Effectiveness of Data Augmentation in Cellular-based Localization Using Deep Learning

The increasing popularity of social networks indicates that the vast amounts of data contained within them could be useful in various implementations, including recommendation systems. Interests and research publications on deep learning-based recommendation systems have largely increased. This study aimed to identify, summarize, and assess studies related to the application of deep learning-based recommendation systems on social media platforms to provide a systematic review of recent studies and provide a way for further research to improve the development of deep learning-based recommendation systems in social environments. A total of 32 papers were selected from previous studies in five of the major digital libraries, including Springer, IEEE, ScienceDirect, ACM, Scopus, and Web of Science, published between 2016 and 2020. Results revealed that even though RS has received high coverage in recent years, several obstacles and opportunities will shape the future of RS for researchers. In addition, social recommendation systems achieving high accuracy can be built by using a combination of techniques that incorporate a range of features in SRS. Therefore, the adoption of deep learning techniques in developing social recommendation systems is undiscovered.

Area under the curve may hide poor generalisation to external datasets

Rapid on-site cytopathology evaluation (ROSE) has been considered an effective method to increase the diagnostic ability of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA); however, ROSE is unavailable in most institutes worldwide due to the shortage of cytopathologists. To overcome this situation, we created an artificial intelligence (AI)-based system (the ROSE-AI system), which was trained with the augmented data to evaluate the slide images acquired by EUS-FNA. This study aimed to clarify the effects of such data-augmentation on establishing an effective ROSE-AI system by comparing the efficacy of various data-augmentation techniques. The ROSE-AI system was trained with increased data obtained by the various data-augmentation techniques, including geometric transformation, color space transformation, and kernel filtering. By performing five-fold cross-validation, we compared the efficacy of each data-augmentation technique on the increasing diagnostic abilities of the ROSE-AI system. We collected 4059 divided EUS-FNA slide images from 36 patients with pancreatic cancer and nine patients with non-pancreatic cancer. The diagnostic ability of the ROSE-AI system without data augmentation had a sensitivity, specificity, and accuracy of 87.5%, 79.7%, and 83.7%, respectively. While, some data-augmentation techniques decreased diagnostic ability, the ROSE-AI system trained only with the augmented data using the geometric transformation technique had the highest diagnostic accuracy (88.2%). We successfully developed a prototype ROSE-AI system with high diagnostic ability. Each data-augmentation technique may have various compatibilities with AI-mediated diagnostics, and the geometric transformation was the most effective for the ROSE-AI system.

Automated precision weed control requires visual methods to discriminate between crops and weeds. State-of-the-art plant detection methods fail to reliably detect weeds, especially in dense and occluded scenes. In the past, using hand-crafted detection models, both color (RGB) and depth (D) data were used for plant detection in dense scenes. Remarkably, the combination of color and depth data is not widely used in current deep learning-based vision systems in agriculture. Therefore, we collected an RGB-D dataset using a stereo vision camera. The dataset contains sugar beet crops in multiple growth stages with a varying weed densities. This dataset was made publicly available and was used to evaluate two novel plant detection models, the D-model, using the depth data as the input, and the CD-model, using both the color and depth data as inputs. For ease of use, for existing 2D deep learning architectures, the depth data were transformed into a 2D image using color encoding. As a reference model, the C-model, which uses only color data as the input, was included. The limited availability of suitable training data for depth images demands the use of data augmentation and transfer learning. Using our three detection models, we studied the effectiveness of data augmentation and transfer learning for depth data transformed to 2D images. It was found that geometric data augmentation and transfer learning were equally effective for both the reference model and the novel models using the depth data. This demonstrates that combining color-encoded depth data with geometric data augmentation and transfer learning can improve the RGB-D detection model. However, when testing our detection models on the use case of volunteer potato detection in sugar beet farming, it was found that the addition of depth data did not improve plant detection at high vegetation densities.

The industry is moving towards maintenance strategies that consider component health, which require extensive collection and analysis of data. Condition monitoring methods that require manual feature extraction and analysis, become infeasible on an industrial scale. Machine learning algorithms can be used to automatically detect and classify faults, however, obtaining sufficient data for training is required for deep learning and other data-driven classification approaches. Data from healthy machine operation is generally available in abundance, while data from representative fault- and operating conditions is limited. This limits both development and deployment of deep learning-based CM systems on an industrial scale. This paper addresses both the challenges of automated analysis and lack of training data. A deep learning classifier architecture utilizing 1-dimensional dilated convolutions is proposed. Dilation of the convolution kernel allows for analysis of raw vibration signals while simultaneously maintaining the receptive field of the classifier enough to capture temporal patterns. The proposed method performs classification in time domain on signal segments of 1 second or shorter. With knowledge of the bearing specification, artificial vibration signals with similar characteristics as an actual bearing fault can be created. In this work, generated fault signals are combined with healthy operational data to obtaintraining data for a deep classifier. Parameters of the vibration model is chosen as distributions rather than fixed values. By using a range parameters in the vibration model, the classifier learns to recognize temporal features from the training data that generalize to unseen data. The effectiveness of the proposed method is demonstrated by training classifiers on generated data and testing on real signals from faulty bearingsat both low and high speed. One dataset containing seeded faults and three run-to-failure tests are used for the demonstration.

Adversarial attacks aim to deceive the target system. Recently, deep learning methods have become a target of adversarial attacks. Even small perturbations could lead to classification errors in deep learning models. In an intrusion detection system using deep learning method, adversarial attack can cause classification error and malicious traffic can be classified as benign. In this study, the effects of adversarial attacks on the accuracy of deep learning-based intrusion detection systems were examined. CICIDS2017 dataset was used to test the detection systems . At first, DDoS attacks weredetected using Autoencoder, MLP, AEMLP, DNN, AEDNN, CNN and AECNN methods. Then, the Fast Gradient Sign Method (FGSM) is used to perform adversarial attacks. Finally, the sensitivity of the methods against the adversarial attacks were examined. Our results showed that the classification performance of deep learning based detection methods decreased up to %17 after the adversarial attacks. The results obtained in this study form the basis for the validation and validation studies of learning-based intrusion detection systems.

Technological developments in artificial intelligence, namely in the area of deep learning, have created new avenues for enhancing accessibility for those with visual impairments. In order to improve the capacity of people who are blind or visually impaired to understand and interact with visual material, this research investigates the creation and use of deep learning-based image description systems. We provide a comprehensive method that uses recurrent neural networks (RNNs) to generate natural language descriptions and convolutional neural networks (CNNs) and Autoencoders for extracting picture features. Our technology automatically creates comprehensive, context-aware descriptions of photographs by incorporating these models, giving users a better knowledge of their surroundings. We show the accuracy and reliability of the system on a wide range of photos through comprehensive testing. According to our research, deep learning-based picture description systems and converting the description in audio and making a promise to empower people who are visually impaired and foster diversity in the digital sphere.

Traditional methods have struggled to meet the increasingly diverse needs of users and industry development, particularly on short video platforms. This paper investigates the application of deep learning-based recommendation systems in the domain of video recommendations and their impact on user experience. It explores how different deep learning algorithms can be utilized to understand user preferences, analyze video content, and subsequently provide personalized recommendations. The study evaluates the accuracy and efficiency of these systems and investigates potential optimization strategies. The aim of this research is to provide a comprehensive perspective on how deep learning-based recommendation systems function in the short video environment and to discuss their future development directions.

With the rapid advancement of information technology, network security issues have become increasingly prominent, posing significant challenges in the field of public administration. Deep learning, as a cutting-edge technology in artificial intelligence, is emerging as a critical tool for enhancing network security management due to its exceptional performance in big data processing and pattern recognition. This paper reviews the basic concepts of deep learning and its current applications in network security management, discusses the design and implementation of deep learning-based network security management systems, and analyzes their effectiveness and evaluation through specific application cases. The results show that deep learning excels in areas such as intrusion detection, malware detection, network traffic analysis, and anomaly detection, significantly enhancing network security defenses. However, the application of deep learning in network security still faces challenges such as data privacy, model robustness, and computational resources. The paper concludes by proposing future development directions, providing theoretical support and practical references for further improving public network security management.

The viral spread of fake news on social media platforms has become a significant concern. Detecting and mitigating the spread of fake news pose a major challenge, requiring extensive effort from fact-checkers, governments, and organizations. However, the speed and volume of disinformation on social media reach far beyond the capacity of manual efforts to prebunk it. In recent years, various automatic fake news detection mechanisms have been proposed, ranging from models focusing on linguistic cues to approaches analyzing network characteristics. While these methods produce successful results, ever-evolving techniques of deception often outpace them. AI-based approaches offer a new opportunity in the subject matter. Especially deep learning-based detection systems provide substantial new ways to understand the context while adapting well to the evolving patterns of fake news. In this study, we explore the evolution of fake news detection. We discuss conventional and automatic fake news detection methods and the state-of-the-art deep learning approaches.

The lane detecting algorithm plays a major role in advanced driver assistance systems (ADAS) and autonomous driving systems. In recent years, deep learning-based lane detection techniques have shown encouraging results; nonetheless, the quality and size of the training data set has a significant impact on how effective these techniques are. Active learning is a technique that can improve the capacity of deep learning-based lane identification systems to repeatedly choose and classify valuable samples from a large body of unlabeled data. In this research, a novel 1-dimensional deep learning approach is used to present an augmented Active Learning based Lane Detection Algorithm (ALDA) that picks informative samples based on diversity- and uncertainty-based criteria. A number of benchmark datasets, including the CUlane, have been used to assess the suggested technique, In terms of accuracy and robustness, the suggested method (ALDA) performs better than four cutting-edge lane detecting algorithms. The findings show that active learning can significantly reduce the quantity of labelled data required for training while preserving good performance. The suggested method may improve the dependability and security of ADAS and autonomous driving systems. When compared to other distinct Deep Learning approaches, the proposed Active Learning based Lane Detection Algorithm (ALDA) obtains an accuracy of 98.01%, Precision of 98.5173%, Recall of 95.2296%, F1 score of 96.845%, mAP of 92.7%, and MSE of 0.0097

Multitask learning (MTL) and data augmentation are becoming increasingly popular in natural language processing (NLP). These techniques are particularly useful when data are scarce. In MTL, knowledge learned from one task is applied to another. To address data scarcity, data augmentation facilitates by providing additional synthetic data during model training. In NLP, the bidirectional encoder representations from transformers (BERT) model is the default candidate for various tasks. MTL and data augmentation using BERT have yielded promising results. However, a detailed study regarding the effect of using MTL in different layers of BERT and the benefit of data augmentation in these configurations has not been conducted. In this study, we investigate the use of MTL and data augmentation from generative models, specifically for category classification, sentiment classification, and aspect-opinion sequence-labeling using BERT. The layers of BERT are categorized into top, middle, and bottom layers, which are frozen, shared, or unshared. Experiments are conducted to identify the optimal layer configuration for improved performance compared with that of single-task learning. Generative models are used to generate augmented data, and experiments are performed to reveal their effectiveness. The results indicate the effectiveness of the MTL configuration compared with single-task learning as well as the effectiveness of data augmentation using generative models for classification tasks.

As one of the main unsolved problems of the current healthcare, cancer and one of its most frequent forms for women, breast cancer, is a popular research area in medicine. Early diagnosis is critical for improving the survival chances of breast cancer patients. Manual/visual diagnosis performed by a clinician is prone to many difficulties like high error rates and subjectivity. In addition, the time cost of the diagnosis procedure is very high and negatively effects the clinical routine. Automatic Computer-Aided Diagnosis (CAD) can be a solution to these problems. Recent research implementing deep learning-based techniques for developing an effective computer-aided breast cancer detection system proved to be very successful. In this paper, those recent deep learning-based automatic breast cancer detection systems and their performances are reviewed in detail for guiding the further research efforts in the field.KeywordsBreast cancerDeep learningComputer aided diagnosis

Children's speaker verification in low and zero resource conditions

Brain computed tomography (CTB) scans are widely used to evaluate intracranial pathology. The implementation and adoption of CTB has led to clinical improvements. However, interpretation errors occur and may have substantial morbidity and mortality implications for patients. Deep learning has shown promise for facilitating improved diagnostic accuracy and triage. This research charts the potential of deep learning applied to the analysis of CTB scans. It draws on the experience of practicing clinicians and technologists involved in development and implementation of deep learning-based clinical decision support systems. We consider the past, present and future of the CTB, along with limitations of existing systems as well as untapped beneficial use cases. Implementing deep learning CTB interpretation systems and effectively navigating development and implementation risks can deliver many benefits to clinicians and patients, ultimately improving efficiency and safety in healthcare.