Search

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potential impact on medical image retrieval, particularly in text-based medical image retrieval (TBMIR) tasks, has not yet been fully realized. This could be attributed to the complexity of the ranking process, as there is ambiguity in treating TBMIR as an image retrieval task rather than a traditional information retrieval or NLP task. To address this gap, our paper proposes a novel approach to re-ranking medical images using a Deep Matching Model (DMM) and Medical-Dependent Features (MDF). These features incorporate categorical attributes such as medical terminologies and imaging modalities. Specifically, our DMM aims to generate effective representations for query and image metadata using a personalized CNN, facilitating matching between these representations. By using MDF, a semantic similarity matrix based on Unified Medical Language System (UMLS) meta-thesaurus, and a set of personalized filters taking into account some ranking features, our deep matching model can effectively consider the TBMIR task as an image retrieval task, as previously mentioned. To evaluate our approach, we performed experiments on the medical ImageCLEF datasets from 2009 to 2012. The experimental results show that the proposed model significantly enhances image retrieval performance compared to the baseline and state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Dynamic modern healthcare systems rely heavily on the contributions of computer scientists. The diagnosis process is a team effort involving many people: patients, their families, healthcare providers, researchers, and policymakers. Computer technology plays a crucial role in supporting this effort by providing a number of essential services to all of these groups. In the early stages of many diseases, a diagnosis can be made automatically using a computer-aided system, with some degree of certainty. This paper presents a hybrid optimal deep learning-based model for tuberculosis disease recognition using MRI images. Several deep learning models are combined to extract the most relevant features from MRI images. In particular, we establish a combination between vision transformer (ViTs) and Efficient-Net models in order to maximize classification accuracy. We conducted experiments to investigate the accuracy of the proposed model using the Shenzhen and Montgomery data set, and found that it yielded substantially more accurate and better results than the state of-the-art works. [ABSTRACT FROM AUTHOR]

In recent years, augmented reality has emerged as an emerging technology with huge potential in image-guided surgery, and in particular, its application in brain tumor surgery seems promising. Augmented reality can be divided into two parts: hardware and software. Further, artificial intelligence, and deep learning in particular, have attracted great interest from researchers in the medical field, especially for the diagnosis of brain tumors. In this paper, we focus on the software part of an augmented reality scenario. The main objective of this study was to develop a classification technique based on a deep belief network (DBN) and a softmax classifier to (1) distinguish a benign brain tumor from a malignant one by exploiting the spatial heterogeneity of cancer tumors and homologous anatomical structures, and (2) extract the brain tumor features. In this work, we developed three steps to explain our classification method. In the first step, a global affine transformation is preprocessed for registration to obtain the same or similar results for different locations (voxels, ROI). In the next step, an unsupervised DBN with unlabeled features is used for the learning process. The discriminative subsets of features obtained in the first two steps serve as input to the classifier and are used in the third step for evaluation by a hybrid system combining the DBN and a softmax classifier. For the evaluation, we used data from Harvard Medical School to train the DBN with softmax regression. The model performed well in the classification phase, achieving an improved accuracy of 97.2%. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive neural network control problem for nonstrict-feedback nonlinear systems with an unknown backlash-like hysteresis and bounded disturbance was presented. Radial basis function neural networks (RBFNN) were used to approximate the unknown functions and the problem of the explosion of complexity problem was handled by utilizing the command filter method. Furthermore, the influence of an unknown backlash-like hysteresis input was addressed by approximating an intermediate variable. Based on the backstepping method and the command filter technique, an adaptive neural network controller was designed via the approximation abilities of RBFNN. With the help of the Lyapunov stability theory, the proposed controller ensures that all of the signals in closed-loop systems are bounded and that the tracking error fluctuates close to the origin within a bounded area. Finally, a real-world example based on the single-link manipulator was shown to demonstrate the viability of the presented approach. [ABSTRACT FROM AUTHOR]

Convolution neural networks (CNNs) have proven to be effective clinical imaging methods. This study highlighted some of the key issues within these systems. It is difficult to train these systems in a limited clinical image databases, and many publications present strategies including such learning algorithm. Furthermore, these patterns are known for making a highly reliable prognosis. In addition, normalization of volume and losses of dice have been used effectively to accelerate and stabilize the training. Furthermore, these systems are improperly regulated, resulting in more confident ratings for correct and incorrect classification, which are inaccurate and difficult to understand. This study examines the risk assessment of Fully Convolutional Neural Networks (FCNNs) for clinical image segmentation. Essential contributions have been made to this planned work: 1) dice loss and cross-entropy loss are compared on the basis of segment quality and uncertain assessment of FCNNs; 2) proposal for a group model for assurance measurement of full convolutional neural networks trained with dice loss and group normalization; And 3) the ability of the measured FCNs to evaluate the segment quality of the structures and to identify test examples outside the distribution. To evaluate the study’s contributions, it conducted a series of tests in three clinical image division applications such as heart, brain and prostate. The findings of the study provide significant insights into the predictive ambiguity assessment and a practical strategies for outside-distribution identification and reliable measurement in the clinical image segmentation. The approaches presented in this research significantly enhance the reliability and accuracy rating of CNNbased clinical imaging methods. [ABSTRACT FROM AUTHOR]

Recently, smart home devices have been widely used to assist and facilitate the lives of human beings. Human activity recognition (HAR) aims to identify human activities using sensors in smartphones. Therefore, it can be employed in many applications, such as remote health monitoring for disabled and elderly people. This paper proposes a granular computing-based approach to classifying human activities using wearable sensing devices. The approach has two main phases: feature selection and classification. In the feature selection phase, the approach attempts to remove redundant and irrelevant attributes. At the same time, the classification phase makes use of granular computing concepts to build the granules and find the relationships between granules at different levels. To evaluate the approach, we applied the dataset to five famous machine learning models. For the comparative evaluation, we also tested other well-known machine learning methods. The experimental results presented in this paper show that the approach outperformed common traditional classifiers in terms of classification precision recall, f-measure, and MCC for most recognized human activities by approximately 97.3%, 94%, 95.5%, and 94.8%, respectively. However, in terms of processing time, it performs comparably. [ABSTRACT FROM AUTHOR]

The democratization of access to internet and social media has given an opportunity for every individual to openly express his or her ideas and feelings. Unfortunately, this has also created room for extremist, racist, misogynist, and offensive opinions expressed either as articles, posts, or comments. While controlling offensive speech in English-, Spanish-, and French- speaking social media communities and websites has reached a mature level, it is much less the case for their counterparts in Arabic-speaking countries. This paper presents a transfer learning solution to detect hateful and offensive speech on Arabic websites and social media platforms. This paper will compare the performance of different BERT-based models trained to classify comments as either abusive or neutral. The training dataset contains comments in standard Arabic as well as four dialects. We will also use their English translations for comparative purposes. The models were evaluated based on five metrics: Accuracy, Precision, Recall, F1-Score, and Confusion Matrix. [ABSTRACT FROM AUTHOR]

The concept of quality of service (QoS) is a new computer technology. Previously, there was a slow internet connection to access the sites and it was slow to send information. But now, it requires speeding up the traffic and increasing the efficiency for audio and video. In this study, we discuss the concepts of QoS provided over the network to achieve these goals. This study aims to compare six algorithms to control the QoS, then, the best algorithm will be selected to improve the traffic. These algorithms are named first in first out (FIFO), priority queuing (PQ), custom queuing (CQ), CQ with low latency queuing (LLQ), weighted fair queuing (WFQ), WFQ with low latency queuing (LLQ), so the behavior of these algorithms can be measured. The results obtained by comparing between them using OPNET simulation show that the best algorithm is the priority queuing algorithm, followed by CQ, then CQ with LLQ, then WFQ, then WFQ with LLQ and finally FIFO. All these results are plotted in the form of graphs to show the paths of these algorithms for the single state with an operation time of 5 minutes for each algorithm. [ABSTRACT FROM AUTHOR]

It has been noted that disease detection approaches based on deep learning are becoming increasingly important in artificial intelligence-based research in the field of agriculture. Studies conducted in this area are not at the level that is desirable due to the diversity of plant species and the regional characteristics of many of these species. Although numerous researchers have studied diseases on plant leaves, it is undeniable that timely diagnosis of diseases on olive leaves remains a difficult task. It is estimated that people have been cultivating olive trees for 6000 years, making it one of the most useful and profitable fruit trees in history. Symptoms that appear on infected leaves can vary from one plant to another or even between individual leaves on the same plant. Because olive groves are susceptible to a variety of pathogens, including bacterial blight, olive knot, Aculus olearius, and olive peacock spot, it has been difficult to develop an effective olive disease detection algorithm. For this reason, we developed a unique deep ensemble learning strategy that combines the convolutional neural network model with vision transformer model. The goal of this method is to detect and classify diseases that can affect olive leaves. In addition, binary and multiclassification systems based on deep convolutional models were used to categorize olive leaf disease. The results are encouraging and show how effectively CNN and vision transformer models can be used together. Our model outperformed the other models with an accuracy of about 96% for multiclass classification and 97% for binary classification, as shown by the experimental results reported in this study. [ABSTRACT FROM AUTHOR]

Over the last few years, the amount of available information has increased exponentially in all professional fields, including the medical field. Modern-day patients have access to a wealth of medical information, whether it be from brochures, newspapers, television campaigns, or internet documents. To facilitate and accelerate the search for medical information, more precise systems have been implemented, such as visual question-and-answer systems. A visual question-and-answer system is designed to provide direct and precise answers to questions asked in natural language. In this context, we propose an optimal deep neural network model based on an adaptive optimization algorithm, which takes medical images and natural language questions as input, then provides precise answers as output. Our model starts by classifying medical questions following an embedding phase. We then use a deep learning model for visual and textual feature extraction and emergence. In this paper, we aim to maximize the accuracy rate and minimize the number of epochs in order to accelerate the process. This is a multi-objective optimization problem. The selection of deep learning model parameters, such as epoch number and batch size, is an essential step in improving the model, thus, we use an adaptive genetic algorithm to determine the optimal deep learning parameters. Finally, we propose a dense layer for answer retrieval. To evaluate our model, we used the ImageCLEF 2019 VQA data set. Our model outperforms existing visual question-and-answer systems and offers a significantly higher retrieval accuracy rate. [ABSTRACT FROM AUTHOR]

Computer science plays an important role in modern dynamic health systems. Given the collaborative nature of the diagnostic process, computer technology provides important services to healthcare professionals and organizations, as well as to patients and their families, researchers, and decision-makers. Thus, any innovations that improve the diagnostic process while maintaining quality and safety are crucial to the development of the healthcare field. Many diseases can be tentatively diagnosed during their initial stages. In this study, all developed techniques were applied to tuberculosis (TB). Thus, we propose an optimized machine learning-based model that extracts optimal texture features from TB-related images and selects the hyper-parameters of the classifiers. Increasing the accuracy rate and minimizing the number of characteristics extracted are our goals. In other words, this is a multitask optimization issue. A genetic algorithm (GA) is used to choose the best features, which are then fed into a support vector machine (SVM) classifier. Using the ImageCLEF 2020 data set, we conducted experiments using the proposed approach and achieved significantly higher accuracy and better outcomes in comparison with the state-of-the-art works. The obtained experimental results highlight the efficiency of modified SVM classifier compared with other standard ones. [ABSTRACT FROM AUTHOR]

Though many researchers have studied plant leaf disease, the timely diagnosis of diseases in olive leaves still presents an indisputable challenge. Infected leaves may display different symptoms from one plant to another, or even within the same plant. For this reason, many researchers studied the effects of those diseases on, at most, two plants. Since olive crops are affected by many pathogens, including bacteria welt, olive knot, Aculus olearius, and olive peacock spot, the development of an efficient algorithm to detect the diseases was challenging because the diseases could be defined in many different ways. For this purpose, we introduce an optimal deep learning model for diagnosing olive leaf diseases. This approach is based on an adaptive genetic algorithm for selecting optimal parameters in deep learning model to provide rapid diagnosis. To evaluate our approach, we applied it in three famous deep learning models. For the comparative evaluation, we also tested other well-known machine learning methods. The experimental results presented in this paper show that our model outperformed the other algorithms, achieving an accuracy of approximately 96% for multiclass classification and 98% for binary classification. [ABSTRACT FROM AUTHOR]

Solar irradiance prediction is an essential one in providing renewable energy proficiently. The solar irradiance plays a major role in solar power system, solar thermal system, and photovoltaic grid-connected system, owing to uncertainty and variability. Conventional data analysis approaches are complex for demonstrating superior generalization. Therefore, the resource planners are flexible in accommodating these uncertainties while executing planning. To enhance the performance of solar irradiance forecasting, a new Variant Input Scoring Optimized Recurrent Neural Network (VIS-ORNN) is developed. The suggested approach includes two stages that are data collection and three stage simulation. At first, the data are gathered from the various meteorological standard dataset. Then, the prediction begins with feeding data directly to the ORNN. Here, the parameters of RNN are optimized with the help of Adaptive Escaping Energy-based Harris Hawks Coyote Optimization (AEE-HHCO) algorithm. Thus, the first score prediction is obtained. In the second phase, the first order statistical features act as an input, and it is given to the same ORNN, in which the second score is determined. In the third phase, the deep features are extracted by Convolutional Neural Network (CNN) that is subjected to the same ORNN for attaining the score. Finally, the final simulation is determined by taking the average of three prediction models. From the experimental results, while taking the MAE, the suggested AEE-HHCO-ORNN method has correspondingly secured 34.3% enhanced than PSO-ORNN, 7.7% enhanced than WOA-ORNN, 21.7% enhanced than COA-ORNN and 26.5% enhanced than HHO-ORNN. Thus, the simulation outcomes reveal that the offered method ensures maximum accuracy while validating with other baseline methodologies. [ABSTRACT FROM AUTHOR]