ABSTRACT This paper introduces a new method for identifying the best planning option for Intermodal Freight Transportation Terminals (IFTTs) under uncertain conditions, utilizing Timed Colored Petri Nets (TCPNs) and cross‐efficiency Fuzzy Data Envelopment Analysis (DEA). The possible planning options for congestion are modeled with TCPN to obtain the behavior of the IFTT in its operational conditions. The performance indicators are calculated as fuzzy triples. Then, cross‐efficiency Fuzzy DEA is employed to compare and rate the planning options. The results show that this approach obtains the best planning option under uncertainty by considering fuzzy solutions to represent each performance indicator's possible range of values. The method allows IFTT decision‐makers to see the full range of possible outcomes compared to the deterministic method and make the best decisions.

Abstract Falling is one of the major health concerns, and its early detection is very important. The goal of this study is an early prediction of impending falls using wearable sensors data. The SisFall data set has been used along with two deep learning models (CNN and a combination model named Conv_Lstm). Also, a dynamic sampling method is offered to improve the accuracy of the models by increasing the equilibrium rate between the samples of the majority and minority classes. To fulfill the main idea of this paper, we present a future prediction strategy. Then, by defining a time variable ‘T’, the system replaces and labels the state of the next T s instead of considering the current state only. This leads to predicting falling states at the beginning moments of balance disturbance. The results of the experiments show that the Conv_Lstm model was able to predict the fall in 78% of cases and an average of 340 ms before the accident. Also, for the Sensitivity criterion, a value of 95.18% has been obtained. A post-processing module based on the median filter was implemented, which could increase the accuracy of predictions to 95%.

Abstract Human activity recognition (HAR) systems employing wearable sensors are a promising area of research for tracking human activity. Recently, wearable devices such as smartwatches and sensors have been developed for activity recognition and monitoring. These systems aim to obtain the subject’s state within his or her environment by exploiting heterogeneous sensors attached to the body. With the development of deep learning, new strategies have emerged to facilitate and solve the HAR problems. In this work, a deep multilayer bidirectional long-short memory (Bi-LSTM) architecture has been implemented to detect human activities. Instead of training a single model as in traditional LSTM methods, two models are presented in the Bi-LSTM scheme, one for learning the input data sequence and the other for learning the reverse sequence. Finally, a new novel postprocessing approach has been proposed based on windowing and voting in the last step to improve the average F1 score. Comprehensive investigations on the three publicly available datasets consisting of a different set of activities were used to evaluate the performance of the proposed framework. The empirical results of this paper on AReM, Mhealth and PAMAP2 datasets attained 95.46, 95.79 and 93.41% average F1 score, respectively. The results also revealed that selecting the window size and implementing the appropriate voting method has a significant effect on improving the average percentage of the F1 score.

Abstract Human activity recognition has been a popular research topic in recent years. The rapid development of deep learning techniques has greatly helped researchers to achieve success in this field. During the training process with deep learning techniques, features and time dependencies between them are well learned. However, researchers generally ignore the distribution of extracted features in the coordinate space despite their significant effect on classification and network convergence status. The present article utilizes a simple but effective centralized coordinate learning method that dispersedly spans extracted features across the coordinate space. This method causes the angle between the features of different classes to increase significantly. A hybrid loss function is also suggested to enhance the discriminative power of learned features. Some experiments were carried out on the OPPORTUNITY and the PAMAP2 datasets. The results showed that the proposed method outperformed the recently proposed deep learning methods, including the Deep ConvLSTM, CNN‐LSTM‐ELM, and Hybrid methods. This high efficiency was due to the identification of discriminative features.

Abstract Today, a directional sensor network is a popular environment for solving the target coverage problem. Monitoring all targets in a DSN is a crucial challenge to scholars working in this field of study. Adjusting the angle and range of the sensors can be an efficient technique for improving the network performance. In this way, the network has the most extended lifespan and, at the same time, spends the least time to find the best cover set. In this method, each sensor dynamically adjusts its own sensing angle in order to find the targets by choosing the best range. The present study proposed a continuous learning automata‐based method to choose the optimum sensing angle for the sensors in a DSN. Then, to evaluate the proposed algorithm performance, its results were compared to those of a conventional automata‐based method whose algorithm worked based on continuous automata. The comparative analysis confirmed the superiority of the proposed method over the conventional automata‐based method regarding the extension of the network lifespan.

Abstract Accurate prediction of a user's movement path has various advantages for many applications, such as optimising a nurse's trajectory in a hospital and assisting elderly or disabled people and making them feel secure and protected in the places where they live. Recently, researchers have suggested techniques based on machine learning and deep learning in this field. However, these approaches have drawbacks such as their low accuracy in classifying the extracted features into associated movement paths, high sensitivity to noisy data, and ignoring time dependencies within raw data. In this work, a three‐phase stacked method named CNN‐LSTM‐FSC is proposed, which uses the Convolutional Neural Network (CNN), Long Short‐Term Memory (LSTM), and Fuzzy Soft‐max Classifier (FSC) to overcome the mentioned constraints. In the first phase, the CNN structure extracts time dependencies within raw data using the stacked convolutional and pooling layer. In the second phase, the long‐term time dependency of the user's movement path is learnt using the LSTM layers, and the user path is determined using a new innovated fuzzy soft‐max classifier. Finally, in the post‐processing phase, by performing a majority voting technique on the k‐adjacent sample predictions of the classifier, the authors have tried to reduce the effects of noise in identifying the user's movement path. Experiments were conducted on the MovementAAL_RSS dataset. The proposed method has successfully reached 93.86%, 93.71%, and 93.26% accuracy rate on the MovementAAL_RSS datasets, with 0%, 5%, and 10% Gaussian noise, respectively, and demonstrates superior results in comparison to the previous literature research.

Summary Providing a pool of various resources and services to customers on the Internet in exchanging money has made cloud computing as one of the most popular technologies. Management of the provided resources and services at the lowest cost and maximum profit is a crucial issue for cloud providers. Thus, cloud providers proceed to auto‐scale the computing resources according to the users' requests in order to minimize the operational costs. Therefore, the required time and costs to scale‐up and down computing resources are considered as one of the major limits of scaling which has made this issue an important challenge in cloud computing. In this paper, a new approach is proposed based on MAPE‐K loop to auto‐scale the resources for multilayered cloud applications. K‐nearest neighbor (K‐NN) algorithm is used to analyze and label virtual machines and statistical methods are used to make scaling decision. In addition, a resource allocation algorithm is proposed to allocate requests on the resources. Results of the simulation revealed that the proposed approach results in operational costs reduction, as well as improving the resource utilization, response time, and profit.