The fundamental way to acquire information is through learning, which is the key indicator of human intellect. The primary method for making computers intelligent is machinelearning. An important part of machine lear...
详细信息
ISBN:
(数字)9798350368949
ISBN:
(纸本)9798350368956
The fundamental way to acquire information is through learning, which is the key indicator of human intellect. The primary method for making computers intelligent is machinelearning. An important part of machinelearning involves simulating human learning, studying, and improving performance and achievement using computers to acquire new skills, identify existing skills, and improve performance. Through the use of machine learning algorithms, which allow computers to see patterns and draw wise conclusions, we have completely changed how we handle and analyze data. Comparative studies are increasingly necessary to evaluate the current state of various algorithms, comprehend the challenges they encounter, and investigate their potential futures as the area of machinelearning continues to grow quickly. machine learning algorithms are studied in this paper from a comparative perspective, covering their current state, challenges, and future prospects. This study seeks to offer academics, practitioners, and decision-makers insightful information and recommendations for choosing the most effective algorithms and overcoming related difficulties by analyzing and contrasting various algorithms. A quick overview of the state of machine learning algorithms is provided in the review’s first part. It shows a wide context of learningalgorithms, such as supervised, unsupervised, semisupervised, and reinforcement. Each algorithm is displayed in accordance with its definition, scalability, performance, applications, advantages, and disadvantages. It is also exhibited in relation to its challenges, which are also mandatory portions that are detailed in a distinct section. Furthermore, the review paper also offers predictions for future perspectives and emerging trends in the machine-learning industry.
Breast cancer is one of the most typical types of cancer in women. It is the second greatest cause of death for women worldwide. Early detection and treatment can raise the likelihood of a full recovery and decrease t...
详细信息
ISBN:
(数字)9798350391213
ISBN:
(纸本)9798350391220
Breast cancer is one of the most typical types of cancer in women. It is the second greatest cause of death for women worldwide. Early detection and treatment can raise the likelihood of a full recovery and decrease the risk of cancer spreading. Therefore, the advancement in breast cancer illness prediction and detection is crucial for living a healthy life. As a result, high cancer prognostic accuracy is crucial for updating therapy aspects and patient survivability standards. machinelearning techniques are now a top area of research because of their significant impact on the early diagnosis of breast cancer. To detect breast cancer, we applied seven machine learning algorithms: Random Forest (RF), Naïve Bayes (NB), Extreme Gradient Boost (XGB), Decision Tree (DT), Support Vector machine (SVM), Logistic Regression (LR), and K-Nearest Neighbors (KNN). We have also performed to-fold cross-validation method to detect breast cancer. The main goal of this study is finding the most effective machine learning algorithms for the prediction and diagnosis of breast cancer through confusion matrices, accuracy, and precision as well as ROC-AUC curves and scores. The study is performed by applying machine learning algorithms through feature scaling and two different splits of the training and testing data sets as well as 10-fold cross-validation methods. In this study, it has been seen that while all the selected classifiers have performed well in detecting breast cancer, the RF exceeds all other classifiers and obtains the best accuracy (97.9%) when the datasets are divided into 75% training and 25% testing data. On the other hand, SVM was found to beat all other classifiers with an accuracy of 98.20% when the datasets are divided into 80% training and 20% testing. Although the average accuracy decreased slightly (97.40%) when we performed to-fold cross-validation technique, SVM was still showing the best performance. This demonstrates that the separation of training and test
Current transformers (CTs) are critical devices in power systems. Their gradual faults (such as insulation aging and core loss) are often hidden and progressive, making them difficult to detect and predict using tradi...
详细信息
ISBN:
(数字)9798350389418
ISBN:
(纸本)9798350389425
Current transformers (CTs) are critical devices in power systems. Their gradual faults (such as insulation aging and core loss) are often hidden and progressive, making them difficult to detect and predict using traditional methods. This paper proposes a gradual fault prediction model for CTs based on machine learning algorithms. By constructing high-dimensional feature vectors, the model extracts, analyzes, and models CT fault characteristics and uses optimized machine learning algorithms to effectively predict gradual faults. First, the study extracts typical fault features from historical operational data of CTs using feature engineering methods and enhances the representation capability of these features through time-series analysis. Subsequently, various machine learning algorithms, including support vector machines (SVM), random forests (RF), and neural networks, are employed to train the fault prediction model. The model’s prediction accuracy and robustness are further improved through ensemble learning strategies. Experimental results show that the proposed model significantly improves the prediction accuracy of gradual faults in CTs, providing better robustness and generalization compared to traditional methods. This research can serve as a technical support for the safe and stable operation of power systems. Finally, the paper discusses the model’s application scenarios and deployment strategies in real-world power systems, providing insights and references for future studies.
machine learning algorithms have become pervasive in diverse applications, revolutionizing various domains. However, the abundance of algorithms, each designed for specific purposes, poses a challenge for both novice ...
详细信息
ISBN:
(数字)9798350343878
ISBN:
(纸本)9798350343885
machine learning algorithms have become pervasive in diverse applications, revolutionizing various domains. However, the abundance of algorithms, each designed for specific purposes, poses a challenge for both novice users and experts in selecting the most suitable model. This research addresses this issue through a comprehensive analysis, leveraging Natural Language Processing (NLP) techniques and the powerful Transformers library. Researcher’s comments from published papers were analyzed using the Transformers library, presenting a novel approach that maps algorithm scores based on adjectives. Results indicate that Neural Networks consistently outperform other algorithms, providing valuable insights for practitioners. Our research contributes to a systematic evaluation framework, aiding researchers in algorithm selection.
In every nation, agriculture has boosted the economy. Agriculture is currently dealing with a number of difficulties, such as irrigation and water management. Crop irrigation plays a crucial role in agricultural produ...
详细信息
ISBN:
(数字)9798350372748
ISBN:
(纸本)9798350372755
In every nation, agriculture has boosted the economy. Agriculture is currently dealing with a number of difficulties, such as irrigation and water management. Crop irrigation plays a crucial role in agricultural production by providing water to crops in regions where rainfall alone is insufficient to meet their needs. This abstract provides an overview of crop irrigation, its importance, and various irrigation methods used in agriculture. Irrigation is a critical component of agricultural production, and advancements in machine learning algorithms have the potential to optimize irrigation practices for crop cultivation. Additionally, machinelearning has developed in several industries to improve quality. machine learning algorithms like Random Forest, K-Nearest Neighbor, Support Vector machine and Decision Tree are used to find the various results. Internet of Things also plays a vital role in irrigation by making use of the sensors. This review's investigation was conducted using a variety of machine learning algorithms.
This research is mainly focused on the early detection of breast cancer in women by their urine samples with nanoparticle sensors. It detects certain enzymes and proteins that can be the main cause of cancer by machin...
详细信息
ISBN:
(数字)9798350349900
ISBN:
(纸本)9798350349917
This research is mainly focused on the early detection of breast cancer in women by their urine samples with nanoparticle sensors. It detects certain enzymes and proteins that can be the main cause of cancer by machine learning algorithms, correlation analysis, and logical regression methods and created a web-based breast cancer prediction website using started nanoparticle urine analysis data, which contains the DNA barcode sequences that match with DNA of patient urine which is user friendly to use for every person. This study mainly focuses on non-invasive cancer. We analyze non-invasive cancer by using urine sample test data collected from the patients, utilizing advanced technology to access DNA signatures associated with breast cancer biomarkers. Our approach involves the barcode of nanoparticle sensors, which matches the urine samples. After the urine samples match, they are applied to the sensors, translated into digital data, and transmitted to a centralized system. Now, the centralized system collaborates with datasets derived from previous breast cancer cases. The algorithm now analyses the urine data and identifies the patterns. Then, it correlates with different stages of breast cancer.
Predicting earthquakes is one of the most challenging scientific endeavors due to the complex and dynamic nature of Earth's crust and the multitude of factors influencing seismic activity. Earthquake prediction re...
详细信息
ISBN:
(数字)9798331518097
ISBN:
(纸本)9798331518103
Predicting earthquakes is one of the most challenging scientific endeavors due to the complex and dynamic nature of Earth's crust and the multitude of factors influencing seismic activity. Earthquake prediction research remains an essential scientific frontier, offering hope for better mitigation strategies and reduced impact in the future. This study examines the prediction of earthquake magnitudes using machinelearning models, namely Random Forest Regression, Decision Tree Regression, and Support Vector Regression. Data such as latitude, longitude and depth were used to test and train the models to forecast magnitude. The performance of each model was evaluated using the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). According to the results, the Support Vector Regression model outperforms the others.
Insider threats, in which someone within an organization poses a risk, are widely regarded as the most dangerous in cybersecurity. Many analysts are working hard to identify and prevent these risks. However, the most ...
详细信息
ISBN:
(数字)9798350307757
ISBN:
(纸本)9798350307764
Insider threats, in which someone within an organization poses a risk, are widely regarded as the most dangerous in cybersecurity. Many analysts are working hard to identify and prevent these risks. However, the most difficult aspect of cybersecurity is determining which computers and users are affected. These computers are connected to servers or monitored by them, but there are no clear indications that attackers are targeting specific users. It is critical for the organization to defend against both internal and external cyberattacks. Cyber security measures should be up to date is critical for protecting our organizations. External threats can be identified easily but to identify insider threats is a complex task. Recently, there has been an increased emphasis on computer security, particularly in developing internal risk detection systems. Artificial intelligence, Internet of Things, distributed computing, data mining, portable ledgers, and data discovery are some of the advanced methods that have gained popularity for mitigating insider risk. Each of these approaches is unique and takes insider threats into account to a varying degree. In this paper, we use different machinelearning models to find out the insiders.
Breast cancer is still a global health concern, chiefly affecting women, as it is one of the major causes of cancer mortality. For the therapy to be effective, early diagnosis of cancer is critical to raising the surv...
详细信息
ISBN:
(数字)9798331529635
ISBN:
(纸本)9798331529642
Breast cancer is still a global health concern, chiefly affecting women, as it is one of the major causes of cancer mortality. For the therapy to be effective, early diagnosis of cancer is critical to raising the survival level and increasing the effectiveness of the procedure. The advancement in the applied technique of machinelearning (ML) has brought further opportunities for early and effective diagnosis of breast cancer. This review paper provides insights into how different ML algorithms including the Support Vector machine (SVM), Convolutional Neural Network (CNN), Random Forests, and many more have contributed to the detection of breast cancer. These algorithms have proved effective in providing solutions to various medical data and imaging including early diagnosis and treatment. The paper also looks at the use of ML with precision medicine to show that these technologies will help minimize false diagnoses and offer better treatment options. This review consolidates recent works and advancements to emphasize the prospect of ML in breast cancer management and calls for more studies to enhance its implementation in practice
This study investigates the predictive capabilities of LBGM, CATB, GBR, ADAB, and XGB models for concrete compressive strength prediction. Through an evaluation of default hyperparameters and comprehensive metrics, in...
详细信息
ISBN:
(数字)9798350378092
ISBN:
(纸本)9798350378108
This study investigates the predictive capabilities of LBGM, CATB, GBR, ADAB, and XGB models for concrete compressive strength prediction. Through an evaluation of default hyperparameters and comprehensive metrics, including R2, MSE, RMSE, MAE, RMSLE, and MAPE, nuanced insights into each algorithm’s performance are obtained. ADAB emerges as a standout performer, displaying lower error rates across multiple metrics, suggesting AdaBoost’s suitability for concrete compressive strength prediction. The analysis of a self-prepared dataset reveals significant variations across different mixture combinations and curing times. This research not only establishes a benchmark for current practices but also provides avenues for future research, including hyperparameter tuning to optimize model performance further. The practical implications for concrete engineering are significant, guiding material composition decisions and contributing to the development of more durable and resilient structures. As the intersection of machinelearning and concrete engineering progresses, this study lays a foundation for tailored approaches to address the specific challenges of predicting concrete compressive strength.
暂无评论