Semi-Supervised Anomaly Detection of Dissolved Oxygen Sensor in Wastewater Treatment Plants.

As the world progresses toward a digitally connected and sustainable future, the integration of semi-supervised anomaly detection in wastewater treatment processes (WWTPs) promises to become an essential tool in preserving water resources and assuring the continuous effectiveness of plants. When these complex and dynamic systems are coupled with limited historical anomaly data or complex anomalies, it is crucial to have powerful tools capable of detecting subtle deviations from normal behavior to enable the early detection of equipment malfunctions. To address this challenge, in this study, we analyzed five semi-supervised machine learning techniques (SSLs) such as Isolation Forest (IF), Local Outlier Factor (LOF), One-Class Support Vector Machine (OCSVM), Multilayer Perceptron Autoencoder (MLP-AE), and Convolutional Autoencoder (Conv-AE) for detecting different anomalies (complete, concurrent, and complex) of the Dissolved Oxygen (DO) sensor and aeration valve in the WWTP. The best results are obtained in the case of Conv-AE algorithm, with an accuracy of 98.36 for complete faults, 97.81% for concurrent faults, and 98.64% for complex faults (a combination of incipient and concurrent faults). Additionally, we developed an anomaly detection system for the most effective semi-supervised technique, which can provide the detection of delay time and generate a fault alarm for each considered anomaly.

Refining skin lesions classification performance using geometric features of superpixels.

This paper introduces superpixels to enhance the detection of skin lesions and to discriminate between melanoma and nevi without false negatives, in dermoscopy images. An improved Simple Linear Iterative Clustering (iSLIC) superpixels algorithm for image segmentation in digital image processing is proposed. The local graph cut method to identify the region of interest (i.e., either the nevi or melanoma lesions) has been adopted. The iSLIC algorithm is then exploited to segment sSPs. iSLIC discards all the SPs belonging to image background based on assigned labels and preserves the segmented skin lesions. A shape and geometric feature extraction task is performed for each segmented SP. The extracted features are fed into six machine learning algorithms such as: random forest, support vector machines, AdaBoost, k-nearest neighbor, decision trees (DT), Gaussian Naïve Bayes and three neural networks. These include Pattern recognition neural network, Feed forward neural network, and 1D Convolutional Neural Network for classification. The method is evaluated on the 7-Point MED-NODE and PAD-UFES-20 datasets and the results have been compared to the state-of-art findings. Extensive experiments show that the proposed method outperforms the compared existing methods in terms of accuracy.

A New Approach in Detectability of Microcalcifications in the Placenta during Pregnancy Using Textural Features and K-Nearest Neighbors Algorithm.

(1) Background: Ultrasonography is the main method used during pregnancy to assess the fetal growth, amniotic fluid, umbilical cord and placenta. The placenta's structure suffers dynamic modifications throughout the whole pregnancy and many of these changes, in which placental microcalcifications are by far the most prominent, are related to the process of aging and maturation and have no effect on fetal wellbeing. However, when placental microcalcifications are noticed earlier during pregnancy, they could suggest a major placental dysfunction with serious consequences for the fetus and mother. For better detectability of microcalcifications, we propose a new approach based on improving the clarity of details and the analysis of the placental structure using first and second order statistics, and fractal dimension. (2) Methods: The methodology is based on four stages: (i) cropping the region of interest and preprocessing steps; (ii) feature extraction, first order-standard deviation (SD), skewness (SK) and kurtosis (KR)-and second order-contrast (C), homogeneity (H), correlation (CR), energy (E) and entropy (EN)-are computed from a gray level co-occurrence matrix (GLCM) and fractal dimension (FD); (iii) statistical analysis (t-test); (iv) classification with the K-Nearest Neighbors algorithm (K-NN algorithm) and performance comparison with results from the support vector machine algorithm (SVM algorithm). (3) Results: Experimental results obtained from real clinical data show an improvement in the detectability and visibility of placental microcalcifications.

Optimized Synthesis of New N-Mustards Based on 2-Mercaptobenzoxazole Derivatives with Antitumor Activity.

New di-(ß-chloroethyl)-amides of some acids derived from 2-mercaptobenzoxazole were prepared by reaction of the corresponding pivalic mixed anhydrides with di-(ß-chloroethyl)-amine. A study regarding the optimization of the chemical reactions was made for the case of di-(ß-chloroethyl)-amines. The quantum chemical analysis by Spartan'14 was made in order to establish the most stable configuration of the ground electronic states for the obtained chemical structures and some physico-chemical parameters of N-mustards reported in this paper. Mercaptobenzoxazoles substituted in the side chain with the cytotoxic group show antitumor activity and they inhibit Ehrlich Ascites in an appreciable proportion compared to the drug I.O.B.-82, as our studies evidenced.

A possible case of Erdheim-Chester Disease.

Aim: To present the case of a 57-year-old male with progressive bilateral proptosis. Material and method: The patient presented with bilateral proptosis and strength deficiency on the upper limbs. During hospitalization, the progression was unfavorable; proptosis progressed, causing a severe loss of vision in the left eye (from 0.8 Snellen to NLP). Results: The imagistic investigation revealed bilateral infiltration of the orbits, infiltrative lesions to the mediastinum and the abdomen. The patient was referred to neurosurgery for further management. Surgical orbital decompression was performed with biopsy. The histopathological examination revealed non-Hodgkin small cell lymphoma. Conclusions: Assembling the clinical and paraclinical data we have suspected the possible diagnosis of Erdheim-Chester disease, however, positive diagnosis has not been achieved.

[Use of Plusoptix as a screening method for refractive ambliopia]. / Folosirea plusoptix ca metoda de screening a ambliopiei refractive.

PURPOSE: Highlighting the differences in the objective refraction using the Plusoptix AO9 comparing them with the refraction performed with TOPCON KR-8900 autorefractor. METHODS: Prospective study for 3 months held in the Ophthalmology Clinic in Iasi, Hospital Sf. Spiridon on a total of 39 children (21 girls and 18 boys) with mean age of 10.61 +/- 5.67 years. Clinical parameters: sex, age, objective refraction obtained with Plusoptix and with autorefractor corrected visual acuity (with different methods depending on each patient age), ortoptic examination (strabic deviation, binocular vision), the presence of symetry/asymetry while measuring with Plusoptix. The results were statistically processed by F-TEST calculating the correlation coefficient, standard deviation, significance level (using the spherical equivalent of the obtained values). RESULTS: Age limits of the studied cases ranged between 2-23 years. Visual acuity of children who had cooperate was between 0.2-1 with correction, achieving best values on right eye than left eye. 8 cases (20.51%) had large differences between measurements made with Plusoptix and autorefractor, half of that (4 cases) had strabismus. Three of these cases were with small hypermetropia and one with small myopia (Plusoptix shows a lower value). In 2 cases occurred higher differences (about 2-2,5D) between the 2 measurements, in patients with average hypermetropia. Plusoptix refraction was not possible at high hypermetropia or high myopia. CONCLUSIONS: This type of determining objective refraction using Plusoptix is a useful method of screening for discovery of refractive errors that can cause refractive amblyopia in young children and in those cases with a difficult collaboration. Because there are differences betweeti this 2 methods, for children with refractive errors are recommended further exploration to determine the appropriate optical correction. Plusoptix is a limited method because it cannot detect the exact values in those cases with high hypermetropia or high myopia.