Convolutional neural networks for the classification of chest X-rays in the IoT era

Multimedia Tools and Applications - Chest X-ray medical imaging technology allows the diagnosis of many lung diseases. It is known that this technology is frequently used in hospitals, and it is...     

A Cognitive Routing Protocol for Bio-Inspired Networking in the Internet of Nano-Things (IoNT)

Mobile Networks and Applications - In this paper, we propose a framework for data delivery in nano-scale networks, where numerous wireless sensors are distributed on a human body, small object,...     

The potential of wind energy via an intelligent IoT-oriented assessment

The Journal of Supercomputing - In contemporary times, renewable energy reliability has been an important field of research that is combined with the Internet of Things (IoT) including the...     

Factors responsible for rapid dissipation of acidic herbicides in the coastal lagoons of the Camargue (Rhône River Delta, France)

This study was aimed at investigating which processes cause acidic herbicides (e.g., bentazone, MCPA and dichlorprop) to rapidly disappear in the lagoons of the Rhône delta, which are peculiar brackish and shallow aquatic environments. The use of the model MASAS (Modeling of Anthropogenic Substances in Aquatic Systems) revealed that sorption, sedimentation, volatilization, flushing and abiotic hydrolysis had a minor role in the attenuation of the investigated herbicides. Laboratory scale biodegradation and photodegradation studies were conducted to better assess the significance of these two processes in the natural attenuation of herbicides in brackish (lagoons) waters with respect to fresh waters (canals draining paddy fields). Herbicide biodegradation rates were significantly lower in lagoon water than in canal water. Consequently, photodegradation was the main dissipation route of all investigated herbicides. The contribution of indirect photolysis was relevant for MCPA and dichlorprop while direct photolysis dominated for bentazone removal. There is a need to further investigate the identity of phototransformation products of herbicides in lagoons.     

Optimized Hexagon-Based Deployment for Large-Scale Ubiquitous Sensor Networks

Ubiquitous Sensor Network describes an application platform comprised of intelligently networked sensors deployed over a large area, supporting multiple application scenarios. On one hand, at the user-end, storing and managing the large amount of heterogeneous data generated by the network is a daunting task. On the other hand, at the network-end, ensuring network connectivity and longevity in a dynamically changing network environment, while trying to provide context-aware application data to the end-users are very challenging for the resource constrained sensor network. While cloud computing offers a cost-effective solution for storage of the large volume of data generated by the underlying heterogeneous network, an equally elegant solution does not exist on the network interface to provide application-aware data. In this paper, we propose the use of cognitive nodes (CNs) in the underlying sensor network to provide intelligent information processing and knowledge-based services to the end-users. We identify tools and techniques to implement the cognitive functionality and formulate a strategy for the deployment of CNs in the underlying sensor network to ensure a high probability of successful data reception among communicating nodes. From Matlab simulations, we were able to verify that in a network with randomly deployed sensor nodes, CNs can be strategically deployed at pre-determined positions, to deliver application-aware data that satisfies the end-user’s quality of information requirements, even at high application payloads.     

Texture-independent recognition of facial expressions in image snapshots and videos

This paper addresses the static and dynamic recognition of basic facial expressions. It has two main contributions. First, we introduce a view- and texture-independent scheme that exploits facial action parameters estimated by an appearance-based 3D face tracker. We represent the learned facial actions associated with different facial expressions by time series. Second, we compare this dynamic scheme with a static one based on analyzing individual snapshots and show that the former performs better than the latter. We provide evaluations of performance using three subspace learning techniques: linear discriminant analysis, non-parametric discriminant analysis and support vector machines.     

Ear recognition with feed-forward artificial neural networks

Biometrics has become one of the most important techniques in recognizing a person’s identity. A person’s face, iris and fingerprint are mostly used in biometrics today. It has been established that there are no two ears exactly alike, even in the cases of identical twins. In this paper, we define a 7-element ear feature set and design and train a feed-forward artificial neural network to recognize a human ear. We train and test the network with 51 ear pictures from 51 different persons. Simulation experiments with various networks with various number of layers and number of neurons per layer and with and without noise are conducted. Results indicate that a 95 % ear recognition accuracy is achieved with a simple 3-layer feed-forward neural network with only a total of 18 neurons even in the presence of some noise. This design outstands previous work in simplicity and implementation cost.     

Embedding new observations via sparse-coding for non-linear manifold learning

Non-linear dimensionality reduction techniques are affected by two critical aspects: (i) the design of the adjacency graphs, and (ii) the embedding of new test data—the out-of-sample problem. For the first aspect, the proposed solutions, in general, were heuristically driven. For the second aspect, the difficulty resides in finding an accurate mapping that transfers unseen data samples into an existing manifold. Past works addressing these two aspects were heavily parametric in the sense that the optimal performance is only achieved for a suitable parameter choice that should be known in advance.