Search

Human activity recognition has become essential to a wide range of applications, such as smart home monitoring, health-care, surveillance. However, it is challenging to deliver a sufficiently robust human activity recognition system from raw sensor data with noise in a smart environment setting. Moreover, imbalanced human activity datasets with less frequent activities create extra challenges for accurate activity recognition. Deep learning algorithms have achieved promising results on balanced datasets, but their performance on imbalanced datasets without explicit algorithm design cannot be promised. Therefore, we aim to realise an activity recognition system using multi-modal sensors to address the issue of class imbalance in deep learning and improve recognition accuracy. This paper proposes a joint diverse temporal learning framework using Long Short Term Memory and one-dimensional Convolutional Neural Network models to improve human activity recognition, especially for less represented activities. We extensively evaluate the proposed method for Activities of Daily Living recognition using binary sensors dataset. A comparative study on five smart home datasets demonstrate that our proposed approach outperforms the existing individual temporal models and their hybridization. Furthermore, this is particularly the case for minority classes in addition to reasonable improvement on the majority classes of human activities. [ABSTRACT FROM AUTHOR] more...

The importance of the surveillance is increasing every day. Surveillance is monitoring of activities, behavior and other changing information. An intelligent automatic system to detect behavior of the human is very important in public places. For this necessity, a framework is proposed to detect suspicious human behavior as well as tracking of human who is doing some unusual activity such as fighting and threatening actions and also distinguishing the human normal activities from the suspicious behavior. The human activity is recognized by extracting the features using the convolution neural network (CNN) on the extracted optical flow slices and pre-training the activities based on the real-time activities. The obtained learned feature creates a score for each input which is used to predict the type of activity and it is classified using multi-class support vector machine (MSVM). This improved design will provide better surveillance system than existing. Such system can be used in public places like shopping mall, railway station or in a closed environment such as ATM where security is the prime concern. The performance of the system is evaluated, by using different standard datasets having different objects and achieved 95% performance as explained in experimental analysis. [ABSTRACT FROM AUTHOR] more...

Object detection is a technologically challenging issue, which is useful for safety in outdoor environments, where this object, frequently, represents an obstacle that must be avoided. Although several object detection methods have been developed in recent years, they usually tend to produce poor results in outdoor environments, being mainly affected by sunlight, light intensity, shadows, and limited computational resources. This open problem is the main motivation for exploring the challenge of developing low-cost object detection solutions, with the characteristic of being easily adaptable and having low power requirements, such as the ones needed in on-board obstacle detection systems in automobiles. In this work, we present a trade-off analysis of several architectures using an FPGA-based design that implements ANNs (FPGA-ANN) for outdoor obstacle detection, focused in road safety. The analyzed FPGA-ANN architectures merge outdoor data gathered by a Kinect sensor, images and infrared data, to construct an outdoor environment model for object detection, which allows to detect if there is an obstacle in the near surroundings of a vehicle. [ABSTRACT FROM AUTHOR] more...

Recently, sentiment analysis has become a focus domain in artificial intelligence owing to the massive text reviews of modern networks. The fast increase of the domain has led to the spring up of assorted sub-areas, researchers are also focusing on subareas at various levels. This paper focuses on the key subtask in sentiment analysis: aspect-based sentiment analysis. Unlike feature-based traditional approaches and long short-term memory network based models, our work combines the strengths of linguistic resources and gating mechanism to propose an effective convolutional neural network based model for aspect-based sentiment analysis. First, the proposed regularizers from the real world linguistic resources can be of benefit to identify the aspect sentiment polarity. Second, under the guidance of the given aspect, the gating mechanism can better control the sentiment features. Last, the basic structure of model is convolutional neural network, which can perform parallel operations well in the training process. Experimental results on SemEval 2014 Restaurant Datasets demonstrate our approach can achieve excellent results on aspect-based sentiment analysis. [ABSTRACT FROM AUTHOR] more...

Brain tumor image segmentation is process of locating the interesting area in terms of objects, like tumor and extracting it for the further process of the image and getting the boundaries of the image for analysis. The bio-medical brain tumor image segmentation is a great challenging field for the today world active researchers with the standardized image datasets and various metrics used for evaluating and comparing the performance of the new algorithm with existing segmentation algorithms. In recent development, these problems are addressed using various image manipulation tools and rapid growth of computer hardware enhancement. Image segmentation was done in three ways: (1) Manual-based (2) Semi-automated-based (3) Fully automated-based. But still be a short of research in the field of brain tumor segmentation and accurate identification of tumor cells. To overcome all the above-mentioned challenges and complexity of the brain tumor segmentation, it need to understand the pre-processing of the image like, registering the image, correction of bias in image, and non-brain tissue removal. In this paper, we propose a new methodology for segmenting the brain tumor from the affected brain image in a significantly efficient way by using deep learning method. [ABSTRACT FROM AUTHOR] more...

Abstract Vision-based mobile robots often suffer from the difficulties of high nonlinear dynamics and precise positioning requirements, which leads to the development demand of more powerful nonlinear approximation in controlling and monitoring of mobile robots. This paper proposes a recurrent emotional cerebellar model articulation controller (RECMAC) neural network in meeting such demand. In particular, the proposed network integrates a recurrent loop and an emotional learning mechanism into a cerebellar model articulation controller (CMAC), which is implemented as the main component of the controller module of a vision-based mobile robot. Briefly, the controller module consists of a sliding surface, the RECMAC, and a compensator controller. The incorporation of the recurrent structure in a slide model neural network controller ensures the retaining of the previous states of the robot to improve its dynamic mapping ability. The convergence of the proposed system is guaranteed by applying the Lyapunov stability analysis theory. The proposed system was validated and evaluated by both simulation and a practical moving-target tracking task. The experimentation demonstrated that the proposed system outperforms other popular neural network-based control systems, and thus it is superior in approximating highly nonlinear dynamics in controlling vision-based mobile robots. [ABSTRACT FROM AUTHOR] more...