Madanapalle Institute of Technology & Science, also known as MITS, is an Indian engineering college. It was established in 1998 in Madanapalle, India. MITS is an affiliate of JNTUA and is approved by AICTE, New Delhi. MITS is a destination for engineering, management, and computer application studies in India.
In order to coordinate EVs along with renewable energy, it is necessary to have accurate forecasting, adaptive control, and a secure energy exchange. The hybrid framework that integrates Transformer forecasting with multi-agent reinforcement learning (MARL) suggested in this paper appears to highly suitable for the intended application. In fact, the Transformer encoder is the one responsible for the accurate predictions of EV load and renewable generation, while MARL policies give the required decentralization and dynamic coordination. Blockchain acts as a safety net for the transactions and a sign of trustworthiness for the prosumers, with IoT-level compression playing the role of latency eliminator in densely packed EV networks. Testing results show that predictive reliability is 96.9%, balancing is 32.7%, efficiency is 26.4%, and latency is 24 ms. Based on the comparison with ML baselines, the framework is 6.8% more accurate, 7.5% more balancing is achieved, 5.9% of the cost optimization is improved, and therefore, the EV–renewable integration is not only scalable but also resilient.
This study evaluates the performance of sustainable mortar incorporating fly ash (FA) and limestone (LS) powder as partial binder replacements and construction and demolition waste (CDW) as an alternative fine aggregate. Cement was replaced by fly ash and limestone powder up to 24
Speed choice plays a major role in road accidents, yet most traffic management strategies do not fully account for differences in driver behavior or changing risk conditions. This study proposes a transparent and risk-aware framework for adaptive speed recommendation by combining unsupervised driver profiling with reinforcement learning. The analysis uses six years of road accident data from India (from 2018 to 2023) comprising tens of thousands of recorded crashes. Drivers are grouped into low, moderate and high-risk categories using Principal Component Analysis and K-means clustering. These risk profiles were then incorporated into a Proximal Policy Optimization agent trained with a safety-focused reward function that reflects driver behavior, road characteristics, environmental conditions and accident severity. The learned policy consistently recommends lower speeds for high-risk drivers and adverse conditions, while allowing higher yet safe speeds in low-risk contexts. Offline proxy-based evaluation using historical accident data shows that moderate speeds in the range of about 50–60 km/h were associated with lower average fatalities and casualties. Model interpretability is supported through SHAP analysis and decision-tree approximations which identify driver age, risk category and posted speed limits as key factors influencing recommendations. Although the framework is evaluated using offline and correlational analysis rather than field deployment, the results demonstrate the potential of interpretable and risk-aware AI systems to support safer speed management and inform intelligent transportation policy decisions.
This study explores fly ash-involved geopolymer concrete (GPC) using silica fume (SF) (0–60 kg/m³) and steel slag (SS) (0–720 kg/m³) as additional industrial byproducts to assess mechanical behavior. Sixteen mix proportions were systematically designed by varying fly ash (340–400 kg/m³), SF, and SS as partial replacements for natural coarse aggregate, activated using a constant 12 M NaOH and Na₂SiO₃ alkaline solution. Experimental evaluation of hardened specimens was done on bulk density, compressive strength (CS), split tensile strength (TS), flexural strength (FS), and ultrasonic pulse velocity (UPV) at 7 days and 28 days of ambient curing. A mix of 7 with 5
Abstract This study describes the design, simulation, and comparative analysis of 5-stage and 7-stage CMOS ring oscillator circuits in 45 nm and 180 nm technology nodes, a combination not previously reported in the open literature under similar conditions. This study quantifies the improvements in oscillatory frequency, power dissipation, propagation time, phase noise, and jitter as the scaling of the transistor progresses at nominal supply voltages of 1.2 V and 1.8 V, respectively. The simulation results obtained using the Cadence Virtuoso environment have been validated using a more accurate analytical model implemented in the Python environment, achieving an average accuracy above 90%. Using a 3000-point dataset, a Gradient Boosting-based machine learning algorithm has been trained to achieve R 2 score 0.9973 and MAPE 1.16%. Using a Particle Swarm Optimization algorithm, a reduction in power dissipation is achieved by 11.9% along with a reduction in simulation runs using the Cadence environment by 66.7%.Comparative analysis with the results reported in the recent literature on the design and analysis of ring oscillator circuits published in the years 2019–2025 reveals the competitive nature of the proposed 7-stage 45 nm ring oscillator design, where the normalized jitter is 1.670%, which is superior to the 5-stage design and is accompanied by a phase noise of -98.6dBc/Hz at a 1 MHz offset.
