Measurement Sensors最新文献

Groundwater, vital for human consumption and agriculture, ecosystem support, and industrial activities, requires sustainable management using proper quality assessment techniques. This study examines the relationship between physicochemical parameters and major ions in groundwater samples collected from 44 regions in Raipur, using sensor-based data acquisition alongside traditional methods. Employing K-means clustering for data discretization, correlations between parameters are highlighted. Results show positive associations among EC, TDS, TH, and TA. ArcGIS interpolation maps visualize spatial distribution. Addressing class imbalance, an upsampling technique is utilized. Machine learning algorithms, including Logistic Regression and Random Forest, classify water quality with accuracies of 98.8 % and 98.3 %, respectively. This research, blending traditional and sensor-based methods, emphasizes informed water management.

The classification of knee osteoarthritis is solely based on contextual factors, with image processing algorithms playing a significant role in computer-aided diagnosis (CAD) systems. The inconsistent real-time pre-processing, on the other hand, has a significant impact on the diagnosing process. In this work, a Densely Connected Fully Convolutional Network (DFCN) for knee osteoarthritis classifier based on multiple learning (ML) strategies effectively classify knee osteoarthritis on the basis of risk estimation. Spatial osteoarthritis contextual vectors extracted by identifying the relationship between contextual variables using a machine learning approach. The hidden convolutional layers are used to compute edge interpretation, contextual cues, and input correction. The fused layer, which is simply a concentration of derived features, supports automatic learning of contextual features of osteoarthritis classification. The standard datasets from the Osteoarthritis Initiative (OAI) and the Multicentre Osteoarthritis Study (MOST) are used for experimental purposes to validate the proposed method. The results shows that the proposed DFCN is significantly improves the feature recognition for accurate classification around 94 % which is significantly higher than existing CNN results and flexibility to real-time implementation in the CAD system. It can also be used to automatically detect osteoarthritis types using a lightweight CNN architecture.

Objective

The worldwide economies are built on agriculture, and plans for food security, resource allocation, and agricultural practices are all heavily influenced by accurate crop production predictions. Predictive models are becoming indispensable tools for predicting crop prospects due to the development of technology based on data.

Limitation

A significant disadvantage of the ER-ETR for Hybrid Crop Yield Prediction System can involve overfitting, particularly in cases when the dataset is small or the model complexity is not well managed. Inaccurate forecasts based on unreported data and decreased generalization can result from approach.

Method

Initially, the dataset is collected from the GitHub and preprocessed using the Standardscaler method. 70 % of the preprocessed data is used as the training set, and the remaining 30 % is used as the testing set. Kernel Principal Component Analysis (KPCA) is employed to extract the feature. The Least Absolute Shrinkage and Selection Operator (LESSO) Regression is used to feature selection.A reliable method for predicting hybrid crop productivity is provided by the suggested ensemble regression that makes use of feature ensemble regression using Extra Tree Regressor (ER-ETR).

Result

A simple internet-based programme for immediate forecasting is created using the Python web framework, and the model that has been trained may be used to predict the resulting profitability. Mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE) and R² were the testing metrics utilized to assess the classification model. With a 95 % accuracy rate, the suggested model is superior to existing models in terms of accuracy in crop production forecasting while still preserving the data's original distribution.Because of the intuitive online interface, stakeholders can forecast immediately and make well-informed decisions on the best use of resources from agriculture.

Conclusion

The study creates a hybrid crop yield prediction system using the ER-ETR approach. Agricultural forecasting benefits greatly from its capacity to integrate several models and take advantage of each one's advantages, which improves prediction accuracy and dependability.

This research focuses on the examination of natural fractures within underground mines, emphasizing their substantial impact on the strength and stability of ore pillars. The study adopts the Strength Reduction Method (SRM) theory and employs the Discrete Fracture Network (DFN) model, offering a novel approach to investigating the behavior of fractured rock masses. The objective of this article is to analyze the influence of natural fractures on the strength of ore pillars by employing SRM and DFN methods. The research begins by establishing a multi-level amplification program that incorporates a homogenization process. The findings reveal that, for a W/H ratio of 0.5, the strength reduction aligns consistently with empirical equations. A notable observation is that when W/H is less than or equal to 1.0, there is good agreement, but when W/H exceeds 1.0, there is a tendency to overestimate pillar strength. Subsequent investigations emphasize the significance of considering pillar development in the overall assessment of pillar forces. The study underscores the importance of integrating pillar development into the analysis, aligning with previously established research results. Therefore, by evaluating the strength and failure mechanism of columns under different aspect ratios, we studied the influence of discrete discontinuous bodies on column stability, revealed the influence of natural cracks on column strength, and provided theoretical basis and reference for the design and support of underground mines.

The term Digital Twin (DT) is defined as the virtual demonstration of an object that is represented through real-time datasets. DT is done through artificial intelligence to enhance decision-making techniques. DT includes the process of simulation, amalgamation, observation, analysis, and conservation. The DT is simply the exact reproduction of the physical structures. DT is used in the identification and evaluation of problems through real-time analysis. It is important to have prior analysis and evaluation of the object before existing in the real world. These digital twins help in the manufacturing and implementation of the production line system. DT includes the production line with the station division and the hours needed for the operating conditions for the assembly process. The systems are integrated to reduce the overall cost parameter. The physical simulation model is employed to obtain higher performance with reduced cost. An artificial neural network with a genetic algorithm is used for the optimization process to achieve a production line system using digital twins.

In order to carry out osmotic purification of black and odorous water and solve the problems of low water flux, reverse solute diffusion and biological pollution affecting the forward osmosis performance, the author proposed the application of graphene nickel oxide nanocomposites in the treatment of black and odorous water. The hydrophilic metal-organic framework (UiO-66 nanoparticle) is embedded into the lamellar structure of graphene nickel oxide as a microporous filler, form ultra-thin “sandwich” film to improve FO performance. The added UiO-66 nano-particles introduce a uniform and suitable nano-channel, which can effectively let water penetrate, at the same time, block the reverse diffusion of Na+. The results show that the film with nanometer thickness formed by GO layer can prevent biological pollution, and the bacteriostatic effect can reach 90 %. In the FO model, the water flux of UiO-66/GO membrane is 29.16 LMH, which is 270 % higher than the original pure graphene nickel oxide membrane, and the reverse solute diffusion is 83.5 % lower (12.86 gMH). It is proved that this study provides an attempt for the application of MOF/GO film in FO process. Combining the excellent overall performance of UiO-66/GO film and the designable features of MOF structure, we expect that MOF/GO film will have broad application prospects as an advanced membrane material of FO technology.

In order to save the consumption of natural high quality aggregate and improve the utilization rate of nano-composite materials, the investigation on the compressive strength and water permeability of nano-composite modified reclaimed aggregate concrete materials was proposed. In this experiment, reclaimed nano-ceramic aggregate was used to replace natural aggregate, and the effects of reclaimed aggregate substitution rate, water-cement ratio and target porosity on the compressive strength and permeability coefficient of reclaimed ceramic aggregate pervious concrete were studied. The reclaimed ceramic aggregate was pretreated with modifier. The results show that with the increase of substitution rate, the compressive strength decreases and the permeability coefficient has little difference. With the increase of water-cement ratio, the compressive strength increases first and then decreases, and the water permeability coefficient has little difference, but the value is lower when the water-cement ratio is greater than 0.4. As the target pore increases, the compressive strength decreases and the permeability coefficient increases. The optimal test scheme is as follows: the replacement rate is 40 %, the water-cement ratio is 0.35, and the porosity is 15 %. In this case, the performance of the specimen is better.

Conclusion

With the increase of replacement rate, the performance index of recycled aggregate decreases, the compressive strength of pervious concrete decreases continuously, and the permeability coefficient has little difference. With the continuous increase of water-cement ratio, the compressive strength increases first and then decreases, which can meet the construction requirements.

In order to solve the problem that the toughness (impact strength) of the traditional elastomer toughening will decrease its rigidity (modulus) while improving the toughness (impact strength) of the material, the multi-porous nano-cacO3/polymer composite and its application in building plastics were proposed. In this essay, the mechanical properties of nano-caco3/PVC/CPE and nano-caco3/PP/SBS composites are studied. The results showed that the notch impact strength increased by 15.8 % from 46.8 kJ/m2 to 54.2kJ/m2 when two nano-cacO3 was added into the PP/SBS blend system, indicating that nano-cacO3 also toughened PP to some extent.

Conclusion

Nano Ca-CO3 has remarkable toughening effect on PVC blending system, and also has certain toughening effect on PP blending system. The profile with nano-cacO3 added can ensure the impact performance of low temperature drop hammer, while the notched impact strength, tensile strength, elongation at break and flexural modulus of the simply supported beam are significantly improved compared with the profile without nano-cacO3 added. The application of nano CaCO3/PVC/CPE composites in the profile of PVC doors and Windows is studied.

The present research and study, aimed to develop a new predictive model that easily navigate to the challenges of risk factors causing a heart stroke and accurately detect the early chances of having the stroke. Knowledge of risk factors impacting in the deterioration of a patient's health in causing the severity of heart stroke, helps future research work in prognosis of heart stoke and implement feature selection techniques by considering all such risk factors. Clustering of binary classes perfectly, without any noise, is a major advantage in predicting heart stroke patients' condition in their early stages of severity. Novel initial centroid selection method FRM is developed which considered the best until date resulting in 100 % clustering of patients into binary classes, which significantly contribute to the enhancement of accuracy results. Major objective is integrating clustering technique with classification algorithms Naïve Bayes, Decision Tree and Artificial Neural Network and built three prediction systems, FRM-NB, FRM-DT, and FRM-ANN performed the best when compared to existing systems, resulting in the best accuracy values in predicting early risk of heart stroke and reducing chances of recurrent heart strokes. We have achieved the best accuracy of 94 % (FRM-NB) and 97 % (FRM-DT), sensitivity of 90 % (FRM-NB) and 95 % (FRM-DT), specificity score of 97 % (FRM-NB) AND 90 % (FRM-DT) and AUC-ROC score of 0.976 (FRM-NB) and 0.953(FRM-DT). FRM-ANN model achieved an accuracy of 98 % with 100 % sensitivity and 0.99 score of AUC, which till date no existing research has achieved.

Multipliers show a dynamic part in numerous uses such as digital signal processing, filters and so on. Hence, the performance of the multiplier circuit has also to be improved more for better results. The circuit of the multiplier should be more compact and efficient to achieve the best outcome. Symmetric stacking counter circuit is designed using reversible logic gates and it reduces the power consumption. Various symmetric stacked counters are designed and used to implement the Wallace tree multiplier. The proposed multiplier is consumes 0.798mw of power and PDP of 2.47. The designed multiplier is power efficient as compared with existing methods with slight increase in delay. The proposed multiplier is used in low power application like modulators and demodulators.