Search

Precision and timeliness in breast cancer detection are paramount for improving patient outcomes. Traditional diagnostic methods have predominantly relied on unimodal approaches, but recent advancements in medical data analytics have enabled the integration of diverse data sources beyond conventional imaging techniques. This review critically examines the transformative potential of integrating histopathology images with genomic data, clinical records, and patient histories to enhance diagnostic accuracy and comprehensiveness in multi-modal diagnostic techniques. It explores early, intermediate, and late fusion methods, as well as advanced deep multimodal fusion techniques, including encoder-decoder architectures, attention-based mechanisms, and graph neural networks. An overview of recent advancements in multimodal tasks such as Visual Question Answering (VQA), report generation, semantic segmentation, and cross-modal retrieval is provided, highlighting the utilization of generative AI and visual language models. Additionally, the review delves into the role of Explainable Artificial Intelligence (XAI) in elucidating the decision-making processes of sophisticated diagnostic algorithms, emphasizing the critical need for transparency and interpretability. By showcasing the importance of explainability, we demonstrate how XAI methods, including Grad-CAM, SHAP, LIME, trainable attention, and image captioning, enhance diagnostic precision, strengthen clinician confidence, and foster patient engagement. The review also discusses the latest XAI developments, such as X-VARs, LeGrad, LangXAI, LVLM-Interpret, and ex-ILP, to demonstrate their potential utility in multimodal breast cancer detection, while identifying key research gaps and proposing future directions for advancing the field.

Due to the availability of massive numbers of items for any product on the Web, the burden of selecting an item is borne by the user. A Recommender System (RS) is a useful tool that has been employed to save the user’s time by recommending preferred items for him/her efficiently. Collaborative-based RS’s use the latent factor or/and the neighbourhood techniques including matrix factorization (MF), which is an efficient approach utilizing latent factors. The idea of the approach is based on calculating similarities through between users and items simultaneously, to predict appropriate recommendations. MF can be seen as mathematical model capable to split an entity into multiple smaller entries through an ordered rectangular array of functions, to discover the features or information underlying the interactions between users and items. The technique factorizes the user-item rating matrix ( $R$ ) (first-level factorization) into users ( $P$ ) and items ( $Q$ ) matrices. A recent RS system, named NLM, combines the neighbourhood and the latent factor techniques to produce attractive results. This paper proposes to improve the NLM method by proposing a more effective technique, named NLM+, by further factorizing $P$ and $Q$ using MF (second-level factorization). To the best of our knowledge, current studies in this field have not considered the use of the aforementioned two levels of factorizing. To validate our method, CiaoDVD, MovieLens, and FilmTrust datasets have been used and incorporated to demonstrate that NLM+ improves NLM by 48% and 42% in the recall and the precision values, respectively.

Objective: Millions of people have been affected by coronavirus disease 2019 (COVID-19), which has caused millions of deaths around the world. Artificial intelligence (AI) plays an increasing role in all areas of patient care, including prognostics. This paper proposes a novel predictive model based on one dimensional convolutional neural networks (1D CNN) to use clinical variables in predicting the survival outcome of COVID-19 patients. Methods and procedures: We have considered two scenarios for survival analysis, 1) uni-variate analysis using the Log-rank test and Kaplan-Meier estimator and 2) combining all clinical variables ( $n$ =44) for predicting the short-term from long-term survival. We considered the random forest (RF) model as a baseline model, comparing to our proposed 1D CNN in predicting survival groups. Results: Our experiments using the univariate analysis show that nine clinical variables are significantly associated with the survival outcome with corrected p < 0.05. Our approach of 1D CNN shows a significant improvement in performance metrics compared to the RF and the state-of-the-art techniques (i.e., 1D CNN) in predicting the survival group of patients with COVID-19. Conclusion: Our model has been tested using clinical variables, where the performance is found promising. The 1D CNN model could be a useful tool for detecting the risk of mortality and developing treatment plans in a timely manner. Clinical impact: The findings indicate that using both Heparin and Exnox for treatment is typically the most useful factor in predicting a patient’s chances of survival from COVID-19. Moreover, our predictive model shows that the combination of AI and clinical data can be applied to point-of-care services through fast-learning healthcare systems.

Abstract Steganography is the art of secret communication and steganalysis is the art of detecting the hidden messages embedded in digital media covers. One of the covers that is gaining interest in the field is video. Presently, the global IP video traffic forms the major part of all consumer Internet traffic. It is also gaining attention in the field of digital forensics and homeland security in which threats of covert communications hold serious consequences. Thus, steganography technicians will prefer video to other types of covers like audio files, still images, or texts. Moreover, video steganography will be of more interest because it provides more concealing capacity. Contrariwise, investigation in video steganalysis methods does not seem to follow the momentum even if law enforcement agencies and governments around the world support and encourage investigation in this field. In this paper, the authors review the most important methods used so far in video steganalysis and sketch the future trends. To the best of the authors’ knowledge this is the most comprehensive review of video steganalysis produced so far.

Precise prediction on brain age is urgently needed by many biomedical areas including mental rehabilitation prognosis as well as various medicine or treatment trials. People began to realize that contrasting physical (real) age and predicted brain age can help to highlight brain issues and evaluate if patients’ brains are healthy or not. Such age prediction is often challenging for single model-based prediction, while the conditions of brains vary drastically over age. In this work, we present an age-adaptive ensemble model that is based on the combination of four different machine learning algorithms, including a support vector machine (SVR), a convolutional neural network (CNN) model, and the popular GoogLeNet and ResNet deep networks. The ensemble model proposed here is nonlinearly adaptive, where age is taken as a key factor in the nonlinear combination of various single-algorithm-based independent models. In our age-adaptive ensemble method, the weights of each model are learned automatically as nonlinear functions over age instead of fixed values, while brain age estimation is based on such an age-adaptive integration of various single models. The quality of the model is quantified by the mean absolute errors (MAE) and spearman correlation between the predicted age and the actual age, with the least MAE and the highest Spearman correlation representing the highest accuracy in age prediction. By testing on the Predictive Analysis Challenge 2019 (PAC 2019) dataset, our novel ensemble model has achieved a MAE down to 3.19, which is a significantly increased accuracy in this brain age competition. If deployed in the real world, our novel ensemble model having an improved accuracy could potentially help doctors to identify the risk of brain diseases more accurately and quickly, thus helping pharmaceutical companies develop drugs or treatments precisely, and potential offer a new powerful tool for researchers in the field of brain science.

The carotid artery is a major blood vessel that supplies blood to the brain. Plaque buildup in the arteries can lead to cardiovascular diseases such as atherosclerosis, stroke, ruptured arteries, and even death. Both invasive and non-invasive methods are used to detect plaque buildup in the arteries, with ultrasound imaging being the first line of diagnosis. This paper presents a comprehensive review of the existing literature on ultrasound image analysis methods for detecting and characterizing plaque buildup in the carotid artery. The review includes an in-depth analysis of datasets; image segmentation techniques for the carotid artery plaque area, lumen area, and intima–media thickness (IMT); and plaque measurement, characterization, classification, and stenosis grading using deep learning and machine learning. Additionally, the paper provides an overview of the performance of these methods, including challenges in analysis, and future directions for research.

The electroencephalography (EEG) signal is a noninvasive and complex signal that has numerous applications in biomedical fields, including sleep and the brain–computer interface. Given its complexity, researchers have proposed several advanced preprocessing and feature extraction methods to analyze EEG signals. In this study, we analyze a comprehensive review of numerous articles related to EEG signal processing. We searched the major scientific and engineering databases and summarized the results of our findings. Our survey encompassed the entire process of EEG signal processing, from acquisition and pretreatment (denoising) to feature extraction, classification, and application. We present a detailed discussion and comparison of various methods and techniques used for EEG signal processing. Additionally, we identify the current limitations of these techniques and analyze their future development trends. We conclude by offering some suggestions for future research in the field of EEG signal processing.

Common carotid intima-media thickness (CIMT) is a common measure of atherosclerosis, often assessed through carotid ultrasound images. However, the use of deep learning methods for medical image analysis, segmentation and CIMT measurement in these images has not been extensively explored. This study aims to evaluate the performance of four recent deep learning models, including a convolutional neural network (CNN), a self-organizing operational neural network (self-ONN), a transformer-based network and a pixel difference convolution-based network, in segmenting the intima-media complex (IMC) using the CUBS dataset, which includes ultrasound images acquired from both sides of the neck of 1088 participants. The results show that the self-ONN model outperforms the conventional CNN-based model, while the pixel difference- and transformer-based models achieve the best segmentation performance.

Quantum machine learning (QML) is a new field in its infancy, promising performance enhancements over many classical machine learning (ML) algorithms. Data reuploading is a QML algorithm with a focus on utilizing the power of a singular qubit as an individually capable classifier. Recently, there have been studies set out to explore the concept of data re-uploading in a classification setting, however, important aspects are often not considered in experiments, which may hinder our understanding of the methodology’s performance. In this work, we conduct an analysis of the single-qubit data re-uploading methodology, in relation to the effect that system depth has on classification and robustness performances against the influence of environmental noise during training. This is aimed towards bridging together previous works in order to solidify the concepts of the methodology, and provide reasonable insight into how transferable the methodology is when applied to non-synthetic data. To further demonstrate the findings, we also analyse the results of a case study using a subset of MNIST data. From this work, our experimental results support that an increase in system depth can lead to higher classification performances, as well as improved stability during training in noisy environments, with the sharpest performance improvements seemingly occurring between 1–3 uploading layer repetitions. Leading on from our experimental results, we suggest areas for further exploration, to ensure we can maximize classification performance when using the data re-uploading methodology.

Image steganography is used to hide a secret image inside a cover image in plain sight. Traditionally, the secret data is converted into binary bits and the cover image is manipulated statistically to embed the secret binary bits. Overloading the cover image may lead to distortions and the secret information may become visible. Hence the hiding capacity of the traditional methods are limited. In this paper, a light-weight yet simple deep convolutional autoencoder architecture is proposed to embed a secret image inside a cover image as well as to extract the embedded secret image from the stego image. The proposed method is evaluated using three datasets - COCO, CelebA and ImageNet. Peak Signal-to-Noise Ratio, hiding capacity and imperceptibility results on the test set are used to measure the performance. The proposed method has been evaluated using various images including Lena, airplane, baboon and peppers and compared against other traditional image steganography methods. The experimental results have demonstrated that the proposed method has higher hiding capacity, security and robustness, and imperceptibility performances than other deep learning image steganography methods.

Image Steganography is the process of hiding information which can be text, image or video inside a cover image. The secret information is hidden in a way that it not visible to the human eyes. Deep learning technology, which has emerged as a powerful tool in various applications including image steganography, has received increased attention recently. The main goal of this paper is to explore and discuss various deep learning methods available in image steganography field. Deep learning techniques used for image steganography can be broadly divided into three categories - traditional methods, Convolutional Neural Network-based and General Adversarial Network-based methods. Along with the methodology, an elaborate summary on the datasets used, experimental set-ups considered and the evaluation metrics commonly used are described in this paper. A table summarizing all the details are also provided for easy reference. This paper aims to help the fellow researchers by compiling the current trends, challenges and some future direction in this field.

Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.

The prevalent use of surveillance cameras in public places and advancements in computer vision warrant most sought-after research in the domain of anomalous activity detection. Anomaly detection has shown promising applications for suspicious activity detection. In this paper, we propose a bagging framework IBaggedFCNet that leverages the power of ensembles for robust classification to detect anomalies in videos. Our approach, which investigates state-of-the-art Inception-v3 image classification network, requires no video segmentation prior to feature extraction that can produce unstable segmentation results and cause a high memory footprint. We show improvement empirically on multiple benchmark datasets, most prominently on the UCF-Crime dataset. Moreover, we experiment with different ensemble fusion methods, including static and dynamic techniques, and also prove our single model's predictive accuracy in localizing anomaly in surveillance videos.

Malware, a lethal weapon of cyber attackers, is becoming increasingly sophisticated, with rapid deployment and self-propagation. In addition, modern malware is one of the most devastating forms of cybercrime, as it can avoid detection, make digital forensics investigation in near real-time impossible, and the impact of advanced evasion strategies can be severe and far-reaching. This makes it necessary to detect it in a timely and autonomous manner for effective analysis. This work proposes a new systematic approach to identifying modern malware using dynamic deep learning-based methods combined with heuristic approaches to classify and detect five modern malware families: adware, Radware, rootkit, SMS malware, and ransomware. Our symmetry investigation in artificial intelligence and cybersecurity analytics will enhance malware detection, analysis, and mitigation abilities to provide resilient cyber systems against cyber threats. We validated our approach using a dataset that specifically contains recent malicious software to demonstrate that the model achieves its goals and responds to real-world requirements in terms of effectiveness and efficiency. The experimental results indicate that the combination of behavior-based deep learning and heuristic-based approaches for malware detection and classification outperforms the use of static deep learning methods.

Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient’s symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.

Abstract Background Due to the presence of high noise level in tomographic series of energy filtered transmission electron microscopy (EFTEM) images, alignment and 3D reconstruction steps become so difficult. To improve the alignment process which will in turn allow a more accurate and better three dimensional tomography reconstructions, a preprocessing step should be applied to the EFTEM data series. Results Experiments with real EFTEM data series at low SNR, show the feasibility and the accuracy of the proposed denoising approach being competitive with the best existing methods for Poisson image denoising. The effectiveness of the proposed denoising approach is thanks to the use of a nonparametric Bayesian estimation in the Contourlet Transform with Sharp Frequency Localization Domain (CTSD) and variance stabilizing transformation (VST). Furthermore, the optimal inverse Anscome transformation to obtain the final estimate of the denoised images, has allowed an accurate tomography reconstruction. Conclusion The proposed approach provides qualitative information on the 3D distribution of individual chemical elements on the considered sample.

Despite the significant improvement in accuracy supervised learning has brought into person re-identification (re-id), the availability of sufficient fully annotated data from concerned camera-views poses a problem for real-life applications. To alleviate the burden of intensive data annotation, one way is to resort to unsupervised methods. This has motivated us to propose a novel algorithm for unsupervised video-based person re-id applications. To achieve this, the frames of a person video tracklet are divided into a set of clusters that are subsequently matched using a distance measure based on the Naive Bayes nearest neighbor algorithm and Spearman distance. Knowing that person's sequences may suffer from substantial changes in viewpoint, pose, and illumination distortions, our technique allows the rejection of poor and noisy clusters while retaining the most discriminative ones for matching. Experiments on three widely used datasets for video person re-id PRID2011, iLIDS-VID and MARS have been carried out, and the results demonstrate the superiority of the proposed approach.

The capability to perform facial analysis from video sequences has significant potential to positively impact in many areas of life. One such area relates to the medical domain to specifically aid in the diagnosis and rehabilitation of patients with facial palsy. With this application in mind, this paper presents an end-to-end framework, named 3DPalsyNet, for the tasks of mouth motion recognition and facial palsy grading. 3DPalsyNet utilizes a 3D CNN architecture with a ResNet backbone for the prediction of these dynamic tasks. Leveraging transfer learning from a 3D CNNs pre-trained on the Kinetics data set for general action recognition, the model is modified to apply joint supervised learning using center and softmax loss concepts. 3DPalsyNet is evaluated on a test set consisting of individuals with varying ranges of facial palsy and mouth motions and the results have shown an attractive level of classification accuracy in these tasks of 82% and 86% respectively. The frame duration and the loss function affect was studied in terms of the predictive qualities of the proposed 3DPalsyNet, where it was found shorter frame duration's of 8 performed best for this specific task. Centre loss and softmax have shown improvements in spatio-temporal feature learning than softmax loss alone, this is in agreement with earlier work involving the spatial domain.

Undersea/subsea data collection via automated underwater vehicles (AUVs) plays an important role for marine biodiversity research, while it is often much more challenging than the data collection above ground via satellites or AUVs. To enable the automated undersea/subsea data collection system, the AUVs are expected to be able to automatically track the objects of interest through what they can “see” from their mounted underwater cameras, where videos or images could be drastically blurred and degraded in underwater lighting conditions. To solve this challenge, in this work, we propose a cascaded framework by combining a DCGAN (deep convolutional generative adversarial network) with an object detector, i.e., single-shot detector (SSD), named DCGAN+SSD, for the detection of various underwater targets from the mounted camera of an automated underwater vehicle. In our framework, our assumption is that DCGAN can be leveraged to alleviate the impact of underwater conditions and provide the object detector with a better performance for automated AUVs. To optimize the hyperparameters of our models, we applied a particle swarm optimization (PSO)-based strategy to improve the performance of our proposed model. In our experiments, we successfully verified our assumption that the DCGAN+SSD architecture can help improve the object detection toward the undersea conditions and achieve apparently better detection rates over the original SSD detector. Further experiments showed that the PSO-based optimization of our models could further improve the model in object detection toward a more robust and fair performance, making our work a promising solution for tackling the challenges in AUVs.

Gaze estimation, which is a method to determine where a person is looking at given the person’s full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with angular-error of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.

Among various palmprint identification methods proposed in the literature, sparse representation for classification (SRC) is very attractive offering high accuracy. Although SRC has good discriminative ability, its performance strongly depends on the quality of the training data. In particular, SRC suffers from two major problems: lack of training samples per class and large intra-class variations. In fact, palmprint images not only contain identity information but they also have other information, such as illumination and geometrical distortions due to the unconstrained conditions and the movement of the hand. In this case, the sparse representation assumption may not hold well in the original space since samples from different classes may be considered from the same class. This paper aims to enhance palmprint identification performance through SRC by proposing a simple yet efficient method based on an ensemble of sparse representations through an ensemble of discriminative dictionaries satisfying SRC assumption. The ensemble learning has the advantage to reduce the sensitivity due to the limited size of the training data and is performed based on random subspace sampling over 2D-PCA space while keeping the image inherent structure and information. In order to obtain discriminative dictionaries satisfying SRC assumption, a new space is learned by minimizing and maximizing the intra-class and inter-class variations using 2D-LDA. Extensive experiments are conducted on two publicly available palmprint data sets: multispectral and PolyU. Obtained results showed very promising results compared with both state-of-the-art holistic and coding methods. Besides these findings, we provide an empirical analysis of the parameters involved in the proposed technique to guide the neophyte.

The tasks of face detection and landmark localisation are a key foundation for many facial analysis applications, while great advancements have been achieved in recent years there are still challenges to increase the precision of face detection. Within this paper, we present our novel method the Integrated Deep Model (IDM), fusing two state-of-the-art deep learning architectures, namely, Faster R-CNN and a stacked hourglass for improved face detection precision and accurate landmark localisation. Integration is achieved through the application of a novel optimisation function and is shown in experimental evaluation to increase accuracy of face detection specifically precision by reducing false positive detection's by an average of 62%. Our proposed IDM method is evaluated on the Annotated Faces In-The-Wild, Annotated Facial Landmarks In The Wild and the Face Detection Dataset and Benchmark face detection test sets and shows a high level of recall and precision when compared with previously proposed methods. Landmark localisation is evaluated on the Annotated Faces In-The-Wild and 300-W test sets, this specifically focuses on localisation accuracy from detected face bounding boxes when compared with baseline evaluations using ground truth bounding boxes. Our findings highlight only a small 0.005% maximum increase in error which is more profound for the subset of facial landmarks which border the face.

While there has been a massive increase in research into face recognition, it remains a challenging problem due to conditions present in real life. This paper focuses on the inherently present issue of partial occlusion distortions in real face recognition applications. We propose an approach to tackle this problem. First, face images are divided into multiple patches before local descriptors of Local Binary Patterns and Histograms of Oriented Gradients are applied on each patch. Next, the resulting histograms are concatenated, and their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, patches are randomly selected using the concept of random sampling to finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers are combined to generate the final recognition outcome. Experimental results based on the AR face database and the Extended Yale B database show the effectiveness of our proposed technique.

Abstract Video visualization (VV) is considered to be an essential part of multimedia visual analytics. Many challenges have arisen from the enormous video content of cameras which can be solved with the help of data analytics and hence gaining importance. However, the rapid advancement of digital technologies has resulted in an explosion of video data, which stimulates the needs for creating computer graphics and visualization from videos. Particularly, in the paradigm of smart cities, video surveillance as a widely applied technology can generate huge amount of videos from 24/7 surveillance. In this paper, a state of the art algorithm has been proposed for 3D conversion from traffic video content to Google Map. Time-stamped glyph-based visualization is used effectively in outdoor surveillance videos and can be used for event-aware detection. This form of traffic visualization can potentially reduce the data complexity, having holistic view from larger collection of videos. The efficacy of the proposed scheme has been shown by acquiring several unprocessed surveillance videos and by testing our algorithm on them without their pertaining field conditions. Experimental results show that the proposed visualization technique produces promising results and found effective in conveying meaningful information while alleviating the need of searching exhaustively colossal amount of video data.

The outcome for patients diagnosed with facial palsy has been shown to be linked to rehabilitation. Dense 3D morphable models have been shown within the computer vision to create accurate representations of human faces even from single 2D images. This has the potential to provide feedback to both the patient and medical expert dealing with the rehabilitation plan. It is proposed that a framework for the creation and measuring of patient facial movement consisting of a hybrid 2D facial landmark fitting technique which shows better accuracy in testing than current methods and 3D model fitting.

In this paper, we investigate the use of invariant features for speaker recognition. Owing to their characteristics, these features are introduced to cope with the difficult and challenging problem of sensor variability and the source of performance degradation inherent in speaker recognition systems. Our experiments show: (1) the effectiveness of these features in match cases; (2) the benefit of combining these features with the mel frequency cepstral coefficients to exploit their discrimination power under uncontrolled conditions (mismatch cases). Consequently, the proposed invariant features result in a performance improvement as demonstrated by a reduction in the equal error rate and the minimum decision cost function compared to the GMM-UBM speaker recognition systems based on MFCC features.

PURPOSE:This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma. MATERIALS AND METHODS:In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models. RESULTS:Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%. CONCLUSIONS:These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.

This work investigates the problem of detecting hazardous events on roads by designing an audio surveillance system that automatically detects perilous situations such as car crashes and tire skidding. In recent years, research has shown several visual surveillance systems that have been proposed for road monitoring to detect accidents with an aim to improve safety procedures in emergency cases. However, the visual information alone cannot detect certain events such as car crashes and tire skidding, especially under adverse and visually cluttered weather conditions such as snowfall, rain, and fog. Consequently, the incorporation of microphones and audio event detectors based on audio processing can significantly enhance the detection accuracy of such surveillance systems. This paper proposes to combine time-domain, frequency-domain, and joint time-frequency features extracted from a class of quadratic time-frequency distributions (QTFDs) to detect events on roads through audio analysis and processing. Experiments were carried out using a publicly available dataset. The experimental results conform the effectiveness of the proposed approach for detecting hazardous events on roads as demonstrated by 7% improvement of accuracy rate when compared against methods that use individual temporal and spectral features.

Key predistribution schemes have been proposed as means to overcome wireless sensor network constraints such as limited communication and processing power. Two sensor nodes can establish a secure link with some probability based on the information stored in their memories, though it is not always possible that two sensor nodes may set up a secure link. In this paper, we propose a new approach that elects trusted common nodes called “Proxies†which reside on an existing secure path linking two sensor nodes. These sensor nodes are used to send the generated key which will be divided into parts (nuggets) according to the number of elected proxies. Our approach has been assessed against previously developed algorithms, and the results show that our algorithm discovers proxies more quickly which are closer to both end nodes, thus producing shorter path lengths. We have also assessed the impact of our algorithm on the average time to establish a secure link when the transmitter and receiver of the sensor nodes are “ON.†The results show the superiority of our algorithm in this regard. Overall, the proposed algorithm is well suited for wireless sensor networks.