Implementing Machine Learning Research Articles

Challenges and Solutions: Implementing Machine Learning in Salesforce CPQ for Sales Efficiency

The application of ML in Salesforce Configure, Price, Quote (CPQ) systems brings value to improve the efficiency of sales. Nevertheless, this integration experiences several issues. One problem is data management, which has always been an issue for ML, as such systems need large amounts of clean data to generate reliable predictions and use them for automation. Quite often, Salesforce CPQ working with dynamic price, multiple configurations, and real-time quoting addresses different data sources that are hardly consistent. Another issue is the adaptation of specific ML techniques to the requirements of the specific CPQ processes depending on the utilized data and the related development skills, as well as the high computational processing power. Furthermore, real-time performance for quote generation while processing machine learning models may complicate the efficiency of its sales. Some of the solutions to such challenges are the use of strong data integration techniques that enhance data on different platforms to ensure quality data is produced. It is also beneficial for organizations relying on Salesforce CPQ optimization to leverage custom KPIs and tailor machine learning models to improve precision in forecasts and better configure proposals. To complement MLOps performance, it is recommended to implement basic MLOps frameworks alongside cloud-processing power to cut through the latency hurdle as the solution adapts to scale. In addition, considering the integration of the ML models with existing automated Salesforce, one can develop predictive analytics for faster, less time-consuming quotes, lesser human input and fewer mistakes. By using these solutions within Salesforce CPQ driven by machine learning, organisations can unlock the ability to progress through cycles at a faster rate, contain accuracy in software configuration, and optimise operational processes.

Comparison of Deep Learning and Machine Learning Model for Phishing Email Classification

Email is a medium in business communication that people use everyday and not only holds sensitive information but also identity for the user and organization. The uniqueness of information contained make phishing detection and remedy cannot be applied generally. Existing method applied in common on security software such as blacklisting keyword or email address is not enough to outpace evolving phishing method. Nowadays the implementation of machine learning and deep learning grow rapidly fast and the method used by machine learning and deep learning that can learn pattern of inputs and natural language processing making classification to detect email phishing promising, this study present proposed method of phishing mail classification by comparing the use of machine learning and deep learning model, The algorithm used in this paper are recurrent convolutional neural network and random forest with tf-idf and fasttext word embedding. The Dataset contain phishing and legitimate of an email gathered from a trading company in Indonesia. The dataset will be split into 70% for training and 30% for testing. As a result of this comparison, the random forest model with tf-idf word embedding achieve highest accuracy of 100% for the dataset used and the highest accuracy for recurrent convolutional neural network model with fasttext is 98.21%.

Enhancing assessment of direct and indirect exposure of settlement-transportation systems to mass movements by intergraph representation learning

Abstract Amidst the intensifying extreme rainfall patterns due to climate change, global early warning systems for mass movements (e.g. landslides, avalanches) need to provide not only the coarsely aggregated danger reports, but also the necessary fine details to understand its potential implications on critical infrastructures such as transportation systems. In this study, we introduce a novel ‘intergraph’ method that enhances the exposure information using a graph-based machine learning implementation on the hydrological and geological characteristics of mass movements and the underlying connectivity of settlement-transportation systems. Demonstrating the entire country of Norway and the 2020 Gjerdrum quick clay incident as a case study, we integrated the assessment of both direct and indirect exposure information of settlement-transportation systems and their daily 1 km-by-1 km susceptibility map, which were derived from the 68 934 mass movement incidents since 1957 and the connectivity information of 4778 settlements and 257 000 km road networks. Our findings achieved 86.25% accuracy, providing a distribution of improved susceptibility estimates and identifying critical settlements in near-real-time. By interacting the graphical representations of the shared causal drivers of susceptibility and the settlement-transportation system connectivity, our study extends our understanding of the exposure of multiple interacting settlements with a high granularity degree in a unified approach.

Automated detection of deformation mechanisms in re-entrant honeycomb auxetics using machine learning

The intricate geometrical configuration of an auxetic structure enables high energy dissipation capacity at the expense of a highly nonlinear mechanical response. Under external stimuli, complicated deformation mechanisms emerge which dictate the extent of energy dissipation. Recently, the new ‘plastic hinge tracing’ method (Dhari et al., 2021) was introduced to detect such deformation mechanisms for elastoplastic porous materials. This approach is however subjective and cumbersome since it requires monitoring several plastic regions in consecutive deformed configurations. The present study innovatively extends this method by implementing machine learning (ML) techniques for objective detection of deformation modes in auxetics. To this end, a logistic regression ML model was developed to classify the deformation modes of a re-entrant honeycomb structure. The proposed procedure could successfully detect four out of the six deformation modes (‘X’, distorted ‘X’, ‘V’, and ‘V + Z + V’) using the training datasets generated by the finite element analysis and image labels created by K-means clustering algorithm. The success of the proposed automated approach lays the foundation for identifying the deformation mechanisms of other auxetics and porous materials with plastic deformations.

Implementation of Machine Learning in the Categorization of Improvement Areas for Kaizen Submissions

This paper explores the synergy between Kaizen methodologies and Machine Learning, with the goal of improving the efficiency of categorizing areas of improvement. The implementation of Machine Learning algorithms, utilizing the ML.NET tool, has proven to be highly advantageous. These algorithms automate the categorization of Kaizen proposals based on structured data and predefined labels. This automation significantly reduces manual workload, expedites the classification process, and ultimately accelerates decision-making within the realm of continuous improvement. Furthermore, the application of machine learning has improved the categorization accuracy, reduced the risk of human errors, and ensured a more precise assignment to the relevant categories. This, in turn, enhances the quality of the collected information, facilitating well-informed decision-making. Additionally, the automated categorization has streamlined the process for users submitting Kaizen proposals, eliminating the need for manual category selection. This reduces cognitive load and promotes active engagement in the continuous improvement process. Furthermore, the system has introduced a category-based incentive structure, where users accrue points corresponding to the category assigned to their Kaizen proposals. These points can be exchanged for items provided by the company, acting as an additional incentive for active employee participation in the continuous improvement process. In conclusion, the integration of Machine Learning with the ML.NET tool has become a valuable tool for optimizing the management of improvement proposals, resulting in a marked enhancement in efficiency, accuracy, and user engagement in the categorization process.

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network

Cyberattacks are increasingly becoming more complex, which makes intrusion detection extremely difficult. Several intrusion detection approaches have been developed in the literature and utilized to tackle computer security intrusions. Implementing machine learning and deep learning models for network intrusion detection has been a topic of active research in cybersecurity. In this study, artificial neural networks (ANNs), a type of machine learning algorithm, are employed to determine optimal network weight sets during the training phase. Conventional training algorithms, such as back-propagation, may encounter challenges in optimization due to being entrapped within local minima during the iterative optimization process; global search strategies can be slow at locating global minima, and they may suffer from a low detection rate. In the ANN training, the Artificial Bee Colony (ABC) algorithm enables the avoidance of local minimum solutions by conducting a high-performance search in the solution space but it needs some modifications. To address these challenges, this work suggests a Deep Autoencoder (DAE)-based, vectorized, and parallelized ABC algorithm for training feed-forward artificial neural networks, which is tested on the UNSW-NB15 and NF-UNSW-NB15-v2 datasets. Our experimental results demonstrate that the proposed DAE-based parallel ABC-ANN outperforms existing metaheuristics, showing notable improvements in network intrusion detection. The experimental results reveal a notable improvement in network intrusion detection through this proposed approach, exhibiting an increase in detection rate (DR) by 0.76 to 0.81 and a reduction in false alarm rate (FAR) by 0.016 to 0.005 compared to the ANN-BP algorithm on the UNSW-NB15 dataset. Furthermore, there is a reduction in FAR by 0.006 to 0.0003 compared to the ANN-BP algorithm on the NF-UNSW-NB15-v2 dataset. These findings underscore the effectiveness of our proposed approach in enhancing network security against network intrusions.

Implementation of machine learning in $$\ell _{\infty }$$-based sparse Sharpe ratio portfolio optimization: a case study on Indian stock market

Implementation of machine learning in $$\ell _{\infty }$$-based sparse Sharpe ratio portfolio optimization: a case study on Indian stock market

The use of ensembles trees machine learning method in estimating damping of granular materials

Granular Materials (GM) employed within the mechanism of particle dampers attenuate the vibration energy due to their interparticle and particle-wall interactions. Estimating their damping effect using the analytical equivalent single mass approach overlooked the particles' individual losses that are built into the total damping. Alternatively, the numerical techniques (e.g., Discrete Element) are time-inefficient and computationally demanding. Therefore, this study explores the implementation of Machine learning (ML) algorithms to estimate the damping effect of GM. The ML model in this study will rely on a Data-Driven Modeling approach (DDM) incorporating the ensemble tress nonlinear regressor method. The models' training and testing data were obtained from an experimental setup of an acrylic beam internally integrated with Stainless Steel (SS) and glass spheres undergoing low excitation amplitude (RMS <1N). The main aim was to map between seven input features (e.g. filling ratio) and one targeted output: the beam's damped frequency response. Three ensemble trees' algorithms were used to create the DDM; Decision Tree, Random Forest, and XGBoost. The hyperparameter combination based on the Gridsearch CV function increases the prediction accuracy of each model. The developed ML models provided high accuracy (86-93%) in predicting the damping effect of the granular materials spheres.

The Assessment of Early Warning for Insurance Company Using Machine Learning Methods

Developing an early warning indicator is essential to strengthen the financial structure and take necessary precautions in a non-life insurance company. This paper aims to implement machine learning techniques on financial ratios to estimate the capital requirement ratio and investigate the solvency of an insurance company. For this purpose, the historical ratios of insurance companies in an emerging market are considered in accordance with the regulator’s solvency requirements. The ratios collected based on the performances of insurance companies in Türkiye are studied in two cases based on the number of features to be included in to four machine learning algorithms. “Full” data set with 69 and “Boruta” implemented data set with 33 ratios are employed to depict the efficiency of methods in predicting the early warning state of the company in terms of their capital requirement ratio predictions. Additionally, the assessment of these predictions to be utilized as an early warning indicator is performed. The findings illustrate that proposed early warning model predicts well the capital requirement ratio one year in advance. Moreover, among four ML methods, XGBoost achieves a prediction accuracy of 85% for estimating the state of the solvency in an insurance company compared to the other algorithms.

AI Precision for Irrigation, Crop Management, and Pest Control for Sustainable Agriculture in Oman

Abstract The integration of artificial intelligence (AI) precision techniques can improve sustainable agriculture practices in Oman. Our research aims to optimize crop management, pest control, and irrigation techniques by utilizing datasets from the Integrated Crop and Agricultural Resource Data System (ICARDS) and the Integrated Digital Framework for Irrigation Practices (IDFIP). The foundation for well-informed decision-making is provided by the extensive data on soil conditions, weather patterns, and past agricultural practices found in the IDFIP and ICARDS datasets. Our methodology uses Python- implemented machine learning models and sophisticated algorithms. The data is analysed by AI-driven models, which provide useful information for targeted pest control, effective crop management, and precision irrigation. Through the practical use of AI approaches, this research advances the field of precision agriculture. The results could greatly increase agricultural output, preserve water supplies, and reduce their negative effects on the environment. The Sultanate of Oman’s agriculture sector faces numerous obstacles, but integrating AI precision technologies offers a viable way to promote sustainable practices and guarantee food security.

Enhancement of The Performance of Machine Learning Algorithms to Rival Deep Learning Algorithms in Predicting Stock Prices.

This paper objectives to improve stock market prediction accuracy by training data on sentiment analysis of tweets, overcoming volatility and complexity. Utilizing the Use of natural language processing (NLP) algorithms, the tweet's sentiments were classified into (negative - neutral - and positive). The stock value price was predicted by implementing Machine learning algorithms (KNN, SVM, GBM, LR, DT, RF, EL). Among the techniques of ML, (GBM) achieved the greatest results in terms of accuracy (96%). Its results were compared with the results of a deep learning algorithm that uses the same data where GBM got better results, and other algorithms showed results (KNN = 55%, SVM=90%, LR=82%, DT=90%, RF=90%, EL = 88%). The results obtained were superior to previous studies.

Machine learning approaches for improving atomic force microscopy instrumentation and data analytics

Atomic force microscopy (AFM) is a part of the scanning probe microscopy family. It provides a platform for high-resolution topographical imaging, surface analysis as well as nanomechanical property mapping for stiff and soft samples (live cells, proteins, and other biomolecules). AFM is also crucial for measuring single-molecule interaction forces and important parameters of binding dynamics for receptor-ligand interactions or protein-protein interactions on live cells. However, performing AFM measurements and the associated data analytics are tedious, laborious experimental procedures requiring specific skill sets and continuous user supervision. Significant progress has been made recently in artificial intelligence (AI) and deep learning (DL), extending into microscopy. In this review, we summarize how researchers have implemented machine learning approaches so far to improve the performance of atomic force microscopy (AFM), make AFM data analytics faster, and make data measurement procedures high-throughput. We also shed some light on the different application areas of AFM that have significantly benefited from applications of machine learning frameworks and discuss the scope and future possibilities of these crucial approaches.

Toward reliable prediction of CO2 uptake capacity of metal–organic frameworks (MOFs): implementation of white-box machine learning

Toward reliable prediction of CO2 uptake capacity of metal–organic frameworks (MOFs): implementation of white-box machine learning

The Evaluation of Machine Learning Techniques for Isotope Identification Contextualized by Training and Testing Spectral Similarity

Precise gamma-ray spectral analysis is crucial in high-stakes applications, such as nuclear security. Research efforts toward implementing machine learning (ML) approaches for accurate analysis are limited by the resemblance of the training data to the testing scenarios. The underlying spectral shape of synthetic data may not perfectly reflect measured configurations, and measurement campaigns may be limited by resource constraints. Consequently, ML algorithms for isotope identification must maintain accurate classification performance under domain shifts between the training and testing data. To this end, four different classifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron) were trained on the same dataset and evaluated on twelve other datasets with varying standoff distances, shielding, and background configurations. A tailored statistical approach was introduced to quantify the similarity between the training and testing configurations, which was then related to the predictive performance. Wilcoxon signed-rank tests revealed that the OVR-wrapped XGB significantly outperformed the other algorithms, with confidence levels of 99.0% or above for the 133Ba, 60Co, 137Cs, and 152Eu sources. The findings from this work are significant as they outline techniques to promote the development of robust ML-based approaches for isotope identification.

Compatibility Model between Encapsulant Compounds and Antioxidants by the Implementation of Machine Learning

The compatibility between antioxidant compounds (ACs) and wall materials (WMs) is one of the most crucial aspects of the encapsulation process, as the encapsulated compounds’ stability depends on the affinity between the compounds, which is influenced by their chemical properties. A compatibility model between the encapsulant and antioxidant chemicals was built using machine learning (ML) to discover optimal matches without costly and time-consuming trial-and-error experiments. The attributes of the required antioxidant and wall material components were recollected, and two datasets were constructed. As a result, a tying process was performed to connect both datasets and identify significant relationships between parameters of ACs and WMs to define the compatibility or incompatibility of the compounds, as this was necessary to enrich the dataset by incorporating decoys. As a result, a simple statistical analysis was conducted to examine the indicated correlations between variables, and a Principal Component Analysis (PCA) was performed to reduce the dimensionality of the dataset without sacrificing essential information. The K-nearest neighbor (KNN) algorithm was used and designed to handle the classification problems of the compatibility of the combinations to integrate ML in the model. In this way, the model accuracy was 0.92, with a sensitivity of 0.84 and a specificity of 1. These results indicate that the KNN model performs well, exhibiting high accuracy and correctly classifying positive and negative combinations as evidenced by the sensitivity and specificity scores.

Development of machine learning algorithm for loop-mediated isothermal amplification including influence of temperature

To predict amplification in the Loop-Mediated Isothermal Amplification (LAMP) method, a binary model has been developed. This model assesses whether the combination of partial template binding facilitated by multiple primers aligns with a specific signature indicating amplification. For this model, 1512 settings were adjusted, encompassing variations in the extraction oligomer position from the primer, the oligomer length, the number of allowed mismatched bases, and the stringency of the homology position. The optimal set was determined based on the F1 value at a reaction temperature of 60°C, resulting in a value of 0.58. To implement machine learning by amalgamating multiple models, duplicate models were eliminated through cluster analysis. Machine learning using AutoML was performed on 108 distinct models. Consequently, the F1 values were 0.7119 at a reaction temperature of 60°C and 0.7210 at 68°C. The weak correlation between feature importance and the F1 value of the model alone suggests that machine learning utilizing this model incorporates numerous models to enhance prediction accuracy.

Implementing machine learning to predict survival outcomes in patients with resected pulmonary large cell neuroendocrine carcinoma

ABSTRACT Background The post-surgical prognosis for Pulmonary Large Cell Neuroendocrine Carcinoma (PLCNEC) patients remains largely unexplored. Developing a precise prognostic model is vital to assist clinicians in patient counseling and creating effective treatment strategies. Research design and methods This retrospective study utilized the Surveillance, Epidemiology, and End Results database from 2000 to 2018 to identify key prognostic features for Overall Survival (OS) in PLCNEC using Boruta analysis. Predictive models employing XGBoost, Random Forest, Decision Trees, Elastic Net, and Support Vector Machine were constructed and evaluated based on Area Under the Receiver Operating Characteristic Curve (AUC), calibration plots, Brier scores, and Decision Curve Analysis (DCA). Results Analysis of 604 patients revealed eight significant predictors of OS. The Random Forest model outperformed others, with AUC values of 0.765 and 0.756 for 3 and 5-year survival predictions in the training set, and 0.739 and 0.706 in the validation set, respectively. Its superior validation cohort performance was confirmed by its AUC, calibration, and DCA metrics. Conclusions This study introduces a novel machine learning-based prognostic model with a supportive web-based platform, offering valuable tools for healthcare professionals. These advancements facilitate more personalized clinical decision-making for PLCNEC patients following primary tumor resection.

Evaluation of enhanced chemical coagulation method for a case study on colloidal liquid particle in wastewater treatment: Statistical optimization analysis and implementation of machine learning

Coal mines are one of the largest sources of energy supply and generate significant volumes of wastewater. Chemical coagulation is one of the most effective methods for wastewater treatment. In this research, ferric and aluminum-based coagulants, along with polyacrylamide flocculants with positive, negative, and neutral charges, were utilized in chemical coagulation. After applying the Plackett-Burman screening method, it was found that ferric chloride coagulant, neutral flocculant, and slow mixing duration had the greatest impact. The chemical coagulation process was modeled and optimized by examining these factors using the Box–Behnken statistical design as input parameters and sedimentation velocity as the output. Under optimal conditions, the values for ferric chloride coagulant, neutral flocculant, mixing time in slow mode, and sedimentation velocity were determined to be 106.3 mg/L, 3.98 mg/L, 29.6 min, and 1.10 cm/min, respectively. Under optimal conditions, the removal percentages of pollutants, including TSS, turbidity, TDS, COD, and BOD, were obtained at 100%, 100%, 87%, 93%, and 81%, respectively. The experimental data were fitted using the BBD and ANN methods. Both models demonstrated very high agreement, but the ANN method performed better with an AAD% of 0.66, an MSE of 0.0001, and an R2 value of 0.99. All results were calculated with a confidence level above 98%, indicating that both models had very high reliability in modeling and prediction.

Deep learning neural networks for monitoring early-age concrete strength through a surface-bonded PZT sensor configuration

Monitoring the immediate evolution of concrete’s strength is essential to ensure structural integrity and construction efficiency, requiring Forecasting to avoid unforeseen and severe failures during construction. The present investigation introduces an Equivalent structural parametric (ESP) study using a surface-bonded piezo sensor and electromechanical impedance (EMI) methodology to monitor and forecast the strength of concrete by implementing machine learning and deep learning methods. The concrete hydration processes are simulated using COMSOL™ 5.5. The concrete cube’s hydration is represented by altering Young’s modulus and damping ratio to show the rate of curing. Concrete strength development is examined in terms of conductance resonant frequency (CRF) and Conductance resonant peak (CRP). Continuous conductance signature monitoring and data analysis show that CRF and CRP increase with compressive strength. The system’s mechanical impedance is measured, and EMI signatures vs. frequency plots within a specific frequency range are compared to healthy impedance graphs. A mass-spring-damper system with identical properties is identified, and relevant structural parameters are computed. Modern ML algorithms include linear regression (LR), interaction LR, fine, medium, and coarse Gaussian SVM, etc. reliably predict strength with an error rate of less than 2%. Convolutional neural networks (CNN) have advanced image-based recognition, but their usage in EMI-based structural strength assessment is still being studied. A unique strategy using 2D CNN, 2D CNN– Long short-term memory (LSTM), and 2D CNN Bidirectional-LSTM to forecast concrete structure compressive strength shows the potential of deep learning. The proposed 2D CNN-Bi-LSTM model excels in compressive strength prediction, obtaining an R2 value of 0.99 and stabilizing loss error over a few epochs.

The phase space distance between collider events

How can one fully harness the power of physics encoded in relativistic N-body phase space? Topologically, phase space is isomorphic to the product space of a simplex and a hypersphere and can be equipped with explicit coordinates and a Riemannian metric. This natural structure that scaffolds the space on which all collider physics events live opens up new directions for machine learning applications and implementation. Here we present a detailed construction of the phase space manifold and its differential line element, identifying particle ordering prescriptions that ensure that the metric satisfies necessary properties. We apply the phase space metric to several binary classification tasks, including discrimination of high-multiplicity resonance decays or boosted hadronic decays of electroweak bosons from QCD processes, and demonstrate powerful performance on simulated data. Our work demonstrates the many benefits of promoting phase space from merely a background on which calculations take place to being geometrically entwined with a theory’s dynamics.