Showing papers by "Ahmad Almadhor published in 2023"

Efficient Breast Cancer Diagnosis from Complex Mammographic Images Using Deep Convolutional Neural Network

Abstract: Medical image analysis places a significant focus on breast cancer, which poses a significant threat to women's health and contributes to many fatalities. An early and precise diagnosis of breast cancer through digital mammograms can significantly improve the accuracy of disease detection. Computer-aided diagnosis (CAD) systems must analyze the medical imagery and perform detection, segmentation, and classification processes to assist radiologists with accurately detecting breast lesions. However, early-stage mammography cancer detection is certainly difficult. The deep convolutional neural network has demonstrated exceptional results and is considered a highly effective tool in the field. This study proposes a computational framework for diagnosing breast cancer using a ResNet-50 convolutional neural network to classify mammogram images. To train and classify the INbreast dataset into benign or malignant categories, the framework utilizes transfer learning from the pretrained ResNet-50 CNN on ImageNet. The results revealed that the proposed framework achieved an outstanding classification accuracy of 93%, surpassing other models trained on the same dataset. This novel approach facilitates early diagnosis and classification of malignant and benign breast cancer, potentially saving lives and resources. These outcomes highlight that deep convolutional neural network algorithms can be trained to achieve highly accurate results in various mammograms, along with the capacity to enhance medical tools by reducing the error rate in screening mammograms.

Toward explainable AI-empowered cognitive health assessment

Abstract: Explainable artificial intelligence (XAI) is of paramount importance to various domains, including healthcare, fitness, skill assessment, and personal assistants, to understand and explain the decision-making process of the artificial intelligence (AI) model. Smart homes embedded with smart devices and sensors enabled many context-aware applications to recognize physical activities. This study presents XAI-HAR, a novel XAI-empowered human activity recognition (HAR) approach based on key features identified from the data collected from sensors located at different places in a smart home. XAI-HAR identifies a set of new features (i.e., the total number of sensors used in a specific activity), as physical key features selection (PKFS) based on weighting criteria. Next, it presents statistical key features selection (SKFS) (i.e., mean, standard deviation) to handle the outliers and higher class variance. The proposed XAI-HAR is evaluated using machine learning models, namely, random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB) and deep learning models such as deep neural network (DNN), convolution neural network (CNN), and CNN-based long short-term memory (CNN-LSTM). Experiments demonstrate the superior performance of XAI-HAR using RF classifier over all other machine learning and deep learning models. For explainability, XAI-HAR uses Local Interpretable Model Agnostic (LIME) with an RF classifier. XAI-HAR achieves 0.96% of F-score for health and dementia classification and 0.95 and 0.97% for activity recognition of dementia and healthy individuals, respectively.

E2E-DASR: End-to-end deep learning-based dysarthric automatic speech recognition

Abstract: Dysarthria is a motor speech disability caused by weak muscles and organs involved in the articulation process, thereby affecting the speech intelligibility of individuals. Because this condition is linked to physical exhaustion disabilities, individuals not only have communication difficulties, but also have difficulty interacting with digital devices. Automatic speech recognition (ASR) makes an important difference for individuals with dysarthria since modern digital devices offer a better interaction medium that enables them to interact with their community and computers. Still, the performance of ASR technologies is poor in recognizing dysarthric speech, particularly for acute dysarthria. Multiple challenges, including dysarthric phoneme inaccuracy and labeling imperfection, are facing dysarthric ASR technologies. This paper proposes a spatio-temporal dysarthric ASR (DASR) system using Spatial Convolutional Neural Network (SCNN) and Multi-Head Attention Transformer (MHAT) to visually extract the speech features, and DASR learns the shapes of phonemes pronounced by dysarthric individuals. This visual DASR feature modeling eliminates phoneme-related challenges. The UA-Speech database is utilized in this paper, including different speakers with different speech intelligibility levels. However, because the proportion of usable speech data to the number of distinctive classes in the UA-speech database was small, the proposed DASR system leverages transfer learning to generate synthetic leverage and visuals. In benchmarking with other DASRs examined in this study, the proposed DASR system outperformed and improved the recognition accuracy for 20.72% of the UA-Speech database. The largest improvements were achieved for very-low (25.75%) and low intelligibility (33.67%).

Data Augmentation-based Novel Deep Learning Method for Deepfaked Images Detection

Abstract: Recent advances in artificial intelligence have led to deepfake images, enabling users to replace a real face with a genuine one. deepfake images have recently been used to malign public figures, politicians, and even average citizens. deepfake but realistic images have been used to stir political dissatisfaction, blackmail, propagate false news, and even carry out bogus terrorist attacks. Thus, identifying real images from fakes has got more challenging. To avoid these issues, this study employs transfer learning and data augmentation technique to classify deepfake images. For experimentation, 190,335 RGB-resolution deepfake and real images and image augmentation methods are used to prepare the dataset. The experiments use the deep learning models: convolutional neural network (CNN), Inception V3, visual geometry group (VGG19) and VGG16 with a transfer learning approach. Essential evaluation metrics (accuracy, precision, recall, F1-score, confusion matrix and AUC-ROC curve score) are used to test the efficacy of the proposed approach. Results revealed that the proposed approach achieves an accuracy, recall, F1-score and AUC-ROC score of 90% and 91% precision, with our fine-tuned VGG16 model outperforming other DL models in recognizing real and deepfakes.

Adaptively Directed Image Restoration Using Resilient Backpropagation Neural Network

Abstract: Abstract In this modern era, visual data transmission, processing, and analysis play a vital role in daily life. Image denoising is the process of approximately estimating the original version of a degraded image. The presence of unexpected noise (e.g., fixed, random, and Gaussian) is the root cause of degradation, which has been reduced to some extent by many linear and non-linear filters based on a median value. The real issue is developing a strategy that should be generalized enough to effectively restore an image corrupted with multi-nature noise. Many researchers have developed novel concepts, but their tactics must acquire the highest performance in this area. This article proposes a constrained strategy for this problem, i.e., an adaptively directed denoising filter (ADD filter) based on a neural network. It consists of three major stages: training, filtering, and enhancing. First, we train a feed-forward back-propagation neural network on noisy and noise-free pixels for effective differentiation. Second, we apply a one-pass selective filter to the noisy image. The objective of this one-pass filter is to minimize noise using an adaptive median or directional filter based on density. Finally, the iterative directional filter is applied to the pre-processed image to enhance its visual quality. The extensive experiments depict that the proposed system has achieved better subjective results and improved local (structural similarity) and global (peak signal-to-noise ratio or mean square error) statistical measures.

An Improved Fick’s Law Algorithm Based on Dynamic Lens-Imaging Learning Strategy for Planning a Hybrid Wind/Battery Energy System in Distribution Network

Abstract: In this paper, optimal and multi-objective planning of a hybrid energy system (HES) with wind turbine and battery storage (WT/Battery) has been proposed to drop power loss, smooth voltage profile, enhance customers reliability, as well as minimize the net present cost of the hybrid system plus the battery degradation cost (BDC). Decision variables include the installation site of the hybrid system and size of the wind farm and battery storage. These variables are found with the help of a novel metaheuristic approach called improved Fick’s law algorithm (IFLA). To enhance the exploration performance and avoid the early incomplete convergence of the conventional Fick’s law (FLA) algorithm, a dynamic lens-imaging learning strategy (DLILS) based on opposition learning has been adopted. The planning problem has been implemented in two approaches without and considering BDC to analyze its impact on the reserve power level and the amount and quality of power loss, voltage profile, and reliability. A 33-bus distribution system has also been employed to validate the capability and efficiency of the suggested method. Simulation results have shown that the multi-objective planning of the hybrid WT/Battery energy system improves voltage and reliability and decreases power loss by managing the reserve power based on charging and discharging battery units and creating electrical planning with optimal power injection into the network. The results of simulations and evaluation of statistic analysis indicate the superiority of the IFLA in achieving the optimal solution with faster convergence than conventional FLA, particle swarm optimization (PSO), manta ray foraging optimizer (MRFO), and bat algorithm (BA). It has been observed that the proposed methodology based on IFLA in different approaches has obtained lower power loss and more desirable voltage profile and reliability than its counterparts. Simulation reports demonstrate that by considering BDC, the values of losses and voltage deviations are increased by 2.82% and 1.34%, respectively, and the reliability of network customers is weakened by 5.59% in comparison with a case in which this cost is neglected. Therefore, taking into account this parameter in the objective function can lead to the correct and real calculation of the improvement rate of each of the objectives, especially the improvement of the reliability level, as well as making the correct decisions of network planners based on these findings.

Privacy Preserved Cervical Cancer Detection Using Convolutional Neural Networks Applied to Pap Smear Images

Abstract: Image processing has enabled faster and more accurate image classification. It has been of great benefit to the health industry. Manually examining medical images like MRI and X-rays can be very time-consuming, more prone to human error, and way more costly. One such examination is the Pap smear exam, where the cervical cells are examined in laboratory settings to distinguish healthy cervical cells from abnormal cells, thus indicating early signs of cervical cancer. In this paper, we propose a convolutional neural network- (CNN-) based cervical cell classification using the publicly available SIPaKMeD dataset having five cell categories: superficial-intermediate, parabasal, koilocytotic, metaplastic, and dyskeratotic. CNN distinguishes between healthy cervical cells, cells with precancerous abnormalities, and benign cells. Pap smear images were segmented, and a deep CNN using four convolutional layers was applied to the augmented images of cervical cells obtained from Pap smear slides. A simple yet efficient CNN is proposed that yields an accuracy of 0.9113% and can be successfully used to classify cervical cells. A simple architecture that yields a reasonably good accuracy can increase the speed of diagnosis and decrease the response time, reducing the computation cost. Future researchers can build upon this model to improve the model's accuracy to get a faster and more accurate prediction.

Application of nanotechnology in breast cancer screening under obstetrics and gynecology through the use of CNN and ANFIS.

Abstract: Breast cancer is the leading reason of death among women aged 35 to 54. Breast cancer diagnosis still presents significant challenges, and preventing the disease's most severe symptoms requires early detection. The role of nanotechnology in the tumor-treatment has recently attracted a lot of interest. In cancer therapies, nanotechnology plays a major role in the medication distribution process. Nanoparticles have the ability to target tumors. Nanoparticles are favorable and maybe preferable for usage in tumor detection and imaging due to their incredibly small size. Quantum dots, semiconductor crystals with increased labeling and imaging capabilities for cancer cells, are one of the particles that have received the most research attention. The design of the research is cross-sectional and descriptive. From April through September of 2020, data were gathered at the State Hospital. All pregnant women who came to the hospital throughout the first and second trimesters of the research's data collection were included in the study population. 100 pregnant women between the ages of 20 and 40 who had not yet had a mammogram comprised the research sample. 1100 digitized mammography images are included in the dataset, which was obtained from a hospital. Convolutional neural networks (CNN) were used to scan all images, and breast masses and mass comparisons were made using the malignant-benign categorization. The adaptive neuro-fuzzy inference system (ANFIS) then examined all of the data obtained by CNN in order to identify breast cancer early using inputs based on the nine different inputs. The precision of the mechanism used in this technique to determine the ideal radius value is significantly impacted by the radius value. Nine variables that define breast cancer indicators were utilized as inputs to the ANFIS classifier, which was then used to identify breast cancer. The parameters were given the necessary fuzzy functions, and the combined dataset was applied to train the method. Testing was initially performed by 30% of dataset that was later done with the real data obtained from the hospital. The accuracy of the results for 30% data was 84% (specificity =72.7%, sensitivity =86.7%) and the results for the real data was 89.8% (sensitivity =82.3%, specificity =75.9%), respectively.

Wrist-Based Electrodermal Activity Monitoring for Stress Detection Using Federated Learning

Abstract: With the most recent developments in wearable technology, the possibility of continually monitoring stress using various physiological factors has attracted much attention. By reducing the detrimental effects of chronic stress, early diagnosis of stress can enhance healthcare. Machine Learning (ML) models are trained for healthcare systems to track health status using adequate user data. Insufficient data is accessible, however, due to privacy concerns, making it challenging to use Artificial Intelligence (AI) models in the medical industry. This research aims to preserve the privacy of patient data while classifying wearable-based electrodermal activities. We propose a Federated Learning (FL) based approach using a Deep Neural Network (DNN) model. For experimentation, we use the Wearable Stress and Affect Detection (WESAD) dataset, which includes five data states: transient, baseline, stress, amusement, and meditation. We transform this raw dataset into a suitable form for the proposed methodology using the Synthetic Minority Oversampling Technique (SMOTE) and min-max normalization pre-processing methods. In the FL-based technique, the DNN algorithm is trained on the dataset individually after receiving model updates from two clients. To decrease the over-fitting effect, every client analyses the results three times. Accuracies, Precision, Recall, F1-scores, and Area Under the Receiver Operating Curve (AUROC) values are evaluated for each client. The experimental result shows the effectiveness of the federated learning-based technique on a DNN, reaching 86.82% accuracy while also providing privacy to the patient’s data. Using the FL-based DNN model over a WESAD dataset improves the detection accuracy compared to the previous studies while also providing the privacy of patient data.

Retraction Note: Enhanced bat algorithm for COVID-19 short-term forecasting using optimized LSTM

Abstract: [This retracts the article DOI: 10.1007/s00500-021-06075-8.].

Impact of Tree Cover Loss on Carbon Emission: A Learning-Based Analysis

Abstract: Describing the processes leading to deforestation is essential for the development and implementation of the forest policies. In this work, two different learning models were developed in order to identify the best possible model for the assessment of the deforestation causes and trends. We developed autoregressive integrated moving average (ARIMA) model and long short-term memory (LSTM) independently in order to see the trend between tree cover loss and carbon dioxide emission. This study includes the twenty-year data of Pakistan on tree cover loss and carbon emission from the Global Forest Watch (GFW) platform, a known platform to get numerical data. Minimum mean absolute error (MAE) for the prediction of tree cover loss and carbon emission obtained through ARIMA model is 0.89 and 0.95, respectively. The minimum MAE given by LSTM model is 0.33 and 0.43, respectively. There is no such kind of study conducted in order to identify the increase in carbon emission due to tree cover loss most specifically in Pakistan. The results endorsed that one of the main causes of increase in the pollution in the environment in terms of carbon emission is due to tree cover loss.

Ensemble Learning for Fetal Health Classification

Abstract: Cardiotocography (CTG) represents the fetus’s health inside the womb during labor. However, assessment of its readings can be a highly subjective process depending on the expertise of the obstetrician. Digital signals from fetal monitors acquire parameters (i.e., fetal heart rate, contractions, acceleration). Objective: This paper aims to classify the CTG readings containing imbalanced healthy, suspected, and pathological fetus readings. Method: We perform two sets of experiments. Firstly, we employ five classifiers: Random Forest (RF), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LGBM) without over-sampling to classify CTG readings into three categories: healthy, suspected, and pathological. Secondly, we employ an ensemble of the above-described classifiers with the oversampling method. We use a random over-sampling technique to balance CTG records to train the ensemble models. We use 3602 CTG readings to train the ensemble classifiers and 1201 records to evaluate them. The outcomes of these classifiers are then fed into the soft voting classifier to obtain the most accurate results. Results: Each classifier evaluates accuracy, Precision, Recall, F1-scores, and Area Under the Receiver Operating Curve (AUROC) values. Results reveal that the XGBoost, LGBM, and CatBoost classifiers yielded 99% accuracy. Conclusion: Using ensemble classifiers over a balanced CTG dataset improves the detection accuracy compared to the previous studies and our first experiment. A soft voting classifier then eliminates the weakness of one individual classifier to yield superior performance of the overall model.

Harris-Hawk-Optimization-Based Deep Recurrent Neural Network for Securing the Internet of Medical Things

Abstract: The healthcare industry has recently shown much interest in the Internet of Things (IoT). The Internet of Medical Things (IoMT) is a component of the IoTs in which medical appliances transmit information to communicate critical information. The growth of the IoMT has been facilitated by the inclusion of medical equipment in the IoT. These developments enable the healthcare sector to interact with and care for its patients effectively. Every technology that relies on the IoT can have a serious security challenge. Critical IoT connectivity data may be exposed, changed, or even made unavailable to authenticated users in the case of such attacks. Consequently, protecting IoT/IoMT systems from cyber-attacks has become essential. Thus, this paper proposes a machine-learning- and a deep-learning-based approach to creating an effective model in the IoMT system to classify and predict unforeseen cyber-attacks/threats. First, the dataset is preprocessed efficiently, and the Harris Hawk Optimization (HHO) algorithm is employed to select the optimized feature. Finally, machine learning and deep learning algorithms are applied to detect cyber-attack in IoMT. Results reveal that the proposed approach achieved an accuracy of 99.85%, outperforming other techniques and existing studies.

Transfer Learning-based Forensic Analysis and Classification of E-Mail Content

Abstract: Emails have become a crucial element in societal transformation recently. Spam emails have also become more common, making spam filters more important. Several approaches have been attempted to classify emails as spam or non-spam based on their content. However, it is necessary to classify emails based on their contents rather than just analyzing titles, links, and URLs. This paper proposes a novel approach for email analysis and classification based on content into four categories: Normal, Fraudulent, Threatening, and Suspicious emails. We explore the challenges and issues in this forensics paradigm and present a transfer learning-based approach to email forensics. We demonstrate several use cases where email forensics can provide crucial insights for discovering information about criminal situations. Machine learning (ML) and deep learning (DL)-based approaches are used for helping email forensics investigations. We conducted a detailed analysis of ML/DL and transformers to identify the best email analysis approach. It is observed that transformers-based architectures, such as Bidirectional Encoder Representations from Transformers (BERT), achieve the best accuracy of 98%, surpassing existing studies. Furthermore, we discuss various challenges and limitations associated with email forensics, such as data privacy concerns and the need to continuously update the classification model to keep up with new spam techniques.

Nanocatalysts as fast and powerful medical intervention: Bridging cochlear implant therapies and advanced modelling using Hidden Markov Models (HMMs) for effective treatment of infections.

Abstract: As human population growth and waste from technologically advanced industries threaten to destabilise our delicate ecological equilibrium, the global spotlight intensifies on environmental contamination and climate-related changes. These challenges extend beyond our external environment and have significant effects on our internal ecosystems. The inner ear, which is responsible for balance and auditory perception, is a prime example. When these sensory mechanisms are impaired, disorders such as deafness can develop. Traditional treatment methods, including systemic antibiotics, are frequently ineffective due to inadequate inner ear penetration. Conventional techniques for administering substances to the inner ear fail to obtain adequate concentrations as well. In this context, cochlear implants laden with nanocatalysts emerge as a promising strategy for the targeted treatment of inner ear infections. Coated with biocompatible nanoparticles containing specific nanocatalysts, these implants can degrade or neutralise contaminants linked to inner ear infections. This method enables the controlled release of nanocatalysts directly at the infection site, thereby maximising therapeutic efficacy and minimising adverse effects. In vivo and in vitro studies have demonstrated that these implants are effective at eliminating infections, reducing inflammation, and fostering tissue regeneration in the ear. This study investigates the application of hidden Markov models (HMMs) to nanocatalyst-loaded cochlear implants. The HMM is trained on surgical phases in order to accurately identify the various phases associated with implant utilisation. This facilitates the precision placement of surgical instruments within the ear, with a location accuracy between 91% and 95% and a standard deviation between 1% and 5% for both sites. In conclusion, nanocatalysts serve as potent medicinal instruments, bridging cochlear implant therapies and advanced modelling utilising hidden Markov models for the effective treatment of inner ear infections. Cochlear implants loaded with nanocatalysts offer a promising method to combat inner ear infections and enhance patient outcomes by addressing the limitations of conventional treatments.