Explore the vast range of titles available.

Modeling abnormal spatiotemporal events is challenging since data belonging to abnormal activities are less in the course of a surveillance stream. We solve this issue using a normality modeling approach, where abnormalities are detected as deviations from the normal patterns. To this end, we propose a residual spatiotemporal autoencoder, which is trainable end-to-end to carry out the anomaly detection task in surveillance videos. Irregularities are detected using the reconstruction loss, where normal frames are reconstructed well with a low reconstruction cost, and the converse is identified as abnormal frames. We evaluate the effect of residual connections in the STAE architecture and presented good practices to train an autoencoder for video anomaly detection using benchmark datasets, namely CUHK-Avenue, UCSD-Ped2, and Live Videos. Comparisons with the existing approaches prove that the effectiveness of residual blocks is incremental than going deeper with additional layers to train a spatiotemporal autoencoder with good generalization across datasets.

The task of anomaly detection has recently gained much attention in the field of visual surveillance. Video surveillance data is often available in large quantities, but manual annotation of activities in video segments is tedious. Anomaly detection plays a crucial role in various indoor and outdoor surveillance applications. Video anomaly detection is highly challenging and provides a lot of scope and demand for improving detection performance in real-time scenarios. Recently, deep learning-based approaches are promising to detect single-scene video anomalies in real-time. This work starts by highlighting the over-view of deep learning-based video anomaly detection. A thematic taxonomy that includes four major categories and several sub-categories is presented. State-of-the-art deep learning approaches under these categories are reviewed. In addition, few recent one class model based deep learning approaches are evaluated and analyzed in terms of performance. Out of the approaches presented, Generative Adversarial Network (GAN) and Adversarial Autoencoder-based approaches provide a better detection rate. A few important directions are outlined for further research in the field of video surveillance applications.

Hydroxyurea (HU) is found to be beneficial in sickle cell anaemia (SCA) patients, due to its ability to increase foetal haemoglobin (HbF), however, patients show a variable response. Differences in HbF levels are attributed to many factors; but, the role of miRNA in HbF regulation is sparsely investigated. In this study, we evaluated the effect of miRNA expression on HbF induction in relation to hydroxyurea therapy in 30 normal controls, 30 SCA patients at baseline, 20 patients after 3 and 6 months of hydroxyurea (HU) therapy. HbF levels were measured by HPLC. Total RNA and miRNA were extracted from CD71 + erythroid cells and the expression was determined using Taqman probes. The mean HbF level increased 7.54 ± 2.44 fold, after 3 months of HU therapy. After the HU therapy 8 miRNAs were significantly up-regulated while 2 were down-regulated. The increase in miR-210, miR16-1, and miR-29a expression and decrease in miR-96 expression were strongly associated with the HU mediated HbF induction. Post HU therapy, decreased miR-96 expression negatively correlate with HbF and γ-globin gene while increased expression of miR-210, miR-16-1 and miR-29a post HU therapy positively corelate with HbF and γ-globin gene. Thus, suggest that miR-210, miR-16-1 and miR-29a are positive regulator of γ-globin gene and miR-96 is negative regulator of γ-globin gene. The study suggests the role of miR-210, miR16-1, miR-29a, and miR-96 in γ-globin gene regulation leading to HbF induction. Identification of the relevant protein targets might be useful for understanding the HU mediated HbF induction.

Resource-constrained nodes in unattended wireless sensor network (UWSN) operate in a hostile environment with less human intervention. Achieving the optimal quality of service (QoS) in terms of packet delivery ratio, delay, energy, and throughput is crucial. In this paper, we propose a topology control and data dissemination protocol that uses multi-agent reinforcement learning (MRL) and energy-aware convex-hull algorithm, for effective self-configuration and self-optimization (SCSO) in UWSN, called MRL-SCSO. MRL-SCSO maintains a reliable topology in which the effective active neighbor nodes are selected using MRL. The network boundary is determined using convex-hull algorithm to maintain the connectivity and coverage of the network. The boundary nodes transmit data under high traffic load conditions. The performance of MRL-SCSO is evaluated for various nodes count and under different load conditions by using the Contiki’s Cooja simulator. The results showed that MRL-SCSO stabilizes the performance and improves QoS.

Visual perception is a transformative technology that can recognize patterns from environments through visual inputs. Automatic surveillance of human activities has gained significant importance in both public and private spaces. It is often difficult to understand the complex dynamics of events in real-time scenarios due to camera movements, cluttered backgrounds, and occlusion. Existing anomaly detection systems are not efficient because of high intra-class variations and inter-class similarities existing among activities. Hence, there is a demand to explore different kinds of information extracted from surveillance videos to improve overall performance. This can be achieved by learning features from multiple forms (views) of the given raw input data. We propose two novel methods based on the multi-view representation learning framework. The first approach is a hybrid multi-view representation learning that combines deep features extracted from 3D spatiotemporal autoencoder (3D-STAE) and robust handcrafted features based on spatiotemporal autocorrelation of gradients. The second approach is a deep multi-view representation learning that combines deep features extracted from two-stream STAEs to detect anomalies. Results on three standard benchmark datasets, namely Avenue, Live Videos, and BEHAVE, show that the proposed multi-view representations modeled with one-class SVM perform significantly better than most of the recent state-of-the-art methods.

The objectives of our study were to assess the effectiveness of the single Epley manoeuvre per session for three consecutive days and to determine the protocol for treating posterior canal-Benign Paroxysmal Positional Vertigo (pc-BPPV). At our tertiary care centre, 410 patients with a confirmed diagnosis of unilateral pc-BPPV were included in a prospective observational study. For all the participants, the Epley manoeuvre was performed once daily for three consecutive days. Patients with persistent vertigo underwent Semont’s liberatory manoeuvre and were reassessed after one week. The above protocol was repeated for patients who continued to have symptoms. The majority (40.0%) of patients were seen in the 6th decade, followed by the 5th decade (34.4%). Among the study participants, the mean age was 51.57 ± 9.916 years. The male-to-female ratio is 1:1.05. The right ear was affected by 51.75%, and the left by 48.3%. With this protocol, 392 (95.6%) patients were relieved of symptoms by day 3. A six-month recovery rate of 99.75% was achieved. In our study, 99.8% of patients with unilateral pc-BPPV were cured, and 6.34% had a recurrence of symptoms within six months of follow-up. Hence, combining the Epley and the Semont manoeuvres and repeating the manoeuvres on consecutive days has better improvement.

Anomaly detection in surveillance videos is a challenging and demanding task. Autoencoders trained on segments of normal events are expected to give high reconstruction error for abnormal events than that for normal events. However, the assumption of autoencoders giving high reconstruction error is not always true in practice. Since the autoencoder sometimes offers better generalization, it also reconstructs abnormal events well, leading to slightly degraded performance for anomaly detection. Another issue is that the performance of real-time anomalous activity detection in surveillance videos still needs improvement. To address these issues, we propose an Object-centric and Memory-guided residual spatiotemporal autoencoder (OM-RSTAE) to detect video anomalies. The proposed technique achieved improved results over benchmark datasets, namely UCSD-Ped2, Avenue, ShanghaiTech and UCF-Crime datasets.

Hemophilia A (HA) is a genetic disorder of hemostasis associated with a deficiency or reduced activity of clotting factor VIII (FVIII). This disorder remains unacceptably underdiagnosed in India. Early diagnosis and appropriate management of HA can substantially prevent morbidity and mortality. Currently, HA is managed with regular replacement therapy using standard or extended half-life FVIII concentrates or non-factor drug products. The challenges associated with FVIII concentrates include plateauing of drug effect, issues with its administration and adherence to treatment, breakthrough bleeds, and the development of inhibiting antibodies against administered clotting factors. Emicizumab is a bispecific antibody, launched in India in April 2019, for managing patients with HA. To investigate the role of emicizumab in Indian patients with HA, opinions were sought from 13 eminent hematologists and experts from India on the effectiveness of emicizumab in preventing all bleeds, spontaneous bleeds, perioperative bleeds, and intracranial hemorrhage; resolving target joints; and reducing the rate of hospitalizations and fatality associated with HA in children and adults, with or without inhibitors. The benefits of emicizumab over traditional FVIII concentrates include the subcutaneous route of delivery, less frequent dosing, and a lack of inhibitor development, in addition to providing sustained hemostasis without in-depth monitoring. It is a safe and effective management option for all HA patients, especially for patients with certain archetypes, such as those with inhibitors, those with high annualized bleed rates, those living far away from hemophilia care centers, pediatric patients and infants with intravenous access challenges, and those with a history of life-threatening bleeding events.

In this paper, a novel bidirectional multi-input energy harvesting converter (MIEC) for portable device charger is presented. Switches that are separately regulated using different duty ratios are used in the design of such an MIEC power converter. The peak power of the photovoltaic sources may be tracked using such duty ratios, and the battery power can also be managed. The switch with two directions is also a part of this converter. If necessary, the battery can be charged via a USB charger but it is also capable of supplying power to the portable charging devices using sun and vibration harvesting. A battery receives the remaining energy for recharging while the charging current level can be checked. The entire system built using the MATLAB/SIMULINK environment, performances are monitored by the simulation results and validated experimentally.

Fanconi anemia (FA) is a rare inherited syndrome characterized by progressive bone marrow failure (BMF), abnormal skin pigmentation, short stature, and increased cancer risk. BMF in FA is multifactorial and largely results from the death of hematopoietic stem cells due to genomic instability. Also, inflammatory pathology in FA has been previously reported, however the mechanism is still not clear. In literature, decreased NK-cell count and/or impaired NK-cell activity, along with other immunological abnormalities have been described in FA-patients (1). However, to the best of our knowledge, this is the first report showing a defective degranulation mechanism leading to abnormal NK-cell cytotoxicity in FA-patients, which may explain the development of a hyperinflammatory response in these patients. This may predispose some patients to develop Hemophagocytic lymphohistiocytosis (HLH) which manifests with prolonged fever, progressive cytopenias and organomegaly. Early diagnosis and initiation of immunosuppressive therapy in these patients will help to better manage these patients. We also propose FA genes to be listed as a cause of familial HLH.