Digitized smart surveillance and micromanagement using information technology for malaria elimination in Mangaluru, India: an analysis of five-year post-digitization data.

BACKGROUND: Malaria control system (MCS), an Information technology (IT)-driven surveillance and monitoring intervention is being adopted for elimination of malaria in Mangaluru city, Karnataka, India since October 2015. This has facilitated 'smart surveillance' followed by required field response within a timeline. The system facilitated data collection of individual case, data driven mapping and strategies for malaria elimination programme. This paper aims to present the analysis of post-digitization data of 5 years, discuss the current operational functionalities of MCS and its impact on the malaria incidence. METHODS: IT system developed for robust malaria surveillance and field response is being continued in the sixth year. Protocol for surveillance control was followed as per the national programme guidelines mentioned in an earlier publication. Secondary data from the malaria control system was collated and analysed. Incidence of malaria, active surveillance, malariogenic conditions and its management, malariometric indices, shrinking malaria maps were also analysed. RESULTS: Smart surveillance and subsequent response for control was sustained and performance improved in five years with participation of all stakeholders. Overall malaria incidence significantly reduced by 83% at the end of 5 years when compared with year of digitization (DY) (p < 0.001). Early reporting of new cases (within 48 h) was near total followed by complete treatment and vector control. Slide positivity rate (SPR) decreased from 10.36 (DY) to 6.5 (PDY 5). Annual parasite incidence (API) decreased from 16.17 (DY) to 2.64 (PDY 5). There was a negative correlation between contact smears and incidence of malaria. Five-year data analyses indicated declining trends in overall malaria incidence and correlation between closures by 14 days. The best impact on reduction in incidence of malaria was recorded in the pre-monsoon months (~ 85%) compared to lower impact in July-August months (~ 40%). CONCLUSION: MCS helped to micromanage control activities, such as robust reporting, incidence-centric active surveillance, early and complete treatment, documentation of full treatment of each malaria patient, targeted mosquito control measures in houses surrounding reported cases. The learnings and analytical output from the data helped to modify strategies for control of both disease and the vector, heralding the city into the elimination stage.

An Efficient Anomaly Recognition Framework Using an Attention Residual LSTM in Surveillance Videos.

Video anomaly recognition in smart cities is an important computer vision task that plays a vital role in smart surveillance and public safety but is challenging due to its diverse, complex, and infrequent occurrence in real-time surveillance environments. Various deep learning models use significant amounts of training data without generalization abilities and with huge time complexity. To overcome these problems, in the current work, we present an efficient light-weight convolutional neural network (CNN)-based anomaly recognition framework that is functional in a surveillance environment with reduced time complexity. We extract spatial CNN features from a series of video frames and feed them to the proposed residual attention-based long short-term memory (LSTM) network, which can precisely recognize anomalous activity in surveillance videos. The representative CNN features with the residual blocks concept in LSTM for sequence learning prove to be effective for anomaly detection and recognition, validating our model's effective usage in smart cities video surveillance. Extensive experiments on the real-world benchmark UCF-Crime dataset validate the effectiveness of the proposed model within complex surveillance environments and demonstrate that our proposed model outperforms state-of-the-art models with a 1.77%, 0.76%, and 8.62% increase in accuracy on the UCF-Crime, UMN and Avenue datasets, respectively.

Deep Learning-Based Real-Time Multiple-Person Action Recognition System.

Action recognition has gained great attention in automatic video analysis, greatly reducing the cost of human resources for smart surveillance. Most methods, however, focus on the detection of only one action event for a single person in a well-segmented video, rather than the recognition of multiple actions performed by more than one person at the same time for an untrimmed video. In this paper, we propose a deep learning-based multiple-person action recognition system for use in various real-time smart surveillance applications. By capturing a video stream of the scene, the proposed system can detect and track multiple people appearing in the scene and subsequently recognize their actions. Thanks to high resolution of the video frames, we establish a zoom-in function to obtain more satisfactory action recognition results when people in the scene become too far from the camera. To further improve the accuracy, recognition results from inflated 3D ConvNet (I3D) with multiple sliding windows are processed by a nonmaximum suppression (NMS) approach to obtain a more robust decision. Experimental results show that the proposed method can perform multiple-person action recognition in real time suitable for applications such as long-term care environments.

Indigenously developed digital handheld Android-based Geographic Information System (GIS)-tagged tablets (TABs) in malaria elimination programme in Mangaluru city, Karnataka, India.

BACKGROUND: Under-reporting, delayed diagnosis, incomplete treatment and inadequate vector management are few among many factors responsible for uninterrupted transmission of malaria in India. Information technology (IT) and mobile apps can be utilized effectively to overcome these hurdles. Indigenously developed digital handheld geographic information system (GIS)-tagged Android-based tablets (TABs) has been designed especially for implementation of digitization protocol. This has changed the effectiveness of malaria surveillance and intervention strategies in a malaria endemic area of Mangaluru city, Karnataka, India. METHODS: A software was developed and implemented for control measures to create a digital database of each malaria case. Secondary data analyses were carried out to determine and compare differences in malariometric indices between pre- and post-digitization years. With the introduction of this software active surveillance, information education and communication (IEC), and anti-vector measures were made 'incidence-centric'. This means that the entire control measures were carried out in the houses where the malaria cases (index cases) were reported and also in surrounding houses. RESULTS: Annual blood examination rate (ABER) increased from 13.82 to 32.8%. Prompt reporting of new cases had improved (36% within 24 h and 80% within 72 h). Complete treatment and parasite clearance time were documented in 98% of cases. In the second post-digitization year untraceable cases reduced from 11.3 to 2.7%; contact blood smears collection also increased significantly (p < 0.001); Slide Positivity Rate (SPR) decreased from 15.5 to 10.48%; malaria cases reduced by 30%. CONCLUSIONS: IT is very useful in translation of digitized surveillance to core interventions thereby effectively reduce incidence of malaria. This technology can be used effectively to translate smart surveillance to core interventions following the '1-3-7-14' strategy.

An integrative systems biology view of host-pathogen interactions: The regulation of immunity and homeostasis is concomitant, flexible, and smart.

The systemic bio-organization of humans and other mammals is essentially "preprogrammed", and the basic interacting units, the cells, can be crudely mapped into discrete sets of developmental lineages and maturation states. Over several decades, however, and focusing on the immune system, we and others invoked evidence - now overwhelming - suggesting dynamic acquisition of cellular properties and functions, through tuning, re-networking, chromatin remodeling, and adaptive differentiation. The genetically encoded "algorithms" that govern the integration of signals and the computation of new states are not fully understood but are believed to be "smart", designed to enable the cells and the system to discriminate meaningful perturbations from each other and from "noise". Cellular sensory and response properties are shaped in part by recurring temporal patterns, or features, of the signaling environment. We compared this phenomenon to associative brain learning. We proposed that interactive cell learning is subject to selective pressures geared to performance, allowing the response of immune cells to injury or infection to be progressively coordinated with that of other cell types across tissues and organs. This in turn is comparable to supervised brain learning. Guided by feedback from both the tissue itself and the neural system, resident or recruited antigen-specific and innate immune cells can eradicate a pathogen while simultaneously sustaining functional homeostasis. As informative memories of immune responses are imprinted both systemically and within the targeted tissues, it is desirable to enhance tissue preparedness by incorporating attenuated-pathogen vaccines and informed choice of tissue-centered immunomodulators in vaccination schemes. Fortunately, much of the "training" that a living system requires to survive and function in the face of disturbances from outside or within is already incorporated into its design, so it does not need to deep-learn how to face a new challenge each time from scratch. Instead, the system learns from experience how to efficiently select a built-in strategy, or a combination of those, and can then use tuning to refine its organization and responses. Efforts to identify and therapeutically augment such strategies can take advantage of existing integrative modeling approaches. One recently explored strategy is boosting the flux of uninfected cells into and throughout an infected tissue to rinse and replace the infected cells.

Immunological Paradigms, Mechanisms, and Models: Conceptual Understanding Is a Prerequisite to Effective Modeling.

Most mathematical models that describe the individual or collective actions of cells aim at creating faithful representations of limited sets of data in a self-consistent manner. Consistency with relevant physiological rules pertaining to the greater picture is rarely imposed. By themselves, such models have limited predictive or even explanatory value, contrary to standard claims. Here I try to show that a more critical examination of currently held paradigms is necessary and could potentially lead to models that pass the test of time. In considering the evolution of paradigms over the past decades I focus on the "smart surveillance" theory of how T cells can respond differentially, individually and collectively, to both self- and foreign antigens depending on various "contextual" parameters. The overall perspective is that physiological messages to cells are encoded not only in the biochemical connections of signaling molecules to the cellular machinery but also in the magnitude, kinetics, and in the time- and space-contingencies, of sets of stimuli. By rationalizing the feasibility of subthreshold interactions, the "dynamic tuning hypothesis," a central component of the theory, set the ground for further theoretical and experimental explorations of dynamically regulated immune tolerance, homeostasis and diversity, and of the notion that lymphocytes participate in nonclassical physiological functions. Some of these efforts are reviewed. Another focus of this review is the concomitant regulation of immune activation and homeostasis through the operation of a feedback mechanism controlling the balance between renewal and differentiation of activated cells. Different perspectives on the nature and regulation of chronic immune activation in HIV infection have led to conflicting models of HIV pathogenesis-a major area of research for theoretical immunologists over almost three decades-and can have profound impact on ongoing HIV cure strategies. Altogether, this critical review is intended to constructively influence the outlook of prospective model builders and of interested immunologists on the state of the art and to encourage conceptual work.

An ecological and conservation perspective on advances in the applied virology of zoonoses.

The aim of this manuscript is to describe how modern advances in our knowledge of viruses and viral evolution can be applied to the fields of disease ecology and conservation. We review recent progress in virology and provide examples of how it is informing both empirical research in field ecology and applied conservation. We include a discussion of needed breakthroughs and ways to bridge communication gaps between the field and the lab. In an effort to foster this interdisciplinary effort, we have also included a table that lists the definitions of key terms. The importance of understanding the dynamics of zoonotic pathogens in their reservoir hosts is emphasized as a tool to both assess risk factors for spillover and to test hypotheses related to treatment and/or intervention strategies. In conclusion, we highlight the need for smart surveillance, viral discovery efforts and predictive modeling. A shift towards a predictive approach is necessary in today's globalized society because, as the 2009 H1N1 pandemic demonstrated, identification post-emergence is often too late to prevent global spread. Integrating molecular virology and ecological techniques will allow for earlier recognition of potentially dangerous pathogens, ideally before they jump from wildlife reservoirs into human or livestock populations and cause serious public health or conservation issues.