Search Results (8)

Efficient sales route optimization is a critical challenge in logistics and distribution, especially under real-world conditions involving traffic variability and dynamic constraints. This study proposes a novel Hybrid Genetic Algorithm (GAAM-TS) that integrates Adaptive Mutation, Tabu Search, and an LSTM-based travel time prediction model to enable real-time, intelligent route planning. The approach addresses the limitations of traditional genetic algorithms by enhancing solution quality, maintaining population diversity, and incorporating data-driven traffic estimations via deep learning. Experimental results on real-world data from the NYC Taxi dataset show that GAAM-TS significantly outperforms both Standard GA and GA-AM variants, achieving up to 20% improvement in travel efficiency while maintaining robustness across problem sizes. Although GAAM-TS incurs higher computational costs, it is best suited for offline or batch optimization scenarios, whereas GA-AM provides a balanced alternative for near-real-time applications. The proposed methodology is applicable to last-mile delivery, fleet routing, and sales territory management, offering a scalable and adaptive solution. Future work will explore parallelization strategies and multi-objective extensions for sustainability-aware routing. Full article

Accurate traffic prediction is crucial for optimizing taxi demand, managing traffic flow, and planning public transportation routes. Traditional models often fail to capture complex spatial–temporal dependencies. To tackle this, we introduce the Spatio-Temporal Embedding Fusion Transformer (STEFT). This deep learning model leverages attention mechanisms and feature fusion to effectively model dynamic dependencies in traffic data. STEFT includes an Embedding Fusion Network that integrates spatial, temporal, and flow embeddings, preserving original flow information. The Flow Block uses an enhanced Transformer encoder to capture periodic dependencies within neighboring regions, while the Prediction Block forecasts inflow and outflow dynamics using a fully connected network. Experiments on NYC (New York City) Taxi and NYC Bike datasets show STEFT’s superior performance over baseline methods in RMSE and MAPE metrics, highlighting the effectiveness of the concatenation-based feature fusion approach. Ablation studies confirm the contribution of each component, underscoring STEFT’s potential for real-world traffic prediction and other spatial–temporal challenges. Full article

This paper aims to leverage Twitter data to understand travel mode choices during the pandemic. Tweets related to different travel modes in New York City (NYC) are fetched from Twitter in the two most recent years (January 2020–January 2022). Building on these data, we develop travel mode classifiers, adapted from natural language processing (NLP) models, to determine whether individual tweets are related to some travel mode (subway, bus, bike, taxi/Uber, and private vehicle). Sentiment analysis is performed to understand people’s attitudinal changes about mode choices during the pandemic. Results show that a majority of people had a positive attitude toward buses, bikes, and private vehicles, which is consistent with the phenomenon of many commuters shifting away from subways to buses, bikes and private vehicles during the pandemic. We analyze negative tweets related to travel modes and find that people were worried about those who did not wear masks on subways and buses. Based on users’ demographic information, we conduct regression analysis to analyze what factors affected people’s attitude toward public transit. We find that the attitude of users in the service industry was more easily affected by MTA subway service during the pandemic. Full article

Taxi travel time estimation based on real-time traffic flow collection in IoT has been well explored; however, it becomes a challenge to use the limited taxi data to estimate the travel time. Most of the existing methods in this scenario rely on shallow feature engineering. Nevertheless, they have limited performance in learning complex moving patterns. Thus, a Latent Semantic Pulse Sequence-based Deep Neural Network (LSPS-DNN) is proposed in this paper to improve the taxi travel time estimation performance by constructing a latent semantic propagation graph representing the latent path sequence. It first extracts the shallow modal features of trips, such as the time period and spatial location at different granularities. The representation of the pulse propagation graph is then extracted from shallow spatial features using a Pulse Coupled Neural Network (PCNN). Further, the propagation graph is encoded with negative sampling to obtain the embedding of deep propagation features between ODs. Meanwhile, we conduct deep network learning based on the Chengdu and NYC taxi datasets; our experimental evaluation results show it has a better performance compared to traditional feature construction methods. Full article

Traffic flow forecasting is a critical input to intelligent transportation systems. Accurate traffic flow forecasting can provide an effective reference for implementing traffic management strategies, developing travel route planning, and public transportation risk assessment. Recent deep learning approaches of spatiotemporal neural networks to predict traffic flow show promise, but could be difficult to separately model the spatiotemporal aggregation in traffic data and intrinsic correlation or redundancy of spatiotemporal features extracted by the filter of the convolutional network. This can introduce biases in the predictions that interfere with subsequent planning decisions in transportation. To solve the mentioned problem, the filter attention-based spatiotemporal neural network (FASTNN) was proposed in this paper. First, the model used 3-dimensional convolutional neural networks to extract universal spatiotemporal dependencies from three types of historical traffic flow, the residual units were employed to prevent network degradation. Then, the filter spatial attention module was constructed to quantify the spatiotemporal aggregation of the features, thus enabling dynamic adjustment of the spatial weights. To model the intrinsic correlation and redundancy of features, this paper also constructed a lightweight module, named matrix factorization based resample module, which automatically learned the intrinsic correlation of the same features to enhance the concentration of the model on information-rich features, and used matrix factorization to reduce the redundant information between different features. The FASTNN has experimented on two large-scale real datasets (TaxiBJ and BikeNYC), and the experimental results show that the FASTNN has better prediction performance than various baselines and variant models. Full article

Taxi demand forecasting plays an important role in ride-hailing services. Accurate taxi demand forecasting can assist taxi companies in pre-allocating taxis, improving vehicle utilization, reducing waiting time, and alleviating traffic congestion. It is a challenging task due to the highly non-linear and complicated spatial-temporal patterns of the taxi data. Most of the existing taxi demand forecasting methods lack the ability to capture the dynamic spatial-temporal dependencies among regions. They either fail to consider the limitations of Graph Neural Networks or do not efficiently capture the long-term temporal dependencies. In this paper, we propose a Spatial-Temporal Diffusion Convolutional Network (ST-DCN) for taxi demand forecasting. The dynamic spatial dependencies are efficiently captured through a two-phase graph diffusion convolutional network where the attention mechanism is introduced. Moreover, a novel temporal convolution module is designed to learn various ranges of temporal dependencies, including recent, daily, and weekly periods. Inside the module, convolution layers are stacked to handle very long sequences. Experimental results on two large-scale real-world taxi datasets from New York City (NYC) and Chengdu demonstrate that our method significantly outperforms seven state-of-the-art baseline methods. Full article

Millions of individuals rely on urban transportation every day to travel inside cities. However, it is not clear how route parameters (e.g., traffic conditions, waiting times) influence users when selecting a particular route option for their trips. These parameters play an important role in route recommendation systems, and most of the currently available applications omit them. This work introduces a new hybrid-multimodal routing algorithm that evaluates different routes that combine different transportation modes. Hybrid-multimodal routes are route options that might consist of more than one transportation mode. The motivation to use different transportation modes is to avoid unpleasant trip segments (e.g., traffic jams, long walks) by switching to another mode. We show that the possibility of planning a trip with different transportation modes can lead to improvement of cost, duration, and quality of experience urban trips. We outline the main research contributions of this work, as (i) an user experience model that considers time, price, active transportation (i.e., non-motorized transport) acceptability, and traffic conditions to evaluate the hybrid routes; and, (ii) a flow clustering technique to identify relevant mobility flows in low-sampled datasets for reducing the data volume and allow the execution of the analytical evaluation. (i) uses a Discrete Choice Analyses framework to model different variables and estimate a value for user experience in the trip. (ii) is a methodology to aggregate mobility flows by using Spatio-temporal Clustering and identify the most relevant of these flows using Curvature Analysis. We evaluate the proposed hybrid-multimodal routing algorithm with data from the Green and Yellow Taxis of New York, Citi Bike NYC data, and other publicly available datasets; and, different APIs, such as Uber and Google Directions. The results reveal that selecting hybrid routes can benefit passengers by saving time or reducing costs, and sometimes both, when compared to routes using a single transportation mode. Full article

Anomaly detection refers to the problem of identifying abnormal behaviour within a set of measurements. In many cases, one has some statistical model for normal data, and wishes to identify whether new data fit the model or not. However, in others, while there are normal data to learn from, there is no statistical model for this data, and there is no structured parameter set to estimate. Thus, one is forced to assume an individual sequences setup, where there is no given model or any guarantee that such a model exists. In this work, we propose a universal anomaly detection algorithm for one-dimensional time series that is able to learn the normal behaviour of systems and alert for abnormalities, without assuming anything on the normal data, or anything on the anomalies. The suggested method utilizes new information measures that were derived from the Lempel–Ziv (LZ) compression algorithm in order to optimally and efficiently learn the normal behaviour (during learning), and then estimate the likelihood of new data (during operation) and classify it accordingly. We apply the algorithm to key problems in computer security, as well as a benchmark anomaly detection data set, all using simple, single-feature time-indexed data. The first is detecting Botnets Command and Control (C&C) channels without deep inspection. We then apply it to the problems of malicious tools detection via system calls monitoring and data leakage identification.We conclude with the New York City (NYC) taxi data. Finally, while using information theoretic tools, we show that an attacker’s attempt to maliciously fool the detection system by trying to generate normal data is bound to fail, either due to a high probability of error or because of the need for huge amounts of resources. Full article