Key Insights from the SHAP Value Graph:

• number_inpatient: Higher values (more inpatient visits) strongly increase the risk of readmission. The SHAP value rises sharply as the feature value increases, indicating a strong positive correlation with readmission risk.

• number_diagnoses: More diagnoses increase the likelihood of readmission. Higher values correlate with higher SHAP values, suggesting that patients with multiple conditions are at greater risk.

• num_medications: Moderate medication counts slightly increase risk, but extreme values may have diminishing effects. The SHAP trend shows a peak, implying that while more medications generally raise risk, very high numbers might stabilize it.

• number_emergency: Frequent emergency visits increase readmission risk. Higher emergency visits correlate with higher SHAP values, signaling instability in patient health.

• number_outpatient: More outpatient visits reduce readmission risk. The SHAP value decreases as outpatient visits increase, suggesting better ongoing care lowers risk.

• time_in_hospital: Longer stays initially increase risk, but the effect may plateau. SHAP values rise then stabilize, indicating that extended hospitalization alone isn’t linearly predictive.

• num_lab_procedures: Moderate lab tests reduce risk, but excessive tests may indicate complications. The SHAP curve dips then rises slightly, implying optimal monitoring lowers risk, while over-testing may signal severity.

• medical_specialty: Patients treated by specialists have lower readmission risk compared to those managed by generalists or with unrecorded specialties.

• gender_Female: Female patients have slightly lower readmission risk. The negative SHAP value indicates a protective effect compared to males (baseline).

• diag_1_428, diag_1_414: These diagnoses increase risk. High SHAP values confirm that chronic cardiac conditions are strong predictors of readmission.

This Python program calculates the exact volume of sand required for concrete mixing, accounting for sand bulking effects and specified mix ratios.

This Python program calculates the optimal concrete mix ratio by minimizing voids in aggregate composition. The system implements the minimum void method to determine the most efficient proportions of cement, fine aggregate (FA), and coarse aggregate (CA) based on their void characteristics and practical excess requirements.

This program automates concrete mix design using the fineness modulus method based on the following input parameters: design strength (2000–4500 psi), aggregate size (0.375–1.5 in), vibration type (vibrated/hand-worked), fineness modulus (FA, CA), and aggregate shrinkage factor. This program queries a CSV database to find the optimal combined fineness modulus and cement-to-total-aggregate ratio. Finally, it generates a 1 : FA : CA mix ratio for precise batching.

The Rebar Property Lookup Tool is a simple yet powerful Streamlit application designed to provide quick access to essential rebar (reinforcement bar) properties. Users can select a standard bar number (e.g., #3, #5, #8) from a dropdown menu, and the tool instantly displays key specifications, including diameter and cross-sectional area.

Key Features:

• User-Friendly Interface: Intuitive dropdown selection for bar numbers.

• Instant Results: Displays diameter and cross-sectional area in a clean, tabular format.

• Time-Saving: Eliminates the need for manual reference to rebar charts, streamlining design and calculations.

The Beam Stress Analyzer is a Streamlit-based web application designed to evaluate the stress distribution and safety of reinforced concrete beams under bending moments. Users input key parameters such as concrete compressive strength, steel yield point, beam dimensions, and applied bending moment. The tool calculates stresses in the concrete (top and bottom fibers) and steel reinforcement, comparing them against material limits to determine if the section is safe or at risk of cracking/yielding.

Key Features:

• Input Validation: Accepts user-provided beam and material properties.

• Stress Calculations: Computes concrete compressive/tensile stresses and steel tensile stress.

• Safety Checks: Flags whether the concrete is uncracked and if steel stresses are below yield.

• Clear Output: Presents in a concise format with pass/fail indicators for quick interpretation.

Example 1

Example 2

The Bus Fleet Requirement Calculator is a tool designed to estimate the total number of buses needed for a city or region based on various transportation parameters. It takes inputs such as population, per capita trip rate, bus occupancy, fleet utilization, and operational metrics (e.g., average trip length and daily distance traveled by buses) to compute the optimal number of buses required. This tool is useful for urban planners, transportation authorities, and policymakers to ensure efficient public transit systems that meet passenger demand while optimizing resource allocation.

This Streamlit-based Python application is designed to optimize and visualize bus schedules during peak hours for efficient public transportation management. The system calculates the optimal number of buses required based on route parameters, passenger demand, and operational constraints, then generates a detailed timetable and visual timeline of bus movements.

Key Features:

• Input Analysis: Collects route length, average speed, passenger trips, and bus capacity to determine fleet requirements

• Schedule Optimization: Calculates journey times, terminal times, and headways to create an efficient bus rotation schedule

• Interactive Timetable: Generates a clear tabular schedule showing departure/arrival times at all terminals

• Visual Timeline: Provides a graphical representation of bus movements throughout the peak period

• User-Friendly Interface: Simple form-based input with immediate visual outputs

IntelliSignal is a Streamlit-based web application designed to optimize and visualize two-phase traffic signal timing for isolated cross-junctions. The tool takes user inputs such as inter-green times, red/yellow intervals, and traffic flow data (including arrival flows and saturation flows for North-South and East-West arms) to compute the optimal cycle time and effective green times for each phase.

Key Features:

• User-Friendly Interface: Input fields for traffic parameters like inter-green times, flow rates, and saturation flows.

• Automated Calculations: Computes cycle time, effective green times, and inter-green intervals based on traffic engineering principles.

• Visual Timing Diagram: Displays a clear, annotated signal timing diagram showing phases (Green, Amber, Red), helping users visualize the signal sequence.

• Traffic Efficiency: Aims to reduce congestion by balancing green times according to actual traffic demand and saturation flow rates.