Identification of intracranial haemorrhage (ICH) using ResNet with data augmentation using CycleGAN and ICH segmentation using SegAN

Multimedia Tools and Applications - Intracranial Haemorrhage (ICH) occurring due to any injury to the brain is a fatal condition and its timely diagnosis is critically important. In this work, we...     

Iterative nonlinear detection for SFBC SC–FDMA uplink MIMO transmission systems

Single‐carrier frequency division multiple access (SC‐FDMA) systems with space frequency block coding (SFBC) transmissions achieve both spatial and frequency diversity gains in wireless communications. However, SFBC SC‐FDMA schemes using linear detectors suffer from severe performance deterioration because of noise enhancement propagation and additive noise presence in the detected output. Both issues are similar to inter‐symbol‐interference (ISI). Traditionally, SC‐FDMA system decision feedback equalizer (DFE) is often used to eliminate ISI caused by multipath propagation. This article proposes frequency domain turbo equalization based on nonlinear multiuser detection for uplink SFBC SC‐FDMA transmission systems. The presented iterative receiver performs equalization with soft decisions feedback for ISI mitigation. Its coefficients are derived using minimum mean squared error criteria. The receiver configuration study is Alamouti's SFBC with two transmit and two receive antennas. New receiver approach is compared with the recently proposed suboptimal linear detector for SFBC SC‐FDMA systems. Simulation results confirm that the performance of the proposed iterative detection outperforms conventional detection techniques. After a few iterations, bit‐error‐rate performance of the proposed receiver design is closely to the matched filter bound. Copyright © 2016 John Wiley & Sons, Ltd.     

Efficient and secure data hiding in video sequence with three layer security: an approach using chaos

The fast development of communication and technology has created new challenges to transfer data securely. The techniques widely used to secure the data are cryptography and steganography. This paper presents a video steganography method to secure the information to be transmitted. Information transmitted can be an image, audio, text or video. This article presents a new technique that embeds data in the spatial domain of the cover video frame. The method employs chaotic maps to generate Random Positions (RP) to hide the information bits, random numbers for selecting the frames at which the information to be hidden and confusion order to encrypt the cover frame. The video frame is first selected based on Frame Selection (FS) is encrypted by applying Confusion Order (CO) and then embedding is carried out on the random positions generated. After embedding, the decrypted cover frame is replaced in a video sequence for transmission. This method provides three-level security in extracting the hidden secret information and also 25% of embedding capacity. Experimental outcomes (PSNR and payload) confirm that the method is competent.

     

Routing using reinforcement learning in vehicular ad hoc networks

In vehicular ad hoc networks (VANETs), the frequent change in vehicle mobility creates dynamic changes in communication link and topology of the network. Hence, the key challenge is to address and resolve longer transmission delays and reduced transmission stability. During the establishment of routing path, the focus of entire research is on traffic detection and road selection with high traffic density for increased packet transmission. This reduces the transmission delays and avoids carry-and-forward scenarios; however, these techniques fail in obtaining accurate traffic density in real-time scenario due to rapid change in traffic density. Thus, it is necessary to create a model that efficiently monitors the traffic density and assist VANETs in route selection in an automated way with increased accuracy. In this article, a novel machine learning architecture using deep reinforcement learning (DRL) model is proposed to monitor and estimate the data essential for the routing protocol. In this model, the roadside unit maintains the traffic information on roads using DRL. The DRL predicts the movement of the vehicle and makes a suitable routing path for transmitting the packets with improved transmission capacity. It further uses predicted transmission delays and the destination location to choose the forwarding directions between two road safety units (RSUs). The application of DRL over VANETs yields increased network performance, which provides on-demand routing information. The simulation results show that the DRL-based routing is effective in routing the data packets between the source and destination vehicles than other existing method.     

Quality of Service Enhancement in Wireless Sensor Network Using Flower Pollination Algorithm

Programming and Computer Software - One of the renowned and drastically rising research works is developing and deploying emerging applications under wireless sensor networks. Surveillance...     

Iterative MMSE equalization and CFO compensation for the uplink SC‐FDMA transmission

Single‐carrier frequency division multiple access is greatly sensitive to carrier frequency offset (CFO) between transceivers. This leads to the destruction of orthogonality among subcarriers, which in turn leads to inter‐carrier interference and multiple access interference between different users. Minimum mean square error (MMSE) equalizer that uses an inverse operation on an interference matrix with a dimension equal to the number of subcarriers is normally used to invalidate CFO effects. Hence, the terminal processing complexity is very high. The proposed conjugate gradient method attempts to mitigate the higher computational complexity by iteratively evaluating the MMSE solution without direct matrix inverse operation. To further mitigate the multiple access interference, MMSE combined with parallel interference cancellation is also implemented. The analysis of the proposed method shows better performance and fast convergence in single‐carrier frequency division multiple access systems. The maximum iteration number to formulate an accurate solution is almost equal to the number of active users in the uplink access. Simulation results bring out the effectiveness of the present method compared with the existing CFO compensation schemes in terms of computational complication and system performance with large frequency offsets. Copyright © 2016 John Wiley & Sons, Ltd.     

CANFIS based glioma brain tumor classification and retrieval system for tumor diagnosis

Brain tumor classification and retrieval system plays an important role in medical field. In this paper, an efficient Glioma Brain Tumor detection and its retrieval system is proposed. The proposed methodology consists of two modules as classification and retrieval. The classification modules are designed using preprocessing, feature extraction and tumor detection techniques using Co‐Active Adaptive Neuro Fuzzy Inference System (CANFIS) classifier. The image enhancement can be achieved using Heuristic histogram equalization technique as preprocessing and further texture features as Local Ternary Pattern (LTP) features and Grey Level Co‐occurrence Matrix (GLCM) features are extracted from the enhanced image. These features are used to classify the brain image into normal and abnormal using CANFIS classifier. The tumor region in abnormal brain image is segmented using normalized graph cut segmentation algorithm. The retrieval module is used to retrieve the similar segmented tumor regions from the dataset for diagnosing the tumor region using Euclidean algorithm. The proposed Glioma Brain tumor classification methodology achieves 97.28% sensitivity, 98.16% specificity and 99.14% accuracy. The proposed retrieval system achieves 97.29% precision and 98.16% recall rate with respect to ground truth images.     

QoSTRP: A Trusted Clustering Based Routing Protocol for Mobile Ad-Hoc Networks

Programming and Computer Software - One of the secured communication methods in MANET is providing a Trust Management (TM). A TM calculates a trust value for all the participants in the...     

Understanding the thermodynamic micro-environment inside a pan coater using a data logging device

Objective: The objective of the current study was to establish the use of PyroButton data-logging device to monitor and quantify the thermodynamic environment (temperature and humidity) of a pan coating process.

Material and methods: PyroButtons were placed (fixed) at various locations in a pan coater, including exhaust plenum, spray-gun bar, baffles and were also allowed to freely move with the tablet-bed. A full factorial design of experiments (DOE) study on three process parameters, exhaust temperature, pan speed and spray rate was conducted on a 24 inch pan coater, using a coating system and a core tablet combination expected to have a narrow process operating space.

Results: It was shown that the PyroButtons can provide a detailed and useful signature of the coating process. PyroButton data showed that the tablet-bed temperature was always lower than exhaust temperature and that the difference was a function of the operating conditions such as spray rate. Similarly, the tablet-bed humidity was found to always be higher than exhaust humidity. Some of the DOE batches showed coating defects (logo-bridging). It was shown that the relative humidity (RH), as measured by the freely-moving PyroButtons in the tablet-bed, correlated well with the logo-bridging events. A critical RH value (30%) was established, above which logo-bridging was observed for the selected formulation.

Conclusions: This study showed that PyroButtons can provide very meaningful micro-environmental data that can be correlated to coating defects, and can aid in establishing a process design space for a given coating and tablet formulation.