Articles

The pharmaceutical industry is undergoing a profound transformation driven by advancements in Information Technology (IT), with Enterprise Resource Planning (ERP) systems playing a pivotal role in reshaping operations. These systems offer integrated solutions that streamline key business processes, such as production, inventory management, supply chain optimization, regulatory compliance, and data integration, contributing significantly to operational efficiency and organizational agility. This paper explores the evolution and impact of ERP systems within the pharmaceutical sector, highlighting their contributions to overcoming the industry’s inherent challenges, including complex regulatory requirements, the need for accurate and real-time data, and the demand for supply chain resilience. The integration of cloud-based ERP solutions, the incorporation of emerging technologies like Artificial Intelligence (AI), Machine Learning (ML), and the Internet of Things (IoT), and enhanced data analytics capabilities have revolutionized pharmaceutical IT. These advancements not only reduce operational costs, improve forecasting accuracy, and enhance collaboration but also ensure compliance with stringent global regulations, such as Good Manufacturing Practices (GMP) and FDA guidelines. Moreover, ERP systems have been instrumental in managing the pharmaceutical supply chain, ensuring product traceability, and improving inventory control and order fulfillment processes. This manuscript examines how ERP systems enable pharmaceutical companies to maintain high standards of product quality, improve decision-making, and ensure the safety and efficacy of drugs through robust tracking and auditing mechanisms. A case study of a pharmaceutical company that implemented an ERP system demonstrates the tangible benefits, including increased operational efficiency, improved compliance rates, and enhanced customer satisfaction. However, despite the clear advantages, challenges such as customization complexities, data integration issues, and resistance to change remain. As the pharmaceutical industry continues to evolve, ERP systems will remain a cornerstone of digital transformation, facilitating smarter decision-making, better resource management, and enhanced collaboration across global operations. This paper also identifies future trends, including the potential of AI and blockchain technologies in further strengthening ERP systems and transforming the pharmaceutical landscape.

Recent advancements in the screening, diagnosis, and management of obstructive sleep apnea (OSA) have significantly improved patient outcomes. For screening, the use of home sleep apnea testing (HSAT) has become more prevalent, offering a convenient and cost-effective alternative to traditional in-lab polysomnography. HSAT devices have shown good specificity and sensitivity, particularly in patients with a high pre-test probability of OSA. In terms of diagnosis, advancements in wearable technology and mobile health applications have enabled continuous monitoring of sleep patterns and respiratory parameters. These tools provide valuable data that can be used to identify OSA more accurately and promptly. Additionally, machine learning algorithms are being integrated into diagnostic processes to enhance the accuracy of OSA detection by analyzing large datasets and identifying patterns indicative of the condition. Management of OSA has also seen significant progress. Continuous positive airway pressure (CPAP) therapy remains the gold standard, but new developments include auto-adjusting CPAP devices that optimize pressure settings based on real-time feedback. Mandibular advancement devices and hypoglossal nerve stimulation are emerging as effective alternatives for patients who are CPAP-intolerant. Furthermore, lifestyle interventions such as weight management, positional therapy, and exercise have been shown to complement medical treatments, leading to better overall outcomes. This review article highlights these advancements that collectively contribute to improved patient adherence, reduced symptoms, and enhanced quality of life for individuals with OSA.

Sentiment analysis, a vital aspect of natural language processing, involves the application of machine learning models to discern the emotional tone conveyed in textual data. The use case for this type of problem is where businesses can make informed decisions based on customer feedback, identify the sentiments of their employees, and make decisions on hiring or retention, or for that matter, classify a text based on its topic like whether it is about a particular subject like physics or chemistry as is useful in search engines. The model leverages a sequential architecture, transforms words into dense vectors using an Embedding layer, and captures intricate sequential patterns with two Long Short-Term Memory (LSTM) layers. This model aims to effectively classify sentiments in text data using a 50-dimensional embedding dimension and 20 % dropout layers. The use of rectified linear unit (ReLU) activations enhances non-linearity, while the SoftMax activation in the output layer aligns with the multi-class nature of sentiment analysis. Both training and test accuracy were well over 80%.

The integration of LiDAR and Artificial Intelligence (AI) has revolutionized feature detection in urban environments. LiDAR systems, which utilize pulsed laser emissions and reflection measurements, produce detailed 3D maps of urban landscapes. When combined with AI, this data enables accurate identification of urban features such as buildings, green spaces, and infrastructure. This synergy is crucial for enhancing urban development, environmental monitoring, and advancing smart city governance. LiDAR, known for its high-resolution 3D data capture capabilities, paired with AI, particularly deep learning algorithms, facilitates advanced analysis and interpretation of urban areas. This combination supports precise mapping, real-time monitoring, and predictive modeling of urban growth and infrastructure. For instance, AI can process LiDAR data to identify patterns and anomalies, aiding in traffic management, environmental oversight, and infrastructure maintenance. These advancements not only improve urban living conditions but also contribute to sustainable development by optimizing resource use and reducing environmental impacts. Furthermore, AI-enhanced LiDAR is pivotal in advancing autonomous navigation and sophisticated spatial analysis, marking a significant step forward in urban management and evaluation. The reviewed paper highlights the geometric properties of LiDAR data, derived from spatial point positioning, and underscores the effectiveness of machine learning algorithms in object extraction from point clouds. The study also covers concepts related to LiDAR imaging, feature selection methods, and the identification of outliers in LiDAR point clouds. Findings demonstrate that AI algorithms, especially deep learning models, excel in analyzing high-resolution 3D LiDAR data for accurate urban feature identification and classification. These models leverage extensive datasets to detect patterns and anomalies, improving the detection of buildings, roads, vegetation, and other elements. Automating feature extraction with AI minimizes the need for manual analysis, thereby enhancing urban planning and management efficiency. Additionally, AI methods continually improve with more data, leading to increasingly precise feature detection. The results indicate that the pulse emitted by continuous wave LiDAR sensors changes when encountering obstacles, causing discrepancies in measured physical parameters.

The most prevalent technique behind security data breaches exists through SQL Injection Attacks. Organizations and individuals suffer from sensitive information exposure and unauthorized entry when attackers take advantage of SQL injection (SQLi) attack vulnerability’s severe risks. Static and heuristic defense methods remain conventional detection tools for previous SQL injection attacks study's foundation is a detection system developed using the Gated Recurrent Unit (GRU) network, which attempts to efficiently identify SQL Injection attacks (SQLIAs). The suggested Gated Recurrent Unit model was trained using an 80:20 train-test split, and the results showed that SQL injection attacks could be accurately identified with a precision rate of 97%, an accuracy rate of 96.65%, a recall rate of 92.5%, and an F1-score of 94%. The experimental results, together with their corresponding confusion matrix analysis and learning curves, demonstrate resilience and outstanding generalization ability. The GRU model outperforms conventional machine learning (ML) models, including K-Nearest Neighbor’s (KNN), and Support Vector Machine (SVM), in terms of identifying sequential patterns in SQL query data. Recurrent neural architecture proves effective in the detection of SQLi attacks through its ability to provide secure protection for contemporary web applications.

Over the past few decades, cardiovascular disease and related complications have surpassed all others as the important causes of death on a universal scale. At the moment, they are the important cause of mortality universal, including in India. It is important to know how to find cardiovascular problems early so that patients get better care and prices go down. This project utilizes the UCI Heart Disease Dataset to develop ML and DL models capable of detecting cardiac diseases. Heart illness was categorized using Convolutional Neural Network (CNN) models, which are able to detect intricate patterns in supplied data. A confusion matrix rating, an F1-score, a ROC curve, accuracy, precision, and recall were some of the measures used to grade the model. It did much better than the Neural Network, Deep Neural Network (DNN), and Gradient Boosted Trees (GBT) models, with 91.71% accuracy, 88.88% precision, 82.75% memory, and 85.70% F1-score. Comparative study showed that CNN was the most accurate model. Other models had different balances between accuracy and recall. The experiment results show that the optional CNN model is a decent way to identify cardiovascular disease. This means that it could be used in healthcare systems to find diseases earlier and treat patients better.

High-Performance Computing (HPC) is indispensable for large-scale scientific simulations, but achieving optimal performance on modern supercomputers is increasingly challenging. As HPC systems scale toward exascale, they face escalating complexity in hardware, software, and workloads. Traditional optimization methods (manual tuning and heuristic algorithms) struggle to cope with dynamic workloads and intricate system behaviors. Artificial Intelligence (AI) techniques offer a promising approach to address these challenges. This article provides an overview of AI-powered optimization in HPC, focusing on how machine learning and related AI methods enhance performance, efficiency, and scalability of scientific simulations. We survey key AI techniques applied to HPC optimization including machine learning for performance modeling, deep reinforcement learning for resource management, and AI-driven surrogate models for accelerating simulations and illustrate their impact through case studies in domains such as job scheduling and fluid dynamics. We discuss the practical applications of these techniques, highlighting reported performance gains (e.g., substantial reductions in simulation run time and improved resource utilization). We also examine the challenges in integrating AI with HPC (such as training overhead, data movement, and reliability concerns) and outline future directions for research. The convergence of AI and HPC is poised to produce “smart” simulation workflows that intelligently adapt and optimize in real time, pushing the frontiers of scientific computing.

Consumer behavior is evolving, demanding a wide range of products with fast shipping and reliable service. The automotive aftermarket industry, worth billions, requires efficient distribution systems to stay competitive. Manufacturers strive to balance growth with product and service excellence. Distributors and retailers face the challenge of maintaining competitive pricing while keeping inventory levels low. An adequate supply chain and accurate product data are crucial for product availability and reducing stock issues. This ultimately increases profits and customer satisfaction.

The stock market is very volatile and hard to predict accurately due to the uncertainties affecting stock prices. However, investors and stock traders can only benefit from such models by making informed decisions about buying, holding, or investing in stocks. Also, financial institutions can use such models to manage risk and optimize their customers' investment portfolios. In this paper, we use the Long Short-Term Memory (LSTM-RNN) Recurrent Neural Networks (RNN) to predict the daily closing price of the Amazon Inc. stock (ticker symbol: AMZN). We study the influence of various hyperparameters in the model to see what factors the predictive power of the model. The root mean squared error (RMSE) on the training was 2.51 with a mean absolute percentage error (MAPE) of 1.84%.

The swift changes in the complexity of the project, scarcity of resources, and pressure on the organization have demonstrated the necessity of more intelligent and data-driven planning and scheduling methods. Conventional methods tend to be less effective in the tasks of uncertainty management, dynamic environment, and dynamism of the project ecosystems of the modern world. The application of machine learning (ML) in the planning and scheduling of projects is thoroughly reviewed in this paper, and it is evident that ML may help to improve the accuracy of forecasts, optimize resource distribution, and make decisions. This paper offers an analysis of the basic concepts of project management, evidence-based practices, and how supervised and unsupervised learning, as well as reinforcement learning concepts, can be combined in the scheduling process. Furthermore, the new literatures are examined to bring out new techniques, including predictive modelling, optimization algorithms, simulation-based planning and adaptive scheduling models. The review determines the main strengths, weaknesses, and gaps in the research that impact the adoption of ML-driven approaches. All in all, the paper describes the ways in which machine learning technologies can change the traditional way of project management by creating efficient, resilient, and proactive planning systems.

Machine learning operations (MLOps) comprises the practices, methods, and tooling that facilitate the deployment of reliable ML models in production environments. While many aspects of cloud data platforms are designed to enable reliability, only some managed ML services support the MLOps goals of continuous integration, continuous delivery, data lineage tracking, associated reproducibility, governance, and security. Furthermore, reliability encompasses not only the fulfillment of service-level objectives, but also systematic monitoring, alerting, and incident response automation. Architectural patterns are proposed to enable reliable deployment in cloud data platforms, focusing on the implementation of continuous integration and testing pipelines for ML models and the formulation of continuous delivery and rollout strategies. Continuous integration pipelines reduce the risk of regressions and ensure sufficient model performance at the time of deployment, while continuous delivery pipelines enable rapid updates to production models within acceptable risk profiles. The landscape of publicly available MLOps frameworks, tools, and services is also examined, emphasizing the pros and cons of established and rising solutions in containerization, orchestration, model serving, and inference. Containerization and orchestration contributes to the building of reliable deployment pipelines in cloud data platforms, whether general-purpose tools (e.g. Docker and Kubernetes) or solutions tailored for ML workloads. Containerized serving frameworks designed for high-throughput, low-latency inference can benefit a wide range of business applications, while auto-scaling and model versioning capabilities enhance the ease of use of cloud-native ML services.

M&A is a strategic concept of business growth through consolidation, gaining market access, increasing strategic positions, and increasing operational efficiency. To understand the dynamics of M&A, this paper looks at aspects such as targeted firm identification, evaluation, bidding for the target firm, and post-acquisition integration. All forms of M&A, including horizontal, vertical, conglomerate, and acquisitions, are discussed in terms of goals and values, including synergy, cost reduction, competitive advantages, and access to better technology. However, issues such as cultural assimilation, adhesion to regulations, and calculating an inaccurate value are also resolved. The paper then goes deeper to provide insight into how predictive analytics applies to M&A, using ML to improve decision-making with forecasting benefits. Including healthcare, education, and construction industries, the presented predictive models using regression analysis, neural networks, and ensemble techniques help to make decisions. Through time series and real-time data, PDA enables sound M&A strategies, effective risk management and smooth integration.

This paper leverages gene and cell therapy research in diverse disorders ranging from monogenic to infectious diseases to cancer and emerging breakthroughs, where one can harness individual genes or a synthetic gene sequence designed based on a shared molecular pattern in infected cells to better fight various disorders [1]. A pivotal task is to predict the performances of candidate gene therapies to guide clinical translational research using methods such as retrospective bioinformatic analyses. Implementing them to a large-scale gene therapy database reveals that it is feasible to construct and apply well-performing interpretable, supervised learning models [2]. Preliminary evidence of machine learning approaches' statistical significance helps clinicians and biomedical researchers, market participants, and regulatory and economic experts derive relevant, practical applications, thereby enhancing the deployment of gene therapy and genomics to achieve positive, long-term growth for humanity while alleviating the ongoing worldwide economic burden precipitated by prolonged and recurring diseases. Deploying machine learning techniques to accelerate gene and cell therapy drug development and trials shall also mitigate the existing obstacle of limited patient access to emerging, transformative medical innovations such as gene therapy due to skyrocketing prices, which often herald gene therapy products as the world's most expensive medicines [3]. Moreover, in preventing patients from accessing effective, life-saving genetic medicines, there commonly exists a multidimensional access gap encompassing the availability, affordability, and quality or acceptability of these clinical treatments. The ensuing substantial gap has repeatedly been documented and mainly emanates from differential institutional and socio-political choices around resource allocation at international and domestic levels [4]. Particularly, it is also due to the stringent licensure and regulatory approval processes underpinned by insufficient evidence for novel safety and clinical efficacy profiles for genetic therapies in multiple micro-local diagnoses and subpopulations. We believe that a higher likelihood of gene therapy adoption shall result when the clinical evidence path contains adequate representation from the most diverse and relevant patient populations [5].

Failure prediction can be achieved through prognostics, which provides timely warnings before failure. Failure prediction is crucial in an effective prognostic system, allowing preventive maintenance actions to avoid downtime. The prognostics problem involves estimating the remaining useful life (RUL) of a system or component at any given time. The RUL is defined as the time from the current time to the time of failure. The goal is to make accurate predictions close to the failure time to provide early warnings. J S Grewal and J. Grewal provide a comprehensive definition of RUL in their paper "The Kalman Filter approach to RUL estimation." A process is a quadruple (XU f P), where X is the state space, U is the control space, P is the set of possible paths, and f represents the transition between states. The process involves applying control values to change the system's state over time.

With the rapid growth of online communication platforms, the identification and management of toxic comments have become crucial in maintaining a healthy online environment. Various machine learning approaches have been employed to tackle this problem, ranging from traditional models to more recent attention-based transformer networks. This paper aims to compare the performance of attention-based transformer networks with several traditional machine learning methods for toxic comments classification. We present an in-depth analysis and evaluation of these methods using a common benchmark dataset. The experimental results demonstrate the strengths and limitations of each approach, shedding light on the suitability and efficacy of attention-based transformers in this domain.

The effects on the elderly are disproportionately Alzheimer’s disease (AD) is one of the most prevalent and chronic types of dementia. Alzheimer's disease (AD), a fatal illness that can harm brain structures and cells long before symptoms appear, is currently incurable and incurable. Using brain MRI pictures from a publicly accessible Kaggle dataset, this study suggests a prediction model based on Convolutional Neural Networks (CNNs) to help with the early detection of Alzheimer's disease. Four levels of dementia have been applied to the 6,400 photos in the collection: not demented, slightly demented, moderately demented, and considerably mildly demented. Pixel normalization, class balancing utilizing data augmentation techniques, and picture scaling to 128×128 pixels were all part of a thorough workflow for data preparation. To improve the gathering of spatial dependence in volumetric MRI data, a 3D convolutional neural network (CNN) architecture was used. We used important performance measures including F1-score, recall, accuracy, precision, and log loss to gauge the model's effectiveness. A review of the available data indicates that the total F1-score, accuracy, recall, and precision were 99.0%, 99.0%, and 99.38%, respectively. The findings demonstrate the model's potential for practical use in early AD diagnosis and establish its robustness with the help of confusion matrix analysis and performance curves.

Financial markets have become more and more complex, so has been the number of data sources. Stock price prediction has hence become a tough but important task. The time dependencies in stock price movements tend to escape from traditional models. In this work, a hybrid ARIMA-LSTM model is suggested to enhance accuracy of stock price forecasts. Based on time series indicators like adjusted closing prices of S&P 500 stocks over a decade (2010–2019), the ARIMA-LSTM model combines influences of both autoregressive time series forecasting with the substantial sequence learning property of LSTM. Data preprocessing in all aspects including missing values interpolation, outlier’s detection and data scaling – Min-Max guarantees data quality. The model is trained on 90/10 training/testing split and met with main performance metrics: MaE, MSE & RMSE. As indicated in the results, the proposed ARIMA-LSTM model gives a MAE value and MSE value of 0.248 and 0.101 respectively and RMSE of 0.319, a measure high accuracy on stock price prediction. Coupled comparative analysis with other Artificial Neural Networks (ANN) and BP Neural Networks (BPNN) are examples of machine learning reference models, further illustrates the suitability and superiority of ARIMA-LSTM approach as compared to the underlying models with the least MAE and strong predictive capability. This work demonstrates the efficiency of integrating the classical time series models with deep learning methods for financial forecasting.

In the constantly evolving world of cloud computing, appropriate resource allocation is essential for both keeping costs down and ensuring an ongoing flow of apps and services. Because of its adaptability to specific tasks and human behavior, machine learning (ML) is a desirable choice for fulfilling those needs. This study Efficient cloud resource allocation is critical for optimizing performance and cost in cloud computing environments. In order to improve the precision of resource allocation, this study investigates the use of Long Short-Term Memory (LSTM). The LSTM model achieved 97% accuracy, 97.5% precision, 98% recall, and a 97.8% F1-score (F1-score: harmonic mean of precision and recall), according to experimental data. The confusion matrix demonstrates strong classification performance across several resource classes, while the accuracy and loss curves verify steady learning with minimal overfitting. The suggested LSTM model performs better than more conventional ML (machine learning) models like Gradient Boosting (GB) and Logistic Regression (LR), according to a comparative study. These findings underscore the LSTM (Long Short-Term Memory) model’s robustness and suitability for dynamic cloud environments, enabling more accurate forecasting and efficient resource management.

Advances in web-centric cloud computing have facilitated the establishment of an integrated cloud environment connecting a wide variety of clinical trial stakeholders. A web-centric cloud framework is proposed for real-time monitoring and risk prediction during clinical trials. The framework focuses on identifying relevant datasets, developing a data-management interface, and implementing machine-learning algorithms for data analysis. Detailed descriptions of the data-management interface and the machine-learning processes are provided, targeting active clinical trials with therapeutic uses in cancer. Demonstrations utilize publicly available clinical-trial data from the ClinicalTrials.gov repository. The real-time monitoring and risk prediction systems were assessed by developing five supervised-classification-machine-learning models for trial-status prediction and six unsupervised models for patient-safety-profile assessment, each representing a different phase of the clinical-trial process. All supervised models yielded high accuracy and area-under-the-curve values at the testing stage, while the unsupervised models demonstrated practical applicability. The results underscore the advantages of using the trial-status algorithm, the patient-safety-profile model, and the proposed framework for performing real-time monitoring and risk prediction of clinical trials.

Today, the presentation of a three-dimensional model of real-world features is very important and widely used and has attracted the attention of researchers in various fields, including surveying and spatial information systems, and those interested in the three-dimensional reconstruction of buildings. The building is the key part of the information in a three-dimensional city model, so extracting and modeling buildings from remote sensing data is an important step in building a digital model of a city. LiDAR technology due to its ability to map in all three modes of one-dimensional, two-dimensional, and three-dimensional is a suitable solution to provide hyperspectral and comprehensive images of the building in an urban environment. In this review article, a comprehensive review of the methods used in identifying buildings from the past to the present and appropriate solutions for the future is discussed.