An enhanced Support Vector Machine classification framework by using Euclidean distance function for text document categorization

This paper presents the implementation of a new text document classification framework that uses the Support Vector Machine (SVM) approach in the training phase and the Euclidean distance function in the classification phase, coined as Euclidean-SVM. The SVM constructs a classifier by generating a decision surface, namely the optimal separating hyper-plane, to partition different categories of data points in the vector space. The concept of the optimal separating hyper-plane can be generalized for the non-linearly separable cases by introducing kernel functions to map the data points from the input space into a high dimensional feature space so that they could be separated by a linear hyper-plane. This characteristic causes the implementation of different kernel functions to have a high impact on the classification accuracy of the SVM. Other than the kernel functions, the value of soft margin parameter, C is another critical component in determining the performance of the SVM classifier. Hence, one of the critical problems of the conventional SVM classification framework is the necessity of determining the appropriate kernel function and the appropriate value of parameter C for different datasets of varying characteristics, in order to guarantee high accuracy of the classifier. In this paper, we introduce a distance measurement technique, using the Euclidean distance function to replace the optimal separating hyper-plane as the classification decision making function in the SVM. In our approach, the support vectors for each category are identified from the training data points during training phase using the SVM. In the classification phase, when a new data point is mapped into the original vector space, the average distances between the new data point and the support vectors from different categories are measured using the Euclidean distance function. The classification decision is made based on the category of support vectors which has the lowest average distance with the new data point, and this makes the classification decision irrespective of the efficacy of hyper-plane formed by applying the particular kernel function and soft margin parameter. We tested our proposed framework using several text datasets. The experimental results show that this approach makes the accuracy of the Euclidean-SVM text classifier to have a low impact on the implementation of kernel functions and soft margin parameter C.     

A new external sorting algorithm with no additional disk space

This paper is concerned with an external sorting algorithm with no additional disk space. The proposed algorithm is a hybrid one that uses Quicksort and special merging process in two distinct phases. The algorithm excels in sorting a huge file, which is many times larger than the available memory of the computer. This algorithm creates no extra backup file for manipulating huge records. For this, the algorithm saves huge disk space, which is needed to hold the large file. Also our algorithm switches to special merging process after the first phase that uses Quicksort. This reduces the time complexity and makes the algorithm faster.     

A data mining approach for machine fault diagnosis based on associated frequency patterns

Bearings play a crucial role in rotational machines and their failure is one of the foremost causes of breakdowns in rotary machinery. Their functionality is directly relevant to the operational performance, service life and efficiency of these machines. Therefore, bearing fault identification is very significant. The accuracy of fault or anomaly detection by the current techniques is not adequate. We propose a data mining-based framework for fault identification and anomaly detection from machine vibration data. In this framework, to capture the useful knowledge from the vibration data stream (VDS), we first pre-process the data using Fast Fourier Transform (FFT) to extract the frequency signature and then build a compact tree called SAFP-tree (sliding window associated frequency pattern tree), and propose a mining algorithm called SAFP. Our SAFP algorithm can mine associated frequency patterns (i.e., fault frequency signatures) in the current window of VDS and use them to identify faults in the bearing data. Finally, SAFP is further enhanced to SAFP-AD for anomaly detection by determining the normal behavior measure (NBM) from the extracted frequency patterns. The results show that our technique is very efficient in identifying faults and detecting anomalies over VDS and can be used for remote machine health diagnosis.     

Inflammation Causes Exacerbation of COVID-19: How about Skin Inflammation?

COVID-19 is a recently emerged viral infection worldwide. SARS-CoV-2, the causative virus, is believed to have emerged from bat coronaviruses, probably through host conversion. The bat coronavirus which has the highest gene homology to SARS-CoV-2 specifically infects deep forest bats in China whose habitat extends through the Middle East to Southern Europe. Host conversion might have occurred due to the deforestation by humans exposing wild bats to the environment they had never encountered before. SARS-CoV-2 infects cells through two mechanisms: through its receptor ACE2 with the help of enzyme TMPRSS and through membrane fusion with the help of elastases in the inflammatory condition. Obesity, hypertension, diabetes mellitus, and pulmonary diseases cause poor prognosis of COVID-19. Aging is another factor promoting poor prognosis. These diseases and aging cause low-level and persistent inflammation in humans, which can promote poor prognosis of COVID-19. Psoriasis and atopic dermatitis are the major inflammatory skin diseases. These inflammatory skin conditions, however, do not seem to cause poor prognosis for COVID-19 based on the epidemiological data accumulated so far. These mechanisms need to be elucidated.     

MicroRNA Changes Up to 24 h following Induced Hypoglycemia in Type 2 Diabetes

Hypoglycemia, as a complication of type 2 diabetes (T2D), causes increased morbidity and mortality but the physiological response underlying hypoglycemia has not been fully elucidated. Small noncoding microRNA (miRNA) have multiple downstream biological effects. This pilot exploratory study was undertaken to determine if induced miRNA changes would persist and contribute to effects seen 24 h post-hypoglycemia. A parallel, prospective study design was employed, involving T2D (n = 23) and control (n = 23) subjects. The subjects underwent insulin-induced hypoglycemia (2 mmol/L; 36 mg/dL); blood samples were drawn at baseline, upon the induction of hypoglycemia, and 4 h and 24 h post-hypoglycemia, with a quantitative polymerase chain reaction analysis of miRNA undertaken. The baseline miRNAs did not differ. In the controls, 15 miRNAs were downregulated and one was upregulated (FDR < 0.05) from the induction of hypoglycemia to 4 h later while, in T2D, only four miRNAs were altered (downregulated), and these were common to both cohorts (miR-191-5p; miR-143-3p; let-7b-5p; let-7g-5p), correlated with elevated glucagon levels, and all were associated with energy balance. From the induction of hypoglycemia to 24 h, 14 miRNAs were downregulated and 5 were upregulated (FDR < 0.05) in the controls; 7 miRNAs were downregulated and 7 upregulated (FDR < 0.05) in T2D; a total of 6 miRNAs were common between cohorts, 5 were downregulated (miR-93-5p, let-7b-5p, miR-191-5p, miR-185-5p, and miR-652-3p), and 1 was upregulated (miR-369-3p). An ingenuity pathway analysis indicated that many of the altered miRNAs were associated with metabolic and coagulation pathways; however, of the inflammatory proteins expressed, only miR-143-3p at 24 h correlated positively with tumor necrosis factor-α (TNFa; p < 0.05 and r = 0.46) and negatively with toll-like receptor-4 (TLR4; p < 0.05 and r = 0.43). The MiRNA levels altered by hypoglycemia reflected changes in counter-regulatory glucagon and differed between cohorts, and their expression at 24 h suggests miRNAs may potentiate and prolong the physiological response. Trial registration: ClinicalTrials.gov {"type":"clinical-trial","attrs":{"text":"NCT03102801","term_id":"NCT03102801"}}NCT03102801.     

Destructive and non-destructive evaluation of concrete for optimum sand to aggregate volume ratio

Aggregates are the biggest contributor to concrete volume and are a crucial parameter in dictating its mechanical properties. As such, a detailed experimental investigation was carried out to evaluate the effect of sand-to-aggregate volume ratio (s/a) on the mechanical properties of concrete utilizing both destructive and non-destructive testing (employing UPV (ultrasonic pulse velocity) measurements). For investigation, standard cylindrical concrete samples were made with different s/a (0.36, 0.40, 0.44, 0.48, 0.52, and 0.56), cement content (340 and 450 kg/m³), water-to-cement ratio (0.45 and 0.50), and maximum aggregate size (12 and 19 mm). The effect of these design parameters on the 7, 14, and 28 d compressive strength, tensile strength, elastic modulus, and UPV of concrete were assessed. The careful analysis demonstrates that aggregate proportions and size need to be optimized for formulating mix designs; optimum ratios of s/a were found to be 0.40 and 0.44 for the maximum aggregate size of 12 and 19 mm, respectively, irrespective of the W/C (water-to-cement) and cement content.     

The effect of triangular shutter type flow deflector perforated baffle plate on the thermofluid performance of a heat exchanger

The study aimed to investigate the heat transfer (HT) properties of a tubular heat exchanger (HX) by using innovative baffle plate arrangements. The newly designed baffle plate was circular with triangular openings and adjustable triangular flow deflectors. These deflectors were strategically placed at the inlet of the HX to create a swirling flow downstream. Three baffle plates were installed along the flow direction with different length-to-diameter ratios (pitch ratios) to assess their impact on HT, pressure drop, and thermal enhancement factor. The study compared these results with a smooth channel under varying Reynolds numbers (16,500–29,500). The findings revealed that both the pitch ratio (0.6–1.2) and the inclination angle of the deflectors (30⁰–50⁰) significantly affected the HX's performance. Notably, the baffle plate with a deflector inclination angle of 30° and a pitch ratio of 1 showed a remarkable average improvement of 36.5% compared to other angles and ratios.     

microRNAs Are Abundant and Stable in Platelet-Rich Fibrin and Other Autologous Blood Products of Canines

Various microRNAs (miRNAs) present in autologous blood products of canines have not been studied recently. We aimed to elucidate the existence of miRNAs in platelet-rich fibrin (PRF) and the stability of canine autologous blood products under various storage conditions. Total RNAs were isolated from PRF and other autologous blood products following newly adapted protocols used in commercial kits for plasma and tissue samples. Quantitative real-time polymerase chain reaction analysis (qPCR) was used to detect miRNAs in autologous blood products. The miR-16, miR-21, miR-155, and miR-146a were abundant in PRF and other autologous blood products of canines. Furthermore, we found they could maintain stability under protracted freezing temperatures of −30 °C for at least one month. Our findings revealed that PRF might be a stable resource for various canine miRNAs.     

Ensemble learning of diffractive optical networks

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning.Specifically,there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization,power efficiency and computation speed.Diffractive deep neural networks(D²NNs)form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers.D²NNs have demonstrated success in various tasks,including object classification,the spectral encoding of information,optical pulse shaping and imaging.Here,we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning.After independently training 1252 D²NNs that were diversely engineered with a variety of passive input filters,we applied a pruning algorithm to select an optimized ensemble of D²NNs that collectively improved the image classification accuracy.Through this pruning,we numerically demonstrated that ensembles of N=14 and N=30 D²NNs achieve blind testing accuracies of 61.14±0.23%and 62.13±0.05%,respectively,on the classification of GFAR-10 test images,providing an inference improvennent of>16%compared to the average performance of the individual D²NNs within each ensemble.These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.