Inner speech recognition using electroencephalogram (EEG) signals shows strong potential for developing assistive communication technologies. Existing methods often process spatial and temporal features separately, lack interpretability, and are usually tested on a single dataset, limiting their generalization. This study proposes a dual-branch deep learning framework that combines spatial features extracted through common spatial patterns (CSPs) with spectral-temporal features derived from multitaper spectrograms, using convolutional and long short-term memory networks. The model was evaluated on two public datasets, achieving classification accuracies of 89.99% and 92.47% in subject-dependent experiments. Subject-independent evaluation using leave-one-subject-out cross-validation yielded reduced accuracies of 26.20% and 20.47%, reflecting intersubject variability. Interpretability analyses using saliency maps, gradient-weighted class activation mapping, and feature contribution ratios highlighted physiologically meaningful patterns related to model decisions. The proposed method demonstrates strong performance and interpretability for subject-dependent inner speech recognition; while future work will focus on increasing data diversity and improving subject-independent generalization. This study contributes to the development of reliable and explainable EEG-based inner speech decoding for communication applications.

Accurate and efficient recognition of cardiac arrhythmias is crucial for fast diagnosis and accurate prevention of cardiovascular diseases. This paper investigates the use of an electrocardiogram (ECG) signal analysis based on hybrid form of orthogonal polynomials, namely, Squared Krawtchouk-Tchebichef Polynomials (SKTP) to obtain accurate recognition of cardiac arrhythmias. The proposed method exploits the combined properties representation power of Krawtchouk and Tchebichef moments to capture discriminative characteristics of ECG waveforms. The SKTP has the ability to enhance the feature robustness against noise and baseline wander. ECG signals from the compiled MIT-BIH arrhythmia dataset are used for performance evaluation of the proposed method. SKTP-based features are then computed from each segment and fed into Support Vector Machine (SVM) for arrhythmia classification. Experimental results demonstrate that the proposed method achieves high recognition performance compared to the existing works, attaining an overall accuracy of 91.33%. The findings indicate that SKTP-based features provide a compact, and discriminative representation of ECG signals, making them suitable for real-time arrhythmia monitoring in wearable and telemedicine applications.

Speech enhancement algorithms and machine learning can play a fundamental role in signal processing to improve speech quality. These techniques can be used to reduce noise and distortions in speech signals, hence ensuring clearer and more intelligible speech. By leveraging advanced machine learning, speech enhancement algorithms not only improve the listener’s auditory system, but also increase the efficacy of speech recognition systems. In particular, deep learning is a class of machine learning techniques, which have recently been used in speech enhancement. This paper proposes the use of Discrete Hahn polynomials (DHPs) o extract spectral features from noisy signals using fully connected neural networks and convolutional neural network. Deep learning can efficiently capture the contextual information of speech signals, resulting in superior improvements in speech quality and intelligibility properties. The results are evaluated based on the well-known TIMIT database. The results show that the presented model is able to enhance the speech signal for different conditions.

Cloud storage capacity for surveillance videos is restricted by the massive amounts of bandwidth needed to upload them and the substantial storage space they consume. As a result, researchers are actively exploring methods to reduce file sizes while maintaining critical visual details. The goal is to achieve a balance between minimizing the storage size required and preserving video quality, all while keeping costs as low as possible and achieving the best possible results. This paper proposes a developed approach to optimize surveillance video compression. Specifically, each frame, after being acquired, is applied to extract regions of interest (ROI) where motion has occurred, ensuring that the entire desired area is captured. Next, the extracted areas with no changes are zeroed out, reducing unnecessary data. The resulting area is then encoded and transmitted. When the encoded video is received, the decoding process is carried out to restore the video to its original content, i.e., video frames. Three datasets are used to evaluate the performance of the developed algorithm. In addition, the obtained results are compared to the basic video, which shows that the developed algorithm produced good results, outperforming the MJPEG algorithm and existing algorithms.

Speech is considered the most important way for communication between humans. However, various types of noise degrade speech signals and reduce speech clarity. Usually, speech should be clear as much as possible to be used in the application at hand such as mobile telephony, Tele-communication and hearing aids systems, smart phone applications. Speech enhancement techniques aim to enhance the clarity and quality of speech, thereby improving its overall intelligibility. This is performed using various speech enhancement algorithms (SEA) like filtering, spectral subtraction, and deep learning techniques. This paper provides a brief review on different SEA, and it contains the study of several enhancement models with a discussion of their properties. An investigation of the enhancement process in time and transform domain is performed. Some basic types of background noise are explained with providing a brief description of the challenges and opportunities of speech enhancement processes. The presented paper relates to several research studies in the field of speech enhancement, observed up to 2024. This paper presented the use of enhancement techniques for suppression process through judging several enhancement algorithms for getting the best performance.

To date, cardiovascular disease (CVD) is responsible for a considerable number of deaths each year. Hence, developing an effective CVD prediction model is essential to reducing mortality rates. To this end, this paper makes use of different machine learning (ML) classifiers such as logistic regression (LG), K-nearest neighbor (KNN), support vector machine (SVM), gradient boosting (GB), and adaptive boosting (AdaB) to improve CVD prediction performance. In addition, this paper investigates the use of ML based on the ANOVA feature selection method and voting ensemble model by aggregating different ML classifiers to improve CVD prediction. The CVD performance is evaluated using key metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The results demonstrate that the proposed approach achieves the highest CVD prediction accuracy compared to state-of-the-art methods recording 93.44%. The findings obtained in this paper suggest that the SVM ANOVA feature selection and ensemble approaches can be considered practical strategies for improving the prediction accuracy of CVD.

Discrete Hahn moments are considered efficient orthogonal moments applied in various scientific areas such as signal processing and computer vision. It has a high energy compaction, considered an advantage for speech enhancement algorithm (SEA). Most conventional SEA present undesirable distortion to the improved signal. Minimizing these issues demands a robust estimator. Therefore, this paper presents Hahn moments-based linear and non-linear estimators. Wiener filter and minimum mean squared error (MMSE) sense are used to form the estimators. These estimators with Hahn moments reduce the distortion in various underlying speech conditions. The presented SEA is evaluated in terms of different quality and intelligibility measurements. The experimental results show the advantage and effectiveness of the proposed system over other existing works.

Machine learning, a part of artificial intelligence, is recently used in speech enhancement algorithms (SE). The primary focus of SE is finding the original speech signal from the distorted one. Specifically, deep learning is used in SE because it handles nonlinear mapping problems for complicated features. In this paper, Charlier polynomials-based discrete transform, simply discrete Charlier transform (DCHT), has been used to get the spectra of the noisy signal using a fully connected neural network. Deep learning effectively acquires the context information of speech signal and gets enhanced speech with good quality and intelligibility properties. The proposed algorithm is tested experimentally through self-comparison to obtain the best speech enhancement models corresponding to the DCHT parameter. The experiment is performed with different values of the DCHT parameter. In addition, the well-known TIMIT database is used for evaluation purposes. Different speech measures are used in the experiment. The realized results show the ability of the trained model based on DCHT to enhance the speech signal and provide good results on specific conditions.

Abstract pattern is very commonly used in the textile and fashion industry. Pattern design is an area where designers need to come up with new and attractive patterns every day. It is very difficult to find employees with a sufficient creative mindset and the necessary skills to come up with new unseen attractive designs. Therefore, it would be ideal to identify a process that would allow for these patterns to be generated on their own with little to no human interaction. This can be achieved using deep learning models and techniques. One of the most recent and promising tools to solve this type of problem is Generative Adversarial Networks (GANs). In this paper, we investigate the suitability of GAN in producing abstract patterns. We achieve this by generating abstract design patterns using the two most popular GANs, namely Deep Convolutional GAN and Wasserstein GAN. By identifying the best-performing model after training using hyperparameter optimization and generating some output patterns we show that Wasserstein GAN is superior to Deep Convolutional GAN.

Amongst different types of cancer, skin cancer has shown an increasing trend over the decade. Skin cancer is mainly caused due to exposure of human skin to ultraviolet rays, due to overexposure to the sun. Early diagnosis of skin cancer can help in preventing the further spread of the deadly disease. But there is a lack of clinical services and expertise, and this situation has worsened due to the ongoing pandemic. An automated system to guide the clinicians is the need of the hour. There are a lot of AI-based systems developed using datasets that are publicly available. Especially, deep learning-based solutions are available which detect the malignancy and classify it into a particular type of malignancy. CNN is a proven technology in the diagnosis of skin cancer. Various models based on transfer learning have been developed. The various systems that have been developed are still in the early stages of clinical deployment. There are still many challenges and open issues. It is proposed to investigate the work done so far and to develop a model with matching or improved performance. HAM 10000 dataset containing dermoscopic images is used for the research work. Dataset preprocessing is done to resize the images and to augment the dataset. The class imbalance has been addressed using data augmentation. Three models have been trained and tested. CNN-based, MobileNet V2 and Resnet50 based models have been built and tested. Achieved a validation accuracy of 86% for CNN, 96% for MobileNet and 89% for ResNet50.

Summary Discrete Tchebichef polynomials (DTPs) and their moments are effectively utilized in different fields such as video and image coding, pattern recognition, and computer vision due to their remarkable performance. However, when the moments order becomes large (high), DTPs prone to exhibit numerical instabilities. In this article, a computationally efficient and numerically stable recurrence algorithm is proposed for high order of moment. The proposed algorithm is based on combining two recurrence algorithms, which are the recurrence relations in the and ‐directions. In addition, an adaptive threshold is used to stabilize the generation of the DTP coefficients. The designed algorithm can generate the DTP coefficients for high moment's order and large signal size. By large signal size, we mean the samples of the discrete signal are large. To evaluate the performance of the proposed algorithm, a comparison study is performed with state‐of‐the‐art algorithms in terms of computational cost and capability of generating DTPs with large polynomial size and high moment order. The results show that the proposed algorithm has a remarkably low computation cost and is numerically stable, where the proposed algorithm is 27 times faster than the state‐of‐the‐art algorithm.

To control and manage traffics as well as guide the driver on roads, the lines on the roads are used. In addition, these lines serve as barriers and to ensure the safe, smooth and harmonious flow of traffic. However, in some countries, these lines are missed and causes the driving chaos; and thus, car accidents happen. A car accident is one of the most causes of death and the majority of the accident are due to human error. This research works aims to help driver to provide safety roads and reduces or eliminate care accidents. Object detection is a technique used to find and locate objects in images. In this works, YOLO Version 3 is the network used to detect the object in the frame because of its speed, simplicity, and ability to predict as well as classify objects. In addition, a steering angle circuit is designed and implemented to measure the direction of the car. The steering angle measurements is used with object detection (vehicles and pedestrians) to issue a warning when these objects are close to the driving car (10 meters). After the objects are detected using YOLO V3, the distance of the detected objects is measured using the height of the object. While being affordable and low-cost, the system achieved positive and competitive results, this system can be used at night and in dark environments.

Large number of image datasets have been generated with diverse functionality and applications. This is because of the development in communication technologies and affordable image acquisition devices. However, the generated image datasets require an efficient search engine to retrieve images that meet the needs of end-user. Content-Based Image Retrieval (CBIR) is an automatic mechanism to retrieve images from relevant class according to their visual content. In this paper, local and global features are combined to provide a powerful image descriptor. CBIR performance is measured through two major key factors which are: accuracy and retrieval time. The first one is related to the amount of retrieved images from the same semantic class while the latter is related to the speed of the search. There is a tradeoff between these two factors. In this regard, this paper proposes CBIR algorithm based on feature fusion and support vector machine (SVM). The feature are texture, shape, and color features. The statistical moments, mean and standard deviation are calculated after transforming the RGB channels to moments' domain through the use of SKTP to construct the color descriptor. Canny Edge Detection and LBP are utilized to construct edge and texture descriptors, respectively. WANG dataset is used to assess the performance of the proposed algorithms. The proposed algorithm focused on achieving an interesting accuracy level (90.15 %) through the use of SVM classifier. Thus, the proposed algorithm achieved its goal and outperformed existing algorithms.

Medical images and videos are utilized to discover, diagnose and treat diseases. Managing, storing, and retrieving stored images effectively are considered important topics. The rapid growth of multimedia data, including medical images and videos, has caused a swift rise in data transmission volume and repository size. Multimedia data contains useful information; however, it consumes an enormous storage space. Therefore, high processing time for that sheer volume of data will be required. Image and video applications demand for reduction in computational cost (processing time) when extracting features. This paper introduces a novel method to compute transform coefficients (features) from images or video frames. These features are used to represent the local visual content of images and video frames. We compared the proposed method with the traditional approach of feature extraction using a standard image technique. Furthermore, the proposed method is employed for shot boundary detection (SBD) applications to detect transitions in video frames. The standard TRECVID 2005, 2006, and 2007 video datasets are used to evaluate the performance of the SBD applications. The achieved results show that the proposed algorithm significantly reduces the computational cost in comparison to the traditional method.

Discrete orthogonal functions are important tools in digital signal processing. These functions received considerable attention in the last few decades. This study proposes a new set of orthogonal functions called discrete Krawtchouk–Tchebichef transform (DKTT). Two traditional orthogonal polynomials, namely, Krawtchouk and Tchebichef, are combined to form DKTT. The theoretical and mathematical frameworks of the proposed transform are provided. DKTT was tested using speech and image signals from a well‐known database under clean and noisy environments. DKTT was applied in a speech enhancement algorithm to evaluate the efficient removal of noise from speech signal. The performance of DKTT was compared with that of standard transforms. Different types of distance (similarity index) and objective measures in terms of image quality, speech quality, and speech intelligibility assessments were used for comparison. Experimental tests show that DKTT exhibited remarkable achievements and excellent results in signal compression and speech enhancement. Therefore, DKTT can be considered as a new set of orthogonal functions for futuristic applications of signal processing.