About
WHAT I DO: I help car-sharing companies • vacation property • real estate sales • primary…
Articles by Yue
Activity
-
Startups demand a long-term commitment, often consuming three to five years of your life. If you’re not ready to commit, it might not be the right…
Startups demand a long-term commitment, often consuming three to five years of your life. If you’re not ready to commit, it might not be the right…
Liked by Yue Wang
-
Today, I attended the last horse race at the Singapore Turf Club, soaking in the atmosphere as the country bid farewell to an iconic establishment…
Today, I attended the last horse race at the Singapore Turf Club, soaking in the atmosphere as the country bid farewell to an iconic establishment…
Liked by Yue Wang
-
Am honoured to be participating as a panelist at the Green Software Foundation's Global Summit in Singapore in October 2024, organised by Singapore's…
Am honoured to be participating as a panelist at the Green Software Foundation's Global Summit in Singapore in October 2024, organised by Singapore's…
Liked by Yue Wang
Experience
-
Safnect
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Education
Licenses & Certifications
Publications
-
Home and Work Place Prediction for Urban Planning Using Mobile Network Data
MDM 2014
We present methods to predict and validate home and work places of users using their mobile network data. Home and work place distribution of a city helps in making urban development decisions. In the literature many methods are presented to predict home and work places using GPS data. Unlike GPS data mobile network data do not provide exact locations of a phone event. This makes accurate prediction of home and work places more difficult for mobile network data. We use a novel criterion that…
We present methods to predict and validate home and work places of users using their mobile network data. Home and work place distribution of a city helps in making urban development decisions. In the literature many methods are presented to predict home and work places using GPS data. Unlike GPS data mobile network data do not provide exact locations of a phone event. This makes accurate prediction of home and work places more difficult for mobile network data. We use a novel criterion that combines an extracted feature from mobile data (i.e., inactivity – no phone event for a given period of time) with a 3rd party data about location category to predict the home location. Results show that the new criterion gives better prediction accuracy than inactivity alone. We predict work place using the idea that one goes to her work place on most of the weekdays but rarely on weekends. Validation of home and work place prediction is not straight forward. We validate our methods using correlation with 3rd party data. Multiple correlations between different statistics are performed to ensure reliability. Validation results show that our proposed methods are about 25% more accurate than existing methods both for the home and work place prediction.
Other authors -
Oscillation Resolution for Mobile Phone Cellular Tower Data to Enable Mobility Modelling
2014 MDM
One major problem of using location data collected from mobile cellular networks for mobility modelling is the oscillation phenomenon. An oscillation occurs when a mobile phone intermittently switches between cell towers instead of connecting to the nearest cell tower. For the purpose of mobility modeling, the location data needs to be cleansed to approximate the mobile device’s actual location. However, this constitutes a challenge because the mobile device’s true location is not known.
In…One major problem of using location data collected from mobile cellular networks for mobility modelling is the oscillation phenomenon. An oscillation occurs when a mobile phone intermittently switches between cell towers instead of connecting to the nearest cell tower. For the purpose of mobility modeling, the location data needs to be cleansed to approximate the mobile device’s actual location. However, this constitutes a challenge because the mobile device’s true location is not known.
In this paper, we study the oscillation resolution problem. We propose an algorithm framework called DECRE (Detect, Expand, Check, REmove) to detect and remove oscillation logs. To make informed decisions DECRE includes four steps: Detect, to identify log sequences that may contain oscillation using a few heuristics based on the concepts of stable period and moving at impossible speed; Expand, to look before and after suspicious records to gain more information; Check, to check whether a cell tower is observed repeatedly (which is a strong indication of oscillation); and REmove, resolving oscillation by selecting a cell tower to approximate the mobile device’s actual location.
Our experimental results on travel diaries show that our oscillation resolution approach is able to remove records that are far from mobile device’s ground-truth locations, improve the quality of the location data, and performs better than an existing method. Our performance study on large scale cell tower data shows that the MapReduce implementation of our approach is able to process 1 Terabyte of cell tower data in a few hours using a small cluster.Other authors
Courses
-
Advanced statistic theory
-
-
Bayesian hierarchical modeling
-
-
Bioinformatics & Biocomputing
-
-
Categorical data analysis
-
-
Decision making technologies
-
-
Foundation in algorithms
-
-
Neural Network
-
-
Quantitative epidemiological methods
-
-
Statistical learning and data mining
-
-
Stochastic analysis in mathematical finance
-
-
Uncertainty modeling in AI
-
Projects
-
Analyze high-dimensional phenotype data for Alzheimer's disease
-
We studied the genome-‐wide scale of data with millions of SNPs and thousands of case-‐control samples. Instead of studying SNP-‐by-‐SNP association with phenotypes, we studied the association between a pair of SNPs and phenotypes. This can boost the power of detecting the “missing heritability” while in the mean time making the computation grows exponentially. We studied the state-‐of-‐the-‐art methods [2] and empirically observed that exhaustive methods gain the highest power. Based on…
We studied the genome-‐wide scale of data with millions of SNPs and thousands of case-‐control samples. Instead of studying SNP-‐by-‐SNP association with phenotypes, we studied the association between a pair of SNPs and phenotypes. This can boost the power of detecting the “missing heritability” while in the mean time making the computation grows exponentially. We studied the state-‐of-‐the-‐art methods [2] and empirically observed that exhaustive methods gain the highest power. Based on this, we developed the first ever cloud based method called eCEO[3,4] (efficient cloude epistasis computing model in GWAS). This method provides user the flexibility to test the epistasis based on their need and budget.
Honors & Awards
-
Cloudera Certified Developer for Apache Hadoop (CCDH)
Cloudera
Individuals who achieve Cloudera Certified Developer for Apache Hadoop (CCDH) accreditation have demonstrated their technical knowledge, skill, and ability to write, maintain, and optimize Apache Hadoop development projects.
-
First place in 2014 Singtel lifespark hackthon
Singtel lifespark BU
Back for the second time this year, L!feSpark hosted the SingTel’s inaugural internal hackathon, facilitated by Pollenizer. From 6th to 8th November (Thursday – Saturday), creative individuals from all parts of SingTel will come together to validate their business concepts into working prototypes over an intense 60 hours period. L!feSpark hackthon is open to all SingTel Singapore employees and wholly-owned subsidiaries,there are 5 teams from Australia and 2 teams from US in this contest.
-
SingTel SPOT Awards
Singtel
-
Singtel employee of the month
DataSpark, Singtel
Recommendations received
1 person has recommended Yue
Join now to viewMore activity by Yue
-
AI/ML Model validation is important for ensuring the model is safe, effective and deployable. But how to evaluate? In this paper published in PLOS…
AI/ML Model validation is important for ensuring the model is safe, effective and deployable. But how to evaluate? In this paper published in PLOS…
Liked by Yue Wang
-
It’s finally happened! The inaugural opening of our center of AI in Medicine in NTU (C-AIM). This exciting new initiative is the culmination of…
It’s finally happened! The inaugural opening of our center of AI in Medicine in NTU (C-AIM). This exciting new initiative is the culmination of…
Liked by Yue Wang
-
Have a gathering with students and grand-students in Guangzhou VLDB last week. The event coincid with Teachers day (in Singapore) and my 23th…
Have a gathering with students and grand-students in Guangzhou VLDB last week. The event coincid with Teachers day (in Singapore) and my 23th…
Liked by Yue Wang
-
🚀 Applications Now Open for NUS Graduate Research Innovation Programme (NUS GRIP)! 🚀 We are excited to announce that the application period for…
🚀 Applications Now Open for NUS Graduate Research Innovation Programme (NUS GRIP)! 🚀 We are excited to announce that the application period for…
Liked by Yue Wang
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Yue Wang in Singapore
-
Yue Wang
IT Graduate Program at Amadeus
-
Yue Wang
-
YUE WANG
MBA Candidate at Singapore Management University
-
Yue Wang
75 others named Yue Wang in Singapore are on LinkedIn
See others named Yue Wang