Early diagnosis and efficient monitoring of cancer biomarkers depend on the fabrication of sensitive, quick and affordable technologies. In this study, we present a novel electrochemical paper-based immunosensor that combines PEDOT:PSS and Ag-CuO nanocomposite for the sensitive detection of EpCAM antigen, a clinically significant biomarker linked to a variety of epithelial cancers. Ag-CuO boosted the surface area and catalytic activity of PEDOT:PSS-based conducting paper in order to improve the electron transfer kinetics and mechanical stability. Further, electrical conductivity and electrochemical performance were improved by doping the fabricated electrode, Ag-CuO@CP with EG (60
This paper presents the design and synthesis of a new rhodamine-based Schiff base chemosensor (L) with exceptional selectivity and sensitivity for Cd2+. An analysis of L was conducted using various spectroscopic techniques, thereby validating its structure and activity. The chemosensor exhibited a clear turn-on fluorescence response and significant colour change with Cd2+ ions in acetonitrile. Binding investigations confirmed that L interacts with Cd2+ ions in a 1:1 ratio, as shown by Job's plot and Benesi-Hildebrand (B-H) analysis. The binding constant (Ka = 0.107 × 104) highlights the strong and specific interactions between L and Cd2+ ions.The limit of detection was found to be (LOD = 2.01 nM) for Cd2+ ions. DFT studies confirmed the stability of the L-Cd2+ complex, indicating the coordination of Cd2+ to the four atoms in L. The reversible properties of L in the presence of EDTA illustrate its potential as a reusable chemosensor and emphasise its INHIBIT molecular logic gate functionality. Molecular docking analyses of L with the human DNA-binding protein 5VBN were performed to assess its binding affinity and interaction characteristics. The practical application was demonstrated by the effective detection of Cd2+ in actual water, vegetable and fruit juice samples, solid-state sensing tests and filter paper-based assays, highlighting its potential for environmental monitoring.
Internal combustion (IC) engine generates power by burning fuel inside a combustion chamber. However the complex patterns in engine data can be challenging, as machine learning models may struggle with data sparsity. Deep learning models may struggle with real-time fault detection due to their performance can be sensitive to domain shifts, requiring frequent recalibration for varying engine conditions. To overcome these challenges, introduce the Modified Fast Gated Recurrent Neural Network (MFGRNN) for IC engine fault detection. Sensor data collection is the first step in the IC engine fault detection process. It is preprocessed using Gaussian Random Incremental Principal Component Analysis (GRIPCA) to remove redundancy, Transformer-Enabled Generative Adversarial Imputation Network (TE-GAIN) to impute missing data, and Sigmoid Normalization Method (SNM) to standardize the data. Modified Sparse and Low Redundant Subspace Learning based Dual Graph Regularized (MSLSDR) with a modified Least Absolute Shrinkage and Selection Operator (LASSO) regularization is used for feature selection in order to find the pertinent features. These features are input to the Modified Fast Gated Recurrent Neural Network (MFGRNN) for fault detection. Switching from Batch Normalization to Layer Normalization improves hidden state stability and enhances prediction accuracy in recurrent networks. The system classifies engine conditions as normal or faulty. If a fault is detected, it is further classified as either critical or minor for timely maintenance. The method achieves a Precision of 94.65
Modern software development makes extensive use of microservices architectural style primarily because it offers scalability together with flexibility and modularity capabilities. To build a robust system integrating reliability with fault tolerance capabilities is the primary challenge. Multi-dimensional data processing becomes challenging for conventional anomaly detection methods because microservices environments experience continuous changes. Implementing artificial intelligence techniques like LSTM and encoders these research aims to develop a strong anomaly detection model. The methodology proposed by this model achieves real-time processing of data from logs and metrics and tracing with a smooth integration into current observability framework architecture. The detection system reaches high accuracy rates at 94.65
