Deep learning based multimodal urban air quality prediction and traffic analytics.

Urban activities, particularly vehicle traffic, are contributing significantly to environmental pollution with detrimental effects on public health. The ability to anticipate air quality in advance is critical for public authorities and the general public to plan and manage these activities, which ultimately help in minimizing the adverse impact on the environment and public health effectively. Thanks to recent advancements in Artificial Intelligence and sensor technology, forecasting air quality is possible through the consideration of various environmental factors. This paper presents our novel solution for air quality prediction and its correlation with different environmental factors and urban activities, such as traffic density. To this aim, we propose a multi-modal framework by integrating real-time data from different environmental sensors and traffic density extracted from Closed Circuit Television footage. The framework effectively addresses data inconsistencies arising from sensor and camera malfunctions within a streaming dataset. The dataset exhibits real-world complexities, including abrupt camera or station activations/deactivations, noise interference, and outliers. The proposed system tackles the challenge of predicting air quality at locations having no sensors or experiencing sensor failures by training a joint model on the data obtained from nearby stations/sensors using a Particle Swarm Optimization (PSO)-based merit fusion of the sensor data. The proposed methodology is evaluated using various variants of the LSTM model including Bi-directional LSTM, CNN-LSTM, and Convolutions LSTM (ConvLSTM) obtaining an improvement of 48%, 67%, and 173% for short-term, medium-term, and long-term periods, respectively, over the ARIMA model.

Revolutionizing Healthcare with Foundation AI Models.

ChatGPT is a foundation Artificial Intelligence (AI) model that has opened up new opportunities in digital healthcare. Particularly, it can serve as a co-pilot tool for doctors in the interpretation, summarization, and completion of reports. Furthermore, it can build upon the ability to access the large literature and knowledge on the internet. So, chatGPT could generate acceptable responses for the medical examination. Hence. It offers the possibility of enhancing healthcare accessibility, expandability, and effectiveness. Nonetheless, chatGPT is vulnerable to inaccuracies, false information, and bias. This paper briefly describes the potential of Foundation AI models to transform future healthcare by presenting ChatGPT as an example tool.

Privacy-preserving artificial intelligence in healthcare: Techniques and applications.

There has been an increasing interest in translating artificial intelligence (AI) research into clinically-validated applications to improve the performance, capacity, and efficacy of healthcare services. Despite substantial research worldwide, very few AI-based applications have successfully made it to clinics. Key barriers to the widespread adoption of clinically validated AI applications include non-standardized medical records, limited availability of curated datasets, and stringent legal/ethical requirements to preserve patients' privacy. Therefore, there is a pressing need to improvise new data-sharing methods in the age of AI that preserve patient privacy while developing AI-based healthcare applications. In the literature, significant attention has been devoted to developing privacy-preserving techniques and overcoming the issues hampering AI adoption in an actual clinical environment. To this end, this study summarizes the state-of-the-art approaches for preserving privacy in AI-based healthcare applications. Prominent privacy-preserving techniques such as Federated Learning and Hybrid Techniques are elaborated along with potential privacy attacks, security challenges, and future directions.

Selective Deeply Supervised Multi-Scale Attention Network for Brain Tumor Segmentation.

Brain tumors are among the deadliest forms of cancer, characterized by abnormal proliferation of brain cells. While early identification of brain tumors can greatly aid in their therapy, the process of manual segmentation performed by expert doctors, which is often time-consuming, tedious, and prone to human error, can act as a bottleneck in the diagnostic process. This motivates the development of automated algorithms for brain tumor segmentation. However, accurately segmenting the enhanced and core tumor regions is complicated due to high levels of inter- and intra-tumor heterogeneity in terms of texture, morphology, and shape. This study proposes a fully automatic method called the selective deeply supervised multi-scale attention network (SDS-MSA-Net) for segmenting brain tumor regions using a multi-scale attention network with novel selective deep supervision (SDS) mechanisms for training. The method utilizes a 3D input composed of five consecutive slices, in addition to a 2D slice, to maintain sequential information. The proposed multi-scale architecture includes two encoding units to extract meaningful global and local features from the 3D and 2D inputs, respectively. These coarse features are then passed through attention units to filter out redundant information by assigning lower weights. The refined features are fed into a decoder block, which upscales the features at various levels while learning patterns relevant to all tumor regions. The SDS block is introduced to immediately upscale features from intermediate layers of the decoder, with the aim of producing segmentations of the whole, enhanced, and core tumor regions. The proposed framework was evaluated on the BraTS2020 dataset and showed improved performance in brain tumor region segmentation, particularly in the segmentation of the core and enhancing tumor regions, demonstrating the effectiveness of the proposed approach. Our code is publicly available.

Dental caries detection using a semi-supervised learning approach.

Early diagnosis of dental caries progression can prevent invasive treatment and enable preventive treatment. In this regard, dental radiography is a widely used tool to capture dental visuals that are used for the detection and diagnosis of caries. Different deep learning (DL) techniques have been used to automatically analyse dental images for caries detection. However, most of these techniques require large-scale annotated data to train DL models. On the other hand, in clinical settings, such medical images are scarcely available and annotations are costly and time-consuming. To this end, we present an efficient self-training-based method for caries detection and segmentation that leverages a small set of labelled images for training the teacher model and a large collection of unlabelled images for training the student model. We also propose to use centroid cropped images of the caries region and different augmentation techniques for the training of self-supervised models that provide computational and performance gains as compared to fully supervised learning and standard self-supervised learning methods. We present a fully labelled dental radiographic dataset of 141 images that are used for the evaluation of baseline and proposed models. Our proposed self-supervised learning strategy has provided performance improvement of approximately 6% and 3% in terms of average pixel accuracy and mean intersection over union, respectively as compared to standard self-supervised learning. Data and code will be made available to facilitate future research.

Untrained Neural Network Priors for Inverse Imaging Problems: A Survey.

In recent years, advancements in machine learning (ML) techniques, in particular, deep learning (DL) methods have gained a lot of momentum in solving inverse imaging problems, often surpassing the performance provided by hand-crafted approaches. Traditionally, analytical methods have been used to solve inverse imaging problems such as image restoration, inpainting, and superresolution. Unlike analytical methods for which the problem is explicitly defined and the domain knowledge is carefully engineered into the solution, DL models do not benefit from such prior knowledge and instead make use of large datasets to predict an unknown solution to the inverse problem. Recently, a new paradigm of training deep models using a single image, named untrained neural network prior (UNNP) has been proposed to solve a variety of inverse tasks, e.g., restoration and inpainting. Since then, many researchers have proposed various applications and variants of UNNP. In this paper, we present a comprehensive review of such studies and various UNNP applications for different tasks and highlight various open research problems which require further research.

Secure Bluetooth Communication in Smart Healthcare Systems: A Novel Community Dataset and Intrusion Detection System.

Smart health presents an ever-expanding attack surface due to the continuous adoption of a broad variety of Internet of Medical Things (IoMT) devices and applications. IoMT is a common approach to smart city solutions that deliver long-term benefits to critical infrastructures, such as smart healthcare. Many of the IoMT devices in smart cities use Bluetooth technology for short-range communication due to its flexibility, low resource consumption, and flexibility. As smart healthcare applications rely on distributed control optimization, artificial intelligence (AI) and deep learning (DL) offer effective approaches to mitigate cyber-attacks. This paper presents a decentralized, predictive, DL-based process to autonomously detect and block malicious traffic and provide an end-to-end defense against network attacks in IoMT devices. Furthermore, we provide the BlueTack dataset for Bluetooth-based attacks against IoMT networks. To the best of our knowledge, this is the first intrusion detection dataset for Bluetooth classic and Bluetooth low energy (BLE). Using the BlueTack dataset, we devised a multi-layer intrusion detection method that uses deep-learning techniques. We propose a decentralized architecture for deploying this intrusion detection system on the edge nodes of a smart healthcare system that may be deployed in a smart city. The presented multi-layer intrusion detection models achieve performances in the range of 97-99.5% based on the F1 scores.

Explainable, trustworthy, and ethical machine learning for healthcare: A survey.

With the advent of machine learning (ML) and deep learning (DL) empowered applications for critical applications like healthcare, the questions about liability, trust, and interpretability of their outputs are raising. The black-box nature of various DL models is a roadblock to clinical utilization. Therefore, to gain the trust of clinicians and patients, we need to provide explanations about the decisions of models. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provided a comprehensive review of explainable and interpretable ML techniques for various healthcare applications. Along with highlighting security, safety, and robustness challenges that hinder the trustworthiness of ML, we also discussed the ethical issues arising because of the use of ML/DL for healthcare. We also describe how explainable and trustworthy ML can resolve all these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

An active learning method for diabetic retinopathy classification with uncertainty quantification.

In recent years, deep learning (DL) techniques have provided state-of-the-art performance in medical imaging. However, good quality (annotated) medical data is in general hard to find due to the usually high cost of medical images, limited availability of expert annotators (e.g., radiologists), and the amount of time required for annotation. In addition, DL is data-hungry and its training requires extensive computational resources. Furthermore, DL being a black-box method lacks transparency on its inner working and lacks fundamental understanding behind decisions made by the model and consequently, this notion enhances the uncertainty on its predictions. To this end, we address these challenges by proposing a hybrid model, which uses a Bayesian convolutional neural network (BCNN) for uncertainty quantification, and an active learning approach for annotating the unlabeled data. The BCNN is used as a feature descriptor and these features are then used for training a model, in an active learning setting. We evaluate the proposed framework for diabetic retinopathy classification problem and demonstrate state-of-the-art performance in terms of different metrics.

Single-shot retinal image enhancement using untrained and pretrained neural networks priors integrated with analytical image priors.

Retinal images acquired using fundus cameras are often visually blurred due to imperfect imaging conditions, refractive medium turbidity, and motion blur. In addition, ocular diseases such as the presence of cataracts also result in blurred retinal images. The presence of blur in retinal fundus images reduces the effectiveness of the diagnosis process of an expert ophthalmologist or a computer-aided detection/diagnosis system. In this paper, we put forward a single-shot deep image prior (DIP)-based approach for retinal image enhancement. Unlike typical deep learning-based approaches, our method does not require any training data. Instead, our DIP-based method can learn the underlying image prior while using a single degraded image. To perform retinal image enhancement, we frame it as a layer decomposition problem and investigate the use of two well-known analytical priors, i.e., dark channel prior (DCP) and bright channel prior (BCP) for atmospheric light estimation. We show that both the untrained neural networks and the pretrained neural networks can be used to generate an enhanced image while using only a single degraded image. The proposed approach is time and memory-efficient, which makes the solution feasible for real-world resource-constrained environments. We evaluate our proposed framework quantitatively on five datasets using three widely used metrics and complement that with a subjective qualitative assessment of the enhancement by two expert ophthalmologists. For instance, our method has achieved significant performance for untrained CDIPs coupled with DCP in terms of average PSNR, SSIM, and BRISQUE values of 40.41, 0.97, and 34.2, respectively, and for untrained CDIPs coupled with BCP, it achieved average PSNR, SSIM, and BRISQUE values of 40.22, 0.98, and 36.38, respectively. Our extensive experimental comparison with several competitive baselines on public and non-public proprietary datasets validates the proposed ideas and framework.

Enhancing Cyber Security of LoRaWAN Gateways under Adversarial Attacks.

The Internet of Things (IoT) has disrupted the IT landscape drastically, and Long Range Wide Area Network (LoRaWAN) is one specification that enables these IoT devices to have access to the Internet. Former security analyses have suggested that the gateways in LoRaWAN in their current state are susceptible to a wide variety of malicious attacks, which can be notoriously difficult to mitigate since gateways are seen as obedient relays by design. These attacks, if not addressed, can cause malfunctions and loss of efficiency in the network traffic. As a solution to this unique problem, this paper presents a novel certificate authentication technique that enhances the cyber security of gateways in the LoRaWAN network. The proposed technique considers a public key infrastructure (PKI) solution that considers a two-tier certificate authority (CA) setup, such as a root-CA and intermediate-CA. This solution is promising, as the simulation results validate that about 66.67% of the packets that are arriving from an illegitimate gateway (GW) are discarded in our implemented secure and reliable solution.

Global User-Level Perception of COVID-19 Contact Tracing Applications: Data-Driven Approach Using Natural Language Processing.

BACKGROUND: Contact tracing has been globally adopted in the fight to control the infection rate of COVID-19. To this aim, several mobile apps have been developed. However, there are ever-growing concerns over the working mechanism and performance of these applications. The literature already provides some interesting exploratory studies on the community's response to the applications by analyzing information from different sources, such as news and users' reviews of the applications. However, to the best of our knowledge, there is no existing solution that automatically analyzes users' reviews and extracts the evoked sentiments. We believe such solutions combined with a user-friendly interface can be used as a rapid surveillance tool to monitor how effective an application is and to make immediate changes without going through an intense participatory design method. OBJECTIVE: In this paper, we aim to analyze the efficacy of AI and NLP techniques for automatically extracting and classifying the polarity of users' sentiments by proposing a sentiment analysis framework to automatically analyze users' reviews on COVID-19 contact tracing mobile apps. We also aim to provide a large-scale annotated benchmark data set to facilitate future research in the domain. As a proof of concept, we also developed a web application based on the proposed solutions, which is expected to help the community quickly analyze the potential of an application in the domain. METHODS: We propose a pipeline starting from manual annotation via a crowd-sourcing study and concluding with the development and training of artificial intelligence (AI) models for automatic sentiment analysis of users' reviews. In detail, we collected and annotated a large-scale data set of user reviews on COVID-19 contact tracing applications. We used both classical and deep learning methods for classification experiments. RESULTS: We used 8 different methods on 3 different tasks, achieving up to an average F1 score of 94.8%, indicating the feasibility of the proposed solution. The crowd-sourcing activity resulted in a large-scale benchmark data set composed of 34,534 manually annotated reviews. CONCLUSIONS: The existing literature mostly relies on the manual or exploratory analysis of users' reviews on applications, which is tedious and time-consuming. In existing studies, generally, data from fewer applications are analyzed. In this work, we showed that AI and natural language processing techniques provide good results for analyzing and classifying users' sentiments' polarity and that automatic sentiment analysis can help to analyze users' responses more accurately and quickly. We also provided a large-scale benchmark data set. We believe the presented analysis, data set, and proposed solutions combined with a user-friendly interface can be used as a rapid surveillance tool to analyze and monitor mobile apps deployed in emergency situations leading to rapid changes in the applications without going through an intense participatory design method.

A deep dive into COVID-19-related messages on WhatsApp in Pakistan.

The spread of COVID-19 and the lockdowns that followed led to an increase in activity on online social networks. This has resulted in users sharing unfiltered and unreliable information on social networks like WhatsApp, Twitter, Facebook, etc. In this work, we give an extended overview of how Pakistan's population used public WhatsApp groups for sharing information related to the pandemic. Our work is based on a major effort to annotate thousands of text and image-based messages. We explore how information propagates across WhatsApp and the user behavior around it. Specifically, we look at political polarization and its impact on how users from different political parties shared COVID-19-related content. We also try to understand information dissemination across different social networks-Twitter and WhatsApp-in Pakistan and find that there is no significant bot involvement in spreading misinformation about the pandemic.

A Generative Model to Synthesize EEG Data for Epileptic Seizure Prediction.

OBJECTIVE: Scarcity of good quality electroencephalography (EEG) data is one of the roadblocks for accurate seizure prediction. This work proposes a deep convolutional generative adversarial network (DCGAN) to generate synthetic EEG data. Another objective of our study is to use transfer-learning (TL) for evaluating the performance of four well-known deep-learning (DL) models to predict epileptic seizure. METHODS: We proposed an algorithm that generate synthetic data using DCGAN trained on real EEG data in a patient-specific manner. We validate quality of generated data using one-class SVM and a new proposal namely convolutional epileptic seizure predictor (CESP). We evaluate performance of VGG16, VGG19, ResNet50, and Inceptionv3 trained on augmented data using TL with average time of 10 min between true prediction and seizure onset samples. RESULTS: The CESP model achieves sensitivity of 78.11% and 88.21%, and false prediction rate of 0.27/h and 0.14/h for training on synthesized and testing on real Epilepsyecosystem and CHB-MIT datasets, respectively. Using TL and augmented data, Inceptionv3 achieved highest accuracy with sensitivity of 90.03% and 0.03 FPR/h. With the proposed data augmentation method prediction results of CESP model and Inceptionv3 increased by 4-5% as compared to state-of-the-art augmentation techniques. CONCLUSION: The performance of CESP shows that synthetic data acquired association between features and labels very well and by using the augmented data CESP predicted better than chance level for both datasets. SIGNIFICANCE: The proposed DCGAN can be used to generate synthetic data to increase the prediction performance and to overcome good quality data scarcity issue.

Speech Technology for Healthcare: Opportunities, Challenges, and State of the Art.

Speech technology is not appropriately explored even though modern advances in speech technology-especially those driven by deep learning (DL) technology-offer unprecedented opportunities for transforming the healthcare industry. In this paper, we have focused on the enormous potential of speech technology for revolutionising the healthcare domain. More specifically, we review the state-of-the-art approaches in automatic speech recognition (ASR), speech synthesis or text to speech (TTS), and health detection and monitoring using speech signals. We also present a comprehensive overview of various challenges hindering the growth of speech-based services in healthcare. To make speech-based healthcare solutions more prevalent, we discuss open issues and suggest some possible research directions aimed at fully leveraging the advantages of other technologies for making speech-based healthcare solutions more effective.

Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review.

With the advancement in artificial intelligence (AI) and machine learning (ML) techniques, researchers are striving towards employing these techniques for advancing clinical practice. One of the key objectives in healthcare is the early detection and prediction of disease to timely provide preventive interventions. This is especially the case for epilepsy, which is characterized by recurrent and unpredictable seizures. Patients can be relieved from the adverse consequences of epileptic seizures if it could somehow be predicted in advance. Despite decades of research, seizure prediction remains an unsolved problem. This is likely to remain at least partly because of the inadequate amount of data to resolve the problem. There have been exciting new developments in ML-based algorithms that have the potential to deliver a paradigm shift in the early and accurate prediction of epileptic seizures. Here we provide a comprehensive review of state-of-the-art ML techniques in early prediction of seizures using EEG signals. We will identify the gaps, challenges, and pitfalls in the current research and recommend future directions.

Secure and Robust Machine Learning for Healthcare: A Survey.

Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from one-dimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.

Retrospective Motion Correction in Multishot MRI using Generative Adversarial Network.

Multishot Magnetic Resonance Imaging (MRI) is a promising data acquisition technique that can produce a high-resolution image with relatively less data acquisition time than the standard spin echo. The downside of multishot MRI is that it is very sensitive to subject motion and even small levels of motion during the scan can produce artifacts in the final magnetic resonance (MR) image, which may result in a misdiagnosis. Numerous efforts have focused on addressing this issue; however, all of these proposals are limited in terms of how much motion they can correct and require excessive computational time. In this paper, we propose a novel generative adversarial network (GAN)-based conjugate gradient SENSE (CG-SENSE) reconstruction framework for motion correction in multishot MRI. First CG-SENSE reconstruction is employed to reconstruct an image from the motion-corrupted k-space data and then the GAN-based proposed framework is applied to correct the motion artifacts. The proposed method has been rigorously evaluated on synthetically corrupted data on varying degrees of motion, numbers of shots, and encoding trajectories. Our analyses (both quantitative as well as qualitative/visual analysis) establish that the proposed method is robust and reduces several-fold the computational time reported by the current state-of-the-art technique.

Leveraging Data Science to Combat COVID-19: A Comprehensive Review.

COVID-19, an infectious disease caused by the SARS-CoV-2 virus, was declared a pandemic by the World Health Organisation (WHO) in March 2020. By mid-August 2020, more than 21 million people have tested positive worldwide. Infections have been growing rapidly and tremendous efforts are being made to fight the disease. In this paper, we attempt to systematise the various COVID-19 research activities leveraging data science, where we define data science broadly to encompass the various methods and tools-including those from artificial intelligence (AI), machine learning (ML), statistics, modeling, simulation, and data visualization-that can be used to store, process, and extract insights from data. In addition to reviewing the rapidly growing body of recent research, we survey public datasets and repositories that can be used for further work to track COVID-19 spread and mitigation strategies. As part of this, we present a bibliometric analysis of the papers produced in this short span of time. Finally, building on these insights, we highlight common challenges and pitfalls observed across the surveyed works. We also created a live resource repository at https://github.com/Data-Science-and-COVID-19/Leveraging-Data-Science-To-Combat-COVID-19-A-Comprehensive-Review that we intend to keep updated with the latest resources including new papers and datasets.

Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security.

With the advances in machine learning (ML) and deep learning (DL) techniques, and the potency of cloud computing in offering services efficiently and cost-effectively, Machine Learning as a Service (MLaaS) cloud platforms have become popular. In addition, there is increasing adoption of third-party cloud services for outsourcing training of DL models, which requires substantial costly computational resources (e.g., high-performance graphics processing units (GPUs)). Such widespread usage of cloud-hosted ML/DL services opens a wide range of attack surfaces for adversaries to exploit the ML/DL system to achieve malicious goals. In this article, we conduct a systematic evaluation of literature of cloud-hosted ML/DL models along both the important dimensions-attacks and defenses-related to their security. Our systematic review identified a total of 31 related articles out of which 19 focused on attack, six focused on defense, and six focused on both attack and defense. Our evaluation reveals that there is an increasing interest from the research community on the perspective of attacking and defending different attacks on Machine Learning as a Service platforms. In addition, we identify the limitations and pitfalls of the analyzed articles and highlight open research issues that require further investigation.