Browse Articles

PIPENN-EMB ensemble net and protein embeddings generalise protein interface prediction beyond homology

Federated learning based reference evapotranspiration estimation for distributed crop fields

Water resource management and sustainable agriculture rely heavily on accurate Reference Evapotranspiration (ETo). Efforts have been made to simplify the (ETo) estimation using machine learning models. The existing approaches are limited to a single specific area. There is a need for ETo estimations of multiple locations with diverse weather conditions. The study intends to propose ETo estimation of multiple locations with distinct weather conditions using a federated learning approach. Traditional centralized approaches require aggregating all data in one place, which can be problematic due to privacy concerns and data transfer limitations. However, federated learning trains models locally and combines the knowledge, resulting in more generalized ETo estimates across different regions. The three geographical locations of Pakistan, each with diverse weather conditions, are selected to implement the proposed model using the weather data from 2012 to 2022 of the selected three locations. At each selected location, three machine learning models named Random Forest Regressor (RFR), Support Vector Regressor (SVR), and Decision Tree Regressor (DTR), are evaluated for local Evapotranspiration (ET) estimation and the federated global model. The feature importance-based analysis is also performed to assess the impacts of weather parameters on machine learning performance at each selected local location. The evaluation reveals that Random Forest Regressor (RFR) based federated learning outperformed other models with coefficient of determination (R2) = 0.97%, Root Mean Squared Error (RMSE) = 0.44, Mean Absolute Error (MAE) = 0.33 mm day−1, and Mean Absolute Percentage Error (MAPE) = 8.18%. The Random Forest Regressor (RFR) performance yields the local machine learning models against each selected site. The analysis results suggest that maximum temperature and wind speed are the most influential factors in Evapotranspiration (ET) predictions.

Collapse of wave functions in Schrödinger’s wave mechanics

Decoupled level and flow rate control of a two-tank system in beverage production: A comparative analysis of Fuzzy-PID and GA-PID for minimum time operation

Due to the nonlinear characteristics of the valves and the interactions between the controlled variables, designing a control system for coupled tanks is a difficult task. This paper deals with the comparative study between Fuzzy-PID and GA-PID controllers for decoupling level and flow rate control of two tank systems for beverage factories with minimum time optimal operation. In most process control industries, each process requires multiple control variables. Here two input two output (TITO) systems are considered highly interacting multivariable control systems. The decoupling control scheme (Pre-compensator (dynamic) decoupling) is used to reduce the correlation between the controlled and manipulated variables by diagonalizing the system. The two independent SISO systems are further controlled by different controllers so that the system can trace the set point and yield a good time response. Two radically different control approaches are presented and compared for this system’s dynamics, motivated by a desire to provide precise liquid-level control and regulate the flow rate. MATLAB /Simulink model and tuning algorithm (GA) are used for simulation. As the simulation result ensured, the GA-PID controller is the used for the specified system which is based on the transient and steady-state specifications. Quantitatively; the GA-PID controller has 39.167ms rise time, 8.50sec settling time, and -0.393% overshoot; whereas FLC-PID has 118.101ms rise time, 8.65sec settling time, and -0.033% overshoot. But in GA with PID controllers, the external disturbance tolerance capability of the proposed scheme, meaning robustness against external disturbance has a slight difference and FLC-PID has perfectly achieved the robustness. Depending on the result, FLC-PID has more result than GA-PID controller based on the set of specifications. Hence robustness is more important than time performances.

A plunger lifting optimization control method based on APSO-MPC for edge computing applications

Language assessment in primary progressive aphasia: Which components should be tested?

Introduction Primary progressive aphasia (PPA) is a dementia syndrome whose onset and course manifests with language deficits. There is a lack of instruments for clinical assessment of language in dementia and further research in the area is needed. Therefore, the objective of the present study was to identify language tasks that can aid the process of clinically diagnosing PPA and to determine those tasks most impaired in this population. Method A sample of 87 individuals comprising 2 groups was assessed: a PPA group (PPAG) of 29 PPA patients; and a control group (CG) of 58 healthy subjects matched for age and education. All participants underwent a brief cognitive battery followed by a comprehensive language assessment using the MTL-BR Battery. Results A statistically significant performance difference was found between the PPAG and CG on the following tasks: structured interview, oral comprehension of phrases, oral narrative discourse, written comprehension of phrases, written dictation, sentence repetition, semantic verbal fluency, oral naming of nouns and verbs, object manipulation, phonological verbal fluency, body part recognition and left-right orientation, written naming of nouns, oral text comprehension, number dictation, written narrative discourse, written text comprehension and numerical calculations (mental and written). Conclusion The results revealed that performance of PPA patients was poorer compared to healthy subjects on various language tasks. The most useful subtests from the MTL-BR battery for aiding clinical diagnosis of PPA were identified, tasks which should be prioritized when assessing this patient group.

A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm

Enhanced crayfish optimization algorithm: Orthogonal refracted opposition-based learning for robotic arm trajectory planning

In high-dimensional scenarios, trajectory planning is a challenging and computationally complex optimization task that requires finding the optimal trajectory within a complex domain. Metaheuristic (MH) algorithms provide a practical approach to solving this problem. The Crayfish Optimization Algorithm (COA) is an MH algorithm inspired by the biological behavior of crayfish. However, COA has limitations, including insufficient global search capability and a tendency to converge to local optima. To address these challenges, an Enhanced Crayfish Optimization Algorithm (ECOA) is proposed for robotic arm trajectory planning. The proposed ECOA incorporates multiple novel strategies, including using a tent chaotic map for population initialization to enhance diversity and replacing the traditional step size adjustment with a nonlinear perturbation factor to improve global search capability. Furthermore, an orthogonal refracted opposition-based learning strategy enhances solution quality and search efficiency by leveraging the dominant dimensional information. Additionally, performance comparisons with eight advanced algorithms on the CEC2017 test set (30-dimensional, 50-dimensional, 100-dimensional) are conducted, and the ECOA’s effectiveness is validated through Wilcoxon rank-sum and Friedman mean rank tests. In practical robotic arm trajectory planning experiments, ECOA demonstrated superior performance, reducing costs by 15% compared to the best competing algorithm and 10% over the original COA, with significantly lower variability. This demonstrates improved solution quality, robustness, and convergence stability. The study successfully introduces novel population initialization and search strategies for improvement, as well as practical verification in solving the robotic arm path problem. The results confirm the potential of ECOA to address optimization challenges in various engineering applications.

Cannabidiol attenuates lipid metabolism and induces CB1 receptor-mediated ER stress associated apoptosis in ovarian cancer cells

Statistical and machine learning based platform-independent key genes identification for hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most prevalent and deadly form of liver cancer, and its mortality rate is gradually increasing worldwide. Existing studies used genetic datasets, taken from various platforms, but focused only on common differentially expressed genes (DEGs) across platforms. Consequently, these studies may missed some important genes in the investigation of HCC. To solve these problems, we have taken datasets from multiple platforms and designed a statistical and machine learning-based system to determine platform-independent key genes (KGs) for HCC patients. DEGs were determined from each dataset using limma. Individual combined DEGs (icDEGs) were identified from each platform and then determined grand combined DEGs (gcDEGs) from icDEGs of all platforms. Differentially expressed discriminative genes (DEDGs) was determined based on the classification accuracy using Support vector machine. We constructed PPI network on DEDGs and identified hub genes using MCC. This study determined the optimal modules using the MCODE scores of the PPI network and selected their gene combinations. We combined all genes, obtained from previous studies to form metadata, known as meta-hub genes. Finally, six KGs (CDC20, TOP2A, CENPF, DLGAP5, UBE2C, and RACGAP1) were selected by intersecting the overlapping hub genes, meta-hub genes, and hub module genes. The discriminative power of six KGs and their prognostic potentiality were evaluated using AUC and survival analysis.

Inverse association between dietary flavonoid intake and nocturia in middle-aged and older adults from NHANES 2007–2010

Future legal

Coastal environmental changes in Ninh Thuan Province, South-Central Vietnam

Vietnam’s coastal regions are highly vulnerable to natural hazards and human-induced changes, posing significant challenges to their ecological and socio-economic systems. The country’s mangrove vegetation spans its entire coastline and has been depleted for decades in many regions. Notably, Vietnam’s proactive stance on climate change mitigation received significant recognition during the 26th Conference of the Parties (COP26) to the United Nations Framework Convention on Climate Change. This study investigated five critical coastal environmental features (shoreline dynamics, drought conditions, soil salinity trends, mangrove deforestation, and reforestation, as well as spatiotemporal variations in aquaculture and salt farming areas) using satellite data and geospatial analysis. Findings revealed a 58% decline in mangrove areas between 1989 and 2023, with a sharp decline between 1989 and 2001, followed by a gradual recovery. Furthermore, soil salinity along the Ninh Thuan coast indicated a continuous increase, except during the strong La Niña period in 2001. Additionally, aquaculture and salt marshes have expanded significantly, changing land use patterns. These findings highlight the urgent need for integrated coastal zone management to mitigate environmental degradation and enhance ecosystem resilience. Future studies should investigate the socio-economic implications of these changes and evaluate restoration strategies for sustainable coastal development.

Author Correction: A molecular basis for spine color morphs in the sea urchin Lytechinus variegatus

Effects of supplementing a polyphenol-rich sugarcane extract through drinking water on egg production and quality of laying hens

Polyphenols are a wide group of naturally occurring compounds found in plants and have the potential to safeguard living cells. The objective was to evaluate whether the inclusion of a polyphenol-rich sugarcane extract (PRSE) in drinking water could improve egg production and the quality of commercial layers. A total of 120 Shaver Brown hens, aged 43 weeks, were randomly allocated to 12 litter-floor pens in two open-sided poultry houses. The pens were divided into two treatment groups: one receiving 0% (control) and the other 0.05% PRSE in drinking water throughout the study duration. The treatments were prepared by adding PRSE manually into the drinking water daily, and water was given ad libitum. The birds were given commercial layer feed throughout the study. The number of eggs produced, abnormal eggs, and mortality were recorded daily. Egg weight, yolk colour, yolk height, albumen height, Haugh units, and antioxidant properties, were measured at weeks 45, 47 and 49. Supplementing PRSE in the drinking water did not impact hen-day egg production, hen-housed egg production, egg weight, egg mass, or feed conversion ratio. However, there was a trend toward significance in egg weight at week 45. The results indicated that PRSE supplementation led to a significant reduction in yolk colour during week 45 (P = 0.001), although no differences were observed in subsequent weeks. Yolk height, thick albumen height, and haugh units were unaffected by the treatment, while thin albumen height showed a trend towards reduction in the PRSE group at weeks 47 and 49 (P = 0.05). The DPPH assay revealed a significant increase in antioxidant capacity in the PRSE group at week 45 (P = 0.02). The 0.05% PRSE supplementation in drinking water initially enhanced antioxidant capacity but later adversely affected yolk color and thin albumen height.

Phosphorus transitions driven by cyclone biparjoy linked middle east North Africa (MENA) and Indian Thar Desert dust storm pathways in Asia’s largest grassland

Gambling in Connecticut adolescents: Prevalence, socio-demographic characteristics, trauma exposure, suicidality, and other risk behaviors

Adolescent gambling is a public health concern and has been linked to suicidality, various risk behaviors, and poor health outcomes. However, there is a limited understanding of specific risk and protective factors that may influence gambling behavior in Connecticut adolescents, especially in changing gambling environments. This study examines relationships between adolescents reporting gambling in the past-year and a range of health risk behaviors including vaping, traumatic experiences, academic performance, and receipt of social support. Data from the 2019 Youth Risk Behavior Survey in Connecticut high school students stratified by gambling status were examined in bivariate and multivariate analyses. Among 1,807 adolescents, past-year gambling was reported by 453 individuals [25.4%; 95% confidence interval [CI] = 22.7–28.1%]. Gambling prevalence was higher among older males and lower in adolescents of Asian origin. Gambling was further associated with suicidality and risk behaviors including substance use, smoking [traditional tobacco and electronic vapor use], risky use of digital technologies, unsafe sex, and aggressive behaviors. Gambling was also associated with traumatic experiences, depression/dysphoria, poor academic performance, and less familial social support. The results provide an up-to-date estimate of the current prevalence and correlates of gambling among Connecticut adolescents. The results provide recent estimates of the prevalence and correlates of gambling among Connecticut adolescents. The findings highlight the need for further investigation of specific factors like social support that help with designing and implementing tailored interventions.

Optimization and modeling of sulfur removal from liquid fuel using carbon-based adsorbents through synergistic application of RSM and machine learning

Feasibility and efficiency of microalgae cultivation for nutrient recycling and energy recovery from food waste filtrate

With the continuous growth of economic and population, the generation of food waste has significantly increased in recent years. The disposition of food waste, typically through incineration or landfill, can lead to severe health and environmental problems, accompanied by high additional costs. However, the leachate produced from food waste during collection, transportation and landfill operations predominantly contains high levels of nutrients necessary for microalgae growth. The integration of microalgae cultivation into waste treatment for nutrient recycling presents a potential route for energy recovery from food waste. Therefore, this study was conducted to evaluate the feasibility of microalgae cultivation for food waste filtrate treatment. In addition, the optimal cultivation conditions and nutrient removal efficiency for microalgae in food waste filtrate treatment were investigated. The results indicated that Cyanobacterium aponinum exhibited the highest growth rate (0.530 cells d-1) and maximum cell density (9.6 × 106 cells mL-1) among eight potential microalgal species in 10% food waste filtrate treatment under 10,000 lux and 32°C. It was also observed that C. aponinum had significantly higher biomass productivity and nutrient removal efficiency under a 5% CO2 concentration. The successful cultivation of C. aponinum demonstrated that food waste filtrate could be a promising growth medium, reducing the high cost of cultivation with synthetic medium. However, further efforts should be made to utilize microalgae in food waster filtrate treatment, transitioning from laboratory condition to a pilot scale.

Leveraging paired mammogram views with deep learning for comprehensive breast cancer detection