(SEM VI) THEORY EXAMINATION 2024-25 DATA SCIENCE IN IOT

BCIT601 – DATA SCIENCE IN IoT

Time: 3 Hours | Max Marks: 70

SECTION A – Short Answer Questions

(2 × 7 = 14 marks | Attempt ALL)
Write clear definition + 1–2 key points

1. IoT Analytics

IoT analytics is the process of analyzing data generated by IoT devices to extract useful insights for decision-making.
It includes real-time, batch, and predictive analytics.

2. Exploratory Data Analytics (EDA)

EDA is the initial analysis of data to understand patterns, trends, outliers, and relationships using statistical and visual methods.

3. Streaming Analytics vs Prescriptive Analytics

4. Mean vs Deviation                                                            Mean: Average value of dataset

Deviation: Spread of data from the mean                           Deviation shows data variability.

5. Purpose of Data Pre-Engineering in IoT                          Cleaning noisy sensor data

Handling missing values                                                      Data normalization for better analytics accuracy

6. Skewness & Its Significance                                     Skewness measures asymmetry of data distribution.

Positive skew: long right tail                                        Negative skew: long left tail
Helps understand data behavior.

7. Residual Plot

A residual plot shows errors between observed and predicted values.
It helps identify non-linearity and model inadequacy.

SECTION B – Medium Answer Questions

(7 × 3 = 21 marks | Attempt ANY THREE)
Write concept → explanation → example

1. Role of IoT Analytics in Creating Business Value                 IoT analytics helps organizations:

Improve operational efficiency                                                Enable predictive maintenance

Reduce costs and downtime                                                    Enhance customer experience

Example: Smart manufacturing systems.

2. Data Collection Strategies in IoT                                      Sensor-based data collection

Edge data acquisition                                                          Gateway-based aggregation

Cloud-based data ingestion                                            Each strategy balances latency, cost, and reliability.

3. Visualization Techniques for Model Evaluation

Line graphs – trends over time                                              Scatter plots – correlation analysis

Box plots – outliers and spread                                             Heat maps – intensity and patterns

Used for decision-making and performance analysis.

4. Linked Analytical Datasets in IoT

Linked datasets integrate data from multiple IoT sources.

Benefits:                                                                               Better contextual insights

Improved accuracy                                                                Unified analytics view

Example: Smart city data integration.

5. Analytics in IoT-Driven Agriculture                                   Benefits include:

Crop yield prediction                                                            Soil moisture monitoring

Smart irrigation                                                                     Reduced resource wastage

Improves productivity and sustainability.

SECTION C – Attempt ANY ONE

(7 marks)

1. Architecture of an IoT Analytics System                           Main components:

IoT devices & sensors                                                          Data ingestion layer

Data storage (cloud/databases)                                          Analytics & ML engine

Visualization & decision layer                                             Explain with neat block diagram.

2. Streaming Analytics vs Time-Series Analytics