wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Winter_school

Total questions: 25

Worksheet time: 13mins

Name
Class
Date
1.

The gyroscope in an IMU is mainly used to measure:

a)

Linear acceleration

b)

Angular velocity

c)

Magnetic Field strength

d)

Orientation with respect to gravity

2.

Which library is commonly used to deploy TensorFlow Lite models on ESP32?

a)

tflite-micro

b)

PyTorch Mobile

c)

scikit-learn embedded

d)

ONNX Runtime

3.

A vanishing gradient problem is most common in:

a)

Shallow neural networks

b)

Deep networks with sigmoid/tanh activations

c)

Decision trees

d)

K-Nearest Neighbors (KNN)

4.

To improve underwater data acquisition reliability, hydrophones are often arranged in:

a)

Star topology

b)

Sensor fusion arrays

c)

Antenna towers

d)

Random placement

5.

Transfer learning is particularly effective when:

a)

The new dataset is very small but similar to the pretrained dataset

b)

The new dataset is completely unrelated to the source dataset

c)

Training must be done from scratch

d)

The model must be used without any fine-tuning

6.

Which type of error commonly accumulates in IMU-based dead reckoning navigation?

a)

Quantization noise

b)

Bias drift and integration error

c)

Signal reflection

d)

Packet loss

7.

Which of the following best explains the difference between ML and DL?

a)

ML requires GPUs, DL does not

b)

DL can automatically extract features, ML often needs feature engineering

c)

ML is faster but less accurate, DL is slower but always more accurate

d)

ML models always outperform DL

8.

In TinyML workflows, the ESP32 is usually responsible for:

a)

Model training

b)

Cloud-based hyperparameter tuning

c)

Model inference after deployment

d)

Labelling dataset

9.

Multipath propagation in underwater acoustics primarily occurs due to:

a)

Interference from WiFi signals

b)

Sound reflections from the water surface and seabed

c)

Poor sensor calibration

d)

Magnetic field distortion

10.

Sensor fusion algorithms like Kalman filter in IMUs are used to:

a)

Reduce energy consumption

b)

Combine sensor outputs for better accuracy

c)

Increase sampling frequency

d)

Automatically calibrate WiFi signals

11.

For long-range underwater communication, which signal type is most commonly used?

a)

Radio frequency (RF)

b)

Optical signals

c)

Acoustic waves

d)

Infrared

12.

Which communication protocol is least power efficient for sending inference results from ESP32?

a)

Bluetooth Low Energy (BLE)

b)

MQTT over WiFi

c)

UART

d)

SPI

13.

What is the primary advantage of using acoustic waves for underwater communication compared to optical signals?

a)

Higher data transfer rates

b)

Less susceptibility to scattering

c)

Lower power consumption

d)

Longer range capabilities

14.

In the context of machine learning, what does overfitting refer to?

a)

The model performs well on training data but poorly on unseen data

b)

The model is too simple to capture the underlying patterns

c)

The model is trained on too much data

d)

The model has too few parameters

15.

Which of the following is a common method for mitigating bias drift in IMUs?

a)

Reducing the number of measurements

b)

Using a single sensor

c)

Increasing sampling rate

d)

Regular calibration

16.

Which axis convention is most commonly used in IMU sensor coordinate frames?

a)

Left-handed system (X-left, Y-up, Z-forward)

b)

Right-handed system (X-forward, Y-right, Z-down)

c)

Randomized depending on manufacturer

d)

Spherical coordinate system

17.

What is the main purpose of using a microcontroller like ESP32 in TinyML applications?

a)

To perform complex model training

b)

To handle low-power model inference

c)

To store large datasets

d)

To manage cloud services

18.

Which of the following is a common challenge when deploying machine learning models on edge devices?

a)

High computational power requirements

b)

Limited data availability

c)

Increased latency in model inference

d)

Power consumption constraints

19.

In the context of IMUs, what does the term 'drift' refer to?

a)

Random fluctuations in sensor readings

b)

Loss of signal strength

c)

Gradual deviation from the true position over time

d)

Instantaneous changes in orientation

20.

Which metric is most suitable for evaluating an imbalanced classification dataset?

a)

Accuracy

b)

Precision-Recall or F1-score

c)

Mean Squared Error

d)

R² Score

21.

What percentage of global car sales were EVs in 2024?

a)

8%

b)

18%

c)

25%

d)

40%

22.

What is the main advantage of hydrogen fuel cell vehicles (FCEVs) over battery EVs?

a)

Lower manufacturing cost

b)

Faster refueling time

c)

Higher driving range

d)

both Faster refueling time and Higher driving range

23.

Which is currently the largest EV charging network in the world?

a)

Ionity

b)

Electrify America

c)

Tesla Supercharger Network

d)

Shell Recharge

24.

What is the estimated average lifespan of a modern EV battery pack before major degradation?

a)

2–3 years

b)

10–15 years

c)

5–6 years

d)

20–30 years

25.

Norway plans to ban the sale of new petrol/diesel cars from:

a)

2025

b)

2026

c)

2027

d)

2028