BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-2026//speaker//TTGDWD
BEGIN:VTIMEZONE
TZID:JST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:JST
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-2026-GXDADF@talks.osgeo.org
DTSTART;TZID=JST:20260901T170000
DTEND;TZID=JST:20260901T173000
DESCRIPTION:Traffic congestion at signalized intersections is a common issu
 e in urban cities\, which is often caused by static and inefficient traffi
 c light timings that cannot adapt to changing traffic conditions. These lo
 ng wait times lead to a significant amount of time loss\, higher car emiss
 ions\, and higher fuel usage. During peak hours or unforeseen disruptions\
 , traditional traffic light control systems that rely on preset or time-of
 -day-based signal cycles are unfit to handle the dynamic and variable natu
 re of traffic volumes which resulting in slow vehicle movement and increas
 ed in travel time. In addition\, current traffic light control methods do 
 not include spatial data or intelligent prediction tools that are able to 
 analyze for unpredictable characteristic of traffic in urban areas. This g
 ap highlights that an adaptive method for signal optimization is required.
  Hence\, this study aims to derive the optimal traffic light timing at the
  junction by integrating Geographic Information System (GIS) and Artificia
 l Neural Network (ANN) models. Unlike the current fixed-time signal contro
 l practice\, ANN was chosen as it is one of the best machine learning tech
 niques that could be used in predictive modelling. It did not rely on huma
 n in making prediction instead\, it will learn solely on data without rely
 ing on manual assumptions or fixed timing. The historical and current traf
 fic volume data\, together with existing signal timing parameters\, were u
 sed to develop ANN models capable of predicting optimal green time allocat
 ions based on traffic demand patterns for each signal phase. \n\nIn this s
 tudy\, traffic signal optimisation is conducted for a selected signalised 
 intersection at Section 13\, Shah Alam\, Selangor\, Malaysia. The traffic 
 movement at the intersection is divided into multiple signal phases\, incl
 uding straight and right-turn movements from different approaches. Histori
 cal traffic volume data and current traffic volume data are used as input 
 variables in the ANN model\, while the existing signal timing serves as th
 e target output. The ANN model is trained to generate new optimal green ti
 me durations for each signal phase during morning and evening peak periods
 . To evaluate the effectiveness of the optimised signal timings\, microsco
 pic traffic simulation using SUMO is applied. The existing signal timing a
 nd the ANN-predicted optimal timing are simulated and compared using key p
 erformance indicators such as traffic volume discharge\, queue length\, an
 d average waiting time. Through this approach\, the study aims to assess h
 ow intelligent signal timing optimisation can enhance intersection perform
 ance and reduce traffic congestion. \n\nTraffic volume at intersections fl
 uctuates significantly between morning and evening peak hours\, as well as
  across different approaches and movement types. However\, the current sig
 nal timing plans apply uniform green times that may not correspond to actu
 al traffic conditions\, leading to congestion\, long queues\, and ineffici
 ent traffic flow. Therefore\, this study focuses on traffic volume charact
 eristics as the primary factor influencing signal timing optimisation\, sp
 ecifically historical traffic volume and current traffic volume for straig
 ht and right-turn movements. To address this problem\, the first objective
  of this study is to develop an ANN model to optimise traffic light signal
  timing. The model used historical traffic volume data as input variables\
 , current traffic volume data as predictor variables\, and existing signal
  timing as the target output. Through training\, validation\, and testing 
 processes\, the ANN model generated optimised green time durations for eac
 h signal phase based on five weeks of traffic observations. The results de
 monstrate that the ANN model is capable of producing adaptive signal timin
 gs that better reflect real traffic demand compared to conventional fixed-
 time control.\n\nThe SUMO software was used in this study to simulate the 
 optimized traffic signal timing produced by the ANN model. SUMO is an open
 -source\, microscopic traffic simulation software that enables detailed mo
 delling of road networks\, traffic flows\, and signal control systems. It 
 provides a flexible platform for evaluating how different signal timing co
 nfigurations affect traffic performance in terms of delay\, queue length\,
  and vehicle throughout. The traffic network for the selected study area w
 as imported from OSM into SUMO. The network editing and configuration were
  carried out in NETEDIT\, which is a graphical tool in SUMO used to edit a
 nd reorganize road geometry\, lane connections\, and traffic light control
  logic.\nThe simulation results demonstrate that the ANN-optimized signal 
 timings generally improved traffic performance compared to the existing si
 gnal plans. The SUMO simulation enables the evaluation of vehicle throughp
 ut by showing the number of vehicles that can pass through the intersectio
 n under the new signal timing configuration derived using ANN. The evaluat
 ion process involved running two (2) separate simulation scenarios\, exist
 ing fixed time signal timing and optimized signal timings produced by the 
 ANN model. By simulating these two conditions under almost the same traffi
 c demand\, the performance differences could be directly attributed to the
  signal timings adjustment. SUMO will automatically record several key per
 formance indicators (KPIs) during each running simulation\, such as vehicl
 e throughput using Simulation output detector. These indicators were then 
 compared the vehicle volume pass the traffic light intersection.\n\nIn con
 clusion\, it is possible for us to use ANN to predict and optimised the tr
 affic light signal timings based on existing traffic volume conditions. By
  employing historical traffic volume data\, the ANN model was able to gene
 rate optimal green times for multiple signal phases\, thereby instead of s
 etting traffic light timing based on personal experience\, assumptions or 
 manual decisions by engineers\, this study uses data and the ANN model to 
 decide the timings automatically. In addition\, the usage of SUMO for simu
 lation had helped in understanding how much the traffic volume can be cont
 rolled with optimized signal timings. This helps avoid human errors\, pers
 onal references or bias that may affect the traditional signal timing desi
 gn.
DTSTAMP:20260717T225807Z
LOCATION:Cosmos2
SUMMARY:Application of SUMO in Simulation of Optimized Traffic Light Timing
  derived using Artificial Neural Network and GIS - Nabilah Naharudin
URL:https://talks.osgeo.org/foss4g-2026/talk/GXDADF/
END:VEVENT
END:VCALENDAR