This paper presents two efficient frameworks for seizure detection and prediction that depend on statistical analysis. The common thread between them is the selection of certain attributes extracted from the electroencephalography (EEG) signals and the derivation of probability density functions (PDFs) of these attributes in two different types of activities of EEG signals. The first framework is for seizure detection based on scale-invariant feature transform (SIFT). Its idea is to choose some segments for normal and seizure activities. These segments are transformed to 2D matrices to be treated with the well-known SIFT. The feature key-points are extracted from those 2D matrices. The parameter that is used to discriminate between normal and seizure activities is the number of key-points. The PDFs of the number of key-points in cases of normal and seizure activities are estimated and a threshold value is used to classify any new segment as either a seizure or a normal segment. The other framework is for seizure prediction. The discrimination in this case is between normal and pre-ictal activities. A statistical treatment is performed on five attributes extracted from the wavelet transforms of different EEG segments for normal and pre-ictal activities. These attributes are amplitude, local mean, local variance, median and derivative. All PDFs of these attributes are estimated for normal and pre-ictal activities. Thresholds are set for all attributes. Decisions are taken based on these thresholds. Finally, a majority-voting strategy is used to merge decisions taken for all attributes.

This paper is mainly concerned with video watermarking as a tool to secure the video transmission process over wireless channels. In addition, the relatability of the communication process is guaranteed through a hybrid error control scheme. The watermarking depends on applying a hybrid structure of Block-based Singular Value Decomposition (B-SVD) and SVD schemes. The rationale behind the utilization of SVD for video watermarking is the fact that singular values of a frame are not severely affected by noise or disturbance induced on that frame. The error control is performed with an efficient hybrid post-processing scheme, which comprises Spatial Circular-Scan Order Interpolation Algorithm (CSOIA), temporal Partitioning Motion Compensation Algorithm (PMCA) and Bayesian Kalman Filter (BKF). In the proposed framework, cornea and infrared frames are watermarked using two stages of SVD watermarking. The watermarking scheme includes embedding and extraction stages. Two watermark images are embedded in the cornea and infrared frames in the embedding stage using the hybrid structure of B-SVD and SVD schemes. Next, the watermarked cornea or infrared frames are transmitted through the erroneous wireless channel. The received corrupted cornea or infrared frames are recovered using the proposed post-processing error control schemes. Finally, the inverse process of hybrid SVD and B-SVD is employed in the watermark extraction stage. Simulation results for several cornea and infrared frames show that the proposed framework has extremely adequate subjective and objective video quality metrics compared to the traditional methods. In addition, the watermark robustness, security, and detectability are enhanced. Moreover, the experimental results clarify that the proposed watermarking scheme is superior and more secure than the other previous schemes for embedding and extracting watermarks efficiently in the presence of attacks.

Automatic seizure detection and prediction using clinical Electroencephalograms (EEGs) are challenging tasks due to factors such as low Signal-to-Noise Ratios (SNRs), high variance in epileptic seizures among patients, and limited clinical data constraints. To overcome these challenges, this paper presents two approaches for EEG signal classification. One of these approaches depends on Machine Learning (ML) tools. The used features are different types of entropy, higher-order statistics, and sub-band energies in the Hilbert Marginal Spectrum (HMS) domain. The classification is performed using Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbor (KNN) classifiers. Both seizure detection and prediction scenarios are considered. The second approach depends on spectrograms of EEG signal segments and a Convolutional Neural Network (CNN)-based residual learning model. We use 10000 spectrogram images for each class. In this approach, it is possible to perform both seizure detection and prediction in addition to a 3-state classification scenario. Both approaches are evaluated on the Children’s Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) dataset, which contains 24 EEG recordings for 6 males and 18 females. The results obtained for the HMS-based model showed an accuracy of 100

Electroencephalography (EEG) is among the main tools used for analyzing and diagnosing epilepsy. The manual analysis of EEG must be conducted by highly trained clinicians or neuro-physiologists; a process that is considered to have a comparatively low inter-rater agreement. Furthermore, the new data interpretation consumes an excessive amount of time and resources. Hence, an automatic seizure detection and prediction system can improve the quality of patient care in terms of shortening the diagnosis period, reducing manual errors, and automatically detecting debilitating events. Moreover, for patient treatment, it is important to alert the patients of epilepsy seizures prior to seizure occurrence. Various distinguished studies presented good solutions for two-class seizure detection problems with binary classification scenarios. To deal with these challenges, this paper puts forward effective approaches for EEG signal classification for normal, pre-ictal, and ictal activities. Three models are presented for the classification task. Two of them are patient-specific, while the third one is patient non-specific, which makes it better for the general classification tasks. The two-class classification is implemented between normal and pre-ictal activities for seizure prediction and between normal and ictal activities for seizure detection. A more generalized three-class classification framework is considered to identify all EEG signal activities. The first model depends on a Convolutional Neural Network (CNN) with residual blocks. It contains thirteen layers with four residual learning blocks. It works on spectrograms of EEG signal segments. The second model depends on a CNN with three layers. It also works on spectrograms. On the other hand, the third model depends on Phase Space Reconstruction (PSR) to eliminate the limitations of the spectrograms used in the first models. A five-layer CNN is used with this strategy. The advantage of the PSR is the direct projection from the time domain, which keeps the main trend of different signal activities. The third model deals with all signal activities, and it was tested for all patients of the CHB-MIT dataset. It has a superior performance compared to the first models and the state-of-the-art models.

Abstract In the Artificial Intelligence (AI) field, the deep learning is considered a method falls in the wide machine learning algorithms family based on the learning principle. The known traditional and Conventional Neural Networks (CNNs) have been utilized in the pattern recognition techniques based on the deep learning concepts from different images. Due to the importance of the Anomaly Detection (AD) in automatic diagnosis, it is essential and vital point in the image and medical signal processing. In this paper, the AD has been tested and evaluated using the signals of the medical EEG employing the spectrogram and medical corneal images. The deep learning based on the CNN models are employed in the processes of training and testing, each image input passes through a convolution layers series and Kernels filters. For the classification, the pooling and Fully Connected (FC) layers have been utilized for this purpose. In this research paper, the experiments computer simulation have been presented, its results reveal that the success and superiority of the presented proposed techniques in the automated medical diagnosis.

Low-frequency signals comprise different types such as Electroencephalogram (EEG), gyroscope and seismic signals. Processing of EEG signals is performed for tasks such as seizure prediction and detection. On the other hand, processing of seismic and gyroscope signals is performed for tasks such as activity classification. This paper presents two efficient models for anticipation of anomalies from low-frequency signals. A detailed study of EEG seizure prediction is introduced in this paper based on wavelet-domain processing and compression techniques as an example. The first model uses different families of wavelet transform, while the second one concentrates on lossy compression techniques and their effect on further processing for seizure prediction in a realistic signal acquisition and compression scenario. The prediction approach adopts statistical processing with training and testing phases. The training phase comprises estimation of six signal attributes: amplitude, derivative, local mean, local variance, local median and entropy. On the other hand, the testing phase is performed with a thresholding strategy on the selected  probability bins. A majority voting strategy with a moving average smoothing filter is used for decision making. The suggested models are executed on long-term EEG recordings from the available Physio-Net EEG dataset. Simulation results in the first model show that the Daubechies wavelets demonstrate the best prediction results as the filter lengths in these wavelets are longer than those in the Haar wavelet. The obtained results in the second model prove the feasibility of lossy compression, especially Discrete Cosine Transform (DCT) compression for seizure prediction.

Deep learning is one of the most promising machine learning techniques that revolutionalized the artificial intelligence field. The known traditional and convolutional neural networks (CNNs) have been utilized in medical pattern recognition applications that depend on deep learning concepts. This is attributed to the importance of anomaly detection (AD) in automatic diagnosis systems. In this paper, the AD is performed on medical electroencephalography (EEG) signal spectrograms and medical corneal images for Internet of medical things (IoMT) systems. Deep learning based on the CNN models is employed for this task with training and testing phases. Each input image passes through a series of convolution layers with different kernel filters. For the classification task, pooling and fully-connected layers are utilized. Computer simulation experiments reveal the success and superiority of the proposed models for automated medical diagnosis in IoMT systems.

In this paper, we present hybrid watermarking and error control techniques for reliable cornea and infrared frame communication through wireless networks in Internet of Things (IoT) applications. In the proposed watermarking technique, two stages of Singular Value Decomposition (SVD) watermarking are used. In the embedding stage, two watermark images are embedded in either the cornea or infrared frames using Block-based SVD (B-SVD) and SVD schemes, respectively. Then, the resulting watermarked cornea or infrared frames are transmitted through an erroneous wireless channel. At the receiver, the received corrupted cornea or infrared frames are recovered using a proposed hybrid post-processing error control technique. This technique comprises a Circular Spatial-scan Order Interpolation Algorithm (CSOIA) and a temporal Partitioning Motion Compensation Algorithm (PMCA) to reconstruct the erroneous cornea or infrared frames. Then, the Bayesian Kalman Filter (BKF) is utilized in the amelioration process due to its efficiency to smooth the remanent inherent corruptions in the formerly reconstructed frames to obtain high cornea or infrared video quality. After that, the watermark extraction stage is implemented to extract the watermark images from the watermarked frames. Simulation results on several cornea and infrared frames show that the suggested hybrid watermarking, and error control techniques reveal adequate subjective and objective video quality compared to those obtained with the traditional methods. In addition, the watermark detectability, robustness, and security are enhanced. Moreover, the experimental results show that the proposed watermarking technique is superior and more secure than the other previous techniques for embedding and extraction of watermarks, efficiently, in the presence of attacks.

In the field of Artificial Intelligence (AI), deep learning is a method falls in the wider family of machine learning algorithms that works on the principle of learning. Convolutional Neural Networks (CNNs) can be used for pattern recognition from different images based on deep learning. Anomaly detection is a very vital area in medical signal and image processing due to its importance in automatic diagnosis. Anomaly detection from medical EEG signals based on spectrogram and medical corneal images are tested and evaluated in this paper. Technically, deep learning CNN models are used in the train and test processes, each input image will pass through a series of convolution layers with filters (Kernels), pooling, and fully connected layers (FC) for the classification purposes. The presented simulation results reveal the success of the proposed techniques towards automated medical diagnosis.

This paper presents a patient-specific approach for electroencephalography (EEG) channel selection and seizure prediction based on statistical probability distributions of the EEG signals. This approach has two main phases; training and testing phases. In the training phase, few hours of multi-channel nature for each patient representing normal, pre-ictal, and ictal activities are selected. These hours are segmented into non-overlapping 10-s segments and probability density functions (PDFs) are estimated for the signals, their derivatives, local means, local variances, and medians. These PDFs have multiple bins, which are studied separately as random variables across different segments of the same nature. Depending on the PDFs of these random variables for different signal activities and on predefined prediction and false-alarm probability thresholds, bins are selected from certain channel distributions for seizure prediction. In the testing phase, the selected bins only are used for classification of each signal segment activity into pre-ictal or normal states in the prediction process. In the final prediction step, an equal gain decision fusion process is performed leading to a discrete decision sequence representing the activities of all segments. This sequence is filtered with a moving average filter and compared to a patient-specific prediction threshold. Moreover, we have studied the effect of a lossy compression technique on the accuracy of the proposed algorithm using discrete sine transform (DST) compression. This system can be implemented for communication between headset and mobile to give alerts for patients.

Anomaly detection is a very vital area in medical signal and image processing due to its importance in automatic diagnosis. This paper presents three efficient anomaly detection approaches for applications related to Electroencephalogram (EEG) signal processing and retinal image processing. The first approach depends on the utilization of Scale-Invariant Feature Transform (SIFT) for automatic seizure detection. The second one is based on the utilization of digital filters in a statistical framework for seizure prediction. Finally, an automated Diabetic Retinopathy (DR) diagnosis approach is presented based on the segmentation and detection of anomalous objects from retinal images. The presented simulation results reveal the success of the proposed techniques towards automated medical diagnosis.