Project 2
Student id: c12
To select another student or project, return to the Project Page.
<?xml version="1.0" encoding="UTF-8"?>
<?xml-model href="../schema_3302.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
<!--the second line in the document associates the schema, so be sure not to change it-->
<DOC>
<docHead>
<!--required header includes metadata about the assignment (title, author, version)-->
<title>Writing Project 2</title>
<author xml:id="c12">Brent Christy</author>
<version n="3" date="2016-08-09"/>
</docHead>
<fsb_rpt>
<page type="ttl">
<title>Boston Traffic Signal Neural Network</title>
<subTitle>Feasibility Report</subTitle>
<date>August 9th, 2016</date>
<contributors>Brent Christy</contributors>
</page>
<page type="tbl_contents">
<sect n="1" lvl="1">Executive Summary</sect>
<sect n="2" lvl="1">Preliminary requirements analysis</sect>
<sect n="3" lvl="1">Feasibility</sect>
<sect n="1" lvl="2">Technical</sect>
<sect n="2" lvl="2">Economic</sect>
<sect n="6" lvl="1">Success Criteria</sect>
<sect n="7" lvl="1">Design</sect>
<sect n="8" lvl="1">Cost Estimates</sect>
<sect n="9" lvl="1">Report</sect>
<sect n="10" lvl="1">Risk Analysis</sect>
<sect n="11" lvl="1">Conclusion</sect>
</page>
<page type="exec_sum">A network linked traffic signal control system is proposed throughout
the city of Boston. The network will autonomously adjust traffic signal timing depending
on the current traffic conditions using a neural network. The goal of using autonomously
adjusting traffic signals as opposed to timed signals is to reduce the amount of time
spent in traffic in the city. Less time spent in traffic will result in lower fossil
fuel emissions as well as a higher quality of life for commuters. The current traffic
signal system in Boston is well set up to be adapted to take on the neural network
traffic control system. </page>
<page type="pre_req_ana">
<app_ovr type="obj">The objective of the proposed system is to provide an overall
decrease in traffic throughout the city of Boston, especially during peak travel
times.</app_ovr>
<app_ovr type="synergy"> The proposed system will utilize the current traffic control
system which has central control of 544 of 845 lights operated by the Boston
Transportation Department as shown in their 2013 annual report. The program will
also utilize several sensors present at major intersections throughout the
city.</app_ovr>
<app_ovr type="rls">The proposed system will have to comply will all state and federal
laws regarding traffic signals.</app_ovr>
</page>
<page type="fsb">
<fsb_hlgt type="tcnl"> The proposed neural network will require several improvements to
the current control system. Currently, most traffic signals are controlled by preset
timers. These timers are set by traffic control engineers once every five years
after observing traffic for several days. The other traffic signals use both the
timers and some sensors to determine how many cars are currently at the
intersection. For the neural network traffic system, three major actions will need
to take place. First, the remaining 301 of 845 lights will need to be connected to
the central traffic system. This will allow the central program to control all
lights in the city. Second, sensors will have to be placed at large intersections in
the city. These sensors will tell the neural network how many cars are at major
intersections and allow the network to adjust traffic flow depending on the
conditions. The sensors can be applied either on traffic poles as visual sensors or
underneath the pavement as pressure sensors. As there will be a fairly large number
of sensors, most will have to be applied to poles as digging up roads will increase
the implementation time and budget of the project. Last, the neural network will
need to be implemented. This neural network will be connected to all of the traffic
lights and receive the sensor data from the main intersections. The network can
leverage several papers already written on the subject of traffic control with
neural networks.<note type="instructor" resp="#kgs">Are these papers you refernce
elsewhere?</note>
</fsb_hlgt>
<fsb_hlgt type="econ">The effective costs of the project will go to three categories:
connecting the lights to the central network, adding sensors to main intersections,
and coding the neural network. The majority of the cost will go towards the
development of the neural network. Based on the Boston Transportation Department's
current budget, there is a sizeable amount of money that could be allocated towards
these purposes each year over the course of the next five years. </fsb_hlgt>
</page>
<page type="sccs_crt">
<req_sect>Installation <req n="1" title="Central Network"> All traffic lights must be
connected to a central network. This will allow all signals to be controlled by
the neural network implemented in a central location.</req>
<req n="2" title="Sensors"> Pressure or visual sensors must be added to high traffic
volume intersections throughout the city. This will allow the neural network to
adjust the signal timings based on current conditions.</req>
</req_sect>
<req_sect>Software Components <req n="3" title="Autonomously operating"> The timing
system must be able to autonomously operate. Once implemented, the traffic
control system should not require human input unless under extreme
circumstances. It should be able to learn from previous traffic situations and
improve its handling of traffic flow in these situations. </req>
<req n="4" title="Current Condition Adjustment"> The traffic control system must be
able to adjust the timings of lights based on the current conditions. Based on
the inputs from sensors at different locations in the city, the traffic control
system should change the timing.</req>
</req_sect>
</page>
<page type="dsn">
<img
url="http://image.slidesharecdn.com/neuralnetworkforreal-timetrafficsignalcontrol-150206235042-conversion-gate02/95/neural-network-for-real-time-traffic-signal-control-7-638.jpg?cb=1423266888"
>Neural Network Structure</img>
</page>
<page type="cost">
<est type="fnc">$5,000 per light to connect each to the central network. (301 lights) =
$1,505,000</est>
<est type="fnc">$2,000 per intersection that needs sensors (50 intersections) =
$100,000</est>
<est type="fnc">Neural network development = $1,500,000</est>
</page>
<page type="rpt">
<tmln date="2017-01-01"> Neural Network: The software team will begin neural network
development. </tmln>
<tmln date="2017-03-01"> Sensors: Sensors will begin to be installed at major
intersections. Show the team lead the first installation.</tmln>
<tmln date="2017-03-15"> Light Connection: Unconnected lights will begin to be connected
to the central network.</tmln>
<tmln date="2017-06-01"> Neural Network: The neural network team should have a working
model by this point. A demonstration with model data should be available here. At
this point, some sensors will be installed at major intersections and the network
can begin to learn based on real traffic data.</tmln>
<tmln date="2018-03-01"> Sensors and Light Connection: A Check-in meeting with the team
lead. 150 of the previously disconnected lights should be connected to the central
network at this point. Sensors should be installed at the top 15 busiest
intersections</tmln>
<tmln date="2019-06-01"> Neural Network: After approval from the team lead, traffic
signals will start to be controlled by the neural network. Thorough testing will
need to be done and shown to the team lead.</tmln>
<tmln date="2020-01-01">Sensors and Light Connection: All lights controlled by the
Boston Transportation Department should be connected to the neural network. All
planned sensors should be added to intersections as well.</tmln>
<tmln date="2021-06-01">Neural Network: Analysis of the effectiveness of the neural
network controlled traffic system will be conducted after a year and a half of use.
An outside agency will conduct these tests.</tmln>
</page>
<page type="rsk_ana"> There are several potential risks to this system. One risk is lights
getting disconnected from the central system. This can be combated by having preset
timers as backups to the network timing. Preset timers is the current format, so this
backup would not add much extra work to the system. Another risk is the introduction of
self-driving cars. Self-driving cars may eliminate the need for traffic signals which
would prove the system useless. In order for traffic signals to become useless, however,
all cars would need to be autonomous. This is not likely to happen, as normal cars are
so engrained in our society that there will always be people that want to drive cars or
that will be too afraid of self-driving cars to own one. There will always be people
that want to drive antique cars that will not be autonomous. </page>
<page type="conc">
<fsb>Given the current budget and technology, it appears to be reasonable to complete
this task within the proposed five year time frame. With much research already done
on the subject of neural networks, it would be reasonable to create over the course
of several years.</fsb>
<cond>Despite budget concerns throughout the city, this would be a good allocation of
funds to increase the quality of life of workers around the area.</cond>
<sum>The project appears to be technically feasible in that all proposed actions can be
completed given the correct time and resources. Given some room added in the Boston
Transportation Department's budget, there is also enough monetary resources for the
project to work. Last, the large time period proposed for the project will allow the
system to be implemented in a timely manner. Overall, it appears reasonable that the
system can be implemented.</sum>
</page>
</fsb_rpt>
<docReview>
<reviewer type="peer" xml:id="m20">Chi Mo</reviewer>
<report type="peer" resp="#m20">
<p> After reading this feasibility report about the traffic lights neural network, I can
see that the feasibility report is well organized and easy to understand. After a
glance, the report looks feasible. It looks like the author is trying to make the
Boston’s traffic signal more efficient. I don’t understand where does the number 544
of traffic lights come from? It doesn’t have any explanation of it. It has two
feasibility pages which I’m confused so I went through the XML page and realized
that they are in different types. I feel like it can be one page with two
paragraphs. In this draft, it doesn’t have the report page and financial page. I
think it won’t hurt to have these two pages since they are the part of the schema
and may influence the audience’s decision after they read the report. In the risk
analysis page, the author should not only mention the risk but also explain how will
this project reduce some of the risk. You can’t let people know the risk but no
solving plans to it. Also, how is the current Boston traffic signal set up? Why does
it need to be changed into a neural network? I think it will be better if the author
mentioned these. The author uses most of the schema in the same way that we think
when we develop the schema. In the success criteria, I’m not sure it we need more
words to explain it or just do the same as the author did in bullet points? The
schema is well formed and easy to use, thus, the rules of the schema is easy to
follow as the author did. </p>
</report>
<reviewer type="instructor" xml:id="kgs"/>
<report type="instructor" resp="#kgs">
<p>I like that you continued this project from the annotated bibliogrpahy; I feel like
the feasibility report really invites this kind continuation. As far as your
report--I think the strength is in the clarity of the writing and the detail--this
is particularly evident in the success criteria and report pages, which are very
well done. I also think you responded and revised in a productive way following peer
review. One question I have (and this maybe goes back to schema design) is about how
sources are generally cited in this genre? I see some areas where specific numbers,
etc. are used that I would assume have an accompanying reference. These are small
issues, though. On the whole this is very well done.</p>
</report>
</docReview>
</DOC>