A General Framework for Unmet Demand Prediction in On-Demand Transport Services

Li, Wengen; Cao, Jin Xin; Guan, Jihong; Zhou, Shuigeng; Liang, Guanqing; So, Winnie K. Y.; Szczecinski, Michal

doi:10.1109/tits.2018.2873092

Cited by 28 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the more advanced tasks, it becomes a challenge for humans to create the algorithm manually. In actual practice, it becomes an effective platform to create own algorithms with the help of machine rather than program with expected specifications [63][64][65].…”

Section: Concept Of Machine Learningmentioning

confidence: 99%

Implementing Machine Learning for Supply-Demand Shifts and Price Impacts in Farmer Market for Tool and Equipment Sharing

Rakhra

Bhargava

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

Several industries have recently seen the replacement of human labor by automated machinery and equipment. Across the globe, farmers’ attitudes on the use of technology in agriculture are divergent. However, although some people are excited and ready to embrace technology, others are cautious and wary of trying new technologies for the first time. The third category is particularly prevalent in underdeveloped nations such as India, owing to a lack of competence, a lack of effective translation, and most crucially, a lack of financial resources. It is fruitless for the government to attempt to resolve these difficulties due to the fact that they do not take into consideration the changing circumstances and input needs of each agricultural group. Smart Tillage is a cutting-edge framework that was developed to solve the challenges listed above. In India, a decision-based smart engine for the rental and sharing of tools and equipment has been developed, which leverages machine learning methods to proceed towards a selection of tools and equipment. The option is entirely reliant on a variety of input variables, including crop kind, harvest time/month, crop equipment needed, harvest type, and the amount of money available for rental. Additionally, an ideal recommendation engine driven by content and collaborative-based filtering will provide the farmer’s requirements depending on their requirements. In terms of escalation, the proposals would be cost-effective and excellent since they would need little changes in training, technique improvements, and resource management via a new rent-share model similar to that used by Uber. In this work, demand and supply algorithms are used to define market equilibrium, and the results are shown in graphs. This includes discussion of a variety of demand and supply parameters, their impact on market equilibrium prices and quantities, and their effect on shifting demand and supply curves. The many sorts of elasticities (demand, cross-price, supply, income, and so on) are examined, as well as the ramifications for pricing systems that may result from these elasticities.

show abstract

Section: Concept Of Machine Learningmentioning

confidence: 99%

Implementing Machine Learning for Supply-Demand Shifts and Price Impacts in Farmer Market for Tool and Equipment Sharing

Rakhra

Bhargava

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

show abstract

“…Classic machine learning methods such as regression models [14] have been used to predict traffic based on human engineered features, such as orders placed by passengers, drivers' trajectories, points of interest (POI), and weather. Such methods require extensive human efforts in feature engineering and training data preparation.…”

Section: Traditional Methodsmentioning

confidence: 99%

A Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction

Zhao

Tanin

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Traffic prediction is an important and yet highly challenging problem due to the complexity and constantly changing nature of traffic systems. To address the challenges, we propose a graph and attentive multi-path convolutional network (GAMCN) model to predict traffic conditions such as traffic speed across a given road network into the future. Our model focuses on the spatial and temporal factors that impact traffic conditions. To model the spatial factors, we propose a variant of the graph convolutional network (GCN) named LPGCN to embed road network graph vertices into a latent space, where vertices with correlated traffic conditions are close to each other. To model the temporal factors, we use a multi-path convolutional neural network (CNN) to learn the joint impact of different combinations of past traffic conditions on the future traffic conditions. Such a joint impact is further modulated by an attention generated from an embedding of the prediction time, which encodes the periodic patterns of traffic conditions. We evaluate our model on real-world road networks and traffic data. The experimental results show that our model outperforms state-of-art traffic prediction models by up to 18.9% in terms of prediction errors and 23.4% in terms of prediction efficiency.

show abstract

“…Recent decades have witnessed the rapid development of human sensing using various modalities [9,42,43,51,52]. It also facilitates a wide range of applications [8,22,23,31]. Here we discuss three research areas that are most related including voice activity detection, gender identi cation, and personality computing.…”

Section: Related Workmentioning

confidence: 99%

User Profiling Based on Nonlinguistic Audio Data

ShenJiaxing

CaoJiannong

LedermanOren

et al. 2021

ACM Trans. Inf. Syst.

Self Cite

View full text Add to dashboard Cite

User profiling refers to inferring people’s attributes of interest ( AoIs ) like gender and occupation, which enables various applications ranging from personalized services to collective analyses. Massive nonlinguistic audio data brings a novel opportunity for user profiling due to the prevalence of studying spontaneous face-to-face communication. Nonlinguistic audio is coarse-grained audio data without linguistic content. It is collected due to privacy concerns in private situations like doctor-patient dialogues. The opportunity facilitates optimized organizational management and personalized healthcare, especially for chronic diseases. In this article, we are the first to build a user profiling system to infer gender and personality based on nonlinguistic audio. Instead of linguistic or acoustic features that are unable to extract, we focus on conversational features that could reflect AoIs. We firstly develop an adaptive voice activity detection algorithm that could address individual differences in voice and false-positive voice activities caused by people nearby. Secondly, we propose a gender-assisted multi-task learning method to combat dynamics in human behavior by integrating gender differences and the correlation of personality traits. According to the experimental evaluation of 100 people in 273 meetings, we achieved 0.759 and 0.652 in F1-score for gender identification and personality recognition, respectively.

show abstract

A General Framework for Unmet Demand Prediction in On-Demand Transport Services

Cited by 28 publications

References 26 publications

Implementing Machine Learning for Supply-Demand Shifts and Price Impacts in Farmer Market for Tool and Equipment Sharing

Implementing Machine Learning for Supply-Demand Shifts and Price Impacts in Farmer Market for Tool and Equipment Sharing

A Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction

User Profiling Based on Nonlinguistic Audio Data

Contact Info

Product

Resources

About