Irrigation with water containing a variety of microcystins (MCs) may pose potential threat to normal growth of agricultural plants. The mechanism of microcystin-LR (MC-LR) induced phytotoxicity in rice (Oryza sativa L.) at environmental concentrations is still unknown. Rice seedlings were exposed to MC-LR at concentrations of 0.10, 1.0, 10.0 and 50.0 μg·L−1 in hydroponic nutrient solutions for 7, 15, 20, and 34 days in the current study. The absorption and accumulation in leaf and root tissues, as well as a series of key physio-biochemical process changes in leaves of rice at different exposure time points were measured. Results showed that MC-LR could be detected in rice leaves and roots in all exposure groups, however, a significant accumulation trend of MC-LR in plants (BCF > 1) was only found in the lowest group (0.10 μg·L−1). The time-course study revealed a biphasic response of O2•- levels in rice leaves to the exposure of MC-LR, which was more pronounced in higher concentration groups, which could be attributed to the combined effects of antioxidant and detoxification mechanisms in rice. Exposure to 1.0 - 50.0 μg·L−1 MC-LR resulted in significant depletion of GSH and MDA contents in rice leaves at later exposure times. The changes of nitric oxide synthase (NOS) in rice leaves under MC-LR exposure were firstly investigated in the current study. Low MC-LR concentrations promoted NOS activity, whereas high concentrations inhibited NOS activity during the later exposure times, implying that NO may play a role in MC-LR toxicity in rice. Reduced sucrose synthase (SS) activities in rice exposed to MC-LR can reduce the plant's ability to accumulate carbon and thus may be directly related to the reduction in vegetative growth. These findings suggest that even at low concentrations of MC-LR, terrestrial plants' normal physiological status is disrupted, which, when combined with previous findings, helps reveal the mechanism of MC-LR-induced phytotoxicity.

Cervical cancer is one of the ailments that endangers the health of women all over the world and causes infertility. Fortunately, this disease can be avoided. Both the results and participation rates of the current preventative strategy remain poor. Hence, preventative or early detection methods remain challenging and open. In gynecology and computer science fields, few studies on identifying cervical cancer are based on behavior risk factor and machine learning. Moreover, various social and behavioral aspects might often make it more difficult to detect cervical cancer especially in low‑ and middle‑income countries (LMICs). Accordingly, focus on predicting the presence of cervical cancer through behavioral risk factors is the basic structure of this research. We proposed an approach to classify cervical cancer from a social-behavioral perspective using logistic regression to predict cervical cancer. We got significantly improved outcomes than the existing methods. Moreover, we used feature engineering to formulate less dimensionality as a pre-processing step and optimized parameters to be prepared for classification phase. The results proved that using the logistic regression with regularization type L1 had a promising performance. The accuracy of Logistic Regression (LR) L1 was 97.2%. Such results support the proposed work as a reliable classification predictive tool.

Artificial groundwater recharge is commonly used for drinking water supply. The resulting water quality is highly dependent on the raw water quality. In many cases, pre-treatment is required. Pre-treatment improves the drinking water quality, although how and to what extent it affects the subsequent pond water quality and infiltration process, is still unknown. We evaluated two treatment systems by applying different pre-treatment methods for raw water from a eutrophic and temperate lake. An artificial recharge pond was divided into two parts, where one received raw water, only filtered through a micro-screen with 500 µm pores (control treatment), while the other part received pre-treated lake water using chemical flocculation with polyaluminium chloride (PACl) combined with sand filtration, i.e. continuous contact filtration (contact filter treatment). Water quality such as cyanobacterial biomass, microcystin-LR as well as organic matter and nutrients were measured in both treatment processes. We found cyanobacterial biomass and microcystin-LR level after the contact filter treatment was significantly different from the control treatment and also significantly different in the pond water. In addition, with contact filter treatment, total phosphorus (TP) and organic matter removal were significantly improved in the end water, TP was reduced by 96 % (< 20 µg/L) and the total organic carbon (TOC) was reduced by 66 % instead of 55 % (TOC content around 2.1 mg/L instead of 3.0 mg/L). This full-scale onsite experiment demonstrated effective pre-treatment would benefit a more stable water quality system, with less variance and lower cyanotoxin risk. In a broader drinking water management perspective, the presented method is promising to reduce cyanotoxin risk, as well as TP and TOC, which are all predicted to increase with global warming and extreme weather.

Diabetes mellitus is a chronic disease that affects millions of people worldwide. Article focuses on detecting the presence of diabetes in patients using microarray gene data obtained from the pancreas. Handle the high-dimensional nature of the data, four different dimensionality reduction techniques, namely Bessel Function, Discrete Cosine Transform (DCT), Least Square Linear Regression (LSLR), and Artificial Algae Algorithm (AAA) are used. After reduced the data, Meta-heuristic algorithms are applied like Dragonfly Optimization Algorithm (DOA) and Elephant Herding Optimization Algorithm (EHO) for feature selection. Ten classification techniques are using to classify the data in both the format like without feature selection method and with feature selection method. The classification techniques are Non-Linear Regression (NLR), Linear Regression (LR), Gaussian Mixture Model (GMM), Expectation Maximum (EM), Bayesian Linear Discriminant Classifier (BLDC), Logistic Regression (LoR), Softmax Discriminant Classifier (SDC), Support Vector Machine (SVM) with linear kernel, Support Vector Machine (SVM) with polynomial kernel, and Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel. Results showed that the AAA with SVM(RBF) achieved an accuracy of 90% without feature selection. However, when feature selection was applied, with EHO of AAA with SVM(RBF) exhibited the highest accuracy of 95.714%, followed closely by with DOA of AAA with SVM (RBF) at 94.28%.