A rub-impact fault is a complex, nonstationary, and nonlinear fault that occurs in turbines. Extracting features for diagnosing rubbing faults at their early stages requires complex and computationally expensive signal processing approaches that are not always suitable for industrial applications. In this article, a hybrid approach that uses a combination of deep learning and control theory algorithms is introduced for diagnosing rubbing faults of various intensities. Specifically, the system is first modeled based on the autoregressive with eXogenous input Laguerre (ARX-Laguerre) technique. In addition, the ARX-Laguerre proportional-integral observer (PIO) is used to increase the estimation accuracy for the vibration signals containing rubbing faults. Finally, a scalable deep neural network is applied to the output signal of the PIO to perform fault diagnosis and overcome potential problems that may appear when applying a linear observation technique to nonlinear signals. The experimental results demonstrate that the proposed hybrid approach improves the fault differentiation capabilities of a relatively simple linear observation technique when it is applied to a complex nonlinear rubbing fault signal and attains high fault classification accuracy. This result means that the proposed framework is highly suitable for applications in actual industrial environments.

Image segmentation is an essential process in image analysis and is mainly used for automatic object recognition. Fuzzy c-means (FCM) is one of the most common methodologies used in clustering analysis for image segmentation. FCM clustering measures the common Euclidean distance between samples based on the assumption that each feature has equal importance. However, in most real-world problems, features are not considered equally important. To overcome this issue, we present a fuzzy c-means algorithm with spatially weighted information (FCM-SWI) that takes into account the influence of neighboring pixels on the center pixel by assigning weights to the neighbors. These weights are determined based on the distance between a corresponding pixel and the center pixel to indicate the importance of the memberships. Such a process leads to improved clustering performance. Experimental results show that the proposed FCM-SWI outperforms other FCM algorithms (FCM, modified FCM, and spatial FCM, FCM with spatial information, fast generation FCM) in both compactness and separation. Furthermore, the proposed FCM-SWI outperforms the classical algorithms in terms of quantitative comparison scores corresponding to a T1-weighted MR phantom for gray matter, white matter, and cerebrospinal fluid (CSF) slice regions.

Image segmentation plays a crucial role in numerous biomedical imaging applications, assisting clinicians or health care professionals with diagnosis of various diseases using scientific data. However, its high computational complexities require substantial amount of time and have limited their applicability. Research has thus focused on parallel processing models that support biomedical image segmentation. In this paper, we present analytical results of the design space exploration of many-core processors for efficient fuzzy c-means (FCM) clustering, which is widely used in many medical image segmentations. We quantitatively evaluate the impact of varying a number of processing elements (PEs) and an amount of local memory for a fixed image size on system performance and efficiency using architectural and workload simulations. Experimental results indicate that PEs=4,096 provides the most efficient operation for the FCM algorithm with four clusters, while PEs=1,024 and PEs=4,096 yield the highest area efficiency and energy efficiency, respectively, for three clusters.

Medical image segmentation is an indispensable process in viewing and measuring various structures in the brain. However, medical images are inherently low contrast, vague boundaries, and high correlative. The traditional fuzzy c-means (FCM) clustering algorithm considers only the pixel attributes. This leads to accuracy degradation with image segmentation. To solve this problem, this paper proposes a robust segmentation technique, called a Generalized Spatial Fuzzy C-Means (GSFCM) algorithm, that utilizes both given pixel attributes and the spatial local information which is weighted correspondingly to neighbor elements based on their distance attributes. This improves the segmentation performance dramatically. Experimental results with several magnetic resonance (MR) images show that the proposed GSFCM algorithm outperforms the traditional FCM algorithms in the various cluster validity functions.

Medical image registration plays an important role in investigating disease processes and understanding normal development and ageing. An essential component in most medical registration approaches is affine transformation. The affine transformation is made up of any combination of linear transformations (rotation and scaling) followed by translation. These algorithms are generally computationally expensive. The increasing availability of parallel computers makes parallelizing these tasks an attractive option. This paper proposes a massively parallel approach for affine transformations using a representative data parallel architecture to accelerate such algorithms. The result of our parallel approach is outstanding in terms of both processing performance and energy efficiency. The proposed parallel approach achieves a three order of computational capabilities and a second order of energy efficiency of other implementations using commercial processors such as TI DSP and ARM families.

The energy consumed in instruction fetching accounts for a significant portion of total processor energy consumption. Energy consumption as well as performance should be considered when designing high performance embedded processors. In this paper, we present a hardware-based loop detection technique to reduce the energy consumption in the instruction fetch unit (instruction cache and branch prediction logic) for high performance embedded processors. The proposed instruction fetch unit reduces the energy consumed in the instruction cache by replacing the accesses to the large main instruction cache with those to the small selectively accessed cache (SAC). It also reduces the energy consumed in the branch prediction logic by reducing unnecessary accesses to the branch prediction logic. We evaluate the proposed design using a simulation infrastructure based on SimpleScalar and CACTI. Simulation results show that the proposed technique reduces the energy consumption in the instruction cache and the branch prediction logic by 20% and 24% on the average, respectively. Moreover, the proposed scheme shows little performance loss compared to the traditional scheme.

This paper presents an efficient two-stage filtering method that provides highly reliable 4:2:0 YCbCr signals, which are widely used in the image- and video-processing community. In the first phase, we use an index mapping, center-weighted median filter (IMCWMF) to detect and remove noise from luminance (Y) components while inheriting the chrominance components (Cb and Cr) for the selected median luminance. In the second phase, we use a downsampling sigma filter (DSF) to detect and remove noise from the chrominance components while performing the downsampling process. Simulation results indicate that the proposed method outperforms other nonlinear filters in terms of both noise attenuation and signal-detail preservation while providing accurate color channel information for the JPEG compression process and overall image quality.

This paper presents quantized color pack eXtension (QCPX) ISA to accelerate performance of pixel-oriented media processing applications. The QCPX ISA (with a 32 bit word size) supports two packed, quantized (reduced) 16-bit color pixels represented in a YCbCr (Y: luminance, Cr and Cb: chrominance) color format. Unlike typical multimedia instruction set extensions (e.g., MDMX, MMX, ALTIVEC), QCPX obtains substantial performance and code density improvements through implicit support for color pixel processing rather than depending solely on generic subword parallelism. To fully measure its impact, QCPX is evaluated in the context of a massively data-parallel SIMD execution platform where data parallelism is harnessed by an orthogonal mechanism. Simulation results indicate that the 32-bit QCPX ISA achieves an overall average speedup of 584% over the non-QCPX and 88% over the 32-bit MDMX-like ISA with four media applications in a same machine platform. In addition, QCPX results in a higher system utilization in excess of 95% due to a significant reduction of conditional instructions.