A Machine Learning-Based Anomaly Prediction Service for Software-Defined Networks.

Software-defined networking (SDN) has gained tremendous growth and can be exploited in different network scenarios, from data centers to wide-area 5G networks. It shifts control logic from the devices to a centralized entity (programmable controller) for efficient traffic monitoring and flow management. A software-based controller enforces rules and policies on the requests sent by forwarding elements; however, it cannot detect anomalous patterns in the network traffic. Due to this, the controller may install the flow rules against the anomalies, reducing the overall network performance. These anomalies may indicate threats to the network and decrease its performance and security. Machine learning (ML) approaches can identify such traffic flow patterns and predict the systems' impending threats. We propose an ML-based service to predict traffic anomalies for software-defined networks in this work. We first create a large dataset for network traffic by modeling a programmable data center with a signature-based intrusion-detection system. The feature vectors are pre-processed and are constructed against each flow request by the forwarding element. Then, we input the feature vector of each request to a machine learning classifier for training to predict anomalies. Finally, we use the holdout cross-validation technique to evaluate the proposed approach. The evaluation results specify that the proposed approach is highly accurate. In contrast to baseline approaches (random prediction and zero rule), the performance improvement of the proposed approach in average accuracy, precision, recall, and f-measure is (54.14%, 65.30%, 81.63%, and 73.70%) and (4.61%, 11.13%, 9.45%, and 10.29%), respectively.

Blockchain Empowered Federated Learning Ecosystem for Securing Consumer IoT Features Analysis.

Resource constraint Consumer Internet of Things (CIoT) is controlled through gateway devices (e.g., smartphones, computers, etc.) that are connected to Mobile Edge Computing (MEC) servers or cloud regulated by a third party. Recently Machine Learning (ML) has been widely used in automation, consumer behavior analysis, device quality upgradation, etc. Typical ML predicts by analyzing customers' raw data in a centralized system which raises the security and privacy issues such as data leakage, privacy violation, single point of failure, etc. To overcome the problems, Federated Learning (FL) developed an initial solution to ensure services without sharing personal data. In FL, a centralized aggregator collaborates and makes an average for a global model used for the next round of training. However, the centralized aggregator raised the same issues, such as a single point of control leaking the updated model and interrupting the entire process. Additionally, research claims data can be retrieved from model parameters. Beyond that, since the Gateway (GW) device has full access to the raw data, it can also threaten the entire ecosystem. This research contributes a blockchain-controlled, edge intelligence federated learning framework for a distributed learning platform for CIoT. The federated learning platform allows collaborative learning with users' shared data, and the blockchain network replaces the centralized aggregator and ensures secure participation of gateway devices in the ecosystem. Furthermore, blockchain is trustless, immutable, and anonymous, encouraging CIoT end users to participate. We evaluated the framework and federated learning outcomes using the well-known Stanford Cars dataset. Experimental results prove the effectiveness of the proposed framework.

Development and On-Field Deployment of a Mobile-Based Application 'MoSQuIT' for Malaria Surveillance in International Border Districts of Northeast India-Challenges and Opportunities.

The conventional paper-based system for malaria surveillance is time-consuming, difficult to track and resource-intensive. Few digital platforms are in use but wide-scale deployment and acceptability remain to be seen. To address this issue, we created a malaria surveillance mobile app that offers real-time data to stakeholders and establishes a centralised data repository. The MoSQuIT app was designed to collect data from the field and was integrated with a web-based platform for data integration and analysis. The MoSQuIT app was deployed on mobile phones of accredited social health activists (ASHA) working in international border villages in the northeast (NE) Indian states of Assam, Tripura and Arunachal Pradesh for 20 months in a phased manner. This paper shares the challenges and opportunities associated with the use of MoSQuIT for malaria surveillance. MoSQuIT employs the same data entry formats as the NVBDCP's malaria surveillance programme. Using this app, a total of 8221 fever cases were recorded, which included 1192 (14.5%) cases of P. falciparum malaria, 280 (3.4%) cases of P. vivax malaria and 52 (0.6%) mixed infection cases. Depending on network availability, GPS coordinates of the fever cases were acquired by the app. The present study demonstrated that mobile-phone-based malaria surveillance facilitates the quick transmission of data from the field to decision makers. Geospatial tagging of cases helped with easy visualisation of the case distribution for the identification of malaria-prone areas and potential outbreaks, especially in hilly and remote regions of Northeast India. However, to achieve the full operational potential of the system, operational challenges have to be overcome.

Nanoemulsion delivery systems for enhanced efficacy of antimicrobials and essential oils.

The ever-growing threat of new and existing infectious diseases in combination with antimicrobial resistance requires the need for innovative and effective forms of drug delivery. Optimal drug delivery systems for existing and newly developed antimicrobials can enhance drug bioavailability, enable site-specific drug targeting, and overcome current limitations of drug formulations such as short elimination half-lives, poor drug solubility, and undesirable side effects. Nanoemulsions (NE) consist of nanometer-sized droplets stabilized by emulsifiers and are typically more stable and permeable due to their smaller particle sizes and higher surface area compared to conventional emulsions. NE have been identified as a promising means of antimicrobial delivery due to their intrinsic antimicrobial properties, ability to increase drug solubility, stability, bioavailability, organ and cellular targeting potentials, capability of targeting biofilms, and potential to overcome antimicrobial resistance. Herein, we discuss non-drug loaded essential oil-based NE that can confer antimicrobial actions through predominantly physical or biochemical mechanisms without drug payloads. We also describe drug-loaded NE for enhanced antimicrobial efficacy by augmenting the potency of existing antimicrobials. We highlight the versatility of NE to be administered through multiple different routes (oral, parenteral, dermal, transdermal, pulmonary, nasal, ocular, and rectal). We summarize recent advances in the clinical translation of antimicrobial NE and shed light on future development of effective antimicrobial therapy to combat infectious diseases.

FcεRIγ-negative NK cells persist in vivo and enhance efficacy of therapeutic monoclonal antibodies in multiple myeloma.

Monoclonal antibodies (mAbs) are a central component of therapy for hematologic malignancies. Widely used mAb agents in multiple myeloma (MM) include daratumumab and elotuzumab. However, not all patients respond to these agents, and resistance is a significant clinical issue. A recently discovered subset of human natural killer (NK) cells lacking expression of FcεRIγ (g-NK cells) was found to have a multifold increase in antibody-dependent effector functions after CD16 crosslinking. In this study, we tested the capacity of g-NK cells to enhance the efficacy of therapeutic mAbs against MM. In vitro, we found that g-NK cells have strikingly superior anti-myeloma cytotoxicity compared with conventional NK (cNK) cells when combined with daratumumab or elotuzumab (∼sixfold; P < .001). In addition, g-NK cells naturally expressed minimal surface CD38 and SLAMF7, which reduced the incidence of therapeutic fratricide. In tumor-naïve murine models, the persistence of g-NK cells in blood and spleen was >10 times higher than that of cNK cells over 31 days (P < .001). In vivo efficacy studies showed that the combination of daratumumab and g-NK cells led to a >99.9% tumor reduction (by flow cytometry analysis) compared with the combination of daratumumab and cNK cells (P < .001). Moreover, treatment with daratumumab and g-NK cells led to complete elimination of myeloma burden in 5 of 7 mice. Collectively, these results underscore the unique ability of g-NK cells to potentiate the activity of therapeutic mAbs and overcome limitations of current off-the-shelf NK cell therapies without the need for cellular irradiation or genetic engineering.

Single-dose intranasal vaccination elicits systemic and mucosal immunity against SARS-CoV-2.

Despite remarkable progress in the development and authorization of vaccines against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), there is a need to validate vaccine platforms for broader application. The current intramuscular vaccines are designed to elicit systemic immunity without conferring mucosal immunity in the nasal compartment, which is the first barrier that SARS-CoV-2 virus breaches before dissemination to the lung. We report the development of an intranasal subunit vaccine that uses lyophilized spike protein and liposomal STING agonist as an adjuvant. This vaccine induces systemic neutralizing antibodies, IgA in the lung and nasal compartments, and T-cell responses in the lung of mice. Single-cell RNA sequencing confirmed the coordinated activation of T/B-cell responses in a germinal center-like manner within the nasal-associated lymphoid tissues, confirming its role as an inductive site to enable durable immunity. The ability to elicit immunity in the respiratory tract can prevent the establishment of infection in individuals and prevent disease transmission.

Nasal delivery of an IgM offers broad protection from SARS-CoV-2 variants.

Resistance represents a major challenge for antibody-based therapy for COVID-191-4. Here we engineered an immunoglobulin M (IgM) neutralizing antibody (IgM-14) to overcome the resistance encountered by immunoglobulin G (IgG)-based therapeutics. IgM-14 is over 230-fold more potent than its parental IgG-14 in neutralizing SARS-CoV-2. IgM-14 potently neutralizes the resistant virus raised by its corresponding IgG-14, three variants of concern-B.1.1.7 (Alpha, which first emerged in the UK), P.1 (Gamma, which first emerged in Brazil) and B.1.351 (Beta, which first emerged in South Africa)-and 21 other receptor-binding domain mutants, many of which are resistant to the IgG antibodies that have been authorized for emergency use. Although engineering IgG into IgM enhances antibody potency in general, selection of an optimal epitope is critical for identifying the most effective IgM that can overcome resistance. In mice, a single intranasal dose of IgM-14 at 0.044 mg per kg body weight confers prophylactic efficacy and a single dose at 0.4 mg per kg confers therapeutic efficacy against SARS-CoV-2. IgM-14, but not IgG-14, also confers potent therapeutic protection against the P.1 and B.1.351 variants. IgM-14 exhibits desirable pharmacokinetics and safety profiles when administered intranasally in rodents. Our results show that intranasal administration of an engineered IgM can improve efficacy, reduce resistance and simplify the prophylactic and therapeutic treatment of COVID-19.

Single-dose intranasal vaccination elicits systemic and mucosal immunity against SARS-CoV-2.

A safe and durable vaccine is urgently needed to tackle the COVID19 pandemic that has infected >15 million people and caused >620,000 deaths worldwide. As with other respiratory pathogens, the nasal compartment is the first barrier that needs to be breached by the SARS-CoV-2 virus before dissemination to the lung. Despite progress at remarkable speed, current intramuscular vaccines are designed to elicit systemic immunity without conferring mucosal immunity. We report the development of an intranasal subunit vaccine that contains the trimeric or monomeric spike protein and liposomal STING agonist as adjuvant. This vaccine induces systemic neutralizing antibodies, mucosal IgA responses in the lung and nasal compartments, and T-cell responses in the lung of mice. Single-cell RNA-sequencing confirmed the concomitant activation of T and B cell responses in a germinal center-like manner within the nasal-associated lymphoid tissues (NALT), confirming its role as an inductive site that can lead to long-lasting immunity. The ability to elicit immunity in the respiratory tract has can prevent the initial establishment of infection in individuals and prevent disease transmission across humans.

Controlling the Outbreak of COVID-19: A Noncooperative Game Perspective.

COVID-19 is a global epidemic. Till now, there is no remedy for this epidemic. However, isolation and social distancing are seemed to be effective preventive measures to control this pandemic. Therefore, in this article, an optimization problem is formulated that accommodates both isolation and social distancing features of the individuals. To promote social distancing, we solve the formulated problem by applying a noncooperative game that can provide an incentive for maintaining social distancing to prevent the spread of COVID-19. Furthermore, the sustainability of the lockdown policy is interpreted with the help of our proposed game-theoretic incentive model for maintaining social distancing where there exists a Nash equilibrium. Finally, we perform an extensive numerical analysis that shows the effectiveness of the proposed approach in terms of achieving the desired social-distancing to prevent the outbreak of the COVID-19 in a noncooperative environment. Numerical results show that the individual incentive increases more than 85% with an increasing percentage of home isolation from 25% to 100% for all considered scenarios. The numerical results also demonstrate that in a particular percentage of home isolation, the individual incentive decreases with an increasing number of individuals.

Simulating yield response of rice to salinity stress with the AquaCrop model.

The FAO AquaCrop model has been widely applied throughout the world to simulate crop responses to deficit water applications. However, its application to saline conditions is not yet reported, though saline soils are common in coastal areas. In this study, we parameterized and tested AquaCrop to simulate rice yield under different salinity regimes. The data and information required in the model were collected through a field experiment at the Bangladesh Agricultural Research Institute, Gazipur. The experiment was conducted with the BRRI Dhan28, a popular boro rice variety in Bangladesh, with five levels of saline water irrigation, three replicates for each level. In addition, field monitoring was carried out at Satkhira in the southwest coastal region of Bangladesh to collect data and information based on farmers' practices and to further validate the model. The results indicated that the AquaCrop model with most of its default parameters could replicate the variation of rice yield with the variation of salinity reasonably well. The root mean square error and mean absolute error of the model yield were only 0.12 t per ha and 0.03 t per ha, respectively. The crop response versus soil salinity stress curve was found to be convex in shape with a lower threshold of 2 dS m(-1), an upper threshold of 10 dS m(-1) and a shape factor of 2.4. As the crop production system in the coastal belt of Bangladesh has become vulnerable to climate induced sea-level rise and the consequent increase in water and soil salinity, the AquaCrop would be a useful tool in assessing the potential impact of these future changes as well as other climatic parameters on rice yield in the coastal region.