K-NN supervised learning algorithm in the predictive analysis of the quality of the university administrative service in the virtual environment

The objective of this study is to analyze and discuss the metrics of the predictive model using the K-nearest neighbor (K-NN) learning algorithm, which will be applied to the data on the perception of engineering students on the quality of the virtual administrative service, such as part of the methodology was analyzed the indicators of accuracy, precision, sensitivity and specificity, from the obtaining of the confusion matrix and the receiver operational characteristic (ROC) curve. The collected data were validated through Cronbach's Alpha, finding consistency values higher than 0.9, which allows to continue with the analysis. Through the predictive model through the Matlab R2021a software, it was concluded that the average metrics for all classes are optimal, presenting a precision of 92.77%, sensitivity 86.62%, and specificity 94.7%; with a total accuracy of 85.5%. In turn, the highest level of the area under the curve (AUC) is 0.98, which is why it is considered an optimal predictive model. Having carried out this study, it is possible to contribute significantly to the decision-making of the higher institution in relation to the improvement of the quality of the virtual administrative service.

Clustering Application for Condition-based Maintenance in Time-varying Processes: A Review

In the field of industrial process monitoring, more and more interest is being shown in specific process categories. These include time-varying processes, that is, those processes whereby the response one receives as output from the system depends on when the input signal is sent into it. There are many reasons for this process variability and such contexts are not always analyzed with this operational characteristic at their core. At the same time, interest in certain categories of techniques is also becoming more prominent, to meet certain application needs. Among these, clustering and unsupervised techniques in general are gaining ground. This is largely due to the difficulty of finding fault data with which to train, for example, supervised models. On the other hand, the clustering technique, on which this contribution focuses, also makes it possible to compensate for the lack of complete knowledge of the structure of the process itself. With these two considerations in mind, this contribution proposes a literature review on the topic of clustering applied in time-varying contexts, in the maintenance field. The aim is to present an overview of the main fields of study, the role of clustering in this context and the main clustering techniques used.

Study of Heat Transfer Rate in Electric Evaporators of Liquefied Petroleum Gas Using Electrothermal Modeling

In modern domestic and foreign experience of gas power supply to houses and industrial facilities located remotely from the main power station, decentralized gas power supply systems fed with propane-butane mixtures of liquefied petroleum gases from tanks are increasingly used. When using liquefied petroleum gases as the main energy carrier in gas tank systems, they are evaporated artificially in evaporators with an intermediate solid-state or liquid heat transfer agent, under conditions of its natural convection. The main operational characteristic of industrial tube evaporators of propane-butane mixtures of liquefied petroleum gases used for gas power supply from tank installations of housing and communal, industrial and industrial facilities that are remote from the main power supply stations is evaporation capacity. The evaporation capacity of industrial tube evaporators of propane-butane mixtures with a solid-state intermediate heat transfer medium is determined by the heat input from the tubular electric heaters through the aluminum casting layer. Therefore, the study of heat transfer in the solid–state intermediate heat transfer medium-evaporation coil system is the most important prerequisite for the effective operation of industrial tube evaporators of propane-butane mixtures and requires detailed research. To solve the problem of determining the heat transfer resistance between the layers of aluminum casting in contact with the surface of the tubular electric heaters group and the outer evaporation coil surface studies were performed on an electrical model. The average value of the total error of the results of experimental studies on electrothermal modeling is 3.7 %, with a confidence probability of 95 %. Recommendations are given for reducing the thickness of the layers in clear from the lower coil of the evaporative tube coil to the lower generatrix of the solid-state aluminum mass and the upper coil of the evaporative tube coil to the upper generatrix of the solid-state aluminum mass.

The relevance of target product profiles for manufacturers, experiences from the World Health Organization initiative for point-of-care testing for sexually transmitted infections

Background Sexually transmitted infections (STIs) are a significant global public health issue that cause a high burden of disease, especially in low- and middle-income countries. Screening of key populations and early and accurate diagnosis of infection are critical. Testing for syphilis, Chlamydia trachomatis, Neisseria gonorrhoeae, Trichomonas vaginalis, curable STIs, as well as the human papillomavirus (HPV), is frequently unavailable in low-resource settings. Tests for these STIs that can be used at the point of patient care (POCTs) are needed. In recent years, there has been increased attention for STI POCTs, but technical guidance, financial resources and advocacy for additional platforms/tests are required in order to foster the development of STI POCTs. The WHO Department of Sexual and Reproductive Health and Research (SRH) has developed target product profiles (TPPs), a form of technical guidance, for these STI diagnostics. Methods SRH conducted a survey of selected companies that are developing POCTs for one or more of the STIs mentioned above to better understand how these TPPs influence the diagnostic development process – to assess their impact. Results Survey respondents indicated that the STI POCT TPPs provided good guidance with respect to performance expectations and operational characteristics for the tests/platforms. In particular, optimal metrics for sensitivity, specificity, sample types, and time to result were considered to be very useful. Respondents also suggested ways to improve the relevance of the STI POCT TPPs. For example, since it is often not possible for developers to achieve every desired standard, it would be useful to prioritize each performance/operational characteristic of the test and to provide a rationale as to why certain characteristics are considered important. Respondents also emphasized the need to encourage industry participation in the TPP development process and to find creative ways, including via targeted emails, a WHO webpage directed at industry, or a coordinated communications plan to increase awareness of the TPPs. Conclusions Companies value the STI POCT TPPs and want them to continue. In order to maximize impact, WHO should consider the proposals from the manufacturers in the interest of increasing and accelerating access to STI diagnostics and treatment in low-resource settings.

Assessing the Impact of Virtual Standby Systems in Failure Propagation for Complex Wastewater Treatment Processes

This article proposes an original probabilistic modelling methodology named Virtual Standby (VSB), which enables a practical simulation, analysis, and evaluation of the impact on availability and reliability achieved by potential buffering policies on the performance of complex production systems. Virtual Standby (VSB) corresponds to a design and operational characteristic where some machines under a failure scenario are capable to provide for a limited time, continuity to the subsystems downstream before suffering delay which is currently not considered when assessing availability. This feature plays a relevant role on the propagation of the effect of a failure; indeed, it could prevent the propagation by guaranteeing the isolation time needed to recover from its failure, controlling and reducing the production losses downstream. A case study of the preliminary treatment process of a wastewater treatment facility (WWTF) is developed bearing in mind the systemic behaviour in the event of a failure and the specific features of each equipment. VSB is a big advantage for the representation of this complex processes because, among other things, it considers the impact of buffering policies on the perceived availability of the system. This model allows determining different production levels, with a better and easier fitting of the reliability, availability, and production forecast of the process. Finally, the comparison between the VSB simulation results with traditional procedures that do not consider the operational continuity under a failure scenario confirms the strength and precision of the proposal for complex systems.

Regularization based discriminative feature pattern selection for the classification of Parkinson cases using machine learning

Objectives This paper focuses on developing a regularization-based feature selection approach to select the most effective attributes from the Parkinson’s speech dataset. Parkinson’s disease is a medical condition that progresses as the dopamine-producing nerve cells are affected. Early diagnosis often reduces the effect on the individuals, minimizes the advancement over time. In recent times, intelligent computational models are used in many complex cases to diagnose a clinical condition with high precision. These models are intended to find meaningful representation from the data to diagnose the disease. Machine learning acts as a tool, gears up the model learning process through a mathematical baseline. But, not in all cases, machine learning will be demanded to perform optimally. It comes with a few constraints, mainly the representation of the data. The learning models expect a clean, noise-free input, which in-turns produces better discriminative patterns over different categories of classes. Methods The proposed model identified five candidate features as predictors. This feature subset is trained with different varieties of supervised classifiers to trace out the best-performing model. Results The results are validated through accuracy, precision, recall, and receiver’s operational characteristic curves. The proposed regularization- based feature selection model outperformed the benchmark algorithms by attaining 100% accuracy on most of the classifiers, other than linear discriminant analysis (99.90%) and naïve Bayes (99.51%). Conclusions This paper exhibits the need for intelligent models to analyze complex data patterns to assist medical practitioners in better disease diagnosis. The results exhibit that the regularization methods find the best features based on their importance score, which improved the model performance over other feature selection methods.

Design of a Truck Appointment System Considering Drayage Scheduling and Stochastic Turn Time

This paper develops a truck appointment system (TAS) considering variability in turn time at the container terminals. The consideration of this operational characteristic is crucial for optimal drayage scheduling. The TAS is formulated as a stochastic model and solved using the sample averaging approximation (SAA) algorithm. Using turn time distributions obtained from actual data from a U.S. port, a series of experiments is designed to evaluate the effectiveness of the proposed stochastic TAS model compared with the deterministic version where an average turn time is used instead of a distribution. Results of the numerical experiment demonstrate the benefit of the stochastic TAS model given that its drayage cost error was 3.9% lower compared with the deterministic TAS model. This result implies that the schedules produced by the stochastic TAS model are more robust and are able to accommodate a wider range of turn time scenarios. Another key takeaway from the experiment results is that the stochastic TAS model is more beneficial to utilize when the ratio of quotas to requested appointments is lower. Thus, in practice, when this ratio is more likely to be on the lower end, drayage companies would benefit more if the appointment schedule adopts the stochastic approach described in this paper.

Spatial Distribution and Development of Sequential Sampling Plans for Diaphorina citri Kuwayama (Hemiptera: Liviidae)

Vector control in huanglongbing management has been conducted on a calendar basis resulting in high production costs. We addressed this issue and proposed a sequential sampling plan to support decision making for intervention against Diaphorina citri Kuwayama, which is involved in the transmission of the bacteria Candidatus Liberibacter asiaticus, associated with such lethal disease. We analyzed 3,264,660 records from samples gathered from the Mexican trapping program for the monitoring of D. citri; it included weekly inspection of 86,004 yellow sticky traps distributed in the country. Spatial distribution of the insect, estimation of a common k (kc), and sequential sampling plans based on Sequential Probability Ratio Test (SPRT) were determined. Taylor’s power law coefficients were ≥1 indicating aggregation in the spatial distribution of the insect. Common k ranged from 0.0183 to 0.2253 and varied independently of geographic zone or citrus species. We obtained 18 sequential sampling plans, one for each state. In the Average Sample Number (ASN) function, the minimal number of samples to make a decision ranged from 17 to 65. In the Operational Characteristic (OC) function, probabilities for a correct intervention at the threshold of 0.2 D. citri adults/trap in most cases were above 80%. In a field evaluation, the application of sampling plans yielded savings obtained by reduction in the number of interventions for insect control.