Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 9

SAMARA UNIVERSITY

COLLEGE OF ENGINEERING AND TECHNOLOGY


DEPARTMENT OF COMPUTER SCIENCE

Course title: Selected Topics in Computer science

Course code: CoSc4181


Assignment: individual assignment
Name: Mathewos Ayele

Id: 1101985

Section: “B”

Submitted to Ahmed A.
1. Exchange Rate Forecasting
Exchange rate forecasting is very important to evaluate the benefits and risks attached to the
international business environment. : 
International transactions are usually settled in the near future. Exchange rate forecasts are
necessary to evaluate the foreign denominated cash flows involved in international transactions.
Thus, exchange rate forecasting is very important to evaluate the benefits and risks attached to
the international business environment.
There are two pure approaches to forecasting foreign exchange rates:
(1) The fundamental approach, (2) The technical approach: 
1. Fundamental approach
The fundamental approach is based on a wide range of data regarded as fundamental economic
variables that determine exchange rates. These fundamental economic variables are taken from
economic models. Usually included variables are GNP, consumption, trade balance, inflation
rates, interest rates, unemployment, productivity indexes, etc. In general, the fundamental
forecast is based on structural (equilibrium) models. These structural models are then modified to
take into account statistical characteristics of the data and the experience of the forecasters. : 
The fundamental approach is based on a wide range of data regarded as fundamental economic
variables that determine exchange rates.Fundamental Approach:
Practitioners use the fundamental approach to generate equilibrium exchange rates. The
equilibrium exchange rates can be used for projections or to generate trading signals. A trading
signal can be generated every time there is a significant difference between the forecasted
exchange rate and the exchange rate observed in the market.
2. Technical Approach
Technical Approach (TA) focuses on a smaller subset of the available data. In general, it is
based on price information. The analysis is "technical" in the sense that it does not rely on a
fundamental analysis of the underlying economic determinants of exchange rates or asset prices,
but only on extrapolations of past price trends. Technical analysis looks for the repetition of
specific price patterns. Technical analysis is an art, not a science. : 
is looks for the repetition of specific price patterns. Technical analysis is an art, not a science.

1
Exchange Rate Forecast: Models: 
Exchange Rate Forecast: Models Purchasing Power Parity (PPP) Model Uncovered Interest Rate
Parity (UIP) Model Random Walk Model
Purchasing Power Parity (PPP) Model: 
Purchasing Power Parity (PPP) Model Purchasing power parity (PPP) is a theory which states
that exchange rates between currencies are in equilibrium when their purchasing power is the
same in each of the two countries. This means that the exchange rate between two countries
should equal the ratio of the two countries' price level of a fixed basket of goods and services.
When a country's domestic price level is increasing (i.e., a country experiences inflation), that
country's exchange rate must depreciated in order to return to PPP.
Uncovered Interest Rate Parity (UIP) Model: 
Uncovered Interest Rate Parity (UIP) Model a parity condition stating that the difference in
interest rates between two countries is equal to the expected change in exchange rates between
the countries’ currencies. If this parity does not exist, there is an opportunity to make a profit.
"i1" represents the interest rate of country 1"i2" represents the interest rate of country 2"E(e)"
represents the expected rate of change in the exchange rate.

2. ANN in telecommunications
Neural networks are best distinguished from other intelligent techniques in that they are non-
rule-based and can additionally be made stochastic so that the same action does not necessarily
take place each time for the same input.

The following features have been advanced for artificial neural networks in telecommunications

 Data interpretation

table structure interpretation & text recognition for conversion of telephone company tabular
drawings Arabic character recognition system real-time identification of language from raw
speech waveforms temporal difference learning applied to continuous speech recognition
keyword search in handwritten documents face recognition self-organizing finite state vector
quantization for image coding.

Network Design Management Routing and Control

A distributed reinforcement leaning scheme for network routing a learning model for adaptive
network routing optimal traffic routing using the self-organization principle.

2
Hopfield optimization techniques applied to routing in computer networks scheduling problems
in radio networks using Hopfield networks new q-routing approaches to adaptive traffic control.
Dynamic routing in at networks with effective bandwidth estimation intelligent capacity
evaluation/planning with clustering algorithms. Neural networks for network topological design
location prediction in mobile networks at network control.

Fault management

Learning Index Rules and Adaptation Functions for a Communications Network Fault
Resolution System Using Distributed Neural Networks to Identify Faults in Switching Systems
Pre-processor for a Fault Diagnosis Expert System Prediction of Access Line Growth.

Fraudulent use of cellular phone detection


Whenever a completed phone call is made a call detail record (CDR) is created. Depending
on the operation currently being performed the structure of these will vary, however, for our
investigations we have produced a generic record, which encapsulates all the salient features,
which are required. These Include account number, telephone number, date and time of call,
the duration, the originating area and receiving area, as well as a number of other fields.
These records therefore constitute an enormous database within which anomalous use must

be detected

3. Speech Recognition
Speech recognition, or speech-to-text, is the ability of a machine or program to
identify words spoken aloud and convert them into readable text. Rudimentary speech
recognition software has a limited vocabulary and may only identify words and
phrases when spoken clearly.

Speech recognition uses a broad array of research in computer science, linguistics and
computer engineering. Many modern devices and text-focused programs have speech
recognition functions in them to allow for easier or hands-free use of a device.

3
How does speech recognition work?
Speech recognition systems use computer algorithms to process and interpret spoken
words and convert them into text. A software program turns the sound a microphone
records into written language that computers and humans can understand, following
these four steps:

 analyze the audio;

 break it into parts;

 digitize it into a computer-readable format; and

 Use an algorithm to match it to the most suitable text representation.


What applications is speech recognition used for?
Speech recognition systems have quite a few applications. Here is a sampling of them.

Mobile device: Smartphones use voice commands for call routing, speech-to-text processing,
voice dialing and voice search.

Education: Speech recognition software is used in language instruction. The software hears the
user's speech and offers help with pronunciation.

Customer service: Automated voice assistants listen to customer queries and provide helpful
resources.

Healthcare applications: Doctors can use speech recognition software to transcribe notes in real
time into healthcare records.

Disability assistance: Speech recognition software can translate spoken words into text
using closed captions to enable a person with hearing loss to understand what others are saying.
Speech recognition can also enable those with limited use of their hands to work with computers,
using voice commands instead of typing.

Court reporting:  Software can be used to transcribe courtroom proceedings, precluding the
need for human transcribers.

Hands-free communication: Drivers use voice control for hands-free communication,


controlling phones, radios and global positioning systems, for instance.

Speech recognition algorithms

4
 Artificial intelligence: AI and machine learning methods like deep learning and neural
networks are common in advanced speech recognition software.

 Natural language processing. NLP eases and accelerates the speech recognition process.


Advantages of speech recognition
 Machine-to-human communication
 Readily accessible
 Continuous, automatic improvement and Easy to use
Disadvantages of speech recognition
 Inconsistent performance
 Speed
 Source file issues
4. Petroleum refinery process control
An oil refinery or petroleum refinery is an industrial process plant where crude oil is
processed and refined into more useful products such as petroleum naphtha, gasoline, diesel
fuel, and asphalt base, heating oil, kerosene, and liquefied petroleum gas. Oil refineries are
typically large, sprawling industrial complexes with extensive piping running throughout,
carrying streams of fluids between large chemical processing units. In many ways, oil
refineries use much of the technology of, and can be thought of, as types of chemical plants.
The crude oil feed stock has typically been processed by an oil production plant. There is
usually an oil depot at or near an oil refinery for the storage of incoming crude oil feedstock
as well as bulk liquid products.
Petroleum refineries are very large industrial complexes that involve a great many different
processing units and auxiliary facilities such as utility units and storage tanks. Each refinery
has its own unique arrangement and combination of refining processes largely determined by
the refinery location, desired products and economic considerations. There are most probably
no two refineries that are identical in every respect.
Oil in the process of production is also required by production wells, injection wells and
observation wells on the oil and gas reservoirs for mining, observation and control, oil
refining, can be obtained can be divided into four categories: fuel, lubricating oil, bitumen,

5
Chemists use the following steps:
1. The oldest and most common way to separate things into various components (called
fractions), is to do it using the differences in boiling temperature. This process is called
fractional distillation. You heat, let it vaporize and then condense the vapor.
2. Newer techniques use chemical processing on some of the fractions to make others, in a
process called conversion. Chemical processing, for example, can break longer chains into
shorter ones. This allows a refinery to turn diesel fuel into gasoline depending on the demand
for gasoline.
3. Refineries must treat the fractions to remove impurities.
4. Refineries combine the various fractions (processed, unprocessed) into mixtures to make
desired products. For example, different mixtures of chains can create gasoline with different
octane reading
5. Airline marketing tactician

An example of the neural network is the Airline Marketing Tactician (AMT). This is a marketing
application incorporated with a neural network. Additionally, the system also incorporates an
expert system, which increases its efficiency in information processing.
The neural system is integrated with a form of feed forward neural network. It functions as a
marketing control of airline seat allocations. The system functions as a notification system that
advice the airline company on its seat allocation process. Additionally, the system also provides
a recommended mode of booking in all departures. By providing such information, an airline
is safe guarded from the physical monitoring of its booking system. In an argument by Hurwitz
(2011) this particular networks makes it efficient for both consumers and the organization.
Consumers are exposed to less physical requirements such as booking and selection of seats. The
organization, alternatively, is enabled to effectively monitor its seat allocation without interfering
with the comfort of the consumer.  

Expert system

6
An example of an expert system is the Real Time Process Control. It is categorized as a control
system, which enables les an organization to keep in check its main activities. The expert system
is also created in respect to the capability of the mind of humans to regulate the bodily functions
as well as interpreting occurrences
The main functions of the expert system are repairing, predicting, monitoring, and interpreting
system behaviors. By checking systems behavior, an organization minimizes the risks that may
arise from system errors. The expert system also improves the way in which an organization
attends to its consumers.
6. Bankruptcy Prediction

Closely related to credit risk evaluation is the prediction of bankruptcy of firms. Strictly defined,
bankruptcy occurs when debtors are unable to repay outstanding debts. While bankruptcy
prediction constitutes part of the credit Risk evaluation process, it is vital for banks and
companies to constantly monitor their credit risk exposure. Because of the two-class framework
(firms that go bankrupt and firms that do not), the basic Optimization framework is similar as
suggested for credit risk assessment. The difficulty and difference to credit risk assessment lies
however in the relatively longer aspired forecasting period and the difficulty in predicting the
exact time of bankruptcy.

Bankruptcy prediction is the art of predicting bankruptcy and various measures of financial


distress of public firms. It is a vast area of finance and accounting research. The importance of
the area is due in part to the relevance for creditors and investors in evaluating the likelihood that
a firm may go bankrupt.

Advantages of Bankruptcy

1. Automatic Stay
2. Increased Credit Score Rating
3. Unsecured Debts Paid Off
4. Bankruptcy Exemptions

7
Disadvantages of Bankruptcy

1. Loss of Property 3. Credit Card Score


2. Domino Effect 4. Domino Effect

You might also like