Browse Articles

Forecasting of natural gas consumption in China’s logistics industry based on semi-hierarchical control

This paper proposes a research framework based on semi-hierarchical control, analyzes the mechanism of gas instead of oil in China’s logistics industry, and uses several forecasting methods to forecast. The research findings include that: (1) the driving mechanism of substitution of natural gas for gasoline and diesel indicates that natural gas is encouraged by China’s policies and the cost of use is lower, China’s logistics industry will reduce its dependence on gasoline and diesel. (2) By using grey forecasting method, regression trend method and Bass model to forecast natural gas consumption in logistics industry, they show that the forecasting results under different circumstances are helpful for China’s government departments to estimate the consumption trend of natural gas in logistics industry according to different market environments. (3) Based on the reverse feedback mechanism of semi -hierarchical control, combined forecasting methods are established, the hard problem that the combined forecasting coefficients are also solved. Combined forecasting methods are useful complements to meet the forecasting demands of logistics industry’s natural gas consumption, and further improve the forecasting accuracy. (4) According to mean relative error, the error percentages of grey forecasting, regression trend method and Bass model are respectively in 5.373%, 2.9%, and 5.94%, the error percentages of combined forecasting methods are within 2.9%−3.1%, the combined forecasting methods have better forecasting stability.

Prediction of electrical load demand using combined LHS with ANFIS

Enhancement prediction of load demand is crucial for effective energy management and resource allocation in modern power systems and especially in medical segment. Proposed method leverages strengths of ANFIS in learning complex nonlinear relationships inherent in load demand data. To evaluate the effectiveness of the proposed approach, researchers conducted hybrid methodology combine LHS with ANFIS, using actual load demand readings. Comparative analysis investigates performing various machine learning models, including Adaptive Neuro-Fuzzy Inference Systems (ANFIS) alone, and ANFIS combined with Latin Hypercube sampling (LHS), in predicting electrical load demand. The paper explores enhancing ANFIS through LHS compared with Monte Carlo (MC) method to improve predictive accuracy. It involves simulating energy demand patterns over 1000 iterations, using performance metrics through Mean Squared Error (MSE). The study shows superior predictive performance of ANFIS-LHS model, achieving higher accuracy and robustness in load demand prediction across different time horizons and scenarios. Thus, findings of this research contribute to advanced developments rather than previous research by introducing a combined predictive methodology that leverages LHS to ensure solving limitations of previous methods like structured, stratified sampling of input variables, reducing overfitting and enhancing adaptability to varying data sizes. Additionally, it incorporates sensitivity analysis and risk assessment, significantly improving predictive accuracy. Using Python and Simulink Matlab, Combined LHS with ANFIS showing accuracy of 96.42% improvement over the ANFIS model alone.

Correction for Arseni et al., TFIIH-dependent <i>MMP-1</i> overexpression in trichothiodystrophy leads to extracellular matrix alterations in patient skin

Margin weighted robust discriminant score for feature selection in imbalanced gene expression classification

High-dimensional gene expression data poses significant challenges for binary classification, particularly in the context of feature selection methods. Conventional methods, for example, Proportional Overlap Score, Wilcoxon Rank-Sum Test, Weighted Signal to Noise Ratio, ensemble Minimum Redundancy and Maximum Relevance, Fisher Score and Robust Weighted Score for unbalanced data are impacted by key challenges, such as, class imbalance and redundancy. To mitigate these issues, customized feature selection methods are required to tackle the class imbalance issue. This study proposes a more robust solution, Margin Weighted Robust Discriminant Score, for feature selection in the context of high dimensional imbalanced problems. MW-RDS integrates a minority amplification factor to ensure the impact of minority class observation during feature ranking process. The amplification factor along with class specific stability weights obtained from minority-focused robust discriminant score are used for achieving maximum differential capability of genes/features. The score is weighted by margin weights extracted from support vectors to enhance the discriminative power of genes/features thereby highlighting its potential for class separation. Finally, top-ranked genes/features are constrained using ℓ1-regularization to discard redundant genes while identifying the most significant ones. The performance of the proposed method is tested on 9 openly accessible gene expression datasets, using Random Forest, Support Vector Machines, and Weighted k Nearest Neighbors classifiers in term of performance metrics, i.e., accuracy, sensitivity, specificity, F1-score, and precision. The results reveal that the proposed method outperforms the existing methods in most of the cases. Boxplots and stability-plots are also generated to gain a deeper understanding of the results. To futher assess the efficacy of the proposed method, the paper also gives a detailed simulation study.

An overview of the treatment interventions and assessment of fear-avoidance for chronic musculoskeletal pain in adults: A scoping review protocol

Introduction The Fear-Avoidance (FA) model aims to explain how an acute pain experience can develop into a persistent state. The FA model considers five core components: kinesiophobia, pain-related fear, catastrophisation, victimisation, and interpersonal social environment. Amongst these, kinesiophobia, tends to dominate the literature on chronic musculoskeletal pain. As a result, current reviews have not considered the other core components of the FA model when exploring its interventions. Moreover, several synonyms of the term kinesiophobia is not reflected in their search strategies. Coupled with the preference of particular study designs and outcome measures, this scoping review aims to provide and characterise an overview of treatment interventions that consider all study designs, relevant outcome measures, FA components, and FA component synonyms. Methods and analysis Eligible studies will be in English or with an available English translation from 1970 onwards. Databases to be searched include Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, The Allied and Complementary Database (AMED), PEDro, Web of Science, and grey literature. We will include studies involving participants ≥18 years old with chronic musculoskeletal pain, and interventions targeting FA and/or its components. Three review authors will independently screen papers using preestablished eligibility criteria and conduct assessments of risk of bias, with a fourth independent researcher employed to resolve disagreements where found. Qualitative synthesis techniques will be used to characterise the interventions. Patient and Public Involvement (PPI) has been utilised to develop this protocol and will be conducted following completion of the systematic review to discuss and reflect on the findings. Ethics and dissemination This systematic review does not require ethical approval as existing data will be used and the PPI to be conducted is an involvement activity rather than study data. The results will be disseminated through a peer-reviewed journal and via national and international conferences. Open Science Framework registration number This protocol is registered on Open Science Framework: https://doi.org/10.17605/OSF.IO/NR37A

Correction for Bizup et al., Cochlear zinc signaling dysregulation is associated with noise-induced hearing loss, and zinc chelation enhances cochlear recovery

Feasibility, user satisfaction, and knowledge improvement after a VR training program for healthcare professionals managing behavioral and psychological symptoms of dementia (BPSD): Protocol for the FORMSPC-REALVI single-arm pre-post study

Background Behavioral and psychological symptoms are a common challenge for healthcare professionals when managing patients with dementia, and effective verbal and nonverbal communication skills are crucial in caring for such patients. Objectives This article describes a research study protocol for investigating the effectiveness of a virtual reality (VR) training program for healthcare professionals in managing disruptive behavioral and psychological symptoms of dementia (BPSD), such as aggressiveness, agitation, and care refusal. Methods The training scenarios were co-designed with ten healthcare professionals and implemented using an immersive 3D VR platform. Forty geriatric healthcare professionals will participate in a 2-hour training session using VR movies and a Moodle-based theoretical reinforcement. Before and after the training, participants will complete self-assessment questionnaires and knowledge-based quizzes designed to evaluate their perceived competence and understanding of appropriate communication strategies with patients displaying BPSD. The primary outcome will be the change in quiz scores between the pre- and post-training evaluations. Secondary outcomes include training satisfaction, perceived competence, and system usability. Hypotheses Trial registration This study is registered in the French General Data Protection Regulation (GDPR) registry of Assistance Publique – Hôpitaux de Paris (N° 2022 0518135339–18 May 2022). As the trial targets health-providers and measures effects only on them (and not on providers’ patients), clinical trial registration is not required (see ICMJE guidelines: https://www.icmje.org/about-icmje/faqs/clinical-trials-registration/).

Identifying the effectiveness of face mask in a large population with a network-based fluid model

Face masks are important in respiratory disease control, yet their effectiveness varies widely depending on the mask material and its fit on the wearer’s face. In this study, a new semi-analytical flow network model based on the Kármán-Pohlhausen technique is introduced and utilized to efficiently assess mask performance across diverse facial features that represent the observed variations inside a large population. The reduced-order model enables the evaluation of the role of different facial geometrical features with significantly lower computational costs compared to traditional computational fluid dynamics simulations. This research reveals that the area around the nose, particularly without a nose clip, is most susceptible to peripheral leakage and high-velocity jets due to larger gaps. It is argued that subtle variations in facial features, especially the zygomatic arch, significantly influence leakage patterns, emphasizing the importance of customized mask designs. The study also elucidates the complex role of nose clips in improving sealing efficacy for tightly fitted masks and redirecting leaked flow in typical imperfect facemasks. This dual function of nose clips significantly influences overall mask performance, though the exact impact varies depending on individual facial features and mask fit. The reduced-order fluid model presented here has the potential to quantify the effectiveness of face masks for a large population and influence the design of future face masks, with a focus on minimizing or redirecting leakage jets to mitigate the dispersion of respiratory aerosols thus enhancing public health strategies for respiratory disease control.

CausNet-partial: ‘Partial Generational Orderings’ based search for optimal sparse Bayesian networks via dynamic programming with parent set constraints

In our recent work, we developed a novel dynamic programming algorithm to find optimal Bayesian networks with parent set constraints. This ‘generational orderings’ based dynamic programming algorithm—CausNet—efficiently searches the space of possible Bayesian networks. The method is designed for continuous as well as discrete data, and continuous, discrete and survival outcomes. In the present work, we develop a variant of CausNet—CausNet-partial—where we introduce the space of ‘partial generational orderings’, which is a novel way to search for small and sparse optimal Bayesian networks from large dimensional data. We test this method both on simulated and real data. In simulations, CausNet-partial shows superior performance when compared with three state-of-the-art algorithms. We apply it also to a benchmark discrete Bayesian network ALARM, a Bayesian network designed to provide an alarm message system for patient monitoring. We first apply the original CausNet and then CausNet-partial, varying the partial order from 5 to 2. CausNet-partial discovers small sparse networks with drastically reduced runtime as expected from theory. To further demonstrate the efficacy of CausNet-partial, we apply it to an Ovarian Cancer gene expression dataset with 513 genes and a survival outcome. Our algorithm is able to find optimal Bayesian networks with different number of nodes as we vary the partial order. On a personal computer with a 2.3 GHz Intel Core i9 processor with 16 GB RAM, each processing takes less than five minutes. Our ‘partial generational orderings’ based method CausNet-partial is an efficient and scalable method for finding optimal sparse and small Bayesian networks from high dimensional data.

Complexity myths and the misappropriation of evolutionary theory

Recent papers by physicists, chemists, and geologists lay claim to the discovery of new principles of evolution that have somehow eluded over a century of work by evolutionary biologists, going so far as to elevate their ideas to the same stature as the fundamental laws of physics. These claims have been made in the apparent absence of any awareness of the theoretical framework of evolutionary biology that has existed for decades. The numerical indices being promoted suffer from numerous conceptual and quantitative problems, to the point of being devoid of meaning, with the authors even failing to recognize the distinction between mutation and selection. Moreover, the promulgators of these new laws base their arguments on the idea that natural selection is in relentless pursuit of increasing organismal complexity, despite the absence of any evidence in support of this and plenty pointing in the opposite direction. Evolutionary biology embraces interdisciplinary thinking, but there is no fundamental reason why the field of evolution should be subject to levels of unsubstantiated speculation that would be unacceptable in any other area of science.

Pain expectations, experiences and coping strategies used by post-operative patients: A descriptive phenomenological study

Objectives Post-operative pain(POP) is still an unresolved problem worldwide, including in limited-resource countries such as Ghana. Earlier studies have mainly focused on postoperative pain experiences of patient with little attention to their pain expectations and coping strategies. The current study sought to qualitatively explore pain expectations, pain experiences, and coping strategies used by adult surgical patients to help add patients’ perspectives to surgical pain management. Methods A descriptive phenomenological design approach was used to study nine purposively sampled surgical patients receiving care at a regional hospital in Ghana. Participants were individually interviewed before and during the postoperative period to share their opinions on their pain expectations, postoperative pain experiences, and coping strategies. Recruitment and data collection took place between July 8, 2021, and August 30, 2021. The semi-structured individual interviews were audio-recorded, transcribed verbatim, and content analysed to generate themes that described participants’ accounts. Results The participants consisted of six females and three males, aged 24–40, who had undergone major surgeries. This study derived three main themes: diverse pain expectations and experiences, post-operative pain effects, and post-operative pain coping strategies. The study revealed that participants had different pain expectations and experiences, and surgical pain affected their activities of daily living and emotions. Participants coped with the postoperative pain by using personal strategies and seeking support from nurses. Conclusion Pain expectation of surgical patients affects their post-operative pain experiences. Surgical patients use coping strategies in their post-operative pain management. More needs to be done in reducing surgical patients’ experience of post-operative pain.

A plaque recognition algorithm for coronary OCT images by Dense Atrous Convolution and attention mechanism

Currently, plaque segmentation in Optical Coherence Tomography (OCT) images of coronary arteries is primarily carried out manually by physicians, and the accuracy of existing automatic segmentation techniques needs further improvement. To furnish efficient and precise decision support, automated detection of plaques in coronary OCT images holds paramount importance. For addressing these challenges, we propose a novel deep learning algorithm featuring Dense Atrous Convolution (DAC) and attention mechanism to realize high-precision segmentation and classification of Coronary artery plaques. Then, a relatively well-established dataset covering 760 original images, expanded to 8,000 using data enhancement. This dataset serves as a significant resource for future research endeavors. The experimental results demonstrate that the dice coefficients of calcified, fibrous, and lipid plaques are 0.913, 0.900, and 0.879, respectively, surpassing those generated by five other conventional medical image segmentation networks. These outcomes strongly attest to the effectiveness and superiority of our proposed algorithm in the task of automatic coronary artery plaque segmentation.

Strategic planning as a catalyst for sustainability: A mediated model of strategic intent and formulation in manufacturing SMEs

This study examines the influence of Systematic Strategic Planning (SSP) on the Sustainable Performance (SP) of manufacturing Small and Medium Enterprises (SMEs) in Pakistan. Despite SMEs’ vital contribution to economic growth, there is limited empirical research on how strategic planning enhances sustainable performance in SMEs operating in emerging economies facing political and economic instability. Drawing on the Triple Bottom Line (TBL) and Resource-Based View (RBV) theories, this study investigates the mediating roles of Strategic Intent (SI) and Strategic Formulation (SF) in the SSP-SP relationship. A quantitative research design was employed, and data were collected through structured questionnaires distributed to senior executives and decision-makers of manufacturing SMEs. A total of 410 valid responses were received. Structural Equation Modeling (SEM) was applied using AMOS 28 software to analyze the data and test the hypothesized relationships. The results demonstrate that SSP has a significant direct effect on SP and an indirect effect through SI and SF. Specifically, the components of SSP—strategic analysis, strategy creation, strategy execution, and monitoring and evaluation—enhance SMEs’ economic, environmental, and social performance. The study highlights that adopting systematic strategic planning practices enables SMEs to navigate complex and uncertain environments, achieve competitive advantage, and contribute to sustainable development goals. This research fills a critical gap in the literature by focusing on manufacturing SMEs in Pakistan, an under-researched context in the sustainability and strategic management fields. It offers practical insights for SME managers and policymakers to develop and implement comprehensive strategic planning frameworks that foster sustainability. The study also provides theoretical contributions by integrating SI and SF as key mediators within the TBL and RBV theoretical frameworks.

First report of field-evolved resistance to insecticides in Spodoptera frugiperda (Lepidoptera: Noctuidae) from Punjab, Pakistan

The fall armyworm, Spodoptera frugiperda, is one of the major destructive pests of agriculture in Pakistan. The widespread use of insecticides for the management of S. frugiperda has resulted in the field-evolved resistance to insecticides in different strains worldwide. However, field-evolved resistance to insecticides has not yet been reported in S. frugiperda from Pakistan. Following reports of control failure of S. frugiperda in Punjab, Pakistan, a study was planned to investigate resistance to insecticides from different classes in field strains of S. frugiperda to confirm whether the resistance was indeed evolving. Here, we explored resistance to spinetoram, emamectin benzoate, indoxacarb, diflubenzuron, methoxyfenozide, chlorpyrifos and cypermethrin in seven field strains and compared them with a laboratory susceptible reference (Lab-SF) strain of S. frugiperda. Compared with the Lab-SF strain at the LC50 levels, the field strains exhibited 24.8–142.7 (spinetoram), 33.4–91.4 (emamectin benzoate), 30.1–90.6 (indoxacarb), 16.1–38.4 (diflubenzuron), 18.4–51.8 (methoxyfenozide), 37.1–222.9 (chlorpyrifos), and 61.9–540.6 (cypermethrin) fold resistance ratios (RRs). In the presence of detoxification enzyme inhibitors [piperonyl butoxide (PBO) and S,S,S-tributyl phosphorotrithioate (DEF)], the toxicity of all the insecticides, with the exception of spinetoram, was significantly enhanced in the tested field strains of S. frugiperda, providing insight into the metabolic mechanism of resistance. Additionally, compared with the Lab-SF strain, the resistant field strains exhibited elevated activities of detoxification enzymes such as glutathione S-transferases (GST), carboxylesterases (CarE) and mixed-function oxidases (MFO). Overall, the findings of the present study provide robust evidence of field-evolved resistance to insecticides in S. frugiperda, which needs to be managed to minimize yield losses of different crops caused by this global pest.

Enhancing ECG disease detection accuracy through deep learning models and P-QRS-T waveform features

Cardiovascular diseases (CVDs) have surpassed cancer and become the major cause of death worldwide. An electrocardiogram (ECG) is a non-invasive and quicker method for diagnosing abnormal heart conditions. While research has extensively focused on ECG analysis for disease classification, it has been primarily directed toward binary classification or classification of Arrhythmias, highlighting the dire need for detailed classification models. This study utilises the extensive PTB-XL database ECG records to develop a robust method for classifying various heart abnormalities. The data with unique labels is filtered through the Butterworth bandpass filter and Discrete Wavelet Transform (DWT) db-8. The R-peaks of the clean signal were used to detect the subsequent morphological features, i.e., P-QRS-T intervals and amplitudes. The feature set was balanced using the Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC) and fed into Convolutional Neural Network (CNN) and Deep Neural Network (DNN) with 5-fold cross-validation. The models classified the ECG records into one normal and four abnormal classes: Conduction Disturbance (CD), Myocardial Infarction (MI), Hypertrophy (HYP), and ST-T Changes (STTC). Performance metrics such as F1 score, recall, precision, and accuracy were evaluated for each model. The CNN model achieved a mean accuracy of 81% ± 0.03, while the DNN model achieved a mean accuracy of 84% ± 0.01. One key finding is that Hypertrophy (HYP) was consistently classified with up to 98% accuracy. Thus, the study demonstrates the effectiveness of combining advanced signal processing and deep learning techniques for precise multi-class heart disease classification using P-QRS-T features, paving the way for future real-time clinical applications.

Characterization of lightning-induced overvoltages in wind farms

Wind farms are exposed to various weather hazards, including lightning strikes, which can pose significant risks. However, the impact of different wind farm topologies on the magnitude of lightning-induced overvoltages has not been extensively studied, creating a gap in existing literature. This paper addresses this gap by analyzing the characteristics of lightning-induced overvoltages injected into the grid for various wind farm topologies. The scientific scope of this study is to evaluate the influence of wind farm topology on the severity of different types of lightning-induced overvoltages including positive, negative, and double-peaked lightning strikes, using simulation-based analysis. The topologies tested include radial, single-sided ring (SSR), double-sided ring (DSR), and star topologies. The results demonstrate that radial topology leads to the highest overvoltage injection, while switching to SSR, DSR, or star topologies results in reductions of overvoltage by 11.5% to 51.0%, 39.5% to 66.0%, and 62.3% to 89.0%, respectively. These results support a topology-based risk assessment approach, offering clear guidance for selecting configurations that improve lightning resilience.

Markov approach for inventory control with meta-heuristics in intermittent demand environment

Demand variability directly affects inventory management. The variability of intermittent demand causes high lost sales or holding costs. While lost sales reduce customer satisfaction, keeping excessive stock also creates high costs for companies. This situation can be prevented with an appropriate inventory policy. In this study, a Markov-based proactive inventory management approach supported by metaheuristic methods is proposed in the inventory management of intermittent demands. The main contribution of the proposed approach is to find a lower and upper limit for stock by modeling the intermittent demands in the past period with the Markov process. With these optimized limits, it is aimed to balance the largest costs caused by intermittent demands, namely stock and lost sales costs. The intermittent demands used were randomly generated in 4 different sizes from small to large. The proposed approach contributes to inventory management by minimizing the negativities caused by demand variability through the Markov process. A mathematical model has been proposed for stock level optimization, but no feasible solution has been found. The mathematical model was transformed into a fitness function and a solution was provided with the Tabu Search Algorithm and Simulated Annealing. The inventory management process of intermittent demand was first evaluated without the Markov approach, and then the Markov approach was included in the process. The results showed that the Markov approach was a good tool for inventory management of intermittent demand. When the results were examined, the stock limits computed with the Markov process balanced the increased inventory cost and lost sales costs due to intermittent demand.

Multi-omics analysis and single-cell sequencing revealed the lysosome associated molecular subtypes and prognostic model development of papillary thyroid carcinoma

Papillary thyroid carcinoma (PTC) is the most common endocrine carcinoma in recent years, necessitating more precise risk stratification to accurately identify low-risk patients. Although preliminary evidence exists, studies on lysosomes in PTC are limited. This study utilized multi-omics data from the TCGA database to comprehensively investigate the genomic and biological characteristics of lysosomes in PTC patients and identify lysosome-associated genes (LAGs) linked to PTC prognosis. We developed a LAG scoring system for risk stratification based on the expression levels of risk coefficients and independent prognostic LAG variables. Clinical value was assessed through immune infiltration analysis, pathological subgroup analysis, immunotherapy response, and drug sensitivity prediction. Single-cell sequencing from the GEO database was used to analyze PTC samples, and bioinformatics findings were validated using western blot, qRT-PCR, colony formation, and Transwell assays. A new LAG scoring system was developed based on five prognostic LAGs, with single-cell sequencing revealing their expression in different cell types. The role of one LAG, DNASE2B, in PTC cell cloning, proliferation, and invasion was further confirmed in vitro. This comprehensive study highlights the complex interactions between lysosomes and PTC biology, offering new insights into the role of lysosomes in PTC and identifying potential targets for intervention.

Protocol for evaluating the cost-effectiveness of Mongolia’s sugar-sweetened beverages tax using double machine learning

Elevated consumption of sugar-sweetened beverages (SSBs) has been associated with an increase in obesity, type 2 diabetes, and other non-communicable diseases (NCDs), a significant health and economic burden on Mongolia. To address this, the government has introduced a 20% SSB tax set to take effect in 2027. This study conducts a Cost-Effectiveness Analysis (CEA) using a Markov cohort model, incorporating Double Machine Learning (DML) to estimate price elasticity and assess policy-driven consumption changes while addressing potential confounding. The analysis integrates DML-estimated price elasticity and consumption shifts with disease transition probabilities, simulating outcomes for the 2023 Mongolian population, aged over 15 years old, over two time horizons of 20 years and a lifetime. The model estimates changes in obesity prevalence, healthcare costs, and disease burden, translating them into Disability-Adjusted Life Years (DALYs) averted, and Quality-Adjusted Life Years (QALYs) gained. Tax revenue projections and sensitivity analyses further assess the robustness of assumptions. By combining machine learning-based causal inference with economic modelling, this study provides policy-relevant evidence on the cost-effectiveness of SSB taxation, supporting data-driven decision-making for public health strategies in Mongolia, highlighting the tax’s potential to reduce the burden of NCDs and promote healthier behaviours.

Innovative data techniques for centrifugal pump optimization with machine learning and AI model

In modern centrifugal pump machines (CPM), a data acquisition system encompassing software- hardware interfacing is essential for parameter recording. The quality of recorded data plays a crucial role and directly influences the data transformation phase in machine learning (ML) and deep learning (DL) models. The Dewesoft FFT DAQ system is designed to extract the high-quality data from the CPM based on sensor fusion technology. The data recorded from DAQ system undergoes thorough in-depth analysis, processing &amp; transformation before being incorporated into machine learning (ML) or artificial intelligence models. This paper emphasizes the importance of data cleaning, pre-processing, and applying appropriate methodologies to transform raw data into a valuable resource that can be utilized by ML and AI models. Key techniques include Exploratory Data Analysis (EDA), Data Visualization, and Feature Engineering (FE), which collectively enhance data interpretability. Following these transformations, hypothesis testing validates the data’s integrity, ensuring reliability for subsequent modeling. The validated data is employed to train machine learning classifiers and deep learning algorithms, targeting a 27.25% enhancement in operational efficiency based on F1 score. Additionally, it decreases model training time by 180 seconds, facilitating predictive maintenance of critical performance metrics and minimizing downtime. The assessment of model performance relies on Precision, Recall, and F1 score. This approach leverages recent advancements in data science to derive actionable insights from CPM data, facilitating more informed decision-making and optimization of pump operations.