A Seminar Report On

Neural Networks

Submitted in the partial fulfillment of the requirements for the award of the degree of

BACHELOR OF TECHNOLOGY
IN
ELECTRONICS & COMMUNICATION ENGINEERING

SUBMITTED BY
G HARISH - 15K81A04D5
Under the esteemed guidance
Of
Mrs.L. LAVANYA
ASSISTANT PROFESSOR
DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING
St.MARTIN’S ENGINEERING COLLEGE
Non-Minority College,Affiliated to JNTUH, Approved By AICTE
NBA Accredited,ISO 9001:2008

2015-2019
ACKNOWLEDGEMENT

I express my thanks and gratitude to RAJIV SRIVASTAVA Ph.D ,HEAD OF THE

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING,
St.MARTIN’S ENGINEERING COLLEGE for his encouraging and guidance in carrying out
the seminar. I would like to express our gratitude and indebtedness to Mrs.L.LAVANYA,my
coordinator, for his valuable advice and guidance.

I owe my sincere gratitude to our principal Dr.P.SANTOSH KUMAR PATRA and also
to our College Management Committee Members for giving the encouragement that helped me.

I here thank one and all who extended a helping hand in the accomplishment of the
project.

G HARISH

15K81A04D5
 Seminar Report on

Neural Networks
 Abstract

The artificial neural network (ANN), or simply neural network, is a machine learning method
evolved from the idea of simulating the human brain. The data explosion in modem drug discovery
research requires sophisticated analysis methods to uncover the hidden causal relationships
between single or multiple responses and a large set of properties. The ANN is one of many
versatile tools to meet the demand in drug discovery modeling. Compared to a traditional
regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN
also has excellent fault tolerance and is fast and highly scalable with parallel processing. This
chapter introduces the background of ANN development and outlines the basic concepts crucially
important for understanding more sophisticated ANN. Several commonly used learning methods
and network setups are discussed briefly at the end of the chapter.

Keywords:LoRa; Internet of Things; long range; low power

Contents

1.Introduction 1
1.1 Related Work ............................................................................................ 2
1.2 Statement of Purpose ................................................................................ 3

2.LoRa overview 4
2.1 LoRa Protocol Stack ................................................................................. 5
2.2 Lora Network Architecture ....................................................................... 5

3.LoRa Physical Layer 7

3.1 Overview of the physical layer ................................................................ 7
3.2 Parameters of the physical layer .............................................................. 7
3.3 Physical Frame Format ............................................................................ 9
3.4 Performance Evaluation .........................................................................10

4.The LoRaWAN Protocol

4.1 Components of a LoRaWAN Network ...................................................14
4.2 LoRaWAN Message
Format .................................................................. 15
4.3 End-Device Setup .................................................................................. 16
4.4 LoRaWan MAC Commands ...................................................................16

5.LoRaWAN Analysis 22
5.1 Single Device Maximal Throughput and MTU ..................................... 18
5.2 Total Capacity and Channel
Load........................................................... 19
5.3 Estimation of the Collision Rate ............................................................ 19
5.4 The Network Server Role ...................................................................... 22
5.5 The Gateway Role .................................................................................. 23

6.Conclusion 25
List Of Figures

Figure 1. LoRa network architecture.

Figure 2. Frequency variation over time of a sample signal emitted by a LoRa
transmitter. Data taken from. fc is the central frequency of the channel, and BW is
the bandwidth.
Figure 3. Structure of a LoRa frame. N∈ {1..4}.
Figure 4. The LoRa testbed. (a) The LoRa end-device; (b) the LoRa gateway.
Figure 5. Minimal observed RSSIs with different spreading factors.
Figure 6. Map of LoRa eld test.
Figure 7. Packet delivery ratio of the LoRa eld test.
Figure 8. LoRaWAN frame format. The sizes of the elds are in bits.
Figure 9. Maximum throughput attained by a single device using LoRaWAN.
Figure 10. Link capacity usage and packet collision rate for a LoRaWAN network
and compared to an ALOHA network.
Figure11.Link capacity usage and packet collision rate for a LoRaWAN network
when using con rmed messages.
Figure 12. An example of shared gateways in LoRa. The gateways can forward the
packet to different network servers.
List of Tables

Table 1. Semtech SX1276 LoRa receiver sensitivity in dBm at different

bandwidths and spreading factors