Malla Reddy Engineering College

The rising challenges of liver disease prediction necessitates precise and responsive diagnostic protocols to optimize therapeutic measures. This research article advances a diagnostic framework predicated upon an Intelligent Adaptive Neuro-Fuzzy Inference System (I-ANFIS), engineered to integrate the diagnostic strengths of Artificial Intelligence (AI), adaptive learning, and fuzzy reasoning for effective results in liver disease prediction. The architecture of I-ANFIS merges neuro-fuzzy methodologies with adaptive learning capacity, whereby fuzzy inference rules and membership functions autonomously recalibrate in response to the intrinsic statistical embodied within the liver disease-based input dataset. Within the proposed architecture, supervised machine learning derives inference rules and parametric fine-tuning from a comprehensive repository of liver disease manifestations, enabling contextualized profiling of heterogeneous patient datasets. Empirical validation within the investigation confirms the procedural viability of the I-ANFIS mechanism across markedly diverse liver disease phenotypes and demographic sub-groups, substantiating a scalable computational diagnostic modality. System performance was measured in accuracy, sensitivity, specificity, and overall reliability. The system performance was compared with other conventional diagnostic methods to determine the superior capability of the suggested I-ANFIS frame. Moreover, the paper provides a great in-depth explanation of the mathematical modelling of the I-ANFIS algorithm by clearly explaining the underlying principles. The study demonstrates I-ANFIS’s superior performance with metrics such as accuracy (92%), precision (93%), recall (91%), and F1 Score (92%) using a diverse dataset of liver disease cases. Comparative analysis with CNN (Accuracy: 88%, Precision: 87%, Recall: 89%, F1 Score: 88%), RNN (Accuracy: 85%, Precision: 84%, Recall: 83%, F1 Score: 83.5%), and LSTM (Accuracy: 90%, Precision: 89%, Recall: 88%, F1 Score: 88.5%) highlights I-ANFIS’s strengths in convergence rate (80%), robustness (90%), and moderate memory usage (50%) and data preprocessing requirements (50%). It describes the application of adaptive learning, fuzzy logic, and neural networks to clarify the role of each in developing an intelligent diagnostic tool. Some applications of the optimized liver disease diagnosis system, in reality, include its use in detecting diseases at early stages, personal treatment planning, and improved patient outcomes.

Fretting, a phenomenon caused by small oscillations between tightly fitted components under cyclic loading, leads to crack initiation due to high stresses at the contact interface. This process significantly affects the lifespan of various mechanical elements, including bolted and riveted joints, key-way shaft couplings, and blade-dovetail contact areas in turbine engines. This study investigates the contact stresses at the interface of two configurations—a cylinder on a flat surface and a ball-in-cup arrangement—using the Finite Element Analysis (FEA) package ANSYS and Hertzian Elliptical Contact Theory. The analysis considers mechanical cyclic loads and evaluates their impact on stress distribution. The study specifically examines steel components, commonly used in engineering applications, to determine the stress concentrations that contribute to fretting fatigue. The findings provide critical insights into contact stress behavior, aiding in the design of more durable mechanical connections.

Enhancing the performance of bituminous mixes is critical for developing durable and sustainable pavements to make them withstand increasing traffic loads and extreme environmental conditions. The growing demand for more resilient and long-lasting pavements necessitates innovative solutions to mitigate rutting and fatigue-related failures under increasing traffic loads and extreme environmental conditions. This study aims to assess the combined effects of nano-modifiers (nano-silica and nano-clay) and fiber reinforcements (polyester and glass fibers) on enhancing the mechanical performance of bituminous mixes, focusing on stiffness, tensile strength, fatigue life, and rutting resistance. An attempt has been made in this study to evaluate the influence of nano-modifiers such as nano-silica and nano-clay, combined with fiber reinforcements like polyester and glass fibers, on mechanical properties, of bituminous mixes. Nano-silica increased the dynamic modulus to 6.2 GPa, a 38

Globally, concrete remains the most used construction product in all kinds of projects related to civil engineering, largely because good raw aggregates are hard to come. Consequently, recycled aggregates made from waste from construction and demolition are being utilized in concrete more and more. Crushed concrete rubble as a substitution to natural coarse aggregates into concrete after it has been segregated from construction and demolition waste and sieved. For the current investigation, materials that follow were incorporated to make recycled aggregate concrete (RAC): OPC 53 grade, water, sulphonated naphthalene formaldehyde-based super plasticizer, natural and recycled coarse aggregate (NCA, RCA), natural and recycled fine aggregate (NFA, RFA) with 10 to 35

Over the past few years, multiple waves of COVID-19 (C19) have impacted millions globally. The optimal treatment for C19 remains uncertain, as vaccinated individuals have also experienced illness. C19 can be diagnosed swiftly and precisely, thereby preserving lives and shielding patients from expensive therapies. Researchers have used different types of clinical imaging, like chest CT scans (CCT) and X-rays (CXR), to find C-19. However, using ECG images to find people who are infected with C19 has gotten less attention. We utilize ECG samples for diagnosing C19 due to their accessibility, in contrast to CCT and CXR images. Researchers frequently transform ECG data into integer format prior to utilizing any methodology, leading to increased processing overhead. Accurately and swiftly identifying C19 using the ECG modality is both challenging and time-consuming. In this study, we used paper-based ECG images in an improved hybrid deep learning model called ResNet50+BiLSTM to try to solve these problems. We used BiLSTM to label ECG images as C19 with no findings after removing the last softmax layer and immobilizing the two residual connections after the first residual block in ResNet50. The ECG images are pre-processed using hexaxial feature mapping to convert paper-based EEG images into 2D colored images. We then use ResNet50 to effectively extract the features of the processed images, aiding in the classification process. We use LGBM for feature-based classification in this process. This combination provides dependable feature extraction with reduced training configurations. The Enhanced BiLSTM achieved the best accuracy of 97.22