Deep Generative Learning Models for Cloud Intrusion Detection Systems.

Intrusion detection (ID) on the cloud environment has received paramount interest over the last few years. Among the latest approaches, machine learning-based ID methods allow us to discover unknown attacks. However, due to the lack of malicious samples and the rapid evolution of diverse attacks, constructing a cloud ID system (IDS) that is robust to a wide range of unknown attacks remains challenging. In this article, we propose a novel solution to enable robust cloud IDSs using deep neural networks. Specifically, we develop two deep generative models to synthesize malicious samples on the cloud systems. The first model, conditional denoising adversarial autoencoder (CDAAE), is used to generate specific types of malicious samples. The second model (CDAEE-KNN) is a hybrid of CDAAE and the K -nearest neighbor algorithm to generate malicious borderline samples that further improve the accuracy of a cloud IDS. The synthesized samples are merged with the original samples to form the augmented datasets. Three machine learning algorithms are trained on the augmented datasets and their effectiveness is analyzed. The experiments conducted on four popular IDS datasets show that our proposed techniques significantly improve the accuracy of the cloud IDSs compared with the baseline technique and the state-of-the-art approaches. Moreover, our models also enhance the accuracy of machine learning algorithms in detecting some currently challenging distributed denial of service (DDoS) attacks, including low-rate DDoS attacks and application layer DDoS attacks.

EEG Peak Detection in Cognitive Conflict Processing Using Summit Navigator and Clustering-Based Ranking.

Correct detection of peaks in electroencephalogram (EEG) signals is of essence due to the significant correlation of those potentials with cognitive performance and disorders. This paper proposes a novel and non-parametric approach to detect prediction error negativity (PEN) in cognitive conflict processing. The PEN candidates are first located from the input signal via an adaptation of a recent effective method for local maxima extraction, processed in a multi-scale manner. The found candidates are then fused and ranked based on their shape and location-based features. False positives caused by candidates' magnitude are eliminated by rotating the sorted candidate list where the one with the second-best ranking score will be identified as PEN. The EEG data collected from a 3D object selection task have been used to verify the efficacy of the proposed approach. Compared with the state-of-the-art peak detection techniques, the proposed method shows an improvement of at least 2.67% in accuracy and 6.27% in sensitivity while requires only about 4 ms to process an epoch. The accuracy and computational efficiency of the proposed technique in the detection of PEN in cognitive conflict processing would lead to promising applications in performance improvement of brain-computer interfaces (BCIs).

Analog-Domain Suppression of Strong Interference Using Hybrid Antenna Array.

The proliferation of wireless applications, the ever-increasing spectrum crowdedness, as well as cell densification makes the issue of interference increasingly severe in many emerging wireless applications. Most interference management/mitigation methods in the literature are problem-specific and require some cooperation/coordination between different radio frequency systems. Aiming to seek a more versatile solution to counteracting strong interference, we resort to the hybrid array of analog subarrays and suppress interference in the analog domain so as to greatly reduce the required quantization bits of the analog-to-digital converters and their power consumption. To this end, we design a real-time algorithm to steer nulls towards the interference directions and maintain flat in non-interference directions, solely using constant-modulus phase shifters. To ensure sufficient null depth for interference suppression, we also develop a two-stage method for accurately estimating interference directions. The proposed solution can be applicable to most (if not all) wireless systems as neither training/reference signal nor cooperation/coordination is required. Extensive simulations show that more than 65 dB of suppression can be achieved for 3 spatially resolvable interference signals yet with random directions.

The molecular chaperone GRP170 protects against ER stress and acute kidney injury in mice.

Molecular chaperones are responsible for maintaining cellular homeostasis, and one such chaperone, GRP170, is an endoplasmic reticulum (ER) resident that oversees both protein biogenesis and quality control. We previously discovered that GRP170 regulates the degradation and assembly of the epithelial sodium channel (ENaC), which reabsorbs sodium in the distal nephron and thereby regulates salt-water homeostasis and blood pressure. To define the role of GRP170 - and, more generally, molecular chaperones in kidney physiology - we developed an inducible, nephron-specific GRP170-KO mouse. Here, we show that GRP170 deficiency causes a dramatic phenotype: profound hypovolemia, hyperaldosteronemia, and dysregulation of ion homeostasis, all of which are associated with the loss of ENaC. Additionally, the GRP170-KO mouse exhibits hallmarks of acute kidney injury (AKI). We further demonstrate that the unfolded protein response (UPR) is activated in the GRP170-deficient mouse. Notably, the UPR is also activated in AKI when originating from various other etiologies, including ischemia, sepsis, glomerulonephritis, nephrotic syndrome, and transplant rejection. Our work establishes the central role of GRP170 in kidney homeostasis and directly links molecular chaperone function to kidney injury.

Learning Latent Representation for IoT Anomaly Detection.

Internet of Things (IoT) has emerged as a cutting-edge technology that is changing human life. The rapid and widespread applications of IoT, however, make cyberspace more vulnerable, especially to IoT-based attacks in which IoT devices are used to launch attack on cyber-physical systems. Given a massive number of IoT devices (in order of billions), detecting and preventing these IoT-based attacks are critical. However, this task is very challenging due to the limited energy and computing capabilities of IoT devices and the continuous and fast evolution of attackers. Among IoT-based attacks, unknown ones are far more devastating as these attacks could surpass most of the current security systems and it takes time to detect them and "cure" the systems. To effectively detect new/unknown attacks, in this article, we propose a novel representation learning method to better predictively "describe" unknown attacks, facilitating supervised learning-based anomaly detection methods. Specifically, we develop three regularized versions of autoencoders (AEs) to learn a latent representation from the input data. The bottleneck layers of these regularized AEs trained in a supervised manner using normal data and known IoT attacks will then be used as the new input features for classification algorithms. We carry out extensive experiments on nine recent IoT datasets to evaluate the performance of the proposed models. The experimental results demonstrate that the new latent representation can significantly enhance the performance of supervised learning methods in detecting unknown IoT attacks. We also conduct experiments to investigate the characteristics of the proposed models and the influence of hyperparameters on their performance. The running time of these models is about 1.3 ms that is pragmatic for most applications.

Effect of extraction methods on mobilizable colloids and associated phosphorus from reservoir sediment.

Mobilizable colloids from reservoir sediment contain nutrients and contaminants, thus may affect water quality once being released. A major obstacle to evaluate the quantity and quality of mobilizable colloids in natural system is the using of appropriate method for colloid extraction from sediment and their separation from dissolved and particulate phases. This work evaluates the role of different extraction methods (agitation, sonication at sediment pH, and sonication at alkaline pH) on the characteristics (mass, size, shape and composition) of water-mobilizable colloids from sediment of Champsanglard dam reservoir (France). Attention has been paid to phosphorus (P), an important element in controlling eutrophication. Recovered colloids were highly affected on both quantity and quality according to the different applied protocols. The less aggressive agitation liberated low-energy water-dispersible colloids without physical damage and with less modification in colloidal chemical composition and shape, whereas sonication released 10-20 times higher colloid quantity but in lower size, due to physically disruption of fragile sediment structure or aggregated/chained colloids. In contrast, alkaline pH intensified colloid release by fortified repulsive forces between colloids and dissolution of organic coat. Concerning phosphorus, competition with hydroxide ions for sorption site or dissolution of phosphate minerals in alkaline pH caused release of dissolved P to solution and decrease of P content in recovered colloids. A special care should be paid to method selection according to the aim of the study and when comparing data from experiments conducted with different colloid extraction methods.

Genome-Scale Metabolic Model of Caldicellulosiruptor bescii Reveals Optimal Metabolic Engineering Strategies for Bio-based Chemical Production.

Metabolic modeling was used to examine potential bottlenecks that could be encountered for metabolic engineering of the cellulolytic extreme thermophile Caldicellulosiruptor bescii to produce bio-based chemicals from plant biomass. The model utilizes subsystems-based genome annotation, targeted reconstruction of carbohydrate utilization pathways, and biochemical and physiological experimental validations. Specifically, carbohydrate transport and utilization pathways involving 160 genes and their corresponding functions were incorporated, representing the utilization of C5/C6 monosaccharides, disaccharides, and polysaccharides such as cellulose and xylan. To illustrate its utility, the model predicted that optimal production from biomass-based sugars of the model product, ethanol, was driven by ATP production, redox balancing, and proton translocation, mediated through the interplay of an ATP synthase, a membrane-bound hydrogenase, a bifurcating hydrogenase, and a bifurcating NAD- and NADP-dependent oxidoreductase. These mechanistic insights guided the design and optimization of new engineering strategies for product optimization, which were subsequently tested in the C. bescii model, showing a nearly 2-fold increase in ethanol yields. The C. bescii model provides a useful platform for investigating the potential redox controls that mediate the carbon and energy flows in metabolism and sets the stage for future design of engineering strategies aiming at optimizing the production of ethanol and other bio-based chemicals. IMPORTANCE The extremely thermophilic cellulolytic bacterium, Caldicellulosiruptor bescii, degrades plant biomass at high temperatures without any pretreatments and can serve as a strategic platform for industrial applications. The metabolic engineering of C. bescii, however, faces potential bottlenecks in bio-based chemical productions. By simulating the optimal ethanol production, a complex interplay between redox balancing and the carbon and energy flow was revealed using a C. bescii genome-scale metabolic model. New engineering strategies were designed based on an improved mechanistic understanding of the C. bescii metabolism, and the new designs were modeled under different genetic backgrounds to identify optimal strategies. The C. bescii model provided useful insights into the metabolic controls of this organism thereby opening up prospects for optimizing production of a wide range of bio-based chemicals.

A Comprehensive Survey of Enabling and Emerging Technologies for Social Distancing-Part I: Fundamentals and Enabling Technologies.

Social distancing plays a pivotal role in preventing the spread of viral diseases illnesses such as COVID-19. By minimizing the close physical contact among people, we can reduce the chances of catching the virus and spreading it across the community. This two-part paper aims to provide a comprehensive survey on how emerging technologies, e.g., wireless and networking, artificial intelligence (AI) can enable, encourage, and even enforce social distancing practice. In this Part I, we provide a comprehensive background of social distancing including basic concepts, measurements, models, and propose various practical social distancing scenarios. We then discuss enabling wireless technologies which are especially effect- in social distancing, e.g., symptom prediction, detection and monitoring quarantined people, and contact tracing. The companion paper Part II surveys other emerging and related technologies, such as machine learning, computer vision, thermal, ultrasound, etc., and discusses open issues and challenges (e.g., privacy-preserving, scheduling, and incentive mechanisms) in implementing social distancing in practice.

A Comprehensive Survey of Enabling and Emerging Technologies for Social Distancing-Part II: Emerging Technologies and Open Issues.

This two-part paper aims to provide a comprehensive survey on how emerging technologies, e.g., wireless and networking, artificial intelligence (AI) can enable, encourage, and even enforce social distancing practice. In Part I, an extensive background of social distancing is provided, and enabling wireless technologies are thoroughly surveyed. In this Part II, emerging technologies such as machine learning, computer vision, thermal, ultrasound, etc., are introduced. These technologies open many new solutions and directions to deal with problems in social distancing, e.g., symptom prediction, detection and monitoring quarantined people, and contact tracing. Finally, we discuss open issues and challenges (e.g., privacy-preserving, scheduling, and incentive mechanisms) in implementing social distancing in practice. As an example, instead of reacting with ad-hoc responses to COVID-19-like pandemics in the future, smart infrastructures (e.g., next-generation wireless systems like 6G, smart home/building, smart city, intelligent transportation systems) should incorporate a pandemic mode in their standard architectures/designs.

A profiling analysis of contributions of cigarette smoking, dietary calcium intakes, and physical activity to fragility fracture in the elderly.

Fragility fracture and bone mineral density (BMD) are influenced by common and modifiable lifestyle factors. In this study, we sought to define the contribution of lifestyle factors to fracture risk by using a profiling approach. The study involved 1683 women and 1010 men (50+ years old, followed up for up to 20 years). The incidence of new fractures was ascertained by X-ray reports. A "lifestyle risk score" (LRS) was derived as the weighted sum of effects of dietary calcium intake, physical activity index, and cigarette smoking. Each individual had a unique LRS, with higher scores being associated with a healthier lifestyle. Baseline values of lifestyle factors were assessed. In either men or women, individuals with a fracture had a significantly lower age-adjusted LRS than those without a fracture. In men, each unit lower in LRS was associated with a 66% increase in the risk of total fracture (non-adjusted hazard ratio [HR] 1.66; 95% CI, 1.26 to 2.20) and still significant after adjusting for age, weight or BMD. However, in women, the association was uncertain (HR 1.30; 95% CI, 1.11 to 1.53). These data suggest that unhealthy lifestyle habits are associated with an increased risk of fracture in men, but not in women, and that the association is mediated by BMD.

Subject-Independent ERP-Based Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) are desirable for people to express their thoughts, especially those with profound disabilities in communication. The classification of brain patterns for each different subject requires an extensively time-consuming learning stage specific to that person, in order to reach satisfactory accuracy performance. The training session could also be infeasible for disabled patients as they may not fully understand the training instructions. In this paper, we propose a unified classification scheme based on ensemble classifier, dynamic stopping, and adaptive learning. We apply this scheme on the P300-based BCI, with the subject-independent manner, where no learning session is required for new experimental users. According to our theoretical analysis and empirical results, the harmonized integration of these three methods can significantly boost up the average accuracy from 75.00% to 91.26%, while at the same time reduce the average spelling time from 12.62 to 6.78 iterations, approximately to two-fold faster. The experiments were conducted on a large public dataset which had been used in other related studies. Direct comparisons between our work with the others' are also reported in details.

Real-time analysis on ensemble SVM scores to reduce P300-Speller intensification time.

In most Brain-Computer Interface systems, especially the P300-Speller, there must be a harmonized balance between the accuracy and the spelling time. One major drawback of the classical 36-choice P300-Speller is the slow rate of character elicitation. This paper aims to propose a real-time signal processing method to decrease the spelling time by exploiting the score margins of the ensemble Support Vector Machine classifiers during real-time P300-Speller flashes, rather than just getting the classifiers' highest scores. Our experiments were conducted on the dataset of the BCI Competition III and resulted in a successful character rate of over 96% with just approximately 15 to 20 seconds for each character spelling session. As compared with the fixed 31.5 seconds of the best original approach of the competition, our proposed method significantly reduces the required spelling time by over 30% while maintaining the desired classification accuracy.

Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores.

Freezing of gait (FoG) is common in Parkinsonian gait and strongly relates to falls. Current clinical FoG assessments are patients' self-report diaries and experts' manual video analysis. Both are subjective and yield moderate reliability. Existing detection algorithms have been predominantly designed in subject-dependent settings. In this paper, we aim to develop an automated FoG detector for subject independent. After extracting highly relevant features, we apply anomaly detection techniques to detect FoG events. Specifically, feature selection is performed using correlation and clusterability metrics. From a list of 244 feature candidates, 36 candidates were selected using saliency and robustness criteria. We develop an anomaly score detector with adaptive thresholding to identify FoG events. Then, using accuracy metrics, we reduce the feature list to seven candidates. Our novel multichannel freezing index was the most selective across all window sizes, achieving sensitivity (specificity) of (). On the other hand, freezing index from the vertical axis was the best choice for a single input, achieving sensitivity (specificity) of () for ankle and () for back sensors. Our subject-independent method is not only significantly more accurate than those previously reported, but also uses a much smaller window (e.g., versus ) and/or lower tolerance (e.g., versus ).Freezing of gait (FoG) is common in Parkinsonian gait and strongly relates to falls. Current clinical FoG assessments are patients' self-report diaries and experts' manual video analysis. Both are subjective and yield moderate reliability. Existing detection algorithms have been predominantly designed in subject-dependent settings. In this paper, we aim to develop an automated FoG detector for subject independent. After extracting highly relevant features, we apply anomaly detection techniques to detect FoG events. Specifically, feature selection is performed using correlation and clusterability metrics. From a list of 244 feature candidates, 36 candidates were selected using saliency and robustness criteria. We develop an anomaly score detector with adaptive thresholding to identify FoG events. Then, using accuracy metrics, we reduce the feature list to seven candidates. Our novel multichannel freezing index was the most selective across all window sizes, achieving sensitivity (specificity) of (). On the other hand, freezing index from the vertical axis was the best choice for a single input, achieving sensitivity (specificity) of () for ankle and () for back sensors. Our subject-independent method is not only significantly more accurate than those previously reported, but also uses a much smaller window (e.g., versus ) and/or lower tolerance (e.g., versus ).

The Triple Functions of D2 Silencing in Treatment of Periapical Disease.

INTRODUCTION: Dental caries is the most widespread chronic infectious disease. Inflammation in pulp tissues caused by dental caries will lead to periapical granulomas, bone erosion, loss of the tooth, and severe pain. Despite numerous efforts in recent studies to develop effective treatments for dental caries, the need for a potent therapy is still urgent. METHODS: In this study, we applied a gene-based therapy approach by administering recombinant adeno-associated virus (AAV)-mediated Atp6v0d2 (d2) RNA interference knockdown of d2 gene expression to prevent periapical bone loss and suppress periapical inflammation simultaneously. RESULTS: The results showed that d2 depletion is simultaneously capable of reducing bone resorption with 75% protection through reducing osteoclasts, enhancing bone formation by increasing osterix expression, and inhibiting inflammation by decreasing T-cell infiltration. Notably, AAV-mediated gene therapy of d2 knockdown significantly reduced proinflammatory cytokine expression, including tumor necrosis factor α, interferon-γ, interleukin-1α, and interleukin 6 levels in periapical diseases caused by bacterial infection. Quantitative real-time polymerase chain reaction revealed that d2 knockdown reduced osteoclast-specific functional genes (ie, Acp5 and Ctsk) and increased osteoblast marker genes (ie, Osx and Opg) in periapical tissues. CONCLUSIONS: Collectively, our results showed that AAV-mediated d2 depletion in the periapical lesion area can prevent the progression of endodontic disease and bone erosion while significantly reducing the inflammatory over-response. These findings show that the depletion of d2 simultaneously reduces bone resorption, enhances bone formation, and inhibits inflammation caused by periapical diseases and provide significant insights into the potential effectiveness of AAV-sh-d2-mediated d2 silencing gene therapy as a major endodontic treatment.

One year experience using mycobacterial blood cultures to diagnose tuberculosis in patients with prolonged fever in Vietnam.

INTRODUCTION: To evaluate the use of mycobacterial blood cultures (MBC) in diagnosing tuberculosis (TB) in patients with prolonged fever admitted to a Vietnamese referral hospital. RESULTS: MBCs from 94 patients (66% male; median age 33 years; 75% HIV positive) were evaluated: 14 were mycobacterium positive (all HIV positive), and MBC was the only positive specimen in 9 cases (41%). Three positive cases were identified as Mycobacterium avium and the remaining M. tuberculosis (one case could not be identified). CONCLUSION: MBC can be a valuable additional method to diagnose TB, particularly in immunosuppressed HIV patients when sputum cannot be collected.