Cognitive Radio Questions and Answers – Techniques – Artificial Intelligence – 2


This set of Cognitive Radio Multiple Choice Questions & Answers (MCQs) focuses on “Techniques – Artificial Intelligence – 2”.

1. Which among the following is the basic component of artificial neural networks?
a) Motors
b) Neurons
c) Nephrons
d) Nuclei
View Answer

Answer: b
Explanation: Artificial neural networks are constructed using nodes which imitate the functionality of biological neurons. The network is a collection of algorithms that vaguely meets the performance of human brain in recognition of patterns.

2. What type of connection is present between nodes in neural networks?
a) Sampled
b) Not weighted
c) Weighted
d) Non-existent
View Answer

Answer: c
Explanation:The connection between neurons or nodes is weighted. If the number associated with the weight is positive, then it is an excitatory condition. If the number associated with the weight is negative, then it is an inhibitory condition.

3. What type of approach do artificial neurons employ for computation?
a) Comparative
b) Connectionistic
c) Conservative
d) Condensed
View Answer

Answer: b
Explanation: The distributed signal activity being carried out at once through connections may be represented using numbers. The connection is improved based on collected information over time and this process is referred to as learning.

4. What function calculates the value to be given as input to a neuron based on the output obtained by the last processed neuron?
a) Correlation
b) Direction
c) Propagation
d) Signalling
View Answer

Answer: c
Explanation: The propagation function is responsible for determining the input to a neuron in accordance to the output obtained from the previously processed neurons and their connections labelled as weighted sum. A bias term may be included to the outcome of the propagation function.

5. What is the terminology used to describe the connection where a set of neuron in one layer is connected to one neuron in the next layer?
a) Fully connected
b) Partially connected
c) Splitting
d) Pooling
View Answer

Answer: d
Explanation: The various types of connections used to join neurons present in adjacent layers contribute to the organisation of the neural network. When every neuron is connected to every neuron in the next layer, it is called as fully connected. When a set of neurons is connection to one neuron in the next layer, it is called as pooling.

6. Which among the following maybe used for modulation detection in neural networks?
a) Phase based probability
b) Time based probability
c) Time based statistics
d) Phase based statistics
View Answer

Answer: c
Explanation: Artificial neural networks may be used for signal classification and modulation detection in cognitive radio. The popular techniques employed for modulation classification is called as time based statistics and frequency analysis. The neurons and complex algorithms make it possible to build and process data in interesting ways.

7. In ____ time, Markov chain is called as ____
a) continuous, Markov process
b) discrete, Markov process
c) continuous, Bayesian process
d) discrete, Bayesian process
View Answer

Answer: a
Explanation: A Markov chain is a stochastic model. It represents a progression of events in which the probability of each event depends on the state achieved by the past event.

8. What does the term “hidden” refer to in hidden Markov model technique?
a) Parameters of input
b) Sate sequence
c) Parameters of model
d) Fixed standards of model
View Answer

Answer: b
Explanation: In a hidden Markov model, the state is not directly available to the observer. The output, dependant on the state, is available. The parameters of the model are not hidden, and the model is referred to as hidden Markov model even when the parameters are explicitly available.

9. Which among the following is not commonly determined by using hidden Markov model?
a) Channel transition probabilities
b) Decision making in cellular network
c) Channel quality
d) Signal classification
View Answer

Answer: d
Explanation: Hidden Markov models use past data to predict future actions. It may be used to describe channel quality. It determines whether the process should move to the next or remain in the present state. The current channel statistics may be modelled and use for decision making in cellular network.

10. A hidden Markov model can be considered a generalisation of mixture model.
a) True
b) False
View Answer

Answer: a
Explanation: A mixture model is used to represent the presence of a sub-category within an overall category. In hidden Markov model, the hidden variables are related based on Markov process and are not independent of each other. The hidden variables control the mixture component to be selected for each observation.

Sanfoundry Global Education & Learning Series – Cognitive Radio.

To practice all areas of Cognitive Radio, here is complete set of 1000+ Multiple Choice Questions and Answers.

Participate in the Sanfoundry Certification contest to get free Certificate of Merit. Join our social networks below and stay updated with latest contests, videos, internships and jobs!

Manish Bhojasia - Founder & CTO at Sanfoundry
Manish Bhojasia, a technology veteran with 20+ years @ Cisco & Wipro, is Founder and CTO at Sanfoundry. He is Linux Kernel Developer & SAN Architect and is passionate about competency developments in these areas. He lives in Bangalore and delivers focused training sessions to IT professionals in Linux Kernel, Linux Debugging, Linux Device Drivers, Linux Networking, Linux Storage, Advanced C Programming, SAN Storage Technologies, SCSI Internals & Storage Protocols such as iSCSI & Fiber Channel. Stay connected with him @ LinkedIn | Youtube | Instagram | Facebook | Twitter