Customer Review Analysis by Hybrid Unsupervised Learning Applying Weight on Priority Data

Growth discordance in twin pregnancies is associated with increased perinatal morbidity and mortality, yet the patterns of discordance progression and the utility of Doppler assessments remain underinvestigated. The objective of this study was to conduct a longitudinal assessment of intertwin growth and Doppler discordance to identify possible distinct patterns and to investigate the predictive value of longitudinal discordance patterns for adverse perinatal outcomes in twin pregnancies. This retrospective cohort study included twin pregnancies followed and delivered at a tertiary hospital in London (United Kingdom) between 2010 and 2023. We included pregnancies with at least 3 ultrasound assessments after 18 weeks and delivery beyond 34 weeks' gestation. Monoamniotic twin pregnancies, pregnancies with twin-to-twin transfusion syndrome, genetic or structural abnormalities, or incomplete data were excluded. Data on chorionicity, biometry, Doppler indices, maternal characteristics and obstetrics, and neonatal outcomes were extracted from electronic records. Doppler assessment included velocimetry of the umbilical artery, middle cerebral artery, and cerebroplacental ratio. Intertwin growth discordance was calculated for each scan. The primary outcome was a composite of perinatal mortality and neonatal morbidity. Statistical analysis involved multilevel mixed effects regression models and unsupervised machine learning algorithms, specifically k-means clustering, to identify distinct patterns of intertwin discordance and their predictive value. Predictive models were compared using the area under the receiver operating characteristic curve, calibration intercept, and slope, validated with repeated cross-validation. Analyses were performed using R, with significance set at P<.05. Data from 823 twin pregnancies (647 dichorionic, 176 monochorionic) were analyzed. Five distinct patterns of intertwin growth discordance were identified using an unsupervised learning algorithm that clustered twin pairs based on the progression and patterns of discordance over gestation: low-stable (n=204, 24.8%), mild-decreasing (n=171, 20.8%), low-increasing (n=173, 21.0%), mild-increasing (n=189, 23.0%), and high-stable (n=86, 10.4%). In the high-stable cluster, the rates of perinatal morbidity (46.5%, 40/86) and mortality (9.3%, 8/86) were significantly higher compared to the low-stable (reference) cluster (P<.001). High-stable growth pattern was also associated with a significantly higher risk of composite adverse perinatal outcomes (odds ratio: 70.19, 95% confidence interval: 24.18-299.03, P<.001; adjusted odds ratio: 76.44, 95% confidence interval: 25.39-333.02, P<.001). The model integrating discordance pattern with cerebroplacental ratio discordance at the last ultrasound before delivery demonstrated superior predictive accuracy, evidenced by the highest area under the receiver operating characteristic curve of 0.802 (95% confidence interval: 0.712-0.892, P<.001), compared to only discordance patterns (area under the receiver operating characteristic curve: 0.785, 95% confidence interval: 0.697-0.873), intertwin weight discordance at the last ultrasound prior to delivery (area under the receiver operating characteristic curve: 0.677, 95% confidence interval: 0.545-0.809), combination of single measurements of estimated fetal weight and cardiopulmonary resuscitation discordance at the last ultrasound prior to delivery (area under the receiver operating characteristic curve: 0.702, 95% confidence interval: 0.586-0.818), and single measurement of cardiopulmonary resuscitation discordance only at the last ultrasound (area under the receiver operating characteristic curve: 0.633, 95% confidence interval: 0.515-0.751). Using an unsupervised machine learning algorithm, we identified 5 distinct trajectories of intertwin fetal growth discordance. Consistent high discordance is associated with increased rates of adverse perinatal outcomes, with a dose-response relationship. Moreover, a predictive model integrating discordance trajectory and cardiopulmonary resuscitation discordance at the last visit demonstrated superior predictive accuracy for the prediction of composite adverse perinatal outcomes, compared to either of these measurements alone or a single value of estimated fetal weight discordance at the last ultrasound prior to delivery.

In this paper, a novel unsupervised machine learning (ML) algorithm is presented for the expeditious RF fingerprinting of LoRa modulated chirps. Identification based on received signal strength indicator (RSSI) alone is unlikely to yield a robust means for sensor authentication within critical infrastructure deployment. Here, an unsupervised ML algorithm is used to rapidly train an artificial neural network (ANN) matrix creating self-organizing maps (SOMs) for each authentic transmitter and a potential rogue node. A general classifier can be trained on the SOMs for precisely profiling each transmitter as either genuine or rogue. By means of experimental validation, this methodology demonstrated cent-percent success in recognizing each transmitter, either being a real or a rogue node.

Determinants of the competitive advantage of dairy supply chains: Evidence from the Chinese dairy industry

In this paper, we study phase transitions of the q-state Potts model through a number of unsupervised machine learning techniques, namely Principal Component Analysis (PCA), k-means clustering, Uniform Manifold Approximation and Projection (UMAP), and Topological Data Analysis (TDA). Even though in all cases we are able to retrieve the correct critical temperatures $$T_\textrm{c}(q)$$ , for $$q=3,4$$ and 5, results show that non-linear methods as UMAP and TDA are less dependent on finite-size effects. This study may be considered as a benchmark for the use of different unsupervised machine learning algorithms in the investigation of phase transitions.

Especially common in discrete manufacturing, timed event systems often require a high degree of synchronization for healthy operation. Discrete event system methods have been used as mathematical tools to detect known faults, but do not scale well for problems with extensive variability in the normal class. A hybridized discrete event and data-driven method is suggested to supplement fault diagnosis in the case where failure patterns are not known in advance. A unique fault diagnosis framework consisting of signal data from programmable logic controllers, a Timed Petri Net of the normal process behavior, and machine learning algorithms is presented to improve fault diagnosis of timed event systems. Various supervised and unsupervised machine learning algorithms are explored as the methodology is implemented to a case study in semiconductor manufacturing. State-of-the-art classifiers such as artificial neural networks, support vector machines, and random forests are implemented and compared for handling multi-fault diagnosis using programmable logic controller signal data. For unsupervised learning, classifiers based on principal component analysis utilizing major and minor principal components are compared for anomaly detection. The rule-based extreme random forest classifier achieves the highest validation accuracy of 98% for multi-fault classification. Likewise, the unsupervised learning approach shows similar success, yielding anomaly detection rates of 98% with false alarms under 3%. The industrial feasibility of this method is notable, with the results achieved with a training set 99% smaller than the supervised learning classifiers.

This chapter focuses on producing food under sanitary conditions, and product quality assurance. It covers the sanitary design of plants and equipment, and the prerequisite programs important for food safety during processing. Hazard Analysis Critical Control Point (HACCP) involves a specific process for defining critical parameters about the food, identifying potential hazards, and determining control measures for those hazards that are reasonably likely to occur in the food processing system. The chapter also discusses development of total quality management (TQM), which incorporates improving both the organization and people involved with producing the product. For serious complaints involving foreign material, illness, injury, or allergic reaction, it is common to involve the company's risk management department or insurance company. These groups are best equipped to handle the liability risk to the company. Quality "hazards" should be identified and once again, they should include biological, chemical, and physical factors.

Regulatory framework of pharmaceutical compounding and actual developments of legislation in Europe

Contemporary challenges facing food manufacturing are shaped by the synergistic impact of multiple factors. Most significant among these is continuous technological advancement, unfolding within the context of supply chain globalization and increasingly complex value networks. These factors, compounded by the impact of significant socio-economic disruptions, have diminished the efficacy of traditional approaches to quality and safety assurance for processes and products in the food industry. Consequently, there is an imperative to refine these approaches to enhance their applicability within modern production environments, which are characterized by attributes such as modularity, technological sophistication, an extensive product range, and a high degree of product customization. The objective of this study was to establish the foundational core of manufacturing quality assurance for application within the production environments of modern food enterprises. This core constitutes a homologous, transversal, and additive subsystem that shapes the resultant developmental vector through functional integration into the production system, taking into account the interdisciplinary nature of contemporary complex value networks and stakeholder satisfaction. The study employed lexico-semantic alignment of international interdisciplinary normative documents and contemporary scientific models of quality control subsystems, alongside IDEF0 notation for systemic interconnections and ontological modeling. Based on the results, 10 foundational components were identified, comprising 102 structural and functional elements ensuring the systemic role of these components, and 6 types of interconnections, which collectively constituted the core architecture of the quality assurance subsystem. The proposed architecture is designed to meet contemporary requirements and optimize processes such as integration, monitoring, and regulation across all stages of the value chain through the establishment of a comprehensive technological infrastructure.

ObjectivesThe five-repetition sit-to-stand (5R-STS) test was designed to capture objective functional impairment (OFI), and thus provides an adjunctive dimension in patient assessment. It is conceivable that there are different subsets of patients with OFI and degenerative lumbar disease. We aim to identify clusters of objectively functionally impaired individuals based on 5R-STS and unsupervised machine learning (ML).MethodsData from two prospective cohort studies on patients with surgery for degenerative lumbar disease and 5R-STS times of ≥ 10.5 s—indicating presence of OFI. K-means clustering—an unsupervised ML algorithm—was applied to identify clusters of OFI. Cluster hallmarks were then identified using descriptive and inferential statistical analyses.ResultsWe included 173 patients (mean age [standard deviation]: 46.7 [12.7] years, 45% male) and identified three types of OFI. OFI Type 1 (57 pts., 32.9%), Type 2 (81 pts., 46.8%), and Type 3 (35 pts., 20.2%) exhibited mean 5R-STS test times of 14.0 (3.2), 14.5 (3.3), and 27.1 (4.4) seconds, respectively. The grades of OFI according to the validated baseline severity stratification of the 5R-STS increased significantly with each OFI type, as did extreme anxiety and depression symptoms, issues with mobility and daily activities. Types 1 and 2 are characterized by mild to moderate OFI—with female gender, lower body mass index, and less smokers as Type I hallmarks.ConclusionsUnsupervised learning techniques identified three distinct clusters of patients with OFI that may represent a more holistic clinical classification of patients with OFI than test-time stratifications alone, by accounting for individual patient characteristics.

Wahana Indra Komala (19242542), Andri Yansah (19242561), Resti Pebrina (19242563), Implementation of C4.5 Classification Algorithm Customer Review in Transactions at PT. Dapoer Mamih Dapoer Mamih is a company engaged in the culinary field and is committed to providing the best service to its customers. One way to radiate service quality and customer satisfaction is by analyzing customer Reviews. This study aims to classify customer Reviews in transactions using the C4.5 classification algorithm. The C4.5 algorithm was chosen because of its ability to form an effective Decision Tree in handling categorical and numeric data and handling missing data values. The data used in this study came from customer Reviews collected by the company. The analysis process begins with the data preprocessing stage, attribute selection, model training, and evaluation of model classification performance. The results of the study show that the C4.5 algorithm is able to group customer Reviews into certain categories such as positive, neutral, and negative with an adequate level of accuracy. These findings can be the basis for companies to make strategic decisions in improving service quality and customer experience. Keywords: Classification; C4.5; Customer Reviews; Decision Trees; Data Mining.

The introduction of elements of the concept of digital production is especially important in enterprises manufacturing electronic products that are in demand in all spheres of human activity. To create new objects representing the digital production concept, it is necessary to introduce technological innovations in the production of electronics. This is achieved by solving actual analyzing problems system properties means of production and ensuring product quality. Therefore, the article purpose is to ensure the quality of electronic products based on models and methods for analyzing the means and processes of electronic production. To achieve the goal, the digital production development in a structural framework, functional and informational description are considered. The results of the simulation stages of the production life cycle allowed us to estimate the achieved product quality level while improving the subsystems of automatic installation of printed circuit boards.

B a c k g r o u n d . Nowadays, Ukraine's defense and security sector is undergoing fundamental reforms in the procurement of defense products, particularly in the field of quality assurance of such products through the assessment of quality management systems within the framework of Governmental Quality Assurance (GQA) actions. These reforms require both theoretical and methodological justification regarding the directions of such changes and the mechanisms for their implementation. An important issue is the establishment of unified terminology in the field of quality management and management in general, harmonized with the corresponding terminology of EU and NATO member states. The full-scale invasion of russia into Ukraine has brought to the forefront issues related to the implementation of a governmental quality assurance system. The goal of the study is to analyze the Soviet quality control system and compare it with the state quality assurance system, as well as to justify the establishment of modern management systems in Ukraine. M e t h o d s . The study employed methods such as analysis, synthesis, and generalization, through which proposals for establishing a new system for ensuring the quality of defense-related products were developed and substantiated. R e s u l t s . In the course of the research, the state of the quality control system for defense products was analyzed, specifically its organizational structure, regulatory framework, and capacity to ensure product quality under modern conditions. The study also examined the state quality assurance system according to the following components: structure, scope of work, documentation, and training of specialists. Possible mechanisms of interaction between these systems were explored at the level of individual elements. A significant part of the research addressed issues of terminological inconsistency and conceptual frameworks in the field of management and quality management, taking into account the specific characteristics of the defense sector. C o n c l u s i o n s . An institutional approach was applied to analyze the existing quality control system and the state quality assurance system. The main directions for implementing a modern quality assurance system in the defense sector were identified. This system should be based on a risk-oriented approach and the evaluation of quality management processes within enterprises supplying defense-related products.

Software project effort estimation is a major process in software development cycle. This process helps in decision making in resource allocation and distribution. In this work, a new effort estimation clustering method based on estimation maximization soft-clustering unsupervised machine learning algorithm is proposed. This model classifies any software project into one of four categories. An enterprise will accept to develop a software project if this project is clustered into a class that requires resources equal or less than the enterprises resources. The new model helps in decision making process in one hand and helps consumers in assigning projects to a developing enterprise in the other hand. COCOMO dataset has been used to implement, deploy and test the model. The propose model has been compared with K-means algorithm to show the differences between soft and hard clustering. The paper results show that soft-clustering has the ability to estimate efforts like any supervised machine learning algorithms.

An intrusion detection system (IDS) is an important protection instrument for detecting complex network attacks. Various machine learning (ML) or deep learning (DL) algorithms have been proposed for implementing anomaly-based IDS (AIDS). Our review of the AIDS literature identifies some issues in related work, including the randomness of the selected algorithms, parameters, and testing criteria, the application of old datasets, or shallow analyses and validation of the results. This paper comprehensively reviews previous studies on AIDS by using a set of criteria with different datasets and types of attacks to set benchmarking outcomes that can reveal the suitable AIDS algorithms, parameters, and testing criteria. Specifically, this paper applies 10 popular supervised and unsupervised ML algorithms for identifying effective and efficient ML-AIDS of networks and computers. These supervised ML algorithms include the artificial neural network (ANN), decision tree (DT), k-nearest neighbor (k-NN), naive Bayes (NB), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) algorithms, whereas the unsupervised ML algorithms include the expectation-maximization (EM), k-means, and self-organizing maps (SOM) algorithms. Several models of these algorithms are introduced, and the turning and training parameters of each algorithm are examined to achieve an optimal classifier evaluation. Unlike previous studies, this study evaluates the performance of AIDS by measuring the true positive and negative rates, accuracy, precision, recall, and F-Score of 31 ML-AIDS models. The training and testing time for ML-AIDS models are also considered in measuring their performance efficiency given that time complexity is an important factor in AIDSs. The ML-AIDS models are tested by using a recent and highly unbalanced multiclass CICIDS2017 dataset that involves real-world network attacks. In general, the k-NN-AIDS, DT-AIDS, and NB-AIDS models obtain the best results and show a greater capability in detecting web attacks compared with other models that demonstrate irregular and inferior results.

The uncertainty of mechanical assembly process usually brings great challenge to product quality control and assurance. The systematic approach should be employed in the research to find a comprehensive solution. The quality assurance model for assembly (QAMA), based on the analysis of the major problems in the mechanical assembly process and the factors that affect the quality of products, is established by means of three working models: the assembly process model (APM), the activity control model (ACM), and the quality data model (QDM). The APM formulates the assembly process starting with the analysis of process flow, logical scheme, and key factors. The ACM is built by defining the attributes of control activity, mapping relationship between the control activities and its objects in the multiview space and layers. The ACM presents the control flow with the logical relations among control activities as well as the control rules. Based on the two models mentioned above, the QDM supports the acquisition of quality data through data-collecting carriers along assembly process and defines the data structure to support the system model. All of the three models are grouped into a framework which integrates the technical approaches and solutions for quality assurance in mechanical assembly. Based on modeling studies, a computer-integrated and internet-based system called quality assurance system in mechanical assembly (QAS/MA) has been developed. And the development of QAS/MA proves that APM, ACM, QDM, and QAMA are practical and feasible.