Answer key Artifcial Intelligence Class 10 of board exam 2025

Explanation:
It does not help in stress management. Instead, they increase stress levels, worsen anxiety, and negatively affect mental health.

Other options:
(A) Healthy food → Helps in stress management by providing essential nutrients, boosting energy levels, and stabilizing mood.
(B) Sound sleep → Helps in stress management by improving mental and physical well-being, allowing the body to recover.
(C) Yoga asanas → Helps in stress management by promoting relaxation, reducing muscle tension, and enhancing mindfulness.

Explanation:
Spam commonly refers to unsolicited or junk emails, often advertisements or scams.

Other Options:
(A) Unnecessary images → Unnecessary images may consume space, but they are not classified as spam.
(B) Temporary files → Temporary files are system-generated files used by applications, not spam.
(D) Music files → Music files are media content, not spam.

Explanation:
Does NOT help in self-motivation. Lack of discipline creates distractions and reduces focus.

Other Options:
(A) Focusing on your goal → Helps build self-motivation by giving you direction and purpose.
(B) Planning to achieve your goal → Helps in self-motivation by breaking down tasks into achievable steps.
(D) Helps in self-motivation by boosting confidence and enabling you to leverage your skills effectively.

Explanation:
This occurs when a few people (typically 3–10) communicate effectively with each other.

Other options:
(A) Interpersonal communication → This refers to communication between two individuals, not a small group.
(B) Public communication → This involves communication with a large audience, such as public speaking.
(C) Intrapersonal communication → This refers to communication with oneself, such as self-reflection.

Explanation:
Reema experiments with new ideas, which is a sign of creativity—an essential trait for entrepreneurs.

Other options:
(A) Impatient → Impatience would hinder her creativity and problem-solving abilities.
(C) Under-confident → Reema shows confidence by trying new dishes, indicating she believes in her skills.
(D) Lazy → Her willingness to innovate shows she is proactive, not lazy.

Explanation:
The assertion is valid as AI mimics human traits, but the reason is incorrect because a washing machine does not exhibit AI capabilities.

Rest of all are not appropriate terms.

Explanation:
Statement 1 → The “When” block of the 4Ws canvas refers to the timeframe of the problem or solution, not the stakeholders.
Statement 2 → Stakeholders are indeed the individuals or groups affected by the problem and benefit from the solution covered in Who block of 4Ws canvas.

Explanation:
In AI projects, training is the process where the model learns patterns and relationships from a labeled dataset. During this phase, the model adjusts its internal parameters based on the data. Once trained, the model can then be used to predict outputs when given new or unseen data.

Testing (mentioned in option A) is done after the model is trained to evaluate its performance.
Therefore, the model must be trained first before it can make accurate predictions.

Explanation:
Image processing in Computer Vision involves analyzing and interpreting images to extract valuable information, such as detecting objects, recognizing faces, or identifying patterns.

(A) Editing videos → Involves video editing, not image analysis.
(C) Playing audio files → Irrelevant to image processing.
(D) Compiling codes → Related to programming, not image processing.

Explanation:
Stop words are common words (e.g., “the”, “is”, “an”) that frequently occur in texts but carry little meaningful information.

In Natural Language Processing (NLP), these words are often removed to focus on the more significant terms.

Explanation:
The image shows a location pin, which is a symbol used by Google Maps and other navigation apps.
AI in navigation apps provides real-time directions, traffic updates, and route optimization.

Explanation:
Options A, B, and C relate to genetics and genomics, which focus on studying DNA, diseases, and biological connections.
Option D refers to address lookup, which is unrelated to genetics and genomics and involves data search algorithms rather than biological analysis

Explanation:
Classification + Localization is used to identify and locate a single object in an image.
Object Detection (Option A) is used for multiple objects.
Instance Segmentation (Option C) goes further by identifying and segmenting individual objects.
Non-Localization (Option D) does not specify the location of the object.

Explanation:
SQL (Structured Query Language) is used to manage and manipulate structured data in relational databases.
CSV (Comma-Separated Values) and TXT (plain text) are file formats, not languages.
Spreadsheet refers to an application (like Excel) but is not a language.
TXT files are text files that handle the textual data file.

Explanation:
Function: Creates a concise summary of lengthy content.
Examples: Summarizing news articles or blog posts.
Purpose: Avoids redundancy and highlights key points.

Other Options:
(A) Virtual Assistants
Function: AI-powered programs that interact with users through voice or text.
Examples: Alexa, Siri, Google Assistant.
Purpose: Perform tasks, answer questions, and assist users.

(B) Sentiment Analysis
Function: Identifies the emotional tone of text (positive, negative, or neutral).
Examples: Analyzing customer reviews or social media posts.
Purpose: Understand public opinion or customer feedback.

(C) Text Classification
Function: Categorizes text into predefined labels or classes.
Examples: Spam detection, topic labeling.
Purpose: Organize and categorize large text datasets.

Explanation:
Explanation:
Precision: No → The model predicted “No” (negative outcome).
Reality: Yes → The actual outcome is “Yes” (positive in reality).
Since the model incorrectly predicted “No” when the actual value is “Yes”, it is a False Negative (FN).

Other Options:
(A) False Positive (FP) → Model predicts Yes, but reality is No.
(C) True Positive (TP) → Model correctly predicts Yes when reality is Yes.
(D) True Negative (TN) → Model correctly predicts No when reality is No.

Rest all are incorrect

Explanation:
Overfitting occurs when the model learns the specific details and noise of the training data, rather than the general patterns.
This leads to poor performance on new, unseen data, making it unsuitable for proper evaluation.

In cases of overfitting, the model memorizes the training data instead of generalizing.
As a result, it performs perfectly on the training set but fails on test data.

Explanation:
This measures the percentage of true positives out of all predicted positives.
Precision = TP/ TP + FP

Where:
TP = True Positives
FP = False Positives

Other options:
(B) Recall → This measures the percentage of true positives out of all actual positives.
Recall = TP/ TP + FN
Where:
FN = False Negatives

(C) F1 Score → This is the harmonic mean of Precision and Recall. It balances the two metrics, making it useful when you want to optimize for both.
F1 Score = 2 × Precision × Recall / Precision + Recall
​
(D) Accuracy → This measures how many predictions (both positive and negative) were correct out of all predictions.
Accuracy = TP + TN / TP + TN + FP + FN
Where:
TN = True Negatives

Explanation:
Spam filtering is a classic example of text classification, where emails are classified as either spam or non-spam based on their content.

Other Options:
(A) Virtual Assistants → These are AI-based systems (like Siri, Alexa, or Google Assistant) that understand and respond to natural language commands. They are not specifically designed for spam filtering.

(B) Sentiment Analysis → This involves analyzing the sentiment (positive, negative, or neutral) in text data, often used for reviews and social media analysis, not spam filtering.

(D) Automatic Summarization → This involves generating a concise summary of a larger text, often used for news articles or reports, not for spam filtering.

Explanation:
The Internet of Things (IoT) refers to the network of physical devices connected via the internet, enabling remote monitoring and control.
Turning appliances on and off remotely using an internet-enabled device is a classic example of IoT.

Other Options:
(A) Artificial Intelligence: AI refers to machines performing tasks that typically require human intelligence, such as decision-making, pattern recognition, and learning. While IoT devices may use AI, the ability to control appliances remotely is specifically an IoT function, not purely AI.

(C) Computer Vision (CV) : CV is a field of AI that enables machines to interpret and understand visual information from the real world (e.g., facial recognition, object detection). It is unrelated to remotely controlling devices.

(D) Deep Learning (DL) : DL is a subset of AI that uses neural networks to learn from large datasets.
It is mainly used in complex tasks like image recognition, language processing, and autonomous vehicles, not basic IoT operations.

Explanation:
Musical intelligence involves sensitivity to sound patterns, rhythm, tone, and melody.
People with high musical intelligence are typically skilled in playing instruments, singing, or composing music.

Other Options:
(A) assesses one’s ability to regulate, measure, and understand numerical symbols, abstraction, and logic
This refers to logical-mathematical intelligence, not musical intelligence.
It deals with numerical reasoning and problem-solving abilities.

(B) measures the language processing skills both in terms of understanding or implementation in writing or verbally.
This refers to linguistic intelligence, which involves proficiency in language skills, including reading, writing, and speaking.
It is unrelated to musical intelligence.

(C) evaluates the ability to process information on the environment around us.
This describes naturalistic intelligence, which involves observing and interpreting nature, not musical skills.

Explanation:
True positive: The model correctly predicts a positive case.
True negative: The model correctly predicts a negative case.
Since both predictions match reality, this is the correct answer.

(A) True positive and False positive
True positive: The model correctly predicts a positive case.
False positive: The model incorrectly predicts a positive case when it is actually negative.
Since the false positive does not match reality, this is incorrect.

(C) False positive and False negative
False positive: The model incorrectly predicts a positive case when it is actually negative.
False negative: The model incorrectly predicts a negative case when it is actually positive.
Since both are incorrect predictions, they do not match reality.

(D) True positive and False negative
True positive: The model correctly predicts a positive case.
False negative: The model incorrectly predicts a negative case when it is actually positive.
Since false negative does not match reality, this is incorrect.

Explanation:
Image-based search uses visual data, not sound, to retrieve results.

Explanation:
Smart bots use AI and machine learning algorithms to understand context, process natural language, and respond intelligently.
They can access and retrieve information from large databases directly.
They continuously learn and improve from interactions.
Offer multi-functional capabilities such as:
Conversational responses with contextual understanding.
Database queries and data retrieval.
Personalization based on user behavior.

2. Clear and Concise Emails or Messages: Sending clear and well-structured emails or messages ensures that instructions, deadlines, and important information are effectively conveyed.

3. Open-Door Policy: Encouraging team members to approach the leader freely promotes transparency and trust, making it easier to resolve issues quickly.

4. Use of Collaboration Tools: Utilizing tools like Slack, Microsoft Teams, or Trello enhances real-time communication, task management, and overall collaboration efficiency.

2. Marketing and Promotion: They develop strategies to promote their products or services, attract customers, and increase sales through advertising and branding.

3. Decision-Making and Problem-Solving: Entrepreneurs make critical decisions regarding operations, strategies, and future plans while solving business challenges.

4. Hiring and Managing Employees: They recruit, train, and manage employees, ensuring that the team works efficiently and productively.

2. Use Strong Passwords and Two-Factor Authentication (2FA): Set strong, unique passwords and enable 2FA to enhance device security.

3. Proper Handling and Storage: Keep devices away from moisture, heat, and direct sunlight. Use protective cases to prevent physical damage.

4. Regular Backups: Back up important data to external drives or cloud storage to prevent data loss in case of device failure or theft.

1. Water:
– Scarcity and Overuse: Excessive consumption and wastage of water deplete freshwater resources.
– Pollution: Industrial discharge, agricultural runoff, and plastic waste contaminate water bodies.
– Unequal Distribution: Many regions face water scarcity, while others have abundant water, leading to inequality in access.
– Climate Change Impact: Changing weather patterns affect rainfall, causing droughts or floods.

2. Fuel:
– Depletion of Fossil Fuels: Over-reliance on non-renewable fuels (coal, oil, gas) reduces reserves.
– Pollution and Emissions: Burning fossil fuels releases greenhouse gases, contributing to global warming.
– Energy Inefficiency: Inefficient fuel consumption leads to higher emissions and resource wastage.
– Dependency on Imports: Countries without sufficient fuel reserves rely heavily on imports, affecting their economy and energy security.

(ii) Data Features: Data features are the individual measurable properties or characteristics of the data used to train AI models. Each feature represents a variable or attribute in the dataset.

2. Passenger Demand Forecasting: Use historical data and trends to predict passenger demand for specific routes. Helps in adjusting flight frequencies and optimizing seat allocation. Dynamic Pricing Strategies:

3. Implement dynamic pricing models based on demand, seasonality, and competitor pricing.
Helps maximize revenue and occupancy rates.

4. Delay and Cancellation Prediction: Use machine learning models to predict potential flight delays or cancellations by analyzing factors like weather, maintenance issues, and past patterns. Improves customer experience by providing proactive notifications and alternative options.

2. Improved Treatment Planning and Monitoring: CV helps in 3D image reconstruction and visualization, allowing doctors to create detailed models of organs or tumors.
It assists in treatment planning for surgeries, radiation therapy, and personalized medicine.
Example: In radiology, CV tracks tumor growth over time by comparing successive scans, enabling better treatment adjustments.

3. Automation of Image Analysis and Reporting: Computer Vision automates image segmentation, classification, and annotation, reducing the need for manual intervention.
This speeds up the diagnostic process and ensures consistency in image interpretation.
Example: In pathology, CV models can automatically identify and label tissue abnormalities in biopsy samples.
Real-time Image-guided Surgery:

4. CV provides real-time visual feedback during surgeries by analyzing and enhancing live video feeds.
It helps surgeons with precision and accuracy, reducing risks and improving outcomes.
Example: In robot-assisted surgeries, CV helps track instruments and anatomical structures in real-time, enabling minimally invasive procedures.

False negatives: When the AI model fails to detect an actual fraudulent transaction, marking it as legitimate.
Example: A fraudster makes multiple unauthorized transactions, but the model misses them, assuming they are legitimate.

Example:
An AI hiring tool trained on historical male-dominated data may unfairly favor male candidates, discriminating against women.

AI Access: AI access refers to the availability and inclusivity of AI technologies for different individuals and groups.

Example: In rural areas with poor internet connectivity, students may have limited access to AI-powered educational platforms, creating a digital divide.

It contains the following:
1. Input Data: The leftmost part labeled “Data” represents the input data fed into the system. In deep learning, this could be:
– Images (for image classification tasks)
– Text (for NLP tasks)
– Tabular data (for structured data predictions)

2. Multiple Neural Networks: The diagram shows multiple machine learning algorithms, which in the context of deep learning, represent different neural networks. Each neural network processes the input data independently and learns hidden features or patterns. The “Hidden Rules” in the diagram symbolize the hidden layers of the neural networks, where feature extraction occurs.

3. Parallel Processing: The neural networks work in parallel, each producing an individual prediction (Answer). These models could be different architectures (e.g., CNNs, RNNs, or Transformers) or variations of the same model with different hyperparameters.

4. Combining the Outputs: The predictions from the multiple neural networks are aggregated to form the final answer.
The combination method could be:
– Averaging the outputs (for regression tasks)
– Majority voting (for classification tasks)
– Weighted averaging (for improved accuracy)