User identification through smartphones and wearable sensors holds promise but faces challenges from similarity and variability in user activities. Visualization of smartphone acceleration signals revealed users’ signals exhibit high similarity, as activities share a common underlying structure. For example, walking elicits a repeated general pattern. Therefore, user identification relies on subtle distinguishing factors in fine activity details. At times, patterns are near-indistinguishable between users. To address this, we developed a method leveraging the assumption that prediction uncertainty increases for nonseparable samples. The input data is divided into subsequences, each independently predicted by a convolutional neural network. Predictions are fused through a weighted averaging scheme, where weights quantify prediction uncertainty using the Monte Carlo dropout method. Through experiments on five real-world data sets, the study demonstrates improved performance in identifying users across a range of activities compared to existing methods. It was also directly compared to state-of-the-art methods using two well-known data sets, improving accuracy by 1.29% in one case and 7.98% in the other. These findings validate the effectiveness of the new approach for continuous user identification, even when faced with unpredictable user behavior.

This paper presents an enhanced approach to user identification using smartphone and wearable sensor data. Our methodology involves segmenting input data and independently analyzing subsequences with CNNs . During testing, we apply calibrated Monte-Carlo Dropout to measure prediction uncertainty. By leveraging the weights obtained from uncertainty quantification , we integrate the results through weighted averaging, thereby improving overall identification accuracy. The main motivation behind this paper is the need to calibrate the CNN for improved weighted averaging. It has been observed that incorrect predictions often receive high confidence, while correct predictions are assigned lower confidence. To tackle this issue, we have implemented the Ensemble of Near Isotonic Regression (ENIR) as an advanced calibration technique. This ensures that certainty scores more accurately reflect the true likelihood of correctness. Furthermore, our experiment shows that calibrating CNN reduces the need for Monte Carlo samples in uncertainty quantification , thereby reducing computational costs. Our thorough evaluation and comparison of different calibration methods have shown improved accuracy in user identification across multiple datasets. Our results showed notable performance improvements when compared to the latest models available. In particular, our approach achieved better results than DB2 by 1.12% and HAR by 0.3% in accuracy.

In recent research, clustering algorithms have been utilized to analyze smart card travel patterns. However, these methods often struggle due to the need for a predetermined number of clusters and the challenges posed by the curse of dimensionality. To address these issues and improve travel pattern recognition from smart-card transactions, a new framework has been proposed. This framework uses autoencoders to extract low-dimensional representations from transactions and an ensemble of deep clustering models to identify patterns. Additionally, it compares geodetic and network distances between stations for feature extraction. A key advantage of this approach is its ability to automatically determine the number of clusters and effectively mitigate overfitting using the Sharon index based on Rademacher complexity. When applied to the London metro smart card benchmark with more than 10,000 samples, the framework identified 7 clusters of travel patterns, compared to 3 clusters by baseline methods. Each cluster corresponds to a specific day of the week, uncovering distinct travel behaviors across the week. Furthermore, within each cluster, the framework detected three daily sub-patterns: morning peak, midday, and evening peak. This resulted in 21 unique travel patterns, allowing a detailed analysis of both weekday and weekend travel dynamics. These findings were validated using the Davies-Bouldin, Silhouette, and Calinski-Harabasz indices. The impact of the starting time for daily services has also been analyzed, showing that daily travel patterns are highly sensitive to this parameter.

This paper deals with fuzzy multi-depot bus scheduling (FMDBS) problem in which the objective function and constraints are defined with fuzzy attributes. Credibility relation is used to formulate the problem as an integer multicommodity flow problem. A novel combination of branch-and-price and heuristic algorithms, is proposed to efficiently solve FMDBS problem. In the proposed algorithm, the heuristic algorithm is applied to generate initial columns for the column generation method. Also, a heuristic algorithm is used to improve the generated solutions in each node of the branch-and-price tree. Two sets of benchmark examples are applied to demonstrate the efficiency of the proposed algorithm for large-scale instances. Also, the algorithm is applied to solve the classical multi-depot bus scheduling problem. The results show that the proposed algorithm decreases integrality gap and computational time in comparison with the state-of-the-art algorithms and normal branch-and-price algorithm. Finally, as a case study, the bus schedules in Tehran BRT network are generated.

Regular safety inspections of concrete and steel structures during their serviceability are essential since they directly affect the reliability and structural health. Early detection of cracks helps prevent further damage. Traditional methods involve the detection of cracks by human visual inspection. However, it is difficult to visually find cracks and other defects for extremely large structures because of time and cost constraints. Therefore, the development of smart inspection systems has been given utmost importance. We provide a deep convolutional neural network (DCNN) with transfer learning (TF) technique for crack detection. To reduce false detection rates, the images used to train in the TF technique come from two different datasets (CCIC and SDNET). Moreover, the designed CNN is trained on 3200 images of$256 \times 256$pixel resolutions. Different deep learning networks are considered and the experiments on test images show that the accuracy of the damage detection is more than 99%. Results illustrate the viability of the suggested approach for crack observation and classification.

Abstract With significant advances in vision and natural language processing, the generation of image captions becomes a need. Mathews, Xie, and He extended a new model to generate styled captions by separating semantics and style. In continuation of their work, here, a new captioning model is developed, including an image encoder to extract the features, a mixture of recurrent networks to embed the set of extracted features to a group of words, and a sentence generator that combines the obtained words as a stylized sentence. This Mixture of Recurrent Experts (MoRE) system uses a new training algorithm that derives singular value decomposition from weighting matrices of Recurrent Neural Networks (RNNs) to increase the diversity of captions. Each decomposition step depends on a distinctive factor based on the number of RNNs in MoRE. The used sentence generator gives a stylized language corpus without paired images. Besides, the styled and diverse captions are extracted without training on a densely labeled or styled dataset. MoRE on the COCO dataset generated diverse and stylized image captions without the necessity of extra‐labeling and improved descriptions in terms of content accuracy.

Driving style evaluation by smartphones depends on the quality of the features extracted from sensors data. Typically, these features are extracted based on experiments, expertness, or heuristics. In more modern approaches, some automatic methods such as convolutional neural network (CNN) are used to extract features including obvious and hidden ones. We also used the CNN on acceleration data collected by smartphones to extract the knowledge regarding driving style, vehicle, environment, and human characteristics. We found that this novel idea was more successful for evaluating the driving style compared with the previous machine learning algorithms. However, we faced over-fitting in the training process of the CNN and to avoid this, we proposed the state-of-the-art learning method applying two adaptive regularization schemes called adaptive dropout and adaptive weight decay. To evaluate these techniques, first, we checked the results on three popular large-scale datasets. When we proved the efficiency, we utilized them on two transportation data sets. In transportation-modes dataset, the accuracy was at least 95.8%'; and regarding the driving-style dataset, the classification accuracy was 95%. Thus, the adaptive regularized CNN is an amazing option for driving style evaluation on smartphones.

To protect vulnerable road users (VRU) like children and elderly, this paper presents a new warning system on smartphones. This system has three phases. First, we propose a new geometric approach to activate the system for necessary risky situations. Second, we extract some important features for VRUs and drivers based on their smartphones sensors to estimate the collision risk by using a fuzzy inference engine. Finally, we divide the warning alarms into low risk, medium risk, and high risk. To improve system accuracy, we consider the effects of vehicle acceleration, weather condition, time of day, pedestrian age, and driver age in our system and use 4G wireless communications between VRUs and drivers. Experimental results on 608 samples from six important types of accident situations show that our system for in danger VRUs, has 96% accuracy, 63% recall, and 90% precision. The improvements in accuracy, precision, and F-measure are 5%, 70%, and 42% compared with the previous works. Moreover, the activation phase of our system led to 400-ms reduction in run time while the accuracy improves 22%. Besides, on the random samples extracted from the accident simulator software, the accuracy, recall, and precision of the proposed system improve 98%, 75%, and 60%, which are better than the previous similar systems.

This paper develops a new rule-based decision support system (RB-DSS) to find the safest solutions for routing, scheduling, and assignment in Hazmat transportation management. To define the safe program in RB-DSS, the accident frequency and severity are estimated for different scenarios of transportation, and they are used to classify the scenarios by a new structure of decision tree (DT), which is proposed to select branching variables at the primary levels according to the experts' perception. The outputs of the DT are stated in the form of if-then rules trained by a multilayer perceptron neural network to generalize the safe programs for Hazmat transportation. To illustrate the performance of this approach, the UK road accident data set is used.

Fuzzy mathematics is a generalization in which fuzzy numbers replace real numbers and fuzzy arithmetic replaces real arithmetic. It is an excellent scope for modeling vague and uncertain aspects of the actual environments. In this important area, Dubois and Prade1 defined a fuzzy matrix as a rectangular array of fuzzy numbers. They have also defined the LR type fuzzy numbers with some useful approximate arithmetic operators. The aim of this paper is to extend some useful aspects of linear algebra e.g. determinant, norm and eigenvalue for fuzzy matrices with LR fuzzy number entries by the use of fuzzy arithmetic. Finally, applications in fuzzy analytical hierarchy process (AHP) are investigated.

When the outliers exist in the data set, fuzzy regression gives incorrect results. A few number of researchers considered this problem and proposed linear-programming-based methods and fuzzy least-squares methods to deal with the outliers problem. In this paper, we develop a new model along with a linear-programming-based approach for computation of fuzzy regression models. The problem of outliers is modeled with this approach. Two examples are illustrated to compare the performance of proposed approach with those given in literature. Results from numerical examples show that our approach gives good solutions.