To see the other types of publications on this topic, follow the link: Machine learning (ML) neural nets models.
Journal articles on the topic 'Machine learning (ML) neural nets models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Machine learning (ML) neural nets models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Pandey, Prachi, and Abhijitha Bandaru. "Enhancing predictive accuracy of asset returns by experimenting with ML techniques." SHS Web of Conferences 169 (2023): 01062. http://dx.doi.org/10.1051/shsconf/202316901062.
Full textAbstract:
The unparalleled success of machine learning is indisputable. It has transformed the world with unimaginable solutions to insistent problems. The remarkable accuracy that machine learning manifests for making estimations is an object of fascination for plenty of researchers all over the world. The financial industry has also benefited from the growth of this electrifying field to predict asset returns, creditworthiness of a customer, and portfolio management, among others. In this research, we spotlight how this accuracy is contingent upon the analysis of various aspects of the data. We also experiment with simple techniques to make predictions and our findings suggest how these methods overshadow neural nets. The results indicate that the penalized linear models deliver the best performance. Random forest models had not been effective though. Machine learning models fitted with respect to median quantile loss were similarly observed to typically offer improvements across all machine learning models across all loss metrics. While little is known about the future of asset return that involves various risk and uncertainty, the recent enhancements in a machine learning field can contribute to deep domain training. Machine learning is increasingly gaining popularity nowadays in sectors including engineering, charity work, etc. Recently, even behavioral economics has started to leverage machine-learning expertise.
2
Chandrahas, Mishra, and L. Gupta D. "Deep Machine Learning and Neural Networks: An Overview." IAES International Journal of Artificial Intelligence (IJ-AI) 6, no. 2 (2017): 66–73. https://doi.org/10.5281/zenodo.4108266.
Full textAbstract:
Deep learning is a technique of machine learning in artificial intelligence area. Deep learning in a refined "machine learning" algorithm that far surpasses a considerable lot of its forerunners in its capacities to perceive syllables and picture. Deep learning is as of now a greatly dynamic examination territory in machine learning and example acknowledgment society. It has increased colossal triumphs in an expansive zone of utilizations, for example, speech recognition, computer vision and natural language processing and numerous industry item. Neural network is used to implement the machine learning or to design intelligent machines. In this paper brie introduction to all machine learning paradigm and application area of deep machine learning and different types of neural networks with applications is discussed.
3
Madupu Venkata Vineeth and G.V. Ramana. "Detection of Phishing Websites Using Machine Learning." Metallurgical and Materials Engineering 31, no. 4 (2025): 762–68. https://doi.org/10.63278/1511.
Full textAbstract:
Phishing websites have proven to be a major security concern. Several cyberattacks risk the confidentiality, integrity, and availability of company and consumer data, and phishing is the beginning point for many of them. Many researchers have spent decades creating unique approaches to automatically detect phishing websites. While cutting-edge solutions can deliver better results, they need a lot of manual feature engineering and aren't good at identifying new phishing attacks. As a result, finding strategies that can automatically detect phishing websites and quickly manage zero-day phishing attempts is an open challenge in this field. The web page in the URL which hosts that contains a wealth of data that can be used to determine the web server's maliciousness. Machine Learning is an effective method for detecting phishing. It also eliminates the disadvantages of the previous method. We conducted a thorough review of the literature and suggested a new method for detecting phishing websites using features extraction and a machine learning algorithm. The goal of this research is to use the dataset collected to train ML models and deep neural nets to anticipate phishing websites.
4
Lodes, Lukas, and Alexander Schiendorfer. "Certainty Groups: A Practical Approach to Distinguish Confidence Levels in Neural Networks." PHM Society European Conference 7, no. 1 (2022): 294–305. http://dx.doi.org/10.36001/phme.2022.v7i1.3331.
Full textAbstract:
Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting.
5
Senanayake, Indishe P., Kalani R. L. Pathira Arachchilage, In-Young Yeo, Mehdi Khaki, Shin-Chan Han, and Peter G. Dahlhaus. "Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review." Remote Sensing 16, no. 12 (2024): 2067. http://dx.doi.org/10.3390/rs16122067.
Full textAbstract:
Soil moisture (SM) is a key variable driving hydrologic, climatic, and ecological processes. Although it is highly variable, both spatially and temporally, there is limited data availability to inform about SM conditions at adequate spatial and temporal scales over large regions. Satellite SM retrievals, especially L-band microwave remote sensing, has emerged as a feasible solution to offer spatially continuous global-scale SM information. However, the coarse spatial resolution of these L-band microwave SM retrievals poses uncertainties in many regional- and local-scale SM applications which require a high amount of spatial details. Numerous studies have been conducted to develop downscaling algorithms to enhance the spatial resolution of coarse-resolution satellite-derived SM datasets. Machine Learning (ML)-based downscaling models have gained prominence recently due to their ability to capture non-linear, complex relationships between SM and its driving factors, such as vegetation, surface temperature, topography, and climatic conditions. This review paper presents a comprehensive review of the ML-based approaches used in SM downscaling. The usage of classical, ensemble, neural nets, and deep learning methods to downscale SM products and the comparison of multiple algorithms are detailed in this paper. Insights into the significance of surface ancillary variables for model accuracy and the improvements made to ML-based SM downscaling approaches are also discussed. Overall, this paper provides useful insights for future studies on developing reliable, high-spatial-resolution SM datasets using ML-based algorithms.
6
Parung, Ratu Anggriani Tangke, Hanna Arini Parhusip, and Suryasatriya Trihandaru. "Prototype of Swiftlet Nest Moisture Content Measurement Using Resistance Sensor and Machine Learning." Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 8, no. 5 (2024): 674–80. https://doi.org/10.29207/resti.v8i5.5923.
Full textAbstract:
Swiftlet nests are highly valued for their health and cosmetic benefits, with moisture content crucial in determining their quality. Traditional moisture measurement methods are often slow and can potentially damage the samples. This study introduces PRORESKA, an innovative system utilizing resistance sensors and Machine Learning (ML) for non-destructive, and real-time moisture measurement. The system incorporates a voltage divider circuit to establish a correlation between resistance data and moisture content. Three mathematical models (linear, exponential, and modulated exponential) and a neural network were employed to predict moisture content. Validation tests conducted on paper and swiftlet nests indicated that the neural network model, enhanced through transfer learning, achieved superior accuracy. The results demonstrated a strong correlation between predicted and actual moisture content (R² = 0.9759), with the neural network model attaining a mean squared error (MSE) of 0.01. This method holds significant potential to improve the efficiency and cost-effectiveness of moisture measurement for swiftlet nests and similar applications.
7
Alotaibi, Afnan, and Murad A. Rassam. "Enhancing the Sustainability of Deep-Learning-Based Network Intrusion Detection Classifiers against Adversarial Attacks." Sustainability 15, no. 12 (2023): 9801. http://dx.doi.org/10.3390/su15129801.
Full textAbstract:
An intrusion detection system (IDS) is an effective tool for securing networks and a dependable technique for improving a user’s internet security. It informs the administration whenever strange conduct occurs. An IDS fundamentally depends on the classification of network packets as benign or attack. Moreover, IDSs can achieve better results when built with machine learning (ML)/deep learning (DL) techniques, such as convolutional neural networks (CNNs). However, there is a limitation when building a reliable IDS using ML/DL techniques, which is their vulnerability to adversarial attacks. Such attacks are crafted by attackers to compromise the ML/DL models, which affects their accuracy. Thus, this paper describes the construction of a sustainable IDS based on the CNN technique, and it presents a method for defense against adversarial attacks that enhances the IDS’s accuracy and ensures it is more reliable in performing classification. To achieve this goal, first, two IDS models with a convolutional neural network (CNN) were built to enhance the IDS accuracy. Second, seven adversarial attack scenarios were designed against the aforementioned CNN-based IDS models to test their reliability and efficiency. The experimental results show that the CNN-based IDS models achieved significant increases in the intrusion detection system accuracy of 97.51% and 95.43% compared with the scores before the adversarial scenarios were applied. Furthermore, it was revealed that the adversarial attacks caused the models’ accuracy to significantly decrease from one attack scenario to another. The Auto-PGD and BIM attacks had the strongest effect against the CNN-based IDS models, with accuracy drops of 2.92% and 3.46%, respectively. Third, this research applied the adversarial perturbation elimination with generative adversarial nets (APE_GAN++) defense method to enhance the accuracy of the CNN-based IDS models after they were affected by adversarial attacks, which was shown to increase after the adversarial attacks in an intelligible way, with accuracy scores ranging between 78.12% and 89.40%.
8
Lee, Sangil, Avinash Reddy Mudireddy, Deepak Kumar Pasupula, et al. "Novel Machine Learning Approach to Predict and Personalize Length of Stay for Patients Admitted with Syncope from the Emergency Departmen." Journal of Personalized Medicine 13, no. 1 (2022): 7. http://dx.doi.org/10.3390/jpm13010007.
Full textAbstract:
Background: Syncope, a common problem encountered in the emergency department (ED), has a multitude of causes ranging from benign to life-threatening. Hospitalization may be required, but the management can vary substantially depending on specific clinical characteristics. Models predicting admission and hospitalization length of stay (LoS) are lacking. The purpose of this study was to design an effective, exploratory model using machine learning (ML) technology to predict LoS for patients presenting with syncope. Methods: This was a retrospective analysis using over 4 million patients from the National Emergency Department Sample (NEDS) database presenting to the ED with syncope between 2016–2019. A multilayer perceptron neural network with one hidden layer was trained and validated on this data set. Results: Receiver Operator Characteristics (ROC) were determined for each of the five ANN models with varying cutoffs for LoS. A fair area under the curve (AUC of 0.78) to good (AUC of 0.88) prediction performance was achieved based on sequential analysis at different cutoff points, starting from the same day discharge and ending at the longest analyzed cutoff LoS ≤7 days versus >7 days, accordingly. The ML algorithm showed significant sensitivity and specificity in predicting short (≤48 h) versus long (>48 h) LoS, with an AUC of 0.81. Conclusions: Using variables available to triaging ED clinicians, ML shows promise in predicting hospital LoS with fair to good performance for patients presenting with syncope.
9
Garg, R. "PREDICTING EMERGING MARKET RETURNS WITH SIMPLE MACHINE LEARNING TECHNIQUES." Slovak international scientific journal, no. 95 (May 15, 2025): 30–35. https://doi.org/10.5281/zenodo.15427551.
Full textAbstract:
This study applies simple machine learning techniques to predict Emerging Market (EM) equity returns. It examines excess returns for major EM indices versus relevant benchmarks. Predictor variables were drawn from the same security’s historical excess returns. The intuition is that past performance can be predictive of future investment interest and that predictive relationship is unique for each security. Therefore, a variety of models need to be considered. A total of five models were applied: traditional logistic regressions, ridge, random forest, boosting and neural nets. The results indicate that newer machine learning-based predictive relationships, such as random forest, boosting, and neural nets, generate valuable out-of-sample results. In nearly all countries, there was a machine learning active strategy that delivered higher returns than a passive long strategy. The paper identifies avenues for further exploration of such investment strategies.
10
Michaud, Eric J., Ziming Liu, and Max Tegmark. "Precision Machine Learning." Entropy 25, no. 1 (2023): 175. http://dx.doi.org/10.3390/e25010175.
Full textAbstract:
We explore unique considerations involved in fitting machine learning (ML) models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with increasing parameters and data. We find that neural networks (NNs) can often outperform classical approximation methods on high-dimensional examples, by (we hypothesize) auto-discovering and exploiting modular structures therein. However, neural networks trained with common optimizers are less powerful for low-dimensional cases, which motivates us to study the unique properties of neural network loss landscapes and the corresponding optimization challenges that arise in the high precision regime. To address the optimization issue in low dimensions, we develop training tricks which enable us to train neural networks to extremely low loss, close to the limits allowed by numerical precision.
11
Angerbauer, Simon, Alexander Palmanshofer, Stephan Selinger, and Marc Kurz. "Comparing Human Activity Recognition Models Based on Complexity and Resource Usage." Applied Sciences 11, no. 18 (2021): 8473. http://dx.doi.org/10.3390/app11188473.
Full textAbstract:
Human Activity Recognition (HAR) is a field with many contrasting application domains, from medical applications to ambient assisted living and sports applications. With ever-changing use cases and devices also comes a need for newer and better HAR approaches. Machine learning has long been one of the predominant techniques to recognize activities from extracted features. With the advent of deep learning techniques that push state of the art results in many different domains like natural language processing or computer vision, researchers have also started to build deep neural nets for HAR. With this increase in complexity, there also comes a necessity to compare the newer approaches to the previous state of the art algorithms. Not everything that is new is also better. Therefore, this paper aims to compare typical machine learning models like a Random Forest (RF) or a Support Vector Machine (SVM) to two commonly used deep neural net architectures, Convolutional Neural Nets (CNNs) and Recurrent Neural Nets (RNNs). Not only in regards to performance but also in regards to the complexity of the models. We measure complexity as the memory consumption, the mean prediction time and the number of trainable parameters of the models. To achieve comparable results, the models are all tested on the same publicly available dataset, the UCI HAR Smartphone dataset. With this combination of prediction performance and model complexity, we look for the models achieving the best possible performance/complexity tradeoff and therefore being the most favourable to be used in an application. According to our findings, the best model for a strictly memory limited use case is the Random Forest with an F1-Score of 88.34%, memory consumption of only 0.1 MB and mean prediction time of 0.22 ms. The overall best model in terms of complexity and performance is the SVM with a linear kernel with an F1-Score of 95.62%, memory consumption of 2 MB and a mean prediction time of 0.47 ms. The two deep neural nets are on par in terms of performance, but their increased complexity makes them less favourable to be used.
12
Kalpen, A. K., E. T. Matson, A. K. Zhumadillayeva, and K. A. Dyussekeyev. "SEQUENCE RECOGNITION USING FINITE AUTOMATA WITH MACHINE LEARNING." Bulletin of Shakarim University. Technical Sciences, no. 1(17) (March 29, 2025): 40–48. https://doi.org/10.53360/2788-7995-2025-1(17)-5.
Full textAbstract:
Sequence recognition is a critical task across numerous disciplines. While traditional methods utilizing Finite State Machines (FSMs) offer a structured data representation and high interpretability, their flexibility is limited. Contemporary Machine Learning (ML) algorithms exhibit high accuracy but demand substantial computational resources. Combining these paradigms can enhance the effectiveness of complex sequence recognition. This study explores the integration of FSMs with ML techniques to address sequence analysis problems. Three distinct applications are examined: text classification (spam detection), recognition of genetic sequences related to Alzheimer's disease, and image-based gesture identification. For each, hybrid models were developed and tested, combining Deterministic Finite Automata (DFA), Non-deterministic Finite Automata (NFA), and ML algorithms such as Random Forest, Gradient Boosting, and Multilayer Perceptrons (MLP). Experimental results indicate that these hybrid models achieve performance comparable to traditional ML methods, and in some instances, yield more accurate predictions. In spam classification, neural network models demonstrated the best results, with FSM-neural network combinations providing similar effectiveness. For genetic sequence analysis, gradient boosting-based models exhibited the highest accuracy, with the inclusion of FSMs maintaining performance while enhancing interpretability. In gesture recognition, neural network approaches proved most effective, but integrating FSMs with ensemble methods achieved a high level of predictive capability, surpassing conventional ML models. In conclusion, the integration of FSMs and ML presents a promising avenue in sequence analysis. Future research could focus on optimizing model architectures and applying them to other domains requiring high-precision recognition of intricate structures.
13
Ećim-Đurić, Olivera, Rajko Miodragović, Andrija Rajković, Mihailo Milanović, Zoran Mileusnić, and Aleksandra Dragičević. "Application of machine learning in agriculture." Poljoprivredna tehnika 49, no. 4 (2024): 108–25. https://doi.org/10.5937/poljteh2404108e.
Full textAbstract:
Machine learning (ML) is a key technology driving the modernisation of agriculture. It enables large data sets to be analysed and precise decisions to be made at all stages of agricultural production. ML is used for soil analysis, plant disease detection, weed control, crop species identification and harvest optimisation. Various techniques such as supervised, unsupervised and reinforcement learning help to improve the accuracy of predictions and decisions. Artificial neural networks (ANN), in particular deep neural networks (DNN) and convolutional neural networks (CNN), efficiently analyse images and numerical data and enable precise management of agricultural practises. These technologies contribute to sustainability by reducing the negative impact on the environment and optimising the use of resources. While significant progress has already been made, there is still potential for further development of ML models that cover all phases of the agricultural cycle and make precision agriculture more efficient and safer.
14
Phulari, Shiva, Shravani Pangare, Prasad Sutar, Harshawardhan Thorat, and Shubham Waghale. "Heart Disease Prediction using Machine Learning and Deep Learning." International Scientific Journal of Engineering and Management 04, no. 04 (2025): 1–7. https://doi.org/10.55041/isjem02698.
Full textAbstract:
Heart disease is a leading cause of mortality globally, pointing towards the necessity of effective screening and predictive functions to support early detection and treatment. Based on this research study, an emphasis is placed on developing and executing a robust predictive model for heart disease through the integration of machine learning (ML) and deep learning (DL) methods. Particularly, we utilize Logistic Regression, Support Vector Machine and Random Forest as ML classifiers, while Convolution Neural Networks and Artificial Neural Networks are utilized as DL models for clinical data set analysis and prediction of heart disease risk. For improved performance, we combine state-of-the-art feature extraction techniques with these models to enhance predictive accuracy and model inter predictability. Our experimental results identify that highest performance was achieved by the Random Forest classifier at accuracy of 92% and next by the CNN model with accuracy of 91%, highlighting the strength of deep learning and ensemble methods to pull out subtle patterns from data. Through the use of such algorithms, our research adds to the body of literature in favor of AI-driven solutions in medical diagnosis to improve patient outcomes. Key Words: Heart Disease Prediction, Machine Learning, Deep Learning, Classification Models, Neural Network.
15
Taylor, Joseph, Elmer Ccopa-Rivera, Solomon Kim, Reise Campbell, Rodney Summerscales, and Hyun Kwon. "Machine Learning Analysis for Phenolic Compound Monitoring Using a Mobile Phone-Based ECL Sensor." Sensors 21, no. 18 (2021): 6004. http://dx.doi.org/10.3390/s21186004.
Full textAbstract:
Machine learning (ML) can be an appropriate approach to overcoming common problems associated with sensors for low-cost, point-of-care diagnostics, such as non-linearity, multidimensionality, sensor-to-sensor variations, presence of anomalies, and ambiguity in key features. This study proposes a novel approach based on ML algorithms (neural nets, Gaussian Process Regression, among others) to model the electrochemiluminescence (ECL) quenching mechanism of the [Ru(bpy)3]2+/TPrA system by phenolic compounds, thus allowing their detection and quantification. The relationships between the concentration of phenolic compounds and their effect on the ECL intensity and current data measured using a mobile phone-based ECL sensor is investigated. The ML regression tasks with a tri-layer neural net using minimally processed time series data showed better or comparable detection performance compared to the performance using extracted key features without extra preprocessing. Combined multimodal characteristics produced an 80% more enhanced performance with multilayer neural net algorithms than a single feature based-regression analysis. The results demonstrated that the ML could provide a robust analysis framework for sensor data with noises and variability. It demonstrates that ML strategies can play a crucial role in chemical or biosensor data analysis, providing a robust model by maximizing all the obtained information and integrating nonlinearity and sensor-to-sensor variations.
16
Slieman, Alaa Ali, and Dmitry V. Kozlov. "Evaluating Different Machine Learning Models for Runoff Modelling." E3S Web of Conferences 457 (2023): 02040. http://dx.doi.org/10.1051/e3sconf/202345702040.
Full textAbstract:
Estimation and forecasting of hydrological factors are of particular importance in hydrological modelling, and surface runoff is one of the most important of these factors. Machine learning (ML) models have attracted the attention of researchers in this field. So, this article aims to evaluate several types of ML models such as autoregressive integrated moving average (ARIMA), feed forward back propagation artificial neural network (FFBP-ANN), and adaptive neuro-fuzzy inference system (ANFIS) models in order to estimate runoff values at Al-Jawadiya meteostation in the Orontes River basin in Syria. A large number of ARIMA models were built and the seasonal effect on the models also verified. After that, FFBP-ANN models were used with the change in the number of inputs, the number of hidden layers, and the number of neurons in the hidden layer. Also, a large number of FIS models have been built and artificial neural algorithms have been used in the process of model parameters optimization. The results showed a preference for artificial intelligence models in general over ARIMA models, as well as a slight preference for FFBP-ANN models over ANFIS models. This study recommends expanding the use of ML models to reach the best models for forecasting hydrological factors.
17
Telikani, Akbar, Amirhessam Tahmassebi, Wolfgang Banzhaf, and Amir H. Gandomi. "Evolutionary Machine Learning: A Survey." ACM Computing Surveys 54, no. 8 (2022): 1–35. http://dx.doi.org/10.1145/3467477.
Full textAbstract:
Evolutionary Computation (EC) approaches are inspired by nature and solve optimization problems in a stochastic manner. They can offer a reliable and effective approach to address complex problems in real-world applications. EC algorithms have recently been used to improve the performance of Machine Learning (ML) models and the quality of their results. Evolutionary approaches can be used in all three parts of ML: preprocessing (e.g., feature selection and resampling), learning (e.g., parameter setting, membership functions, and neural network topology), and postprocessing (e.g., rule optimization, decision tree/support vectors pruning, and ensemble learning). This article investigates the role of EC algorithms in solving different ML challenges. We do not provide a comprehensive review of evolutionary ML approaches here; instead, we discuss how EC algorithms can contribute to ML by addressing conventional challenges of the artificial intelligence and ML communities. We look at the contributions of EC to ML in nine sub-fields: feature selection, resampling, classifiers, neural networks, reinforcement learning, clustering, association rule mining, and ensemble methods. For each category, we discuss evolutionary machine learning in terms of three aspects: problem formulation, search mechanisms, and fitness value computation. We also consider open issues and challenges that should be addressed in future work.
18
Telikani, Akbar, Amirhessam Tahmassebi, Wolfgang Banzhaf, and Amir H. Gandomi. "Evolutionary Machine Learning: A Survey." ACM Computing Surveys 54, no. 8 (2022): 1–35. http://dx.doi.org/10.1145/3467477.
Full textAbstract:
Evolutionary Computation (EC) approaches are inspired by nature and solve optimization problems in a stochastic manner. They can offer a reliable and effective approach to address complex problems in real-world applications. EC algorithms have recently been used to improve the performance of Machine Learning (ML) models and the quality of their results. Evolutionary approaches can be used in all three parts of ML: preprocessing (e.g., feature selection and resampling), learning (e.g., parameter setting, membership functions, and neural network topology), and postprocessing (e.g., rule optimization, decision tree/support vectors pruning, and ensemble learning). This article investigates the role of EC algorithms in solving different ML challenges. We do not provide a comprehensive review of evolutionary ML approaches here; instead, we discuss how EC algorithms can contribute to ML by addressing conventional challenges of the artificial intelligence and ML communities. We look at the contributions of EC to ML in nine sub-fields: feature selection, resampling, classifiers, neural networks, reinforcement learning, clustering, association rule mining, and ensemble methods. For each category, we discuss evolutionary machine learning in terms of three aspects: problem formulation, search mechanisms, and fitness value computation. We also consider open issues and challenges that should be addressed in future work.
19
Boya Marqas, Ridwan, Saman M. Almufty, Renas R. Asaad, and Dr Tamara Saad mohamed. "Advancing AI: A Comprehensive Study of Novel Machine Learning Architectures." International Journal of Scientific World 11, no. 1 (2025): 48–85. https://doi.org/10.14419/kwb24564.
Full textAbstract:
The rapid evolution of machine learning (ML) and artificial intelligence (AI) has led to groundbreaking advancements in computational models, empowering applications across diverse domains. This paper provides an in-depth exploration of advanced ML architectures, including transformers, Graph Neural Networks (GNNs), capsule networks, spiking neural networks (SNNs), and hybrid models. These architectures address the limitations of traditional models like convolutional and recurrent neural networks, offering superior accuracy, scalability, and efficiency for complex data. Key applications are discussed, ranging from healthcare diagnostics and drug discovery to financial fraud detection, autonomous systems, and logistics optimization. Despite their potential, these architectures face challenges such as computational overhead, scalability, and interpretability, necessitating interdisciplinary solutions. The paper also outlines future directions in edge computing, explainable AI, quantum machine learning, and few-shot learning, emphasizing the transformative role of advanced ML architectures in reshaping AI’s future.
20
Migo-Sumagang, Maria Victoria, Kathleen B. Aviso, Dominic C. Y. Foo, Michael Short, Purusothmn Nair S. Bhasker Nair, and Raymond R. Tan. "Optimization and decision support models for deploying negative emissions technologies." PLOS Sustainability and Transformation 2, no. 5 (2023): e0000059. http://dx.doi.org/10.1371/journal.pstr.0000059.
Full textAbstract:
Negative emissions technologies (NETs) will be needed to reach net-zero emissions by mid-century. However, NETs can have wide-ranging effects on land and water availability, food production, and biodiversity. The deployment of NETs will also depend on regional and national circumstances, technology availability, and decarbonization strategies. Process integration (PI) can be the basis for decision support models for the selection, planning, and optimization of the large-scale implementation of NETs. This paper reviews the literature and maps the role of PI in NETs deployment. Techniques such as mathematical programming, pinch analysis (PA), process graphs (P-graphs), are powerful methods for planning NET systems under resource or footprint constraints. Other methods such as multi-criteria decision analysis (MCDA), marginal abatement cost curves, causality maps, and machine learning (ML) are also discussed. Current literature focuses mainly on bioenergy with carbon capture and storage (BECCS) and afforestation/reforestation (AR), but other NETs need to be integrated into future models for large-scale decarbonization.
21
Muchisha, Nadya Dwi, Novian Tamara, Andriansyah Andriansyah, and Agus M. Soleh. "Nowcasting Indonesia’s GDP Growth Using Machine Learning Algorithms." Indonesian Journal of Statistics and Its Applications 5, no. 2 (2021): 355–68. http://dx.doi.org/10.29244/ijsa.v5i2p355-368.
Full textAbstract:
GDP is very important to be monitored in real time because of its usefulness for policy making. We built and compared the ML models to forecast real-time Indonesia's GDP growth. We used 18 variables that consist a number of quarterly macroeconomic and financial market statistics. We have evaluated the performance of six popular ML algorithms, such as Random Forest, LASSO, Ridge, Elastic Net, Neural Networks, and Support Vector Machines, in doing real-time forecast on GDP growth from 2013:Q3 to 2019:Q4 period. We used the RMSE, MAD, and Pearson correlation coefficient as measurements of forecast accuracy. The results showed that the performance of all these models outperformed AR (1) benchmark. The individual model that showed the best performance is random forest. To gain more accurate forecast result, we run forecast combination using equal weighting and lasso regression. The best model was obtained from forecast combination using lasso regression with selected ML models, which are Random Forest, Ridge, Support Vector Machine, and Neural Network.
22
Al-Duais, Mohammed, Abdualmajed A. G. Al-Khulaidi, Fatma Susilawati Mohamad, et al. "Comparative Analysis of Machine Learning and Deep learning Techniques for Early Prediction of Breast Cancer." Journal of Future Artificial Intelligence and Technologies 2, no. 2 (2025): 242–54. https://doi.org/10.62411/faith.3048-3719-68.
Full textAbstract:
Breast cancer remains one of the leading causes of death among women worldwide, primarily due to late detection and diagnosis. Early and accurate prediction is essential to improve survival rates. Machine learning (ML) techniques have proven effective in supporting early diagnosis. This study aims to evaluate and compare the performance of three different approaches: traditional ML, ensemble ML, and deep learning (DL) for early prediction of breast cancer using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The methodology includes data collection, preprocessing, and the design of predictive models. Traditional ML algorithms used include Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes (NB), and Decision Tree (DT). Ensemble ML techniques comprise Random Forest (RF), XGBoost, and AdaBoost, while DL models include Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). The models were evaluated using precision, recall, F1-score, and accuracy. The results indicate that XGBoost achieved the highest accuracy (0.99), with strong recall (0.98) and F1-score (0.986), outperforming all other ensemble and traditional ML methods. CNN achieved 0.99 in all evaluation metrics, slightly outperforming RNN, which attained 0.98 accuracy and 0.985 F1-score. These findings confirm that ensemble ML techniques outperform traditional models, while CNN leads among DL models. Furthermore, the proposed models demonstrated superior prediction performance compared to existing studies, particularly in minimizing false negatives, which is critical for healthcare applications.
23
Theofilatos, Athanasios, Cong Chen, and Constantinos Antoniou. "Comparing Machine Learning and Deep Learning Methods for Real-Time Crash Prediction." Transportation Research Record: Journal of the Transportation Research Board 2673, no. 8 (2019): 169–78. http://dx.doi.org/10.1177/0361198119841571.
Full textAbstract:
Although there are numerous studies examining the impact of real-time traffic and weather parameters on crash occurrence on freeways, to the best of the authors’ knowledge there are no studies which have compared the prediction performances of machine learning (ML) and deep learning (DL) models. The present study adds to current knowledge by comparing and validating ML and DL methods to predict real-time crash occurrence. To achieve this, real-time traffic and weather data from Attica Tollway in Greece were linked with historical crash data. The total data set was split into training/estimation (75%) and validation (25%) subsets, which were then standardized. First, the ML and DL prediction models were trained/estimated using the training data set. Afterwards, the models were compared on the basis of their performance metrics (accuracy, sensitivity, specificity, and area under curve, or AUC) on the test set. The models considered were k-nearest neighbor, Naïve Bayes, decision tree, random forest, support vector machine, shallow neural network, and, lastly, deep neural network. Overall, the DL model seems to be more appropriate, because it outperformed all other candidate models. More specifically, the DL model managed to achieve a balanced performance among all metrics compared with other models (total accuracy = 68.95%, sensitivity = 0.521, specificity = 0.77, AUC = 0.641). It is surprising though that the Naïve Bayes model achieved a good performance despite being far less complex than other models. The study findings are particularly useful, because they provide a first insight into performance of ML and DL models.
24
Gupta, Kishor Datta, Sunzida Siddique, Roy George, Marufa Kamal, Rakib Hossain Rifat, and Mohd Ariful Haque. "Physics Guided Neural Networks with Knowledge Graph." Digital 4, no. 4 (2024): 846–65. http://dx.doi.org/10.3390/digital4040042.
Full textAbstract:
Over the past few decades, machine learning (ML) has demonstrated significant advancements in all areas of human existence. Machine learning and deep learning models rely heavily on data. Typically, basic machine learning (ML) and deep learning (DL) models receive input data and its matching output. Within the model, these models generate rules. In a physics-guided model, input and output rules are provided to optimize the model’s learning, hence enhancing the model’s loss optimization. The concept of the physics-guided neural network (PGNN) is becoming increasingly popular among researchers and industry professionals. It has been applied in numerous fields such as healthcare, medicine, environmental science, and control systems. This review was conducted using four specific research questions. We obtained papers from six different sources and reviewed a total of 81 papers, based on the selected keywords. In addition, we have specifically addressed the difficulties and potential advantages of the PGNN. Our intention is for this review to provide guidance for aspiring researchers seeking to obtain a deeper understanding of the PGNN.
25
Murataj, Joel, Abdulsalam Alkholidi, Habib Hamam, and Afrim Alimeti. "A review of deep learning for self-driving cars: case study." CRJ, no. 1 (September 18, 2023): 16–26. http://dx.doi.org/10.59380/crj.v1i1.2723.
Full textAbstract:
Deep Learning (DL) is a subfield of Machine Learning (ML) that deals with algorithms inspired by the structure and function of the brain. DL uses complex algorithms and deep neural nets to train a model. It consists of the learning of artificial neural networks that consider algorithms inspired by the human brain by learning how to use a large amount of data. It includes machine learning, where machines can learn by experience and get skills without human intervention. The importance of deep learning is the ability to process a large number of characteristics allowing deep and powerful learning when dealing with ambiguous data. This paper aims to study and analyze to be updated existing papers related to the deep learning field and introduce our contribution. An additional aim of this review paper is to concentrate on the self-driving cars case study and introduce the new approach with high performance.
26
Tagare, Mohammad M., Urmila R. Pol, Parashuram S. Vadar, and Tejashree T. Moharekar. "Detection of Jackfruit Leaf Disease Using Machine Learning and Deep Learning." International Journal for Research in Applied Science and Engineering Technology 13, no. 4 (2025): 1871–76. https://doi.org/10.22214/ijraset.2025.68592.
Full textAbstract:
Abstract: The detection of diseases in agricultural crops plays a critical role in maintaining healthy yields. Jackfruit (Artocarpus heterophyllus), a tropical fruit, is susceptible to various diseases that impact its leaves. Timely disease detection can significantly reduce crop loss and improve the quality of the harvest. This paper proposes a system for detecting jackfruit leaf diseases using machine learning (ML) and deep learning (DL) techniques. A dataset of healthy and diseased jackfruit leaf images is used to train both traditional ML algorithms (Random Forest) and DL models (Convolutional Neural Networks). The results indicate that deep learning models, particularly CNNs, outperform traditional ML models in terms of classification accuracy, precision, and recall. This system serves as an effective tool for early detection and management of jackfruit leaf diseases, offering an automated solution for farmers.
27
Abdelsattar, Montaser, Mohamed A. Ismeil, Karim Menoufi, Ahmed AbdelMoety, and Ahmed Emad-Eldeen. "Evaluating Machine Learning and Deep Learning models for predicting Wind Turbine power output from environmental factors." PLOS ONE 20, no. 1 (2025): e0317619. https://doi.org/10.1371/journal.pone.0317619.
Full textAbstract:
This study presents a comprehensive comparative analysis of Machine Learning (ML) and Deep Learning (DL) models for predicting Wind Turbine (WT) power output based on environmental variables such as temperature, humidity, wind speed, and wind direction. Along with Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN), the following ML models were looked at: Linear Regression (LR), Support Vector Regressor (SVR), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). Using a dataset of 40,000 observations, the models were assessed based on R-squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). ET achieved the highest performance among ML models, with an R-squared value of 0.7231 and a RMSE of 0.1512. Among DL models, ANN demonstrated the best performance, achieving an R-squared value of 0.7248 and a RMSE of 0.1516. The results show that DL models, especially ANN, did slightly better than the best ML models. This means that they are better at modeling non-linear dependencies in multivariate data. Preprocessing techniques, including feature scaling and parameter tuning, improved model performance by enhancing data consistency and optimizing hyperparameters. When compared to previous benchmarks, the performance of both ANN and ET demonstrates significant predictive accuracy gains in WT power output forecasting. This study’s novelty lies in directly comparing a diverse range of ML and DL algorithms while highlighting the potential of advanced computational approaches for renewable energy optimization.
28
Bhaskar, Lakshmi, Sumana M.N, Varshini S, and Thanushree Anand. "RAINFALL PREDICTION USING MACHINE LEARNING." International Journal of Advanced Research 13, no. 05 (2025): 1211–16. https://doi.org/10.21474/ijar01/21013.
Full textAbstract:
Accurate rainfall prediction is crucial for sectors like agriculture, disaster management, water resource planning, and climate adaptation. However, forecasting rainfall remains a challenge due to the unpredictable nature of atmospheric conditions. In recent years, machine learning (ML) has proven to be a valuable tool in analyzing complex meteorological data, offering an advanced alternative to traditional statistical models. This study explores the use of machine learning techniques for rainfall prediction through MATLAB, a powerful platform for data analysis, algorithm development, and model implementation. Different ML models, such as regression techniques, support vector machines (SVM), decision trees, and neural networks, are applied to analyze historical meteorological data. The models incorporate key features such as temperature, humidity, wind speed, atmospheric pressure, and past rainfall records to enhance predictive accuracy. To optimize results, preprocessing techniques such as normalization, feature selection, and handling missing values are employed. Furthermore, the framework is designed to accommodate large datasets and real-time data, making it scalable and adaptable to various geographical regions and climatic conditions.
29
Chauhan, Mrs Kalpana. "Prediction of Parkinson’s Disease and Severity of Disease using Machine Learning and Deep Learning." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 06 (2025): 1–9. https://doi.org/10.55041/ijsrem50654.
Full textAbstract:
Abstract - Parkinson's Disease (PD) is a progressive neurodegenerative disorder that affects motor functions, speech, and cognition. This project aims to develop an intelligent system for the detection of Parkinson’s Disease using both Machine Learning (ML) and Deep Learning (DL) techniques. We utilize publicly available datasets containing biomedical voice measurements and other biometric signals. The proposed approach involves data preprocessing, feature extraction, and model training using algorithms such as Support Vector Machines (SVM), Random Forest, and deep neural networks like Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN). Our results demonstrate that deep learning models, especially those tailored for time-series or audio data, offer improved accuracy compared to traditional ML models. This project highlights the potential of AI-based tools in assisting healthcare professionals with early and non-invasive diagnosis of Parkinson’s Disease.
30
An, Yaxin, and Sanket A. Deshmukh. "Machine learning approach for accurate backmapping of coarse-grained models to all-atom models." Chemical Communications 56, no. 65 (2020): 9312–15. http://dx.doi.org/10.1039/d0cc02651d.
Full textAbstract:
Four different machine learning (ML) regression models: artificial neural network, k-nearest neighbors, Gaussian process regression and random forest were built to backmap coarse-grained models to all-atom models.
31
Nigus, Mersha, and H. L. Shashirekha. "A Comparison of Machine Learning and Deep Learning Models for Predicting Household Food Security Status." International Journal of Electrical and Electronics Research 10, no. 2 (2022): 308–11. http://dx.doi.org/10.37391/ijeer.100241.
Full textAbstract:
ML and DL algorithms are becoming more popular to predict household food security status, which can be used by the governments and policymakers of the country to provide a food supply for the needy in case of emergency. ML models, namely: k-Nearest Neighbor (kNN), Logistic Regression (LR), Support Vector Machine (SVM), Naive Bayes (NB), Multi-Layer Perceptron (MLP) and DL models, namely: Artificial Neural Network (ANN) and Convolutional Neural network (CNN) are investigated to predict household food security status in Household Income, Consumption and Expenditure (HICE) survey data of Ethiopia. The standard evaluation measures such as accuracy, precision, recall, F1-score, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) are used to evaluate the models' predictive performance, and the experimental results reveal that ANN, a DL model surpassed the ML classifiers with an accuracy of 99.15%
32
Saito, Masahiko, Tomoe Kishimoto, Yuya Kaneta, et al. "Event Classification with Multi-step Machine Learning." EPJ Web of Conferences 251 (2021): 03036. http://dx.doi.org/10.1051/epjconf/202125103036.
Full textAbstract:
The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks, is presented. Pre-optimized ML models are connected and better performance is obtained by re-optimizing the connected one. The selection of an ML model from several small ML model candidates for each sub-task has been performed by using the idea based on Neural Architecture Search (NAS). In this paper, Differentiable Architecture Search (DARTS) and Single Path One-Shot NAS (SPOS-NAS) are tested, where the construction of loss functions is improved to keep all ML models smoothly learning. Using DARTS and SPOS-NAS as an optimization and selection as well as the connections for multi-step machine learning systems, we find that (1) such a system can quickly and successfully select highly performant model combinations, and (2) the selected models are consistent with baseline algorithms, such as grid search, and their outputs are well controlled.
33
Majid Jasim, Karrar, and Joolan Rokan Nayef. "IoT intrusion detection system based on machine learning and deep learning." Iraqi Journal for Computers and Informatics 51, no. 1 (2025): 83–93. https://doi.org/10.25195/ijci.v51i1.552.
Full textAbstract:
The proliferation of Internet of Things IoT devices has amplified cybersecurity challenges, necessitating robust Intrusion Detection Systems IDS to safeguard against threats such as botnets and Distributed Denial-of-Service DDoS attacks. This paper evaluates the performance of Machine Learning ML and Deep Learning DL models on two benchmark datasets, BoT-IoT and CIC-IDS2017, to develop efficient IDS. Among ML models, XGBoost demonstrated the best performance, achieving 99.99% accuracy on BoT-IoT and 99.91% on CIC-IDS2017 with superior computational efficiency. For DL, Convolutional Neural Networks CNNs achieved 99.99% accuracy on BoT-IoT and 99.61% on CIC-IDS2017 with preprocessing, highlighting the critical role of data preparation. These findings underline the effectiveness of advanced ML/DL models and preprocessing techniques in enhancing IoT security, providing a pathway for real-time, scalable intrusion detection in IoT environments.
34
Waghmare, Urvashi. "Plant Diseases Prediction Using Machine Learning." International Journal for Research in Applied Science and Engineering Technology 12, no. 10 (2024): 1459–64. http://dx.doi.org/10.22214/ijraset.2024.64917.
Full textAbstract:
The early detection and accurate prediction of plant diseases are crucial for improving crop health and maximizing agricultural productivity. Traditional methods of disease detection, which rely heavily on manual observation, are often timeconsuming, labor-intensive, and prone to human error. Recent advancements in machine learning (ML) have opened new possibilities for developing efficient, automated systems that can predict plant diseases with high accuracy. This paper explores various machine learning techniques, including supervised and deep learning models, for plant disease prediction. By analyzing features such as leaf texture, color, and environmental data, these models can identify patterns indicative of specific diseases. Several datasets, including real-time image data and environmental metrics (such as humidity, temperature, and soil quality), are utilized to train and evaluate the models. The study focuses on key ML algorithms like Support Vector Machines (SVM), Decision Trees, Random Forests, Convolutional Neural Networks (CNN), and Transfer Learning to understand their efficacy in disease prediction. These models are evaluated based on their accuracy, precision, recall, and computational efficiency. The results demonstrate that deep learning models, particularly CNNs, outperform traditional methods in image-based plant disease identification. In addition, environmental data integration improves the predictive power of ML models, enabling proactive disease management strategies
35
Watson, Oliver P., Isidro Cortes-Ciriano, Aimee R. Taylor, and James A. Watson. "A decision-theoretic approach to the evaluation of machine learning algorithms in computational drug discovery." Bioinformatics 35, no. 22 (2019): 4656–63. http://dx.doi.org/10.1093/bioinformatics/btz293.
Full textAbstract:
Abstract Motivation Artificial intelligence, trained via machine learning (e.g. neural nets, random forests) or computational statistical algorithms (e.g. support vector machines, ridge regression), holds much promise for the improvement of small-molecule drug discovery. However, small-molecule structure-activity data are high dimensional with low signal-to-noise ratios and proper validation of predictive methods is difficult. It is poorly understood which, if any, of the currently available machine learning algorithms will best predict new candidate drugs. Results The quantile-activity bootstrap is proposed as a new model validation framework using quantile splits on the activity distribution function to construct training and testing sets. In addition, we propose two novel rank-based loss functions which penalize only the out-of-sample predicted ranks of high-activity molecules. The combination of these methods was used to assess the performance of neural nets, random forests, support vector machines (regression) and ridge regression applied to 25 diverse high-quality structure-activity datasets publicly available on ChEMBL. Model validation based on random partitioning of available data favours models that overfit and ‘memorize’ the training set, namely random forests and deep neural nets. Partitioning based on quantiles of the activity distribution correctly penalizes extrapolation of models onto structurally different molecules outside of the training data. Simpler, traditional statistical methods such as ridge regression can outperform state-of-the-art machine learning methods in this setting. In addition, our new rank-based loss functions give considerably different results from mean squared error highlighting the necessity to define model optimality with respect to the decision task at hand. Availability and implementation All software and data are available as Jupyter notebooks found at https://github.com/owatson/QuantileBootstrap. Supplementary information Supplementary data are available at Bioinformatics online.
36
Swenson, Charles. "Using Machine Deep Learning AI to Improve Forecasting of Tax Payments for Corporations." Forecasting 6, no. 4 (2024): 968–84. http://dx.doi.org/10.3390/forecast6040048.
Full textAbstract:
This paper aims to demonstrate how machine deep learning techniques lead to relatively accurate forecasts of quarterly corporate income tax payments. Using quarterly data from Compustat for all U.S. publicly traded corporations from 2000 to 2024, I show that neural nets, the tree method, and random forest models provide robust forecasts despite their encompassing COVID-19 pandemic time periods. The results should be of interest to corporate tax planners, stock analysts, and governments.
37
Aravind Teja, Bastipadu. "Fake Social Media Profile Detection using Machine Learning Algorithms." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem47869.
Full textAbstract:
Abstract—social media has reshaped global interactions, offering unprecedented networking opportunities for individuals and businesses. However, its widespread reach also facilitates the rapid spread of harmful content, including hate speech directed at race, gender, religion, and disabilities, potentially causing significant emotional harm. To mitigate these challenges ML and DL techniques are becoming essential tools in identifying fraudulent social media profiles. These advanced methods analyse behavioural patterns, account details, and interactions to detect anomalies that indicate deceptive activity. ML algorithms classify suspicious accounts based on predefined features, while deep learning models—such as neural networks—process vast amounts of data to uncover more complex fraudulent tactics. As fraudsters evolve their strategies, AI-driven solutions continue to improve, enhancing social media security and protecting users from misinformation and scams. This study evaluates six ML models Neural Networks (NN), Naive Bayes (NB), Logistic Regression (LR), XGBoost (XGB), Random Forest (RF), and Support Vector Machine (SVM)using real-time datasets that have undergone pre-processing to optimize feature extraction. Among the evaluated models, SVM achieved the highest accuracy, surpassing both SVM and NB in precision, recall, and F1-score Index Terms—Social Media Profiles, ML, SVM, Naive Bayes, RFC, NN, Logistic Regression, XGBoost.
38
Küçüktopcu, Erdem, Emirhan Cemek, Bilal Cemek, and Halis Simsek. "Hybrid Statistical and Machine Learning Methods for Daily Evapotranspiration Modeling." Sustainability 15, no. 7 (2023): 5689. http://dx.doi.org/10.3390/su15075689.
Full textAbstract:
Machine learning (ML) models, including artificial neural networks (ANN), generalized neural regression networks (GRNN), and adaptive neuro-fuzzy interface systems (ANFIS), have received considerable attention for their ability to provide accurate predictions in various problem domains. However, these models may produce inconsistent results when solving linear problems. To overcome this limitation, this paper proposes hybridizations of ML and autoregressive integrated moving average (ARIMA) models to provide a more accurate and general forecasting model for evapotranspiration (ET0). The proposed models are developed and tested using daily ET0 data collected over 11 years (2010–2020) in the Samsun province of Türkiye. The results show that the ARIMA–GRNN model reduces the root mean square error by 48.38%, the ARIMA–ANFIS model by 8.56%, and the ARIMA–ANN model by 6.74% compared to the traditional ARIMA model. Consequently, the integration of ML with ARIMA models can offer more accurate and dependable prediction of daily ET0, which can be beneficial for many branches such as agriculture and water management that require dependable ET0 estimations.
39
Sharma, Saurabh, Zohaib Hasan, and Vishal Paranjape. "Advancing AutoML: Integrating Traditional Techniques with Neural Network Architectures for Enhanced Predictive Performance." International Journal of Innovative Research in Computer and Communication Engineering 12, no. 07 (2023): 11786–92. http://dx.doi.org/10.15680/ijircce.2024.1207109.
Full textAbstract:
Machine learning (ML) has rapidly progressed and is now extensively used in diverse fields such as healthcare, finance, and more. Although there have been significant advancements, the process of creating ML models that are successful is still intricate and demanding in terms of resources. It necessitates a considerable level of competence in data science and specialized knowledge in the relevant field. The emergence of Automated Machine Learning (AutoML) has been a response to this obstacle, with the goal of making ML accessible to a wider audience by automating the entire process of applying ML to practical problems. This study introduces an innovative AutoML approach that relies on sophisticated machine learning methods. The proposed framework utilizes cutting-edge algorithms to optimize different stages of the ML pipeline, guaranteeing the creation of high-performing models with minimum human involvement. The approach combines conventional machine learning techniques with state-of-the-art neural network structures to provide reliable and scalable solutions. The experimental findings validate the effectiveness of the suggested AutoML solution, attaining a 97.6% accuracy, a mean absolute error (MAE) of 0.403, and a root mean square error (RMSE) of 0.203. The results demonstrate that the suggested solution outperforms existing methods, showing its potential to greatly lower the difficulty of using machine learning applications while also providing a strong basis for future research in automated and interpretable machine learning.
40
Shah, Vishal. "AI Models for Wildlife Population Dynamics: Machine Learning vs. Deep Learning." Journal of Basic and Applied Research International 31, no. 3 (2025): 1–12. https://doi.org/10.56557/jobari/2025/v31i39213.
Full textAbstract:
AI-driven solutions have been involved in the development of ecosystem population models and have shown unprecedented growth in applying these capabilities to the field of conservation sciences. This research article does a systematic comparative analysis of species distribution modeling, population prediction, and wildlife monitoring using machine learning (ML) and deep learning (DL) methods. ML techniques such as Random Forests and Support Vector Machines are the main tools of ML, as they give rise to a high degree of interpretability and computational efficiency, especially within modest data contexts. On the other hand, deep learning techniques, e.g., Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are more useful in image-based population counting and temporal pattern analysis, although they require large data and computational resources. This paper tries to evaluate model performance in terms of the main metrics like prediction accuracy, F1 scores, and computational efficiency, so by doing this, we will be able to see the trade-offs of the two methods. Further, the concerns about data quality, model validation, and spatial distribution within the conservation frameworks are tackled. We cope with such challenges by introducing new mechanisms like multi-modal data fusion, edge computing, and federated learning. The main message that can be drawn from the data is that hybrid AI models, uniform data frameworks, and mixed disciplinary methods are the most successful ways to conserve wildlife. In addition, it can benefit scientists and practitioners in the verification of AIs appropriated for ecological challenges by offering new points as well. The cure-all for this would be to come up with more practical conservation strategies.
41
Ahmed, Mariyam, Dr Gaurav Tamrakar, and Sayanti Benerjee. "Machine Learning Models for Predicting River Pollution from Industrial Discharge." International Journal of Environmental Sciences 11, no. 5s (2025): 657–62. https://doi.org/10.64252/0f09x630.
Full textAbstract:
This research focuses on measuring river pollution due to industrial activities using machine learning (ML) models. The goal is to create and assess ML algorithms which, given specific environmental and industrial indicators, could reliably forecast the level of pollutants. The approach includes gathering information, feature selection, and model training with techniques including Artificial Neural Networks (ANN) and Random Forests (RF). Results clearly reveal that ML models attain a high level of accuracy which allows the sophisticated control of pollution and the development of early alert systems for pollution. It is shown that ML can significantly assist in the management of the environment and water resources, which is vital for industries and decision makers who strive for the reduction of environmental harm.
42
Pal, Sujan, and Prateek Sharma. "A Review of Machine Learning Applications in Land Surface Modeling." Earth 2, no. 1 (2021): 174–90. http://dx.doi.org/10.3390/earth2010011.
Full textAbstract:
Machine learning (ML), as an artificial intelligence tool, has acquired significant progress in data-driven research in Earth sciences. Land Surface Models (LSMs) are important components of the climate models, which help to capture the water, energy, and momentum exchange between the land surface and the atmosphere, providing lower boundary conditions to the atmospheric models. The objectives of this review paper are to highlight the areas of improvement in land modeling using ML and discuss the crucial ML techniques in detail. Literature searches were conducted using the relevant key words to obtain an extensive list of articles. The bibliographic lists of these articles were also considered. To date, ML-based techniques have been able to upgrade the performance of LSMs and reduce uncertainties by improving evapotranspiration and heat fluxes estimation, parameter optimization, better crop yield prediction, and model benchmarking. Widely used ML techniques used for these purposes include Artificial Neural Networks and Random Forests. We conclude that further improvements in land modeling are possible in terms of high-resolution data preparation, parameter calibration, uncertainty reduction, efficient model performance, and data assimilation using ML. In addition to the traditional techniques, convolutional neural networks, long short-term memory, and other deep learning methods can be implemented.
43
Erskine, Samuel Kofi. "Real-Time Large-Scale Intrusion Detection and Prevention System (IDPS) CICIoT Dataset Traffic Assessment Based on Deep Learning." Applied System Innovation 8, no. 2 (2025): 52. https://doi.org/10.3390/asi8020052.
Full textAbstract:
This research utilizes machine learning (ML), and especially deep learning (DL), techniques for efficient feature extraction of intrusion attacks. We use DL to provide better learning and utilize machine learning multilayer perceptron (MLP) as an intrusion detection (IDS) and intrusion prevention (IPS) system (IDPS) method. We deploy DL and MLP together as DLMLP. DLMLP improves the high detection of all intrusion attack features on the Internet of Things (IoT) device dataset, known as the CICIoT2023 dataset. We reference the CICIoT2023 dataset from the Canadian Institute of Cybersecurity (CIC) IoT device dataset. Our proposed method, the deep learning multilayer perceptron intrusion detection and prevention system model (DLMIDPSM), provides IDPST (intrusion detection and prevention system topology) capability. We use our proposed IDPST to capture, analyze, and prevent all intrusion attacks in the dataset. Moreover, our proposed DLMIDPSM employs a combination of artificial neural networks, ANNs, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Consequently, this project aims to develop a robust real-time intrusion detection and prevention system model. DLMIDPSM can predict, detect, and prevent intrusion attacks in the CICIoT2023 IoT dataset, with a high accuracy of above 85% and a high precision rate of 99%. Comparing the DLMIDPSM to the other literature, deep learning models and machine learning (ML) models have used decision tree (DT) and support vector machine (SVM), achieving a detection and prevention rate of 81% accuracy with only 72% precision. Furthermore, this research project breaks new ground by incorporating combined machine learning and deep learning models with IDPS capability, known as ML and DLMIDPSMs. We train, validate, or test the ML and DLMIDPSMs on the CICIoT2023 dataset, which helps to achieve higher accuracy and precision than the other deep learning models discussed above. Thus, our proposed combined ML and DLMIDPSMs achieved higher intrusion detection and prevention based on the confusion matrix’s high-rate attack detection and prevention values.
44
Schmidt, Austin, Md Wasi Ul Kabir, and Md Tamjidul Hoque. "Machine Learning Based Restaurant Sales Forecasting." Machine Learning and Knowledge Extraction 4, no. 1 (2022): 105–30. http://dx.doi.org/10.3390/make4010006.
Full textAbstract:
To encourage proper employee scheduling for managing crew load, restaurants need accurate sales forecasting. This paper proposes a case study on many machine learning (ML) models using real-world sales data from a mid-sized restaurant. Trendy recurrent neural network (RNN) models are included for direct comparison to many methods. To test the effects of trend and seasonality, we generate three different datasets to train our models with and to compare our results. To aid in forecasting, we engineer many features and demonstrate good methods to select an optimal sub-set of highly correlated features. We compare the models based on their performance for forecasting time steps of one-day and one-week over a curated test dataset. The best results seen in one-day forecasting come from linear models with a sMAPE of only 19.6%. Two RNN models, LSTM and TFT, and ensemble models also performed well with errors less than 20%. When forecasting one-week, non-RNN models performed poorly, giving results worse than 20% error. RNN models extended better with good sMAPE scores giving 19.5% in the best result. The RNN models performed worse overall on datasets with trend and seasonality removed, however many simpler ML models performed well when linearly separating each training instance.
45
Md. Rahmathullah. "Advancing Cardiovascular Disease Prediction: An Interpretive Evaluation of Machine Learning and Deep Learning Models." Journal of Information Systems Engineering and Management 10, no. 40s (2025): 566–84. https://doi.org/10.52783/jisem.v10i40s.7441.
Full textAbstract:
The heart is an important organ required for human beings. It is also the main organ of the cardiovascular system which pumps the blood to the body. The Cardiovascular disease (CVD) is the dominant cause of human death worldwide. Therefore, there is an urgent need to develop precise and practical predictive tools for understanding and diagnosing this disease in advance. Owing to advancements in Machine Learning (ML) and Deep Learning (DL), the accuracy of CVD prediction has significantly increased. Therefore, it offers a groundbreaking potential for early disease identification and provides individual treatment for patients. In this study, the prominent models used in ML such as Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), Support Vector Machine (SVM), and K-nearest neighbors (KNN), and important DL models in DL such as artificial neural networks (ANN), convolutional neural networks (CNN), and recurrent neural networks (RNN), were implemented, compared, and critically analysed. By comparing and analysing different existing models, it is proposed that, by using multimodal data and hybrid models, the accuracy can be increased to the next highest benchmark. The paper concludes that the RF and DT models performed extraordinarily well with an accuracy of 98.5% for the dataset used in the present study.
46
Wang, Zihao, Zhen Song, and Teng Zhou. "Machine Learning for Ionic Liquid Toxicity Prediction." Processes 9, no. 1 (2020): 65. http://dx.doi.org/10.3390/pr9010065.
Full textAbstract:
In addition to proper physicochemical properties, low toxicity is also desirable when seeking suitable ionic liquids (ILs) for specific applications. In this context, machine learning (ML) models were developed to predict the IL toxicity in leukemia rat cell line (IPC-81) based on an extended experimental dataset. Following a systematic procedure including framework construction, hyper-parameter optimization, model training, and evaluation, the feedforward neural network (FNN) and support vector machine (SVM) algorithms were adopted to predict the toxicity of ILs directly from their molecular structures. Based on the ML structures optimized by the five-fold cross validation, two ML models were established and evaluated using IL structural descriptors as inputs. It was observed that both models exhibited high predictive accuracy, with the SVM model observed to be slightly better than the FNN model. For the SVM model, the determination coefficients were 0.9289 and 0.9202 for the training and test sets, respectively. The satisfactory predictive performance and generalization ability make our models useful for the computer-aided molecular design (CAMD) of environmentally friendly ILs.
47
Pietan, Lucas, Hayley Vaughn, James R. Howe, et al. "Prioritization of Fluorescence In Situ Hybridization (FISH) Probes for Differentiating Primary Sites of Neuroendocrine Tumors with Machine Learning." International Journal of Molecular Sciences 24, no. 24 (2023): 17401. http://dx.doi.org/10.3390/ijms242417401.
Full textAbstract:
Determining neuroendocrine tumor (NET) primary sites is pivotal for patient care as pancreatic NETs (pNETs) and small bowel NETs (sbNETs) have distinct treatment approaches. The diagnostic power and prioritization of fluorescence in situ hybridization (FISH) assay biomarkers for establishing primary sites has not been thoroughly investigated using machine learning (ML) techniques. We trained ML models on FISH assay metrics from 85 sbNET and 59 pNET samples for primary site prediction. Exploring multiple methods for imputing missing data, the impute-by-median dataset coupled with a support vector machine model achieved the highest classification accuracy of 93.1% on a held-out test set, with the top importance variables originating from the ERBB2 FISH probe. Due to the greater interpretability of decision tree (DT) models, we fit DT models to ten dataset splits, achieving optimal performance with k-nearest neighbor (KNN) imputed data and a transformation to single categorical biomarker probe variables, with a mean accuracy of 81.4%, on held-out test sets. ERBB2 and MET variables ranked as top-performing features in 9 of 10 DT models and the full dataset model. These findings offer probabilistic guidance for FISH testing, emphasizing the prioritization of the ERBB2, SMAD4, and CDKN2A FISH probes in diagnosing NET primary sites.
48
Islam, Mohammad Anwarul, and Ionut E. Iacob. "Manuscripts Character Recognition Using Machine Learning and Deep Learning." Modelling 4, no. 2 (2023): 168–88. http://dx.doi.org/10.3390/modelling4020010.
Full textAbstract:
The automatic character recognition of historic documents gained more attention from scholars recently, due to the big improvements in computer vision, image processing, and digitization. While Neural Networks, the current state-of-the-art models used for image recognition, are very performant, they typically suffer from using large amounts of training data. In our study we manually built our own relatively small dataset of 404 characters by cropping letter images from a popular historic manuscript, the Electronic Beowulf. To compensate for the small dataset we use ImageDataGenerator, a Python library was used to augment our Beowulf manuscript’s dataset. The training dataset was augmented once, twice, and thrice, which we call resampling 1, resampling 2, and resampling 3, respectively. To classify the manuscript’s character images efficiently, we developed a customized Convolutional Neural Network (CNN) model. We conducted a comparative analysis of the results achieved by our proposed model with other machine learning (ML) models such as support vector machine (SVM), K-nearest neighbor (KNN), decision tree (DT), random forest (RF), and XGBoost. We used pretrained models such as VGG16, MobileNet, and ResNet50 to extract features from character images. We then trained and tested the above ML models and recorded the results. Moreover, we validated our proposed CNN model against the well-established MNIST dataset. Our proposed CNN model achieves very good recognition accuracies of 88.67%, 90.91%, and 98.86% in the cases of resampling 1, resampling 2, and resampling 3, respectively, for the Beowulf manuscript’s data. Additionally, our CNN model achieves the benchmark recognition accuracy of 99.03% for the MNIST dataset.
49
Vikrant Sharma. "Comparative Analysis of Machine Learning Models for Intrusion Detection Systems." Panamerican Mathematical Journal 35, no. 3s (2025): 273–85. https://doi.org/10.52783/pmj.v35.i3s.3891.
Full textAbstract:
Intrusion Detection Systems (IDS) play a crucial role in modern cybersecurity, leveraging machine learning (ML) to detect and mitigate cyber threats effectively. This study provides a comparative analysis of multiple ML-based IDS models, including XGBoost, Generative Adversarial Networks (GAN), Artificial Neural Networks (ANN), Support Vector Machines (SVM), Decision Trees, and Random Forest classifiers. The results indicate that XGBoost (98%) and GAN-based IDS (96%) achieve the highest accuracy, demonstrating superior adaptability in detecting sophisticated attacks. ANN and SVM also exhibit strong performance, while traditional classifiers such as Decision Trees and Random Forests struggle with complex attack patterns. Despite ML advancements, challenges related to data quality, computational efficiency, and evolving cyber threats remain. Future research should focus on hybrid ML approaches, adversarial learning, and real-time IDS deployment to enhance security frameworks. This study underscores the importance of adaptive ML-driven IDS models in mitigating cybersecurity risks.
50
Raja, Rehan, Hiba Saleem, Shayan Ahmad, Mohd Arslaan, and Nida Khan. "Cybersecurity Incident Detection (IDs) Using Machine Learning." International Journal of Innovative Research in Computer Science and Technology 13, no. 3 (2025): 15–25. https://doi.org/10.55524/ijircst.2025.13.3.4.
Full textAbstract:
Machine learning (ML) has emerged as a transformative tool in cybersecurity, particularly for automating threat detection processes that traditionally depend on manual analysis. By leveraging algorithms such as convolutional neural networks (CNNs), support vector machines (SVMs), and Bayesian classifiers, ML enables more efficient identification of malicious activities compared to human-driven approaches. However, the application of ML in security contexts faces distinct challenges, including adversarial evasion tactics and the need for interpretable decision-making frameworks. Recent advancements focus on extracting latent patterns from network traffic data to train adaptive models capable of preempting attacks like ransomware and advanced persistent threats (APTs). This review evaluates ML-driven methodologies for securing digital infrastructures, analyzing their efficacy against modern cyberattacks, and addressing limitations such as dataset bias and concept drift. Furthermore, it investigates shifts in attack vectors over the past decade, offering insights into how data-driven models can counteract evolving malware strategies that endanger global networked systems.