Search

This paper proposes a deep learning model that is robust and capable of handling highly uncertain inputs. The model is divided into three phases: creating a dataset, creating a neural network based on the dataset, and retraining the neural network to handle unpredictable inputs. The model utilizes entropy values and a non-dominant sorting algorithm to identify the candidate with the highest entropy value from the dataset. This is followed by merging the training set with adversarial samples, where a mini-batch of the merged dataset is used to update the dense network parameters. This method can improve the performance of machine learning models, categorization of radiographic images, risk of misdiagnosis in medical imaging, and accuracy of medical diagnoses. To evaluate the efficacy of the proposed model, two datasets, MNIST and COVID, were used with pixel values and without transfer learning. The results showed an increase of accuracy from 0.85 to 0.88 for MNIST and from 0.83 to 0.85 for COVID, which suggests that the model successfully classified images from both datasets without using transfer learning techniques. [ABSTRACT FROM AUTHOR]

To solve the problem of low recognition accuracy and long recognition time in conventional methods for digital moving image feature recognition, a method for digital image feature recognition on mobile platforms based on machine learning is proposed. The support vector machine method is used to cluster the dataset, and then the weight reconstruction method is used to reduce the dimension of digital moving image data. The reduced dimension of the digital moving image is embedded in the coordinates to obtain the reduced dimension of the image data information and complete the feature recognition of the digital moving image. The simulation results show that the recognition accuracy of this method in recognizing features of moving digital images is basically stable at more than 95% and the running time is 0.42s. The recognition effect of the proposed method is good, the recognition efficiency is high, and it has some practical application value. [ABSTRACT FROM AUTHOR]

Deep learning methods have led to the state-of-the-art medical applications, such as image classification and segmentation. The data-driven deep learning application can help stakeholders for further collaboration. However, limited labeled data set limits the deep learning algorithms to be generalized for one domain into another. To handle the problem, meta-learning helps to solve this issue especially it can learn from a small set of data. We proposed a meta-learning-based image segmentation model that combines the learning of the state-of-the-art models and then used it to achieve domain adoption and high accuracy. Also, we proposed a prepossessing algorithm to increase the usability of the segment part and remove noise from the new test images. The proposed model can achieve 0.94 precision and 0.92 recall. The ability is to increase 3.3% among the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Nowadays, embedded systems are comprised of heterogeneous multi-core architectures, i.e., CPUs and GPUs. If the application is mapped to an appropriate processing core, then these architectures provide many performance benefits to applications. Typically, programmers map sequential applications to CPU and parallel applications to GPU. The task mapping becomes challenging because of the usage of evolving and complex CPU- and GPU-based architectures. This paper presents an approach to map the OpenCL application to heterogeneous multi-core architecture by determining the application suitability and processing capability. The classification is achieved by developing a machine learning-based device suitability classifier that predicts which processor has the highest computational compatibility to run OpenCL applications. In this paper, 20 distinct features are proposed that are extracted by using the developed LLVM-based static analyzer. In order to select the best subset of features, feature selection is performed by using both correlation analysis and the feature importance method. For the class imbalance problem, we use and compare synthetic minority over-sampling method with and without feature selection. Instead of hand-tuning the machine learning classifier, we use the tree-based pipeline optimization method to select the best classifier and its hyper-parameter. We then compare the optimized selected method with traditional algorithms, i.e., random forest, decision tree, Naïve Bayes and KNN. We apply our novel approach on extensively used OpenCL benchmarks, i.e., AMD and Polybench. The dataset contains 653 training and 277 testing applications. We test the classification results using four performance metrics, i.e., F-measure, precision, recall and R 2 . The optimized and reduced feature subset model achieved a high F-measure of 0.91 and R 2 of 0.76. The proposed framework automatically distributes the workload based on the application requirement and processor compatibility. [ABSTRACT FROM AUTHOR]

Ransomware continues to pose a significant threat to cybersecurity by extorting money from users by locking their devices and personal data. The attackers force the payment of a ransom in order to restore access to personal files. Because of the structural similarity, detection of ransomware and benign applications becomes vulnerable to evasion attacks. Ensemble learning can provide countermeasures, while attackers can use the same technique to improve the effectiveness of their respective attacks. This motivates us to investigate whether the distinct ensemble method can achieve better performance when combined with the voting-based method. This research proposes a hybrid approach that examines permissions, text, and network-based features both statically and dynamically by monitoring memory usage, system call logs, and CPU usage. Ensemble machine learning analyzers on static and dynamic features extracted from Android malware applications (ransomware and non-ransomware) are then trained in the designed model. Our experimental results show that the proposed ensemble classification and detection technique can classify unknown static and dynamic ransomware behavior to mitigate adversarial evasion attacks. [Display omitted] • The designed model extracts and analyzes static network-based features. • Two ML-based ensemble models are proposed for static and dynamic feature sets. • The model is for Android ransomware adversarial evasion attacks. [ABSTRACT FROM AUTHOR]

Cloud computing is the on‐demand provision of computing resources over the Internet, such as cloud storage, computing power, network, and so on. Cloud computing has several advantages, including high speed, cost reduction, data security, and scalability. The main challenge in cloud environment is to balance the workloads and network traffic among the available resources to achieve maximum performance. Several methods have been proposed in the literature for effective load balancing, including heuristic, meta‐heuristic, and hybrid algorithms. The performance of these techniques has been improved by combining machine learning based Artificial Intelligence (AI) techniques and meta‐heuristic algorithms. Most of the existing load balancing techniques are not aware of the content type of user tasks. However, from the literature, the content type of the tasks can be very effective to design a balanced workload distribution system in the cloud. In this work, a novel AI‐assisted hybrid approach called Content‐aware Machine Learning based Load Balancing Scheduler (CA‐MLBS) is proposed. The scheduling system CA‐MLBS combines machine learning and meta‐heuristic algorithms to perform classification based on file type. To achieve this, a Support Vector Machine (SVM) based classifier is used to classify user tasks into different content types such as video, audio, image, and text. A metaheuristic algorithm based on Particle Swarm Optimization (PSO) is used to map users' tasks in the cloud. The proposed approach was implemented and evaluated using a renowned Cloudsim simulation kit and compared with Ant Colony Optimization File Type Format (ACOFTF) and Data Files Type Formatting (DFTF) heuristics. The results of the proposed study show that the proposed CA‐MLBS technique achieved improvements of up to 29%, 29%, and 44% in terms of makespan, response time, and throughput, respectively. [ABSTRACT FROM AUTHOR]

Cervical cancer is one of the deadliest diseases in women worldwide. It is caused by long-term infection of the skin cells and mucosal cells of the genital area of women. The most disturbing thing about this cancer is the fact that it does not show any symptoms when it occurs. In the diagnosis and prognosis of cervical cancer disease, machine learning has the potential to help detect it at an early stage. In this paper, we analyzed different supervised machine learning techniques to detect cervical cancer at an early stage. To train the machine learning model, a cervical cancer dataset from the UCI repository was used. The different methods were evaluated using this dataset of 858 cervical cancer patients with 36 risk factors and one outcome variable. Six classification algorithms were applied in this study, including an artificial neural network, a Bayesian network, an SVM, a random tree, a logistic tree, and an XG-boost tree. All models were trained with and without a feature selection algorithm to compare the performance and accuracy of the classifiers. Three feature selection algorithms were used, namely (i) relief rank, (ii) wrapper method and (iii) LASSO regression. The maximum accuracy of 94.94% was recorded using XG Boost with complete features. It is also observed that for this dataset, in some cases, the feature selection algorithm performs better. Machine learning has been shown to have advantages over traditional statistical models when it comes to dealing with the complexity of large-scale data and uncovering prognostic features. It offers much potential for clinical use and for improving the treatment of cervical cancer. However, the limitations of prediction studies and models, such as simplified, incomplete information, overfitting, and lack of interpretability, suggest that further efforts are needed to improve the accuracy, reliability, and practicality of clinical outcome prediction. [ABSTRACT FROM AUTHOR]

This paper introduces a secure and scalable intelligent transportation and human behavior system to accurately discover knowledge from urban traffic data. The data are secured using blockchain learning technology, where the scalability is ensured by a threaded GPU. In addition, different optimizations are provided to efficiently process data on the GPU. A reinforcement deep learning algorithm is also established to merge local knowledge discovered on each site into global knowledge. To demonstrate the applicability of the proposed framework, intensive experiments have been carried out on well-known intelligent transportation and human behavior data. Our results show that our proposed framework outperforms the baseline solutions for the outlier detection use case. [ABSTRACT FROM AUTHOR]

Recently, numerous Machine Learning (ML) algorithms have been applied in many areas of cybersecurity. However, most of these systems can only be seen as a black box to users. To improve our understanding of such systems, adversarial machine learning approaches can be used. The main features are detected by analyzing the extent of such changes, which helps in identifying the main reasons for misclassification. In this paper, the presented approach has obtained satisfactory results that accurately explains the reasons for misclassifications. Some features of the presented method can be applied to any classifier with defined gradients without the need for modifications. The proposed model can be extended to perform more diagnoses and it can be used for a deeper analysis of systems, obtaining more than 95% accuracy classification on the used datasets in the experiments. [Display omitted] • Explains misclassifications by data-driven AI models using an adversarial approach. • Compute the minimum number of changes to input features required. • Increased average classification accuracy by 2.5% post modification. • Designed a black-box attack to test the correctness and trustworthiness. • Used explanation maps to examine the effectiveness of attacks. [ABSTRACT FROM AUTHOR]