Search

This work was supported by the MCIN/AEI/10. 13039/501100011033/and FEDER "Una manera de hacer Europa" under the RTI2018-098913-B100 project, by the Consejeria de Economia, Innovacion, Ciencia y Empleo (Junta de Andalucia) and FEDER under CV20-45250, A-TIC-080-UGR18, B-TIC-586-UGR20, and P20-00525 projects., Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used., FEDER "Una manera de hacer Europa" RTI2018-098913-B100, Junta de Andalucia European Commission CV20-45250 A-TIC-080-UGR18 B-TIC-586-UGR20 P20-00525 MCIN/AEI/10. 13039/501100011033/

This paper presents a real-time iris segmentation technique that is well suited to a fast implementation on an FPGA. One major hurdle associated with iris segmentation techniques is the use of iterative processes that lead to expensive hardware implementations. To circumvent this, the proposed algorithm uses the sign image obtained from subtracting the background, along with morphological operators to localise the pupil. The outer boundary is located by first normalising a selected image region that contains the iris, and then using a first-order gradient operator. The proposed non-iterative algorithm is implemented on an FPGA. Four near infrared (NIR) iris public databases, namely: CASIA-IrisV3-Lamp, MMU v1.0, ND-IRIS-0405 and NIST ICE 2005, are used to test the proposed algorithm. The proposed method for iris segmentation and normalization gives much better accuracy than the existing state-of-the-art methods implemented on hardware. The proposed realisation requires about 45% fewer logic registers and 52% fewer logic elements than the existing state-of-the-art implementations.

A residue number system (RNS) has an inherent parallel structure that can be utilized for improving computer hardware systems. An RNS represents large integer numbers as a smaller integer set, or residues of a modulo set, without carry propagation between them. Hence mathematical operations, such as addition or subtraction, can be performed on the residues independently. This paper proposes an RNS implementation of motion estimation for the latest video coding standard known as high-efficiency video coding (HEVC) or H.265. Since motion estimation is the most computationally intensive task in video coding, several simplified algorithms are proposed for mitigating the problem, but the majority of them result in a worsening peak signal-to-noise ratio (PSNR) or bit-rate performance, or sometimes both. This paper also proposes a modified algorithm based on a test-zone (TZ) search algorithm, a widely used fast-search algorithm with good rate-distortion performance, suitable for hardware implementation for encoding ultra-high-definition videos in real time. The results show that worst-case PSNR degradation and bit-rate increases compared with the TZ search in the HEVC reference software implementation are negligible, and the hardware gate count is less than for many other designs in the literature.

Scientists have devoted a lot of affords to guarantee the safety of cryptosystems by improving cryptography algorithms, while these systems can still be vulnerable to side-channel information analysis based on neural networks (NNs) and principal component analysis (PCA). PCA can be used as a preprocessing stage, while NNs can learn the signature (power consumption and electromagnetic emission) of an instruction of a cryptography algorithm, and then recognizes it later automatically. This paper investigate the performance of NNs as a powerful classifier to analysis the side-channel information. For this purpose, an experimental investigation was conducted based on the power consumption and electromagnetic emission analysis of a field-programmable gate array implementation of elliptic curve cryptography. In our experimental results, the performance of different NNs topologies are compared which provide useful information for cryptosystem designers. In addition an efficient NN topology is introduced for characterization of side-channel information.

Breast Cancer is a serious threat to women. The identification of breast cancer relies heavily on histopathological image analysis. Among the different breast-cancer image analysis techniques, classifying the images into Benign and Malignant classes, have been an active area of research. The involvement of machine learning for breast-cancer image classification is also an active area of research. Considering the importance of the breast-cancer image classification, this paper has classified a set of histopathological images into Benign and Malignant classes utilizing Neural Network techniques and Random Forest algorithms. As histopathological images suffer intensity variation, in this paper, we have normalized the intensity information by newly proposed intensity normalization techniques, and classify the images using Neural Network techniques and Tree-based classification tools. Investigation shows that the proposed Normalization technique gives the best performance when we use Neural Network techniques but Tree-based algorithms such as the Random Forest algorithm give better performance when we use images without normalization techniques.

This work proposes a residue number system (RNS) based hardware architecture of an elliptic curve cryptography (ECC) processor over prime field. The processor computes point multiplication in Jacobian coordinates by a combined architecture of point doubling and point addition. An optimized modular reduction architecture is also presented that achieves low area by dividing the RNS moduli in small groups and processes the groups one by one. The proposed ECC processor is generic and supports any random curve over F p 256 . The implementation on Virtex-7 and Virtex-6 FPGAs shows comparable performance to the state-of-the-art binary and RNS based ECC processors.

Accurate diagnosis of Autism Spectrum Disorder (ASD) followed by effective rehabilitation is essential for the management of this disorder. Artificial intelligence (AI) techniques can aid physicians to apply automatic diagnosis and rehabilitation procedures. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. DL methods for diagnosis of ASD have been focused on neuroimaging-based approaches. Neuroimaging techniques are non-invasive disease markers potentially useful for ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, proposing optimum procedures for ASD diagnosis with neuroimaging data without exploiting powerful AI techniques like DL may be challenging. In this paper, studies conducted with the aid of DL networks to distinguish ASD are investigated. Rehabilitation tools provided for supporting ASD patients utilizing DL networks are also assessed. Finally, we will present important challenges in the automated detection and rehabilitation of ASD and propose some future works.

Modular multiplication (MM) is the main operation in cryptography algorithms such as elliptic-curve cryptography (ECC) and Rivest-Shamir-Adleman, where repeated MM is used to perform elliptic curve point multiplication and modular exponentiation, respectively. The algorithm for the proposed architecture is derived from the Chinese remainder theorem and performs MM completely within a residue number system (RNS). Moreover, a 40-channel RNS moduli-set is proposed for this architecture to benefit from the short-channel width of the RNS moduli-set. The throughput of the architecture is enhanced by pipelining and pre-computations. The proposed architecture is fabricated as an ASIC using 65-nm CMOS technology. The measurement results are obtained for energy dissipation at different voltage levels from 0.43 to 1.25 V. The maximum throughput of the proposed design is 1037 Mbps while operating at a frequency of 162 MHz with an energy dissipation of 48 nJ. The proposed architecture enables the construction of low-voltage and energy-efficient ECCs.

Public-key cryptosystems such as elliptic curve cryptography (ECC) and Rivest–Shamir–Adleman (RSA) are widely used for data security in computing systems. ECC provides a high level of security with a much smaller key than RSA, which makes ECC a preferred choice in many applications. This study proposes a multi-key ECC based on the residue number system. The proposed architecture employees deep pipelining to allow the concurrent encryption of 21 keys. The proposed architectures are implemented on two different field programmable gate array (FPGA) platforms and results are compared with existing ECC architectures. The proposed implementation on Virtex-7 FPGA achieves a throughput of 1816 kbps at a clock frequency of 73 MHz.

Bone fracture detection from the digital image segmentation is a well-known image processing application which is frequently used to process biomedical images. Hardware realization of different image processing algorithm specially utilizing Field Programmable Gate Array (FPGA) has been gained a great interest among the researchers. FPGA has many significant features like spatial and temporal parallelism that best suits for real-time implementation of image processing. To gain the benefit from these characteristics of a FPGA, a new method for bone fracture detection is proposed and its performance is validated through real-time implementation. Simulation results show that the proposed method give superior performance than the existing method.

A real-time image filtering technique is proposed which could result in faster implementation for fingerprint image enhancement. One major hurdle associated with fingerprint filtering techniques is the expensive nature of their hardware implementations. To circumvent this, a modified anisotropic Gaussian filter is efficiently adopted in hardware by decomposing the filter into two orthogonal Gaussians and an oriented line Gaussian. An architecture is developed for dynamically controlling the orientation of the line Gaussian filter. To further improve the performance of the filter, the input image is homogenized by a local image normalization. In the proposed structure, for a middle-range reconfigurable FPGA, both parallel compute-intensive and real-time demands were achieved. We manage to efficiently speed up the image-processing time and improve the resource utilization of the FPGA. Test results show an improved speed for its hardware architecture while maintaining reasonable enhancement benchmarks.

Motion estimation (ME) is the most computationally intensive task in video encoding. This study proposes a full-search variable-block-size ME for the high-efficiency video coding or H.265 specification. The proposed method reduces memory requirements to a large extent by following a Morton order for data reading and a sum of absolute differences reuse strategy. The data bandwidth demand is also diminished by broadcasting data into multiple processing elements. This ME accelerator supports variable-block-size prediction blocks ranging from 8 × 4 to 64 × 64 , and is reconfigurable in various search ranges for a trade-off between performance and area. The proposed method for very-large-scale integration (VLSI) architecture is synthesized with 32 nm technology, and is capable of real-time encoding of ultra-high-definition (4K-UHD, at 30 Hz) video with a search range of 64 pixels in both horizontal and vertical directions, operating at a frequency of 282 MHz.

The security of cryptographic systems is a major concern for cryptosystem designers, even though cryptography algorithms have been improved. Side-channel attacks, by taking advantage of physical vulnerabilities of cryptosystems, aim to gain secret information. Several approaches have been proposed to analyze side-channel information, among which machine learning is known as a promising method. Machine learning in terms of neural networks learns the signature (power consumption and electromagnetic emission) of an instruction, and then recognizes it automatically. In this paper, a novel experimental investigation was conducted on field-programmable gate array (FPGA) implementation of elliptic curve cryptography (ECC), to explore the efficiency of side-channel information characterization based on a learning vector quantization (LVQ) neural network. The main characteristics of LVQ as a multi-class classifier are that it has the ability to learn complex non-linear input-output relationships, use sequential training procedures, and adapt to the data. Experimental results show the performance of multi-class classification based on LVQ as a powerful and promising approach of side-channel data characterization.

Deep learning-based side channel attacks are burgeoning due to their better efficiency and performance, suppressing the traditional side-channel analysis. To launch the successful attack on a particular public key cryptographic (PKC) algorithm, a large number of samples per trace might need to be acquired to capture all the minor useful details from the leakage information, which increases the number of features per instance. The decreased instance-feature ratio increases the computational complexity of the deep learning-based attacks, limiting the attack efficiency. Moreover, data class imbalance can be a hindrance in accurate model training, leading to an accuracy paradox. We propose an efficient Convolutional Neural Network (CNN) based approach in which the dimensionality of the large leakage dataset is reduced, and then the data is processed using the proposed CNN based model. In the proposed model, the optimal number of convolutional blocks is used to build powerful features extractors within the cost limit. We have also analyzed and presented the impact of using the Synthetic Minority Over-sampling Technique (SMOTE) on the proposed model performance. We propose that a data-balancing step should be mandatory for analysis in the side channel attack scenario. We have also provided a performance-based comparative analysis between proposed and existing deep learning models for unprotected and protected Elliptic curve (ECC) Montgomery Power ladder implementations. The reduced network complexity, together with an improved attack efficiency, promote the proposed approach to be effectively used for side-channel attacks.

Combination of efficient point operation architecture and high intractability feature of cryptographic curve optimizes the performance of the Edward curve cryptography (EdCC) processor ensuring desired security. This research employs the most recently invented twisted Edward curve for performing point operation. A novel architecture of unified point operation has been designed over the 256-bit prime field which can execute Edward curve point doubling and point addition in one module instead of two divide modules. The proposed architecture has been implemented on Virtex-5 field-programmable gate array technology and achieved 5.48 $\mu$ s computational delay and only 10% of available slices for 256-bit point operation. Our design reduces almost 50% of the required clock cycles compared to other designs. Also, it assures a better security characteristic as to the conventional approach. To our best knowledge, the proposed architecture provides better performance in terms of throughput on FPGA than the other work which is effective for the design of the EdCC processor.

Breast cancer is one of the largest causes of women’s death in the world today. Advance engineering of natural image classification techniques and Artificial Intelligence methods has largely been used for the breast-image classification task. The involvement of digital image classification allows the doctor and the physicians a second opinion, and it saves the doctors’ and physicians’ time. Despite the various publications on breast image classification, very few review papers are available which provide a detailed description of breast cancer image classification techniques, feature extraction and selection procedures, classification measuring parameterizations, and image classification findings. We have put a special emphasis on the Convolutional Neural Network (CNN) method for breast image classification. Along with the CNN method we have also described the involvement of the conventional Neural Network (NN), Logic Based classifiers such as the Random Forest (RF) algorithm, Support Vector Machines (SVM), Bayesian methods, and a few of the semisupervised and unsupervised methods which have been used for breast image classification.

Fingerprints are the oldest and most widely used form of biometric identification. Many researchers have addressed the fingerprint classification problem and significant progress has been made in designing automatic fingerprint identification systems (AFIS) over the past two decades. However, some design factors such as lack of reliable minutia extraction algorithms, difficulty in quantitatively defining a reliable match between fingerprint images, poor image acquisition, low contrast images create bottlenecks in achieving the desired performance. Noticeable among them is the fact that digitally acquired fingerprint images are rarely of perfect quality to be used directly with AFIS; one important step is fingerprint enhancement. Conventional fingerprint enhancement methods, such as Gabor and anisotropic filters, do fill the holes and gaps in ridge lines but lack the necessary capability to tackle scar lines. For scar lines, an explicit filling process is proposed that is a mix of Fourier and spatial domain strategies. The proposed method is to make use of the Fourier domain directional field to trace an appropriate candidate for the scar pixels to be replaced with. The necessary components of the process are locating scars, estimating directional field, and the filling strategy. This process can act as front-end to the subsequent Gabor and anisotropic diffusion filtering. The simulation results for synthetic, as well as real fingerprints, show improved performance regarding better extraction of genuine minutia points. HighlightsWe Model a new proposed method to make use of the Fourier domain directional field to trace an appropriate candidate for the scar pixels to be replaced with.The necessary components of the process are locating scars, finding the directional field, and the filling strategy.The strategy relies on the fact that in these linear scars, the ridge/valley pattern is still intact across the scar region.Using this information, the scar boundary is filled with appropriate normal region pixels using the local orientation field.This process can act as front-end to the subsequent Gabor and anisotropic diffusion filtering.

This study presents a description of an efficient hardware implementation of an elliptic curve cryptography processor (ECP) for modern security applications. A high-performance elliptic curve scalar multiplication (ECSM), which is the key operation of an ECP, is developed both in affine and Jacobian coordinates over a prime field of size p using the National Institute of Standards and Technology standard. A novel combined point doubling and point addition architecture is proposed using efficient modular arithmetic to achieve high speed and low hardware utilisation of the ECP in Jacobian coordinates. This new architecture has been synthesised both in application-specific integrated circuit (ASIC) and field-programmable gate array (FPGA). A 65 nm CMOS ASIC implementation of the proposed ECP in Jacobian coordinates takes between 0.56 and 0.73 ms for 224-bit and 256-bit elliptic curve cryptography, respectively. The ECSM is also implemented in an FPGA and provides a better delay performance than previous designs. The implemented design is area-efficient and this means that it requires not many resources, without any digital signal processing (DSP) slices, on an FPGA. Moreover, the area–delay product of this design is very low compared with similar designs. To the best of the authors’ knowledge, the ECP proposed in this study over F p performs better than available hardware in terms of area and timing.

This article proposes a novel architecture to perform modular multiplication in the Residue Number System (RNS) by using sum of residues. The highly parallel architecture is implemented using VHDL and verified by extensive simulations in ModelSim SE. The pipelined and non-pipelined versions of the design are implemented on ASIC and FPGA platforms to allow a broad comparison. The proposed architecture requires only one iteration to complete modular multiplication and achieves 12---90 % less delay as compared to the existing RNS and binary modular multipliers. The complexity of the proposed design is also less than the existing state-of-the-art RNS-based modular multipliers. The high scalability and flexibility of the proposed architecture allows it to be used for a wide range of high-speed applications.

Traditional cryptanalysis assumes that an adversary only has access to input and output pairs, but has no knowledge about internal states of the device. However, the advent of side-channel analysis showed that a cryptographic device can leak critical information. In this circumstance, Machine learning is known as a powerful and promising method of analysing of side-channel information. In this paper, an experimental investigation on a FPGA implementation of elliptic curve cryptography (ECC) was conducted to explore the efficiency of side-channel information characterisation based on machine learning techniques. In this work, machine learning is used in terms of principal component analysis (PCA) for the preprocessing stage and a Cascade-Forward Back-Propagation Neural Network (CFBP) as a multi-class classifier. The experimental results show that CFBP can be a promising approach in characterisation of side-channel information.

Security of embedded systems is the need of the hour. A mathematically secure algorithm runs on a cryptographic chip on these systems, but secret private data can be at risk due to side-channel leakage information. This research focuses on retrieving secret-key information, by performing machine-learning-based analysis on leaked power-consumption signals, from Field Programmable Gate Array (FPGA) implementation of the elliptic-curve algorithm captured from a Kintex-7 FPGA chip while the elliptic-curve cryptography (ECC) algorithm is running on it. This paper formalizes the methodology for preparing an input dataset for further analysis using machine-learning-based techniques to classify the secret-key bits. Research results reveal how pre-processing filters improve the classification accuracy in certain cases, and show how various signal properties can provide accurate secret classification with a smaller feature dataset. The results further show the parameter tuning and the amount of time required for building the machine-learning models.

Side-channel attacks are the class of attacks which exploits the physical leakages of the system to recover the secret key, based on the weakness induced due to implementation of algorithm on embedded systems. AES is mathematically secure but side-channel information can lead to key recovery. Over the last decade, machine learning has been introduced in parallel along with traditional statistical side-channel analysis methods. Accurate classification u sing t he machine-learning-based approaches critically depends on various factors including, precision of the input data-sets which consist of the features, tuning of different parameters for that particular algorithm, per feature sample length, number of validation folds and feature extraction/selection methods. For analysis of leaked signals in this study, hyper-parameter tuning is carried out on the feature data-sets formed on basis of the time and frequency domain properties of the signals. Results provide the comparative analysis of the best choices and leads to concrete selection of the parameters.

This work presents a description of a highperformance hardware implementation of a Montgomery modular multiplier using a residue number system (RNS). An RNS can be considered as self-defense against simple power analysis (SPA) and differential power analysis (DPA) attacks, and can be used for public-key cryptography, such as the Rivest, Shamir and Adleman (RSA) cryptosystem and elliptic curve cryptosystems (ECC). Various kinds of security are required for Big Data analysis. The proposed RNS-based modular multiplier is suitable for public-key cryptography that can be used for Big Data security. It is implemented on field-programmable gate-array (FPGA) technology and optimized by trying different variants of the Montgomery Algorithm on it. The proposed RNS-based modular multiplication takes only 22 ns on the Xilinx Virtex-II FPGA. In addition, it needs relatively few resources on the FPGA, needing only 68 slices.

Side-channel attacks have left the traditional methods of cryptanalysis far behind. The algorithms are mathematically secure, but the side-channel leakage poses a serious security threat. Innovative machine-learning classification methods have remarkably reduced the sampling time as well as the time required to recover the key. However, these results are constrained by high dimensionality, i.e. complex feature data increases the classification time, and at times results in false classification. In this paper, we a im to narrow down the feature space and determine which features contribute most, towards better classification accuracy, for key retrieval from an AES implementation running over Kintex-7. We have provided a comparison of classifying the key bit as 0 or 1 with a varying number of samples and different sets of features. This paper gives practical results of different properties becoming features for extracted power signals using both feature selection and extraction methods.

Deaths due to cancer have increased rapidly in recent years. Among all the cancer diseases, breast cancer causes many deaths in women. A digital medical photography technique has been used for the detection of breast cancer by physicians and doctors, however, they need to give more attention and spend more time to reliably detect the cancer information from the images. Doctors are heavily reliant upon Computer Aided Diagnosis (CAD) for cancer detection and monitoring of cancer. Because of the dependence on CAD for cancer diagnosis, researchers always pay extra attention to designing an automatic CAD system for the identification and monitoring of cancer. Various methods have been used for the breast-cancer image-classification task, however, state-of-the-art deep learning techniques have been utilised for cancer image classification with success due to its self-learning and hierarchical featureextraction ability. In this paper we have developed a Deep Neural Network (DNN) model utilising a restricted Boltzmann machine with “scaled conjugate gradient” backpropagation to classify a set of Histopathological breast-cancer images. Our experiments have been conducted on the Histopathological images collected from the BreakHis dataset.

Despite having a secure algorithm running on a cryptographic chip, in an embedded system device on the network, secret private data is still vulnerable due to Side-Channel leakage information. In this paper, we have focused on retrieving secret-key information obtained from one of the Side Channels, namely Electromagnetic radiation signals. We have captured leaked Electromagnetic signals from a Kintex-7 FPGA, while AES is running over it, and analyzed them using machine and deep-learning based algorithms to classify each bit of the key. Moreover, we aim to analyze the effect of having different signal properties as features in these classification algorithms. The results will help in defining which features give maximum information about the captured signal, hence leading to key recovery.

Biomedical image classification has always been a challenging and critical task which has the highest level of importance. The Deep Neural Network (DNN) has been recently introduced for normal image classification and lately introduced for Biomedical image classification with some advanced engineering. In this paper we have classified an image dataset with a DNN utilizing Long Short Term Memory (LSTM) as well as Gated Recurrent Unit (GRU) for breast-image classification. Instead of directly using raw images, we have utilized frequency-domain information for the image classification. Using our model we have obtained 93.01% Accuracy, 94.00% Recall and 94.00% Precision, which is the best available result on this dataset.

Finding malignancy from Histopathological images is always a challenging task. So far research has been carried out to classify Histopathological images using various techniques and methods. Recently, the state-of-the art Convolutional Neural Network (CNN) has largely been utilized for natural image classification. In this paper, using the advancement of CNN techniques, we have classified a set of Histopathological Breast images into Benign and Malignant classes, which can save doctors and physicians time and also allow patients a second opinion about the disease.

Convolutional Neural Networks (CNN) have brought a revolutionary improvement to image analysis, especially in the image classification field. The technique of natural image classification using the CNN method has been deliberately utilized for medical image classification with some advanced engineering. However, so far in most of the cases CNN model classifies images based on global features extraction from the raw images. In this paper, we have utilized both raw images and some hand-crafted features, and later we classify images using a CNN network. For the classification purposes, we have utilized the BreakHis dataset and achieved a 96.00% accuracy, which is a state-of-the-art result on this dataset.

Breast Cancer is a serious threat and one of the largest causes of death of women throughout the world. The identification of cancer largely depends on digital biomedical photography analysis such as histopathological images by doctors and physicians. Analyzing histopathological images is a nontrivial task, and decisions from investigation of these kinds of images always require specialised knowledge. However, Computer Aided Diagnosis (CAD) techniques can help the doctor make more reliable decisions. The state-of-the-art Deep Neural Network (DNN) has been recently introduced for biomedical image analysis. Normally each image contains structural and statistical information. This paper classifies a set of biomedical breast cancer images (BreakHis dataset) using novel DNN techniques guided by structural and statistical information derived from the images. Specifically a Convolutional Neural Network (CNN), a Long-Short-Term-Memory (LSTM), and a combination of CNN and LSTM are proposed for breast cancer image classification. Softmax and Support Vector Machine (SVM) layers have been used for the decision-making stage after extracting features utilising the proposed novel DNN models. In this experiment the best Accuracy value of 91.00% is achieved on the 200x dataset, the best Precision value 96.00% is achieved on the 40x dataset, and the best F-Measure value is achieved on both the 40x and 100x datasets.

The main task of a fingerprint image enhancement is to enhance the image in such a way that it not only remove the noise but also enhance the reliable minutiae points. For this purpose, in this paper we propose a multi-scale decimation-free directional filter bank method for reliable orientation estimation. This reliable orientation is used in coherence enhancement diffusion and in Gabor filter based enhancement, which overcomes the drawbacks of these two methods. Experimental results show that the proposed method not only enhances the images but also facilitates the minutiae algorithm, by enhancing the true minutiae points.

In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre calculated orientation, by using local and integration scales. From the experiments it is found the proposed scheme is working much better in noisy environment as compared to the traditional Coherence Enhancement Diffusion

In this paper, we propose a novel parallel architecture for fast hardware implementation of elliptic curve point multiplication (ECPM), which is the key operation of an elliptic curve cryptography processor. The point multiplication over binary fields is synthesized on both FPGA and ASIC technology by designing fast elliptic curve group operations in Jacobian projective coordinates. A novel combined point doubling and point addition (PDPA) architecture is proposed for group operations to achieve high speed and low hardware requirements for ECPM. It has been implemented over the binary field which is recommended by the National Institute of Standards and Technology (NIST). The proposed ECPM supports two Koblitz and random curves for the key sizes 233 and 163 bits. For group operations, a finite-field arithmetic operation, e.g. multiplication, is designed on a polynomial basis. The delay of a 233-bit point multiplication is only 3.05 and 3.56 μs, in a Xilinx Virtex-7 FPGA, for Koblitz and random curves, respectively, and 0.81 μs in an ASIC 65-nm technology, which are the fastest hardware implementation results reported in the literature to date. In addition, a 163-bit point multiplication is also implemented in FPGA and ASIC for fair comparison which takes around 0.33 and 0.46 μs, respectively. The area-time product of the proposed point multiplication is very low compared to similar designs. The performance ([Formula: see text]) and Area × Time × Energy (ATE) product of the proposed design are far better than the most significant studies found in the literature.

Breast cancer is the most prevalent form of cancer. Statistics show that breast cancer causes the second highest mortality in women worldwide and around two million new cases were diagnosed every year. Accurate classification of breast cancer has acquired high importance for proper diagnosis which can save doctors and physiologist time. The breast, which contains fatty tissue is more vulnerable to cancer. In this paper, we classify a set of breast images based on Fatty tissue and non-Fatty tissue using a concatenated statistical, structural and textural feature set. For the classification, we have used Support Vector Machine (SVM) and Neural Network (NN) techniques as a classifier tool. Investigation shows that concatenated statistical, structural and textural features provide better classification result.

The latest video coding standard introduced by the joint collaborative team on video coding (JCT-VC) is known as high-efficiency video coding (HEVC) or H.265. HEVC/H.265 is mainly targeted for high-definition videos, and offer more compression than its predecessor. The discrete cosine transform (DCT) is widely used for image and video compression including HEVC. This paper proposes a variablelength DCT architecture for encoding video according to the HEVC/H.265 specifications. The architecture is optimized for most likely block sizes in ultra-high definition (UHD) video, and eliminates unnecessary complexities found in many architectures proposed. The synthesized results with Synopsys design tools show that the proposed method can encode 8K UHD videos @ 60 fps in real-time and accomplishes more than 60% in hardware savings.

Edge-detection techniques have been used for a variety of purposes. For the case of Biomedical information extraction like bone fracture detection, edge plays a vital role. An edge has been detected using different techniques and methods. Among the different techniques, Canny's method has been used since its proposal by J. Canny [1]. Canny methods contain's different steps towards the detection of the edges. Among the stages, the hysteresis linking method is complex as it needs neighbourhood data information. Retrieve this neighbourhood information increases the complexity of the algorithm. To overcome this complexity, we have introduced Fuzzy logic instead of the hysteresis Linking method for edge detection. In this paper, we have combined the Fuzzy edge-detection concept and Canny's method and analyse the performances.

This paper presents an advanced low-cost temperature control system. The system takes the highest performance-cost ratio as its aim. It uses the low-cost 8-bit MCS-51 MCU and integrated temperature sensor to achieve the on-site control. A lower cost remote host computer can be used in this system. In the case of a relatively larger application, it can be expanded to a control system of master-slave distribution and utilize the computing and storage resources of the microcontroller. It realizes a wider range of temperature adjustment, and then put the state of the system into a database of the microcontroller to be ascertained later.

The need for secure communication over the network has increased drastically over recent years, and Elliptic Curve Cryptography (ECC) carries out a significant role in moving secured information. In this work, a hardware implementation of modular arithmetic and group operations over the prime field for an Elliptic Curve Cryptography Processor (ECP) for an efficient security system is proposed. The modular addition or subtraction operation takes only one clock cycle and the modular multiplication, which is designed using the interleaved modular multiplication method, requires 257 clock cycles. For elliptic curve group operation separate point doubling (PD) and point addition (PA) architectures are implemented in Jacobean coordinates. These new architectures are simulated in a Xilinx ISE 14.7. After that, the architectures are implemented in Xilinx Virtex-7 field-programmable gate array (FPGA) with the VHDL language. Proposed modular arithmetic and group operations can be utilized to design an Elliptic Curve Point Multiplication (ECPM).

A new algorithm for modular multiplication in the residue number system (RNS) is presented. Modular reduction is performed using a sum of residues. As all of the residues can be evaluated simultaneously, the algorithm permits a highly parallel implementation and is suitable for performing public-key cryptography operations with very low latency.

Edge-detection methods have been an active area of research among researchers in the area of Digital Signal Processing. Some distinct methods have been recommended for edge extraction within an image. Among the different techniques, Canny and Fuzzy techniques have had very strong support in the edge-detection field. In this work, we have integrated the Canny and Fuzzy methods to extract the edge information from the image. This paper also analyze the performance of this integrated edge-detection algorithm with various performance measuring parameters.

Different features of an image are relevant for different applications. Among the different features as edges which have been analyzed and investigated intensely. Of different edge detection methods, Canny's edge detection method is a pioneer in the edge detection field. However implementing all the steps of the Canny edge detection method in hardware is quite complex. In this paper we have modified two threshold Algorithms. We have also analysed Canny's method with and without incorporating the Hysteresis Linking step, and we have tried to investigate the performance of Canny's method incorporating two modified threshold algorithms.

Modular multiplication is the backbone for the whole asymmetric cryptographic process. In this paper, we have focused on a high-speed hardware implementation of modular multiplication for public-key cryptography, specially for a high-performance Elliptic Curve Crypto-processor (ECC). The proposed design has been implemented over a prime finite field of size p using the National Institute of Standards and Technology (NIST) recommended standards. Field-Programmable Gate-Array (FPGA) technology with the VHDL language has been used for this hardware implementation. The computational time of a 256-bit modular multiplication in a modern Xilinx Virtex-7 FPGA is 1.683 µs at frequency 152.709 MHz; in this technology we have implemented an area-efficient hardware design technique which takes only 605 slices for a 256-bit modular multiplication. The required area and time are also very low compared with all other recent designs. The product of area and time (AT) of our design is also nearly 9–98 times better than the related designs. To our knowledge, our implemented modular multiplication over GF(p) provides a better performance than the recent hardware implementations.

Cryptosystems, even after recent algorithmic improvements, can be vulnerable to side channel attacks (SCA). In this paper, we investigated one of the powerful class of SCA based on machine learning techniques in the forms of Principal Component Analysis (PCA) and multi-class classification. For this purpose, support vector machine (SVM) is investigated as a robust and efficient multi-class classifier along with a proper kernel function and its appropriate parameters. Our experiment performed on data leakage of FPGA implementation of elliptic curve cryptography (ECC), and the results, validated by cross validation approach, compare the efficiency of different kernel functions and the influence of function parameters.

This paper presents a novel approach for automatic pupil segmentation. The proposed algorithm uses local histogram-based threshold, area and eccentricity that looks for the region that has the highest probability of having the pupil. Proposed algorithm is implemented on FPGA using a non-iterative scheme along with hardware optimized median filter and connected component logic algorithm. The proposed algorithm is tested on two public databases namely: CASIA v1.0 and MMU v1.0. Experimental results show that the proposed method has satisfying performance and good robustness against the reflection in the pupil.

Identification of the malignancy of tissues from Histopathological images has always been an issue of concern to doctors and radiologists. This task is time-consuming, tedious and moreover very challenging. Success in finding malignancy from Histopathological images primarily depends on long-term experience, though sometimes experts disagree on their decisions. However, Computer Aided Diagnosis (CAD) techniques help the radiologist to give a second opinion that can increase the reliability of the radiologist’s decision. Among the different image analysis techniques, classification of the images has always been a challenging task. Due to the intense complexity of biomedical images, it is always very challenging to provide a reliable decision about an image. The state-of-the-art Convolutional Neural Network (CNN) technique has had great success in natural image classification. Utilizing advanced engineering techniques along with the CNN, in this paper, we have classified a set of Histopathological Breast-Cancer (BC) images utilizing a state-of-the-art CNN model containing a residual block. Conventional CNN operation takes raw images as input and extracts the global features; however, the object oriented local features also contain significant information—for example, the Local Binary Pattern (LBP) represents the effective textural information, Histogram represent the pixel strength distribution, Contourlet Transform (CT) gives much detailed information about the smoothness about the edges, and Discrete Fourier Transform (DFT) derives frequency-domain information from the image. Utilizing these advantages, along with our proposed novel CNN model, we have examined the performance of the novel CNN model as Histopathological image classifier. To do so, we have introduced five cases: (a) Convolutional Neural Network Raw Image (CNN-I); (b) Convolutional Neural Network CT Histogram (CNN-CH); (c) Convolutional Neural Network CT LBP (CNN-CL); (d) Convolutional Neural Network Discrete Fourier Transform (CNN-DF); (e) Convolutional Neural Network Discrete Cosine Transform (CNN-DC). We have performed our experiments on the BreakHis image dataset. The best performance is achieved when we utilize the CNN-CH model on a 200× dataset that provides Accuracy, Sensitivity, False Positive Rate, False Negative Rate, Recall Value, Precision and F-measure of 92.19%, 94.94%, 5.07%, 1.70%, 98.20%, 98.00% and 98.00%, respectively.

Cryptographic devices, even after recent improvements, are still vulnerable to side channel attacks(SCA). The majority of the available literature of SCA belongs to the traditional methods such as simple and differential analysis methods and template attacks, whilst few studies based on machine learning are available. In this paper, we investigate the side channel analysis based on machine learning techniques in the form of principal component analysis (PCA) and support vector machine (SVM). For this purpose, we verify the efficiency of RBF and POLY kernel functions of SVM classifier under the influence of the number of principal components (PCs). Our experimental results, obtained by cross validation method, comprise the accuracy and computational complexity of this method and can show the validity and the effectiveness of the proposed approach.

Image compression is one of the most widely used groups of signal processing schemes in real-time applications. There are various algorithms for compressing images, each with pros and cons. Each method of data compression behaves differently for various types of data, thus a review of the common image algorithms seems necessary to compare the compression ratio, compression and decompression time, and generated file sizes. This paper aims to provide an insight into the characteristics of commonly used image-compression algorithms. Each algorithm is tested with controlled test images to determine the operational capabilities of each algorithm for different test cases. Subsequently, the performance of each algorithm is simulated and compared with other methods. Discussions on how algorithms behave with various test images are given in detail. The desired outcome of this study is a clear description of compression algorithms, and determining the suitability of each algorithm for different applications.

In this paper, a new robust orientation estimation for Coherence Enhancement Diffusion (CED) is proposed. In CED, proper scale selection is very important as the gradient vector at that scale reflects the orientation of local ridge. For this purpose, a new scheme is proposed in which pre calculated orientation, by using orientation diffusion, is used to find the correct true local scale. From the experiments it is found that the proposed scheme is working much better in noisy environment as compared to the traditional Coherence Enhancement Diffusion.

High performance digital image processing is considered a significant contributes of high performance embedded computing and signal processing projects. In this paper, we have provided the design and implementation of VLSI architecture of multiplier-less DWT image processor. The filter coefficients multiplication is resolved by simple shift and adds. Multi-resolution features of bi-orthogonal DWT and a new scheme of reading images from memory are employed to reduce the memory requirements. The image is processed by the overlapped blocks without dividing the image into sub blocks. The experimental results are provided for power, area and hardware utilization. The proposed design is smaller and faster than designs with multiplier based designs. This is, to our knowledge, the first hardware design paper that provides BDWT image processor from theory description to the front-end synthesis.

Discrete wavelet transform (DWT) has shown great performance in digital image compression and denoising applications. It has been the transformation used for source encoding in JPEG2000 still image compression standard and FBI wavelet scalar quantization. This paper has adopted the lifting DWT which is the most computation-efficient scheme of wavelet analysis and outlines the multi-resolution features of the wavelet transform. Details of the lifting wavelet transform are analyzed to propose a high-speed, less-area and power-efficient digital image compression scheme. Maple 15 has been employed for design and simulation studies.