Search

Convolutional Recurrent architectures are currently preferred for spatio-temporal learning tasks in videos to the 3D convolutional networks which accompany a huge computational burden and it is imperative to understand the working of different architectural configurations. But most of the current works on visual learning, especially for video anomaly detection, predominantly employ ConvLSTM networks and focus less on other possible variants of Convolutional Recurrent configurations for temporal learning which warrants a need to study the different possible variants to make informed, optimal design choices according to the nature of the application at hand. We explore a variety of Convolutional Recurrent architectures and the influence of hyper-parameters on their performance for the task of anomaly detection. Through this work, we also intend to quantify the efficiency of the architectures based on the trade-off between their performance and computational complexity. With comprehensive quantitative and visual evidence, we establish that the ConvGRU based configurations are the most effective and perform better than the popular ConvLSTM configurations on video anomaly detection tasks, in contrast to what is seen from the literature.

A decade ago, the crowdsourcing term was first coined and used to represent a method for expressing the wisdom of the crowd in accomplishing two types of tasks. One type includes tasks that need human intelligence rather than machines, and the other type covers those tasks that can be accomplished with a higher time and cost efficiency using the crowd rather than employing experts. The crowdsourcing process contains five modules: The first is designing incentives to mobilize the crowd to do the required task. This step is followed by four modules for collecting and assuring quality and then verifying and aggregating the received information. The verification and quality control can be done for the tasks, collected data and the participants by having more participants answer the same question or accepting answers only from experts to avoid errors from unreliable participants. Methods of discovering topic experts are utilized to discover reliable candidates in the crowd who have relevant experience in the discussed topic. Expert discovery reduces the number of needed participants per question which reduces the overall cost. This work summarizes and reviews the methods used to accomplish each processing step. Yet, choosing a specific method remains application dependent.

Detecting topics from Twitter streams has become an important task as it is used in various fields including natural disaster warning, users opinion assessment, and traffic prediction. In this article, we outline different types of topic detection techniques and evaluate their performance. We categorize the topic detection techniques into five categories which are clustering, frequent pattern mining, Exemplar-based, matrix factorization, and probabilistic models. For clustering techniques, we discuss and evaluate nine different techniques which are sequential k-means, spherical k-means, Kernel k-means, scalable Kernel k-means, incremental batch k-means, DBSCAN, spectral clustering, document pivot clustering, and Bngram. Moreover, for matrix factorization techniques, we analyze five different techniques which are sequential Latent Semantic Indexing (LSI), stochastic LSI, Alternating Least Squares (ALS), Rank-one Downdate (R1D), and Column Subset Selection (CSS). Additionally, we evaluate several other techniques in the frequent pattern mining, Exemplar-based, and probabilistic model categories. Results on three Twitter datasets show that Soft Frequent Pattern Mining (SFM) and Bngram achieve the best term precision, while CSS achieves the best term recall and topic recall in most of the cases. Moreover, Exemplar-based topic detection obtains a good balance between the term recall and term precision, while achieving a good topic recall and running time.

In this paper, we present a multi-modal approach for driver fatigue and distraction detection. Based on a driving simulator platform equipped with several sensors, we have designed a framework to acquire sensor data, process and extract features related to fatigue and distraction. Ultimately the features from the different sources are fused to infer the driver’s state of inattention. In our work, we extract audio, color video, depth map, heart rate, and steering wheel and pedals positions. We then process the signals according to three modules, namely the vision module, audio module, and other signals module. The modules are independent from each other and can be enabled or disabled at any time. Each module extracts relevant features and, based on hidden Markov models, produces its own estimation of driver fatigue and distraction. Lastly, fusion is done using the output of each module, contextual information, and a Bayesian network. A dedicated Bayesian network was designed for both fatigue and distraction. The complementary information extracted from all the mod- ules allows a reliable estimation of driver inattention. Our experimental results show that we are able to detect fatigue with 98.4 % accuracy and distraction with 90.5 %.

We propose IR-CAS ACN, a fully Automated Crash Notification safety application that enhances accuracy and efficiency with its precise notifications and increased decentralization. It can be considered as an improvement to the BMW Advanced ACN (AACN): It decentralizes the severity calculation by introducing in-vehicle severity estimation. It fully automates the solution and disseminates more informative messages with partial rather than graded relevance that is insensitive to differences in severity within grades. Different IR models are compared using binary and partial effectiveness measures; estimating severity by calculating the Manhattan distance between the crash and severest crash context vectors outperforms tried models.

Intelligent transportation systems (ITS) involve various emerging technologies and applications. This paper presents a comprehensive review of recent advances on data/information fusion and context-awareness referring to ITS. Data/Information fusion is necessary to fuse the data from different sensors and thereby extract relevant information on the target sources. On the other hand, context-aware information processing provides awareness of the driving environments by deploying intelligent query processing and smart information dissemination. The fusion and context-awareness should help in improving ITS operations with better road-awareness service, traffic monitoring, vehicle detection as well as development of new methods. This paper is centered on data fusion and context aware methodologies developed recently in the areas of ITS rather than on their ITS applications. We found that the recent progresses in ITS fusion are devoted to the potential cooperative approaches providing real-time/dynamic vehicle sensing technologies, whereas the recent context awareness techniques are deploying service concepts (e.g. location aware service) and frameworks. It is believed that the newly developed advanced fusion/context-aware techniques are becoming more effective to tackle complex traffic scenarios (e.g. traffic intersection) as well as complex urban environments.

We propose a context aware system for VANET based on information retrieval and show how it supports Service Announcement (SA). VANET IR-CAS enhances scalability through its highly abstract hybrid context model. It uses an ontology that formalizes the semantics of VANET context domain to allow for knowledge sharing. A hybrid vehicular communication (HVC) is utilized to increase the decentralization, exploit vehicle processing power and protect privacy. The employed IR techniques and partial relevance improve the dispatched information relevance to prospective recipients and add to their satisfaction. Using smart service grouping raises filtering efficiency due to reduction in required connection time.

In mobile surveillance systems, complex task allocation addresses how to optimally assign a set of surveillance tasks to a set of mobile sensing agents to maximize overall expected performance, taking into account the priorities of the tasks and the skill ratings of the mobile sensors. This paper presents a market-based approach to complex task allocation. Complex tasks are the tasks that can be decomposed into subtasks. Both centralized and hierarchical allocations are investigated as winner determination strategies for different levels of allocation and for static and dynamic search tree structures. The objective comparison results show that hierarchical dynamic tree task allocation outperforms all the other techniques especially in complex surveillance operations where large number of robots is used to scan large number of areas.

Data clustering is a process of extracting similar groups of the underlying data whose labels are hidden. This paper describes different approaches for solving data clustering problem. Particle swarm optimization (PSO) has been recently used to address clustering task. An overview of PSO-based clustering approaches is presented in this paper. These approaches mimic the behavior of biological swarms seeking food located in different places. Best locations for finding food are in dense areas and in regions far enough from others. PSO-based clustering approaches are evaluated using different data sets. Experimental results indicate that these approaches outperform K-means, K-harmonic means, and fuzzy c-means clustering algorithms.

A dynamic programming fuzzy rule–based (DPFRB) model for optimal operation of reservoirs system is presented in this paper. In the first step, a deterministic dynamic programming (DP) model is used to develop the optimal set of inflows, storage volumes, and reservoir releases. These optimal values are then used as inputs to a fuzzy rule–based (FRB) model to establish the general operating policies in the second step. Subsequently, the operating policies are evaluated in a simulation model. During the simulation step, the parameters of the FRB model are optimized after which the algorithm gets back to the second step in a feedback loop to establish the new set of operating rules using the optimized parameters. This iterative approach improves the value of the performance function of the simulation model and continues until the satisfaction of predetermined stopping criteria. This method results in deriving the operating policies, which are robust against the uncertainty of inflows. These policies are derived by using long-term synthetic inflows and an objective function that minimizes its variance. The DPFRB performance is tested and compared to a model, which uses the commonly used multiple regression–based operating rules. Results show that the DPFRB performs well in terms of satisfying the system target performances and computational requirements.