline algorithms and scores an accuracy of 99% and 98% using MFCCs and Mel-Spectrogram features, respectively.

Enhanced gate-valve failure detection in water distribution networks using ML and pressure data

ABSTRACT This study introduces an innovative diagnostic approach for identifying gate-valve failures in water distribution systems. By implementing high-frequency pressure sensors upstream and downstream of the gate valves, we obtained detailed pressure data that are pivotal for fault diagnosis. We explored three distinct machine-learning algorithms and two data-handling techniques to ensure optimal performance in real-world applications. In our methodology, supervised learning algorithms are used to analyze pressure differentials and predict valve behavior. We rigorously tested these algorithms using both raw and feature-engineered data, and the results indicated the effectiveness of the Gaussian-naïve Bayes model with six extracted features. This approach enhances the precision and reliability of diagnostics in water distribution networks.

Abstract PO1-28-06: Development of a plasma-based real-time qPCR gene expression assay for targeted screening and diagnosis of early-stage breast cancer

Abstract Background Over 12 million US women undergo follow-up breast imaging and exams annually due to breast cancer suspicions, incurring an $8 billion total cost, of which $2.18 billion is attributed to false-positive breast biopsies. Recent updates published to the Mammography Quality Standards Act (MQSA) now recommend supplemental imaging for women with heterogeneously dense and extremely dense breasts, regardless of suspicious findings. Given sensitivity limitations associated with mammography in dense-breasted women, as low as 30-47%, and non-specificity associated with ultrasound and MRI, these recent recommendations are likely to further strain the healthcare system and place substantial burden on patients and providers. With an estimated 25 million dense-breasted women who regularly screen for breast cancer now considered at-risk, there is a critical need for affordable and highly accurate testing, offering better specificity without sacrificing sensitivity. To address this gap, we developed an affordable and accurate plasma-based gene expression assay using real-time qPCR for targeted screening and diagnosis of early-stage breast cancer. Methods In previous studies, 26 cross-correlated mRNA gene targets were discovered and independently validated for non-invasive breast cancer detection across five independent patient cohorts using microarray gene expression profiling, comprised of peripheral blood mononuclear cells (n=337) and saliva (n=20), demonstrating strong efficacy, reproducibility, and concordance across bio-fluids and assay platforms in all studies. A sixth independent validation cohort comprised of 203 plasma samples was subsequently obtained for real-time qPCR clinical assay development and validation in our CLIA laboratory. The CLIA validation cohort was designed to be representative of different diagnosis status, stage, and ethnicity, and included Caucasian, Black/African American, Hispanic, and Asian women. After normalizing mRNA expression and clustering analysis, the signature was refined to 8 target genes and was assessed in a cohort of 87 plasma samples [Table 1] to verify the assay’s diagnostic performance for stage I breast cancer detection, under locked laboratory protocols. We leveraged machine learning methods derived from XGBoost classification, a supervised-learning algorithm that uses sequentially built shallow decision trees to provide accurate results and avoidance of overfitting. Results The XGBoost model, selecting from the 8 mRNA gene targets and patient age, achieved >99% sensitivity, 89% specificity for stage I breast cancer detection in the held-out test set, with an overall diagnostic accuracy of 94.5%. Normalized data showed significant differences in gene expression between healthy controls and stage I patients, and distinct clustering was observed for the 8 mRNA gene signature, including patient age. Conclusions Our plasma-based real-time qPCR gene expression clinical assay, with machine learning, is positioned as a highly accurate non-invasive tool for targeted screening and diagnosis of early-stage breast cancer. Furthermore, a clinically validated assay in this space addresses the need for more targeted diagnostics, while serving as a promising tool for clinicians as they make critical care decisions across the breast health continuum, accelerating time to earlier and more precise intervention and treatment, mitigating unnecessary healthcare expenditures, and reducing the mental, emotional, and financial burden on patients and their families. Citation Format: Martin Keiser, Elizabeth Cormier-May, Matthew Alderdice, Joy Kavanagh, William Guesdon, Heather Healy, Nathalie Jean-Charles, Jay Harness. Development of a plasma-based real-time qPCR gene expression assay for targeted screening and diagnosis of early-stage breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-28-06.

Development and performance assessment of a novel multigeneration clean energy system based on biomass-LNG using a dynamic model and supervised learning algorithms

Combining process integration mechanisms with artificial intelligence (AI) can be used as a tool for maximum use of biomass capacity and energy production. This study proposes a continuous multi-generation hybrid energy production system based on biomass-LNG using the carbon capture, utilization, and storage (CCUS) method. In this system, using the Gibbs free energy minimization approach, a process based on the fluidized bed gasifier was designed, which in addition to producing hydrogen and electricity from biomass, also produces liquid CO2 and precipitated calcium carbonate (PCC) from liquid natural gas and limestone for the first time. This process was also examined from thermal (HHV) and thermodynamic (Exergy) standpoints. The simulation of the gasification unit was able to predict the percentage of exhaust gases from the gasifier with errors of RMSE = 3.8 and RMSE = 3.2 for almond shell and rice shell biomass, respectively. Following that, a dataset with more than 14 million records was generated. Then, machine learning methods were employed to investigate and improve the process's simulation characteristics. The evaluation of 15 machine learning algorithms in the construction of the predictive model showed that ANN, Extra Tree Regressor, and Random Forest are the most accurate algorithms in predicting the desired values (such as hydrogen, work, PCC, liquid CO2, exergy, and HHV) with R2 > 0.99. The dataset analysis showed that the current process could produce 130 kg/h of hydrogen, 375 kWh of work, 2600 kg/h of PCC, and 531 kg/h of liquid carbon dioxide on average. As a final step, a WPF desktop application was developed that simplifies the use of ML models so that the impact of changing the variables can easily be calculated.

Crossflow Microfiltration of Aqueous Suspensions with Guar and Xanthan Gums: Identification of Solutions Using Artificial Neural Networks

Artificial Neural Networks (ANNs) are mathematical models used in the computational area that act in an analogous way to the central nervous system of living beings, which possess the ability of acquiring knowledge in a technique called machine learning, allowing them to recognize patterns and stop numerous applications. Therefore, the objective was to develop Neural Networks capable of identifying aqueous solutions with Guar and Xanthan gums (widely used in the food industry) during the crossflow microfiltration process. The networks were trained in the supervised learning algorithms trainscg, trainlm and traingd, all in the 70/15/15 model, for a range of five to fifteen neurons in the hidden layer, whose datasets were found in the literature, referring to temperature, flow velocity, pressure, transmembrane flow rate, time and membrane pore size. The software used to implement the ANNs was MATLAB and the evaluation criteria consisted of the analysis of the parameters confusion matrix, error histogram,performance and ROC curve. In summary, ten ANNs had satisfactory performances, presenting confusion matrices with accuracies above 98.8%, error histogram graphs being Gaussian centered at 0, decaying performance curves with stopping criterion equal to 6 errors in the validation set and ROC graphs similar to a square with vertices at (0,0), (1,0), (0,1) and (1,1), results considered satisfactory in the literature.

The Phisherman’s Gambit

Phishing remains a pervasive threat in the digital landscape, posing significant risks to individuals and organizations alike. In response, this paper presents a sophisticated approach to phishing website detection utilizing machine learning methodologies. Through the amalgamation of diverse features extracted from URLs, domain attributes, and webpage content, a robust classification framework is constructed. Employing an array of supervised learning algorithms, including decision trees, support vector machines, and neural networks, our proposed system demonstrates its efficacy in accurately discerning phishing websites with notable precision and recall rates. Moreover, feature engineering and selection techniques are implemented to optimize model performance and computational efficiency. Experimental evaluations conducted on comprehensive datasets validate the effectiveness of the proposed approach in proactively identifying and mitigating phishing threats, thereby fortifying cybersecurity measures for users and organizations in the digital realm.

VOC data-driven evaluation of vehicle cabin odor: from ANN to CNN-BiLSTM.

Emissions of volatile organic compounds (VOCs) in vehicles represent a significant problem, causing unpleasant odors. To mitigate VOCs and odors in vehicles, it is critical to choose interior parts with low odor and VOC emissions. However, prevailing odor evaluation methods are subjective, costly, and potentially harmful to the health of evaluators. In this study, we analyzed 139 automotive interior parts and 92 vehicles, establishing a cost-effective, data-driven method for odor evaluation. The contents of benzene, toluene, ethylbenzene, xylene, styrene, formaldehyde, acetaldehyde, acrolein, and total volatile organic compounds (TVOC) were detected by thermal desorption gas chromatography-mass spectrometry (TD-GC/MS) and high-performance liquid chromatography with an ultraviolet detector (HPLC-UV). Professional odor evaluators assessed the odors, identifying intensity levels from 2.0 to 4.5 in interior parts and 2.5 to 3.5 in whole vehicles. Leveraging this data, we applied four supervised learning algorithms to develop predictive models for the odor intensity of both interior parts and entire vehicles. During model training, we implemented early stopping techniques for the artificial neural network (ANN) and convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) models, while optimizing the support vector machine (SVM) and extreme gradient boosting (XGBoost) models using the GridSearch algorithm. The evaluation results reveal that the CNN-BiLSTM model performs the best, achieving an average accuracy of 89% for unknown samples within an odor intensity level of 0.5. The root mean square error (RMSE) is 0.24, and the mean absolute error (MAE) is 0.08. The model also underwent a sevenfold cross-validation, achieving an accuracy of 83.43%. Additionally, we employed SHapley Additive exPlanations (SHAP) for the interpretative analysis of the model, which confirmed the consistency of each VOC's odor contribution with human olfactory rules. By predicting odors based on VOCs through supervised learning, this study reduces the costs and enhances the efficiency and applicability of odor assessment across various vehicle interiors.

Propagating Image-Based Rock Classes from Cored to Non-Cored Depth Intervals Using Supervised Machine Learning

High-resolution image data is instrumental in quantifying the variation of rock fabric in formation evaluation that conventional well logs fail to capture. However, the acquisition of image data for all wells in a reservoir is restricted due to technology limitations and operational constraints and the high cost involved. The main objective of this paper is to propose a workflow to extrapolate rock fabric information from imaged wells to nearby un-imaged wells for enhanced formation evaluation in un-imaged wells. To propagate rock fabric information, we trained a supervised learning algorithm in a well with core photos, CT-scan images, and conventional well logs. Subsequently, the trained model is used to identify fabric-influenced well-log-based rock classes using only conventional well logs in un-imaged depth intervals/well (referred to as fabric-based rock classes). We applied the proposed workflow to two wells in a siliciclastic formation with spatial variation in rock fabric. Comparison of the detected fabric-based rock classes in the nearby depth intervals/well using the trained model with image-based rock classes resulted in an average accuracy of 94%. The outcomes of this paper contribute to accelerated identification of rock types honoring rock fabric while minimizing extensive imaging and coring efforts. Thematic collection: This article is part of the Digitally enabled geoscience workflows: unlocking the power of our data collection available at: https://www.lyellcollection.org/topic/collections/digitally-enabled-geoscience-workflows

Tire mode shape categorization using Zernike annular moment and machine learning classification

This research proposes a framework for categorizing the radial tire mode shapes using machine learning (ML) based classification and feature recognition algorithms, advancing the development of a digital twin for tire performance analysis. Tire mode shape categorization is required to identify modal features in a specific frequency range to maximize driving performance and secure safety. However, the mode categorization work requires a lot of manual effort to interpret modes. Therefore, this study suggests an ML-based classification tool to replace the conventional categorization process with two primary objectives: (1) create a database by categorizing the tire mode shapes based on the identified features and (2) develop an ML-based surrogate model to classify the tire mode shapes without manual effort. The feature map of the tire mode shape is built with the Zernike annular moment descriptor (ZAMD). The mode shapes are categorized using the correlation value derived by the modal assurance criteria (MAC) with all ZAMD values for each tire mode shape and subsequently creating the appropriate labels. The decision tree, random forests, and XGBoost, the representative supervised-learning algorithms for classification, are implemented for surrogate model development. The best-performed classifier can categorize the mode shapes without any manual effort with a high accuracy of 99.5%.

Transformer encoder based self-supervised learning for HVAC fault detection with unlabeled data

Data driven methods are the most studied fault detection and diagnostics (FDD) type in buildings HVAC systems. However, most studies rely on labeled data for specific faults which are hard to find and collect for real systems. While the fault-free data is easier to collect, it is still time consuming to label for large systems operation. Moreover, most of the studies rely on the usage of supervised learning algorithms which do not generalize well beyond the training data making unseen faults hard to detect. In this paper, we define a methodology to use a self-supervised learning method for HVAC systems' FDD using a Transformer encoder, moreover, we tested it on a real case study. By strategically masking portions of the multivariate time-series data using Markov chain approach with two states. The model is trained by predicting these concealed segments. This approach, independent of labeled data, offers a scalable solution for practical HVAC applications. Anomalies are labeled using the Peak Over Threshold (POT) method, which dynamically determines thresholds by fitting reconstruction errors to a generalized Pareto distribution. Subsequent fault diagnostics emphasize features with pronounced reconstruction errors, pinpointing potential HVAC malfunctions. This methodology reduces dependence on labeled datasets and augments the model's generalization, facilitating detection of unobserved faults. This approach was applied to data from a real building. As a results multiple faults were detected mainly due to the malfunctioning of the monitoring system. The model demonstrates the ability to detect both sequential and individual faults. The period from October 19th to December 23rd was detected as a fault period due to the change in the trend of the data because of the monitoring system.

Evaluating Multi-target Regression Framework for Dynamic Condition Prediction in Wellbore

AbstractIn recent years, the focus has shifted towards leveraging physics-based modelling and data-driven analysis to predict drilling incidents and anomalies in real time, with the goal of reducing non-productive periods. However, much of this attention has directed at specific drilling operations like drilling and tripping, leaving other vital processes, such as wellbore conditioning, comparatively overlooked. The primary objective of this study is to employ data-driven techniques for predicting the dynamic state of the wellbore by utilising sensor data, operating parameters, and surface measurements. Accurate predictions are pivotal for automating these processes, promising significant savings in both redundant time and associated costs, ultimately elevating operational efficiency.In this research, the surface drilling parameters such as flowrate, rotation speed, block position, and drill string length are incorporated with the surface measurements such as hookload, pressure, and torque during wellbore conditioning operation to predict further surface sensor measurements. Different parameter settings are evaluated to find the best approach. Six supervised learning algorithms are used to select the best prediction method. The findings reveal that considering all surface parameters and measurements yields the most accurate predictions. Among various single and multi-target regression methods, including deep learning approaches, the Gaussian process and random forest models exhibit the lowest prediction errors.By reliably predicting and understanding wellbore behaviour, this research paves the way for more efficient and autonomous drilling operations in the future, bridging a critical gap in the industry's automation capabilities.

Spam Review Detection using Machine Learning

Customer opinions play a vital role in buying decisions. These days most customers post their opinions about products on blogs, e-commerce sites, review sites, and social networking sites. The above information is consumed by business or corporate organizations, as they are eagerly interested in analyzing consumer views about their products, services, and support. As people buy products after reading the reviews, the kind of reviews that a product attracts are of concern to the sellers. This means that a positive review on the product would bring in sales and a negative one would reduce them. The project leverages Natural Language Processing (NLP) techniques and supervised learning algorithms to build a robust spam review detection system. The system is trained on a dataset comprising genuine and spam reviews, and it extracts various features from the textual content of reviews, such as sentiment analysis, linguistic patterns, and semantic meaning.

Fake Job Detection Using Machine Learning

The research suggests using machine learning classification methods to identify and prevent fake job postings online. Nowadays, many companies prefer to advertise their job vacancies on the internet for easy access by job seekers. However, there are scammers who trick people into paying for non-existent jobs. Through data analysis and machine learning, we can distinguish between legitimate and fake job postings. Various algorithms are utilized to detect fraudulent posts and protect job seekers from falling victim to scams. The system is designed to teach the model how to distinguish between real and fake job listings using past data on fraudulent and legitimate job postings. Initially, supervised learning algorithms like classification techniques can be used to tackle the problem of identifying scammers in job ads. It will utilize multiple machine learning algorithms and choose the one with the best accuracy in predicting if a job posting is legitimate or not. Key Words: Fraud Job, Job Seeker, Machine Learning, Internet Recruitment, Classification

IoT-Based Irrigation System Using Machine Learning for Precision Shallot Farming

Despite the massive production of shallots in Enrekang Regency, South Sulawesi Province, Indonesia, the cultivation method is still very conventional. Shallot cultivation is very challenging because it requires precision irrigation and pest prevention. In this research, we proposed a smart irrigation system to help farmers manage irrigation with more efficient water usage without hampering their pest prevention. The system outcomes were three options: 1) no water needed, 2) water is required and is efficient for watering and 3) water is required but it is not efficient for watering. We used Wireless Sensor Networks and IoT to collect yield parameters, designed a firebase database, and developed a mobile application and a web service embedded with a machine learning application. All applications interacted by using the Representational State Transfer Application Programming Interface. The proposed system architecture successfully gathered cropland data and distributed them to all applications within the system. Furthermore, we analyzed four supervised learning algorithms (decision trees, random forest, gradient boosting, and K-Nearest neighbor), and the random forest was deployed in the web service because it outperformed other algorithms with an accuracy of 94% and AUC Score of 0.90.

Modeling and Estimation of Reference Evapotranspiration using Machine Learning Algorithms: A Comparative Performance Analysis

Fresh, clean water is necessary for human health. Currently, the agriculture sector uses the majority of freshwater for irrigation without using planning or optimization techniques. Evapotranspiration, which may have a major impact in planning water supply management and crop yield improvement, is an element of the hydrological cycle. Accurate anticipation of reference evapotranspiration (ETO) is an intricate job due to its nonlinear behavior. Machine learning approach based model may be an intelligent tool to predict the accurate ETO. This study investigates and compares the predictive skills of three regression based supervised learning algorithms: decision tree (dtr), and random forest (rfr), and k-nearest-neighbors (knnr) along with tuning their hyper-parameters like how many neighbors there are in knnr, minimum samples in dtr at a leaf node and quantity of trees in the rfr scenario to forecast ETO. Every model's performance is quantified on four different groups of meteorological parameters. Groups are created based on close correlation of meteorological parameters with ETo. In this investigation, analysis is carried out on daily meteorological information of New Delhi, India for the periods from 2000 to 2021. The predicted results of the knnr, dtr and rfr models on four groups of meteorological inputs (twelve different models) are compared with ETO obtained from the FAO-PM56 equations. The study's conclusions show that the k-nearest-neighbors and random forest regression-based models outperform the decision tree regression models concerning performance. The finest performance noted by knnr and rfr models with r2 (coefficient of determination) of 0.99 and rmse of 0.21 and 0.22 mm/day respectively whereas dtr model noted r2 of 0.98 and rmse of 0.40 mm/day. Therefor these models may provide scientists, engineers, and farmers with more potent choices for managing water resources and scheduling irrigation.

Spatio-temporal trajectory data modeling for fishing gear classification

International Organizations urge the protection of our oceans and their ecosystems due to their immeasurable importance to humankind. Since illegal fishing activities, commonly known as IUU fishing, cause irreparable damage to these ecosystems, concerned organisms are pushing to detect and combat IUU fishing practices. The automatic identification system allows to locate the position and trajectory of fishing vessels. In this study we address the task of detecting vessels’ fishing gears based on the trajectory behavior defined by GPS position data, a useful task to prevent the proliferation of IUU fishing practices. We present a new database including trajectories that span 7 different fishing gears and analyze these as in a time sequence analysis problem. We leverage from feature extraction techniques from the online signature verification domain to model vessel trajectories, and extract relevant information in the form of both local and global feature sets. We show how, based on these sets of features, the kinematics of vessels according to different fishing gears can be effectively classified using common supervised learning algorithms with accuracies up to 90%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$90\\%$$\\end{document}. Furthermore, motivated by the concerns raised by several organizations on the adverse impact of bottom trawling on marine biodiversity, we present a binary classification experiment in which we were able to distinguish this kind of fishing gear with an accuracy of 99%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$99\\%$$\\end{document}. We also illustrate in an ablation study the relevance of factors such as data availability and the sampling period to perform fishing gear classification. Compared to existing works, we highlight these factors, especially the importance of using sampling periods in the order of minutes instead of hours.

Soil Base Crop Prediction using Machine Learning

In general, agriculture is the backbone [Grab your reader's attention with a great quote from the document or use this space to emphasize a key point. To place this text box anywhere on the page, just drag it.] of India and also plays an important role in Indian economy by providing a certain percentage of domestic product to ensure the food security. But now-a-days, food production and prediction is getting depleted due to unnatural climatic changes, which will adversely affect the economy of farmers by getting a poor yield and also help the farmers to remain less familiar in forecasting the future crops. This research work helps the beginner farmer in such a way to guide them for sowing the reasonable crops by deploying machine learning, one of the advanced technologies in crop prediction. Naive Bayes, a supervised learning algorithm puts forth in the way to achieve it. The seed data of the crops are collected here, with the appropriate parameters like temperature, humidity and moisture content, which helps the crops to achieve a successful growth. In addition as the software, a mobile application for Android is being developed. The users are encouraged to enter parameters like temperature and their location will be taken automatically in this application in order to start the prediction process

Understanding Consumer Perceptions About Smartwatches: Feature Extraction and Opinion Mining Using Supervised Learning Algorithm

Understanding Consumer Perceptions About Smartwatches: Feature Extraction and Opinion Mining Using Supervised Learning Algorithm

Revolutionizing Drug Discovery: Harnessing Machine Learning Algorithms

Drug discovery is a crucial element of biomedical research, with the goal of finding and creating new medical treatments for a variety of illnesses. Yet, the conventional process of finding new drugs is frequently impeded by its intrinsic difficulties, such as expensive expenses, long durations, and poor success rates in trials with patients. Recently, the incorporation of machine learning (ML) algorithms has become a revolutionary method to streamline and improve different phases of drug discovery. This summary offers a glimpse into the rapidly growing area of drug discovery using machine learning algorithms, emphasizing its potential to transform the process of developing treatments. The usual process of discovering drugs involves various stages such as identifying the target, finding lead compounds, conducting preclinical tests, undergoing clinical trials, and obtaining regulatory approval. All these phases require a lot of labor, time, and resources, leading to high attrition rates and limited success in turning potential compounds into approved therapies. Nevertheless, researchers can enhance and speed up crucial parts of the drug discovery process by using ML algorithms. ML algorithms use data to aid in drug discovery by utilizing computational models to examine large quantities of biological, chemical, and clinical data. These algorithms can learn from various types of data, such as genomic data, chemical structures, protein interactions, and clinical outcomes, to discover hidden patterns, find new targets for drugs, and forecast the effectiveness and safety of potential treatments. Moreover, machine learning algorithms allow for the investigation of intricate connections between molecular structures and biological effects, making it easier to create improved drug candidates with better effectiveness and specificity. Important uses of machine learning in pharmaceutical research involve finding and confirming targets, screening compounds and improving leads, repurposing drugs, and tailoring treatments for individuals. Commonly used for classification and regression tasks, supervised learning algorithms like support vector machines and random forests predict compound activity, toxicity, and pharmacokinetic properties. Clustering and dimensionality reduction techniques utilized in unsupervised learning algorithms help analyze vast datasets and discover new drug-target interactions. Advanced abilities for analyzing molecular structures, virtual screening, and designing new drugs are provided by deep learning models like convolutional neural networks and recurrent neural networks. Multiple case studies demonstrate how ML algorithms can significantly impact drug discovery. Collaboration among academia, industry, and research institutions has resulted in the creation of new ML-based methods for drug development, identifying targets, and categorizing patients. Nevertheless, there are challenges accompanying the widespread use of ML in drug discovery. In healthcare, it is crucial to address ethical considerations, regulatory hurdles, and data privacy concerns to ensure the responsible and ethical use of ML algorithms. The potential for transforming drug discovery and therapeutic development is immense with the incorporation of machine learning algorithms. Through utilizing data-driven methods, researchers can speed up the discovery of new potential drugs, enhance the effectiveness of treatments, and ultimately enhance the results for patients. Ongoing innovation, teamwork, and cross-disciplinary studies are crucial to fully leverage the potential of ML in revolutionizing drug discovery and precision medicine.

Sentiment Analysis on The Place of Interest in Malaysia

This study focuses on utilizing machine learning methods for sentiment analysis to identify positive and negative comments regarding Malaysian Places of Interest (PoI). The data was collected from Twitter using social media monitoring software and organized into tables. Pre-processing techniques and Natural Language Processing (NLP) methods were applied to handle missing values and prepare the text data for analysis. The dataset was then split into training and testing sets, and three supervised learning algorithms which are Support Vector Machine, Random Forest, and Naive Bayes were employed to evaluate the sentiment analysis models. The performance of each model was compared, and it was found that Support Vector Machine achieved the highest accuracy, recall score, F1 score, and precision score. This study demonstrates the potential to extend sentiment analysis to analyze sentiments expressed in texts written in the Malay language by utilizing the Malaya corpus. Additionally, visual dashboards can be created to present the findings and provide recommendations based on the insights gathered from the sentiment analysis of PoI feedback.