PRE2018 4 Group7

---

Group members:

Name	Student ID	Email	Study
Emiliyan Greshkov	1281666	e.greshkov@student.tue.nl	Insert
Thomas Janss	1006697	t.f.w.janss@student.tue.nl	Mechanical Engineering
Perry Kloet	1236356	p.a.j.kloet@student.tue.nl	Computer Science
Bram Schut	1019001	b.b.j.schut@student.tue.nl	Insert
Sem de Werdt	1017882	s.j.a.d.werdt@student.tue.nl	Insert

Relevant scientific papers:

Train (Thomas)

Abstract: These days, a lot of passengers are traveling with the train to work or other businesses. Finding a open spot to be seated is rather difficult. The occupancy is not divided proportionally among all train carriages. With …. , it is possible to complete know in advance how to board the train. A few things are necessary to know for this: - Type of train - Occupancy of the train Type of train: It is important to know which train is arriving at the platform. This way, proximity of the doors, disabled compartment, bicycle compartments, 1st class and 2nd class can be displayed. Type of train can be found within the real-time database of NS. With position of the loc known as a fixed place at the platform, al doors also are known. Count people in the train: There are multiple objectives in counting people inside of the train: The first objective is counting the amount of open seats. The second thing is counting the amount of people standing in the coupé. The last thing is counting the amount of people boarding and de-boarding the train. An easy way of counting the amount of people would be infrared cameras. Together with software that can determine the direction of movement, the number of people inside a coupé could be measured (2). What about privacy? (6) To list some other application of counting the people, see (5)

  Manual (Turnstiles) 
  Infrared (IR) beams
  Infrared optic sensors;
  Low ultrasonic frequency sensors, and
  Treadle mats. (Load cells)
  Video camera

In most cases, a Arduino with a wifi connection will suffice. Data transfer to a general data center: This data should be sent to data centers in a secure manner. Thus, this includes the train to have a proper connection to the internet and a working firewall. The datacenter then can send all the data to the platforms, where ….. will display all the information. There are several protocols for this data transfer. We should at least investigate this a little. Display at the platform:

Overhead LED-display with detailed information, like arrival time and carriage occupancy. In-platform LED strips to guide. Interactive screens at the start of the platform reminding the user to seek the best spot. Extend this to an application where people can see the same information as at the platform itself. Display in the train: When inside the train, the exact free spots (upper or lower floor) can be visualized. In such a way, people can find their spot in the quickest way. This is for example done in (4).
Examples: Dilax: (3) Dilax is a company, specialized in determining amount of people in rooms. They already have applications in airports and train stations. Three things that DILAX considers is: • Connecting and disconnecting trains during a journey • Combining cars with and without passenger counting system • Deploying first and second-class cars or separated compartments within cars. Alstom: Used in metro application. Uses different kind of comfort level color. Since people tend to move to higher comfort level colors, boarding behavior of passengers can be influenced. This also has a positive influence on boarding times (1) (4) Pressure sensors inside of the seats are used to validate if there is a person sitting on the chair. NOTE, this would be feasible to test and validate with a scaled prototype. NOTE: Could we maybe add never ending trains? Subtrains that transport people from platform to fast-moving train.

1) https://www.alstom.com/our-solutions/digital-mobility/optimet-real-time-train-occupancy-smoother-passenger-flow-platforms
2) https://www.researchgate.net/publication/280735165_A_robust_system_for_counting_people_using_an_infrared_sensor_and_a_camera
3) https://www.dilax.com/en/public-mobility/portfolio/seat-management/
4) https://www.researchgate.net/publication/323027620_Smart_Bus_An_Automated_Passenger_Counting_System
5) https://www.google.nl/url?sa=t&rct=j&q=&esrc=s&source=web&cd=21&cad=rja&uact=8&ved=2ahUKEwiCudCpgPbhAhUJr6QKHRJQBlM4ChAWMAp6BAgIEAI&url=https%3A%2F%2Fpdfs.semanticscholar.org%2F55a0%2F9a9adb1e7905f99607846f7a286e3f39bf17.pdf&usg=AOvVaw0ZK1-RYUZ15nYZshrA0cHs
6) https://www.usenix.org/legacy/events/hotos03/tech/full_papers/gruteser/gruteser_html/

Traffic light (Thomas)

(2) is impying an interesting objective to our system. These days, intersections can be jammed due to cars being on it while they should wait. This could be controlled using cameras (1) that supply the data to a computer chip for image recognition and processing. A big player in this kind of technology is MARLIN. MARLIN is a system that is tested in Toronto. It can be either used to control a single intersection, or multiple intersections could work together(1). The latter option is the best option to go for, since optimal connecting waiting times can be generated by controlling outgoing vehicles on previous intersections (3). To determine urgency of different vehicles, fuzzy logic can be used (3). Small setups has been done by (4). This system consists out of three parts: An environment, a gateway + script and the IoT.

1) https://ieeexplore.ieee.org/document/7313288
2)https://www.youtube.com/watch?v=v2CC0t7oKBw
3) https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8652045
4) https://ieeexplore-ieee-org.dianus.libr.tue.nl/stamp/stamp.jsp?tp=&arnumber=8656717

Traffic light

Traffic light control systems can be split into single intersection systems (1), which are fairly straightforward, or multi-agent sytems, such as in (2) (using reinforcement learining) or (3). Strategies for designing intelligent traffics lights someghimes include fuzzy logic (4), measuring the car density using cameras (5), or optimising the throughput of junctions (6).
(7) looks specifically at pedestrians crossing the road

1) https://www.sciencedirect.com/science/article/pii/S0947358098701190 2) https://dspace.library.uu.nl/bitstream/handle/1874/20827/wiering_00_multi.pdf?sequence=2 3) https://dspace.library.uu.nl/bitstream/handle/1874/17996/wiering_04_intelligent_traffic.pdf?sequence=2 4) https://ejournal.um.edu.my/index.php/MJCS/article/view/2995 5) http://www.retawprojects.com/uploads/density-based-traffic-signal-system.pdf 6) https://ieeexplore.ieee.org/abstract/document/5594435 7) http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.511.5913&rep=rep1&type=pdf