Powerful Machine Research Articles

Transformer enabled multi-modal medical diagnosis for tuberculosis classification

Recently, multimodal data analysis in medical domain has started receiving a great attention. Researchers from both computer science, and medicine are trying to develop models to handle multimodal medical data. However, most of the published work have targeted the homogeneous multimodal data. The collection and preparation of heterogeneous multimodal data is a complex and time-consuming task. Further, development of models to handle such heterogeneous multimodal data is another challenge. This study presents a cross modal transformer-based fusion approach for multimodal clinical data analysis using medical images and clinical data. The proposed approach leverages the image embedding layer to convert image into visual tokens, and another clinical embedding layer to convert clinical data into text tokens. Further, a cross-modal transformer module is employed to learn a holistic representation of imaging and clinical modalities. The proposed approach was tested for a multi-modal lung disease tuberculosis data set. Further, the results are compared with recent approaches proposed in the field of multimodal medical data analysis. The comparison shows that the proposed approach outperformed the other approaches considered in the study. Another advantage of this approach is that it is faster to analyze heterogeneous multimodal medical data in comparison to existing methods used in the study, which is very important if we do not have powerful machines for computation.

Epigenetic ageing clocks: statistical methods and emerging computational challenges.

Over the past decade, epigenetic clocks have emerged as powerful machine learning tools, not only to estimate chronological and biological age but also to assess the efficacy of anti-ageing, cellular rejuvenation and disease-preventive interventions. However, many computational and statistical challenges remain that limit our understanding, interpretation and application of epigenetic clocks. Here, we review these computational challenges, focusing on interpretation, cell-type heterogeneity and emerging single-cell methods, aiming to provide guidelines for the rigorous construction of interpretable epigenetic clocks at cell-type and single-cell resolution.

Peranan Komunikasi Publik pada Partai Pengusung Pilkada 2024 Kabupaten Bogor (Studi Terhadap Pasangan No 1 Rudy Susmanto dan Ade Ruhandi)

According to the 2024 election commission (election committee) bogor 2024, the winner is the ruhandi no. 1 Rudy susmanto-ade ruhandi, with the 1,559,328 electory-musyafaur rahman with an issue of 559,453. Before the election was held on Wednesday, November 27, 2024, to search out sympathizers for voters, efforts have been made by both sides. A campaign through social media is being carried out to convince voters to make their choice. As the campaign is carried out, the winning couple select more social media campaigns asa form of public communication, while the campaign through mass mobilization is carried out by both prospective couples but higher levels of intensity by the number 1. Rudy susmanto's victory was also affected by images or self-image made public where previous periods had been DPRD's chairman with his very strong integrity character and his firmness for adherence to the prevailing rules. Besides which he created and operated programs that sided with the interests of many. This consistent value makes values a personal plus profile which is also an important aspect for affecting people to make choices during the election. The victory of the 1 Rudy susmanto-jaro ade was also the result of the powerful, dominant and effective party machine with the full 14 parties supporting the 18. The largest party carried by the number one in line rususmanto-jaro ade is senses and golkar. Bogor district's mobility was awarded 12 seats of parliament, while golkar was seven. In the meantime, the party of gerindra and golkar has become a coalition party in sthe 2024 presidential election, which is also a factor in the win of the number 1 group.

A TWO-STEP AUTHENTICATION FACIAL RECOGNITION SYSTEM FOR AUTOMATED ATTENDANCE TRACKING

This study addresses the need for efficient, automated attendance systems through the design of a facial recognition application. Manual attendance systems are slow, error-prone and the retrieval of old records can be tedious. Universally assessable technological developments such as facial recognition software can easily solve these problems. However, the vast amount of computational resources required for its implementation has posed a limitation to its wide adoption. This study presents a two-step approach to resolve these challenges. By leveraging a faster, less-powerful model, as the first step, the workload of facial recognition can be distributed to save time and computational cost. A more powerful machine learning model is applied as the second step, deployed for tasks that are too complex for the first model to handle. The two-step authentication process will also reduce the occurrences of false negatives. Face_recognition, a python library is used for detection and encoding of face images read using python’s opencv library from an IP webcam. A flask application demonstrates this facial recognition functionality. The database connection and communication are accomplished using flask_sqlalchemy. A graphical user interface (web application) is used to interact with users on a high level, showing saved images of logged personnel and their times of entry. The system has a maximum accuracy of 98.78% and precision of 98.82% from tests. This shows its potential for application on a wider scale, with some added improvements such as cloud deployment and larger datasets.

ADVANCED APPLICATIONS OF PHYSICS-INFORMED NEURAL NETWORKS (PINNS) IN R FOR SOLVING DIFFERENTIAL EQUATIONS

Deep learning, a powerful machine learning technique leveraging artificial neural networks, excels in identifying complex patterns and relationships within data. Among its innovations is the emergence of Physics-Informed Neural Networks (PINNs), which have revolutionized the field of applied mathematics by enabling the solution and discovery of differential equations through neural networks. PINNs address two key challenges: data-driven solutions, where the model approximates the hidden solutions of differential equations with fixed parameters, and data-driven discovery, where the network learns parameters that best describe observed data. This study explores the implementation of PINNs within the R programming environment to solve two differential equations: one with boundary conditions y^'-y=0 with y(0)=0 and y(e)=1 boundaries and the Burgers’ Equation. The research utilizes R libraries, including reticulate for Python integration and torch for neural network operations, to demonstrate the versatility and efficacy of PINNs in addressing both data-centric solutions and parameter discovery. The results showcase the ability of PINNs to handle complex, high-dimensional problems, offering a promising alternative to traditional numerical methods for solving differential equations.

Penerapan Machine Learning Algoritma Regresi Linear Untuk Memprediksi Saham Bank BNI

Indonesia has been growing rapidly, one of which can be seen from the economy and technology in Indonesia, at this time the community is almost entirely using machine power technology as a helper of daily life, and the community has also processed a lot of its finances by way of stock investment, with stock investment, the community believes that stocks are invested safer and more profitable. Shares are securities that show proof of ownership or capital market participation of investors in a company (BNI) and shares have a value that is up and down (volatile). Stocks are very important in a company and stocks are a trigger for rising profits in the company. The rise and fall of stock prices in Indonesia has an adverse effect on companies, especially PT Bank Negara Indonesia (Persero), Tbk. the cause of the rise and fall in stock prices is usually caused by several things, namely the condition and performance of the company, risk, dividends, interest rates, economic conditions, government policies, government issues or other issues, the rate of inflation, supply and demand. Machine learning tools used in predicting stocks, using machine learning, the data obtained is more accurate. Machine learning is an artificial intelligence that can process data that is useful for consideration in making decisions and solving problems. Linear regression algorithm is one of the methods used to predict stock data in Bank Negara Indonesia. Linear regression algorithm tries to model the relationship between two variables by matching the linear equation of the stock data to be studied. One variable is considered the explanatory variable and the other variable is called the dependent variable. Prediction a process for systematically estimating BNI stock data that will appear in the future using data obtained from the past. Thus the company can easily find out the stock data in the future.

Memprediksi Data Saham Bank Mandiri Menggunakan Metode Algoritma Regresi Linear Dengan Bantuan Rapid Miner

Indonesia has been growing rapidly, one of which can be seen from the economy and technology in Indonesia, at this time the community is almost entirely using machine power technology as a helper of daily life, and the community has also processed a lot of its finances by way of stock investment, with stock investment, the community believes that stocks are invested safer and more profitable. A stock can be defined as a mark of participation or ownership of an individual investor or institutional investor or trader on their investment or a certain amount of funds invested in a company. Linear regression algorithm is one of the methods used to predict stock data in Bank Mandiri. Linear regression algorithm tries to model the relationship between two variables by matching the linear equation of the stock data to be studied. One variable is considered the explanatory variable and the other variable is called the dependent variable. Prediction a process for systematically estimating Bank Mandiri stock data that will appear in the future using data obtained from the past. Thus the company can easily find out the stock data in the future.

Analysis Of Machine Learning Algorithms For Image Classification

This research aims to use a subset of the CIFAR100 dataset to develop and present an empirical examination of the performance of powerful Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) for object detection. Image datasets, CIFAR10, CIFAR 100, and MINIST image datasets are all common benchmark datasets for testing performance. This research examines the well-known dataset CIFAR 100. Both classifiers' important attributes are combined in the constructed models. The suggested model's algorithm is trained and tested using images from the CIFAR-100 dataset. The CIFAR 100 is made up of 100 different classes, each with 600 photos. CNN and SVM's receptive fields aid in automatically extracting the most identifiable features from these images. The experimental results confirm the effectiveness of the implementation by reaching a maximum recognition accuracy of 0.4919 percent. Results were obtained as maximum accuracy of 0.4817% For the CNN on Coarse Super Label and maximum accuracy of 0.3696% For the CNN on Fine Super Label, while SVM on Coarse Super Label resulted in an accuracy of 0.0795% and SVM on Fine super Label resulted in 0.0285%. According to the results, CNN was able to exceed the benchmark of 39.43% and 24.49%, but SVM was unable to do so.

Emerging Technologies for Advanced Power Electronics and Machine Design in Electric Drives

The paper presents a comprehensive overview of recent advancements in power electronics and electric machine design, focusing on novel topologies, semiconductor technologies, and integrated design techniques for electric drives. New drive topologies are gradually moving from the research phase to practical application, aiming to increase the rated power, efficiency, and reliability of electric drives. Specifically, these topologies can be categorized into series, which focus on increasing the operating voltage; parallel, which aim at enhancing the operating current and adding redundancy; and multiphase, known for offering significant benefits such as improved fault tolerance, higher torque generation, the possibility of synthetic loading, and diverse winding layout options. Emerging wide bandgap semiconductors, such as silicon carbide and gallium nitride, allow for operation at higher frequencies and lower power losses, enabling further drive integration. In terms of design practices, higher computational power, supported by advanced software, enables simulation and analysis in multiple domains (thermal, mechanical, electromagnetic) using multiphysics co-simulation, as well as multi-objective optimization concepts to achieve rapid prototyping of optimized drive systems. All the approaches described are important steps towards further improving electric drives for numerous applications in industry, consumer electronics, and transportation.

Utilization of Environmentally Friendly Energy in Organic Fertilizer Processing Machine

Agriculture is the primary livelihood for most of Indonesia's population, which has vast agricultural land. However, there remains a dependency on chemical fertilizers, which degrade soil quality compared to organic farming that can optimize plant health and productivity. The energy needs in the agricultural sector, including mechanization and fertilizer production, are critical but still heavily reliant on fossil fuels. It is, therefore, essential to reduce this dependency by utilizing environmentally friendly alternative energy sources. This study examines the use of solar energy to power machines in the process of producing organic fertilizer. The tools used in the study include a 100 Wp solar panel, solar energy conversion components, a 12 Volt 33 Ah battery, a ¼ Hp electric motor, a voltage and current meter, a temperature gauge, a sunlight intensity meter, and an organic fertilizer processing machine. The research method analyzes several variables, including sunlight intensity, power, voltage, current, charging time, and battery usage. The study found that the solar panel used was insufficient to power the ¼ HP motor, requiring the addition of three more solar panels and batteries to meet the motor's power requirement of 233 watts. Battery charging tests required 3 hours, and battery usage for machine operation without solar panel installation lasted 1 hour and 40 minutes, while battery usage for machine operation with solar panel installation lasted 6-7 hours. Keywords: Environmentally friendly energy, Fertilizer crushing machine, Organic fertilizer, Solar energy.

Rethreading the needle: A novel molecular index of soil health (MISH) using microbial functional genes to predict soil health management

Soil health relies on the actions and interactions of an abundant and diverse biological community. Current soil health assessments rely heavily on a suite of soil biological, chemical, and physical indicators, often excluding molecular information. Soil health is critical for sustainable agricultural production, and a comprehensive understanding of how microbial communities provide ecosystem services can help guide management practices. To explore the role of microbial function in soil health, 536 soil samples were collected from 26 U.S. states, representing 52 different crops and grazing lands, and analyzed for various soil health indicators. The bacterial functional profile was characterized using 16S ribosomal RNA gene sequencing paired with PICRUSt2 to predict metagenome functions. Functional data were used as predictors in eXtreme Gradient Boosting (XGBoost), a powerful machine learning algorithm, and enzymes important to soil health indicators were compiled into a Molecular Index of Soil Health (MISH). The overall MISH score significantly correlated with non-molecular measures of soil health and management practice adoption. Additionally, several new enzymes were identified as potential targets to better understand microbial mediation of soil health. This low-cost, DNA-based approach to measuring soil health is robust and generalizable across climates.

Leveraging machine learning for sustainable integration of renewable energy generation

Long-term economic benefits and sustainability are provided by the integration of renewable energy sources (RESs) into electrical networks. However, because of their intermittent nature and reliance on environmental factors, RESs pose issues in production and consumption balance. Because renewable energy sources like wind and solar are unpredictable, forecasting their output is essential for planning purposes and maintaining grid stability. This thesis focuses on developing effective instruments and algorithms to improve renewable energy generation estimates and handle abnormalities in consumption. These tools and algorithms include maximum power point tracking and machine learning models like random forest (RF), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost). The methods' effectiveness is confirmed by accuracies higher than 80%, which provides speedier and more user-friendly solutions in comparison to the traditional ways. In the end, our effort seeks to offer practical instruments for anticipatory modelling and mitigating intermittentness in renewable energy sources, enabling their assimilation into current power structures to adequately supply energy requirements in a sustainable manner.

The Use Of Machine Learning, Computational Methods, And Robotics In Bridge Engineering: A Review

In this review paper, the applications of machine learning, computational methods, and robotics to bridge design are considered to help improve structure integrity and resilience. It describes a variety of computational methods, including finite element analysis (FEA) and computational fluid dynamics (CFD), that have been used to calculate failure modes and evaluate the dynamic behavior of bridge structures in extreme conditions, such as earthquakes and floods. It also highlights robotics’ potential to streamline inspection techniques, showing new robotic systems for effective bridge monitoring. Additionally, it points out issues related to data shortages and implementation difficulty and presents future research priorities, such as the need for powerful machine learning algorithms and the use of Internet of Things (IoT) solutions for real-time monitoring. In summary, the paper highlights the life-changing impact of these technologies on the safety and reliability of bridge systems.

Prediction of Two Year Survival Following Elective Repair of Abdominal Aortic Aneurysms at A Single Centre Using A Random Forest Classification Algorithm

The decision to electively repair an abdominal aortic aneurysm (AAA) involves balancing the risk of rupture, periprocedural mortality, and life expectancy. Random forest classifiers (RFCs) are powerful machine learning algorithms. The aim of this study was to construct and validate a random forest machine learning tool to predict two year survival following elective AAA repair. All patients who underwent elective open or endovascular repair of AAA from 1 January 2008 to 31 March 2021 were reviewed. They were assessed using the Vascular Surgery Quality Improvement Program pathway involving cardiopulmonary exercise testing, contrast enhanced computerised tomography scan, and multidisciplinary assessment. Patients were followed up for at least two years. A RFC was developed using 70% of the dataset and validated using 30% to predict survival for at least two years following AAA repair. A total of 925 patients (n = 836 men; n = 89 women) underwent elective repair of AAA; 126 (13.6%) died during the first two years; 11 (1.2%) died from periprocedural mortality. Variable importance analysis suggested that anaerobic threshold, pre-operative haemoglobin, maximal O2 consumption, body mass index, risk category, and forced expiratory volume in 1 second - forced vital capacity ratio were the most important contributors to the model. Sensitivity and specificity of the RFC for prediction of two year survival following surgery was 96.7% (95% CI 94.4 - 99%) and 67.1% (95% CI 61 - 72%); overall accuracy: 92.6% (95% CI 88 - 95%) (positive predictive value: 0.93, negative predictive value: 0.80); 10-fold cross validation revealed area under the receiver operator characteristic curve of 0.88. RFCs based on readily available clinical data can successfully predict survival in the first two years following elective repair of AAA. Such information can contribute to the risk benefit assessment when deciding to electively repair AAAs.

Biomarker identification and gene-drug interaction prediction for breast cancer using machine learning algorithms

Abstract Breast cancer (BC) poses a significant worldwide health challenge, necessitating the identification of its molecular origins and the development of possible treatment approaches. In this investigation, we introduce a pioneering methodology integrating genomic data and machine learning algorithms to identify genes associated with BC and their corresponding drugs. Initially, RNA-sequencing data of normal and malignant BC tissues publicly available in the NCBI GEO database were pre-processed using a standard pipeline. Further, machine learning algorithms, such as logistic regression, support vector machine, and random forest, were used to identify the differentially expressed genes (DEGs). The results were validated based on accuracy, sensitivity, specificity, precision, and F-score. Moreover, we identified the drugs corresponding to DEGs using the DepMap database. Our results revealed that genes such as OC90, KLK9, CXCL10, CDRT1, LCN6, GOLGA7B, and ZNF223 were commonly identified by all three machine learning algorithms. We found that the drugs DIHYDROROTENONE, 4-IODO-6-PHENYLPYRIMIDINE, BMS-754807, ARRY- 886, ESTRAMUSTINE-PHOSPHATE, FR-122047, and PIK 93 produced high correlation values on gene-drug interaction. The present study emphasizes the significance of utilizing genetic data and powerful machine learning algorithms to decipher the intricacies of BC biology and expedite the creation of tailored therapeutic approaches.

Unveiling the Secrets of the Mammogram: A Statistical Journey through Machine Learning Approach

Mammograms, once mere X-ray images, are now powerful allies in the fight against breast cancer. Armed with sophisticated statistical image classification techniques, these images reveal hidden clues that can lead to early detection. Beneath the surface of a mammogram lies a complex tapestry of patterns, each one a potential marker of malignancy. By decoding these intricate patterns, algorithms can identify abnormalities that might otherwise go unnoticed. The Mammographic Image Analysis Society (MIAS) has been at the forefront of this revolution, creating a vast database of digital mammograms. From this treasure trove, we've selected 322 images to put our statistical prowess to the test. Using a powerful machine learning tool known as Support Vector Machine (SVM), we've classified these images into seven categories: • Calcifications (CALC): Tiny, hard deposits. • Circumscribed (CIRC) masses: Well-defined lumps. • Speculated (SPIC) masses: Lumps with spiky edges. • Ill-defined (MISC) masses: Irregular, indistinct lumps. • Architectural distortions (ARCH): Changes in the breast's structure. • Asymmetry(s) (ASYM): Differences between the two breasts. • Normal (NORM): Healthy breast tissue. Our goal is to shed light on the intricate process of mammogram classification and share the insights gained from our analysis presented in the user-friendly language and the analysis is carried out using MATLAB.

TorchSISSO: A PyTorch-based implementation of the sure independence screening and sparsifying operator for efficient and interpretable model discovery

Symbolic regression (SR) is a powerful machine learning approach that searches for both the structure and parameters of algebraic models, offering interpretable and compact representations of complex data. Unlike traditional regression methods, SR explores progressively complex feature spaces, which can uncover simple models that generalize well, even from small datasets. Among SR algorithms, the Sure Independence Screening and Sparsifying Operator (SISSO) has proven particularly effective in the natural sciences, helping to rediscover fundamental physical laws as well as discover new interpretable equations for materials property modeling. However, its widespread adoption has been limited by performance inefficiencies and the challenges posed by its FORTRAN-based implementation, especially in modern computing environments. In this work, we introduce TorchSISSO, a native Python implementation built in the PyTorch framework. TorchSISSO leverages GPU acceleration, easy integration, and extensibility, offering a significant speed-up and improved accuracy over the original. We demonstrate that TorchSISSO matches or exceeds the performance of the original SISSO across a range of tasks, while dramatically reducing computational time and improving accessibility for broader scientific applications.

Automated Forensic Examination of Virtual Assets Using XGBoost

The issues of identification of virtual assets and digital currencies have become more acute in recent years because of increased numbers of transactions, their increased volumes, and complexity in forensic examination. This paper is devoted to a new method of the automated forensic investigation of virtual assets with the help of a powerful machine learning algorithm called XGBoost. XGBoost has very high speed and it is quite useful when dealing with large amounts of data and used for finding patterns that may suggest unlawful operations. The given framework is based on XGBoost by identifying the transactions using their features activities, amount, frequencies, volumes and addresses. Through training the model that is given the historical data, the model is, therefore, able to separate normal and suspicious transactions and alert the decision-making process for further review. Network analysis integration takes the system capability to a new level by enabling the identification of intricate transaction characteristics and the interconnectedness of addressing. Aside from adding automation to the forensic examinations to make it more efficient and accurate, such a procedure assists in identifying the developments of virtual asset transactions. The results show the effectiveness of the XGBoost in supporting the advance of forensic investigators helping them to meet the growing roles that cybercriminals portray in today’s digital asset markets.

Permutation-equivariant quantum convolutional neural networks

Abstract The Symmetric group S n manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. Subgroups of S n arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, such as reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this study we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to S n and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of S n . Our novel EQCNN architecture corresponding to the full permutation group S n is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of S n , our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The S n -equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the S n -equivariant QCNN shows better average performance compared to S n -equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.

Random forest models reveal academic and financial factors outweigh demographics in predicting completion of a year-round veterinary program.

The purpose of this study was to develop random forest classifier models (a type of supervised machine learning algorithm) that could (1) predict students who will or will not complete the DVM degree requirements and (2) identify the top predictors for academic success and completion of the DVM degree. The study utilized Ross University School of Veterinary Medicine student records from 2013 to 2022. Twenty-four variables encompassing demographic (eg, age, race), academic (eg, grade point average), and financial aid (eg, outstanding balances) data were assessed in 11 cross-validated random forest machine learning models. One model was built assessing all years of data and 10 individual models were developed for each enrollment year to compare how the top predictors of success varied among the years. Consistently, only academic and financial factors were identified as being features of importance (predictors) in all models. Demographic factors such as race were not important for predicting student success. All models performed very well to excellently based on multiple performance metrics including accuracy, ranging from 96.1% to 99%, and the areas under the receiver operating characteristic curves, ranging from 98.1% to 99.9%. The random forest algorithm is a powerful machine learning prediction model that performs well with veterinary student academic records and is customizable such that variables important to each veterinary school's student population can be assessed. Identifying predictors of success as well as at-risk students is essential for providing targeted curricular interventions to increase retention and achieve timely completion of a DVM degree.