Touch-Based Active Cloud Authentication Using Traditional Machine Learning and LSTM on a Distributed Tensorflow Framework

In this modern world, mobile devices have been paired with the cloud environment to scale the voluminous amount of generated data. The implementation comes at the cost of privacy as proprietary data can be stolen in transit to the cloud, or victims’ phones can be seized along with synced data from cloud. The attacker can gain access to the phone through shoulder surfing, or even spoofing attacks. Our approach is to mitigate this issue by proposing an active cloud authentication framework using touch biometric pattern. To the best of our knowledge, active cloud authentication using touch dynamics for mobile cloud computing has not been explored in the literature. This research creates a proof of concept that will lead into a simulated cloud framework for active authentication. Given the amount of data captured by the mobile device from user activity, it can be a computationally intensive process for the mobile device to handle with such limited resources. To solve this, we simulated a post-transmission process of data to the cloud so that we could implement the authentication process within the cloud. We evaluated the touch data using traditional machine learning algorithms, such as Random Forest (RF), Support Vector Machine (SVM), and also using a deep learning classifier, the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) algorithms. The novelty of this work is two-fold. First, we develop a distributed tensorflow framework for cloud authentication using touch biometric pattern. This framework helps alleviate the drawback of the computationally intensive recognition of the substantial amount of raw data from the user. Second, we apply the RF, SVM, and a deep learning classifier, the LSTM-RNN, on the touch data to evaluate the performance of the proposed authentication scheme. The proposed approach shows a promising performance with an accuracy of 99.0361% using RF on the distributed tensorflow framework.

Linear Predictive Coefficients-Based Feature to Identify Top-Seven Spoken Languages

Speech recognition in multilingual scenario is not trivial in the case when multiple languages are used in one conversation. Language must be identified before we process speech recognition as such tools are language-dependent. We present a language identification system (or AI tool) to distinguish top-seven world languages namely Chinese, Spanish, English, Hindi, Arabic, Bangla and Portuguese [G. F. Simons and C. D. Fennig (eds.), Ethnologue: Laguage of the Americas and the Pacific, Twentieth Edn. (SIL Internatinal, 2017)]. The system uses linear predictive coefficients-based feature, i.e. the line spectral pair–grade ratio (LSP–GR) feature, and ensemble learning for classification. Experiments were performed on more than 200[Formula: see text]h of real-world YouTube data and the highest possible accuracy of 96.95% was received. The results can be compared with other machine learning classifiers.

Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learning

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new information to such a model presents a challenge due to complex training issues, such as "catastrophic forgetting", and sensitivity to hyper-parameter tuning. However, in this modern world, data is constantly evolving, and our deep learning models are required to adapt to these changes. In this paper, we propose an adaptive hierarchical network structure composed of DCNNs that can grow and learn as new data becomes available. The network grows in a tree-like fashion to accommodate new classes of data, while preserving the ability to distinguish the previously trained classes. The network organizes the incrementally available data into feature-driven super-classes and improves upon existing hierarchical CNN models by adding the capability of self-growth. The proposed hierarchical model, when compared against fine-tuning a deep network, achieves significant reduction of training effort, while maintaining competitive accuracy on CIFAR-10 and CIFAR-100.

Reinforcement Learning With Low-Complexity Liquid State Machines

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear dynamics that transform the inputs into rich high-dimensional representations based on the current and past context. The random input representations can be efficiently interpreted by an output (or readout) layer with trainable parameters. Systematic initialization of the random connections and training of the readout layer using Q-learning algorithm enable such small random spiking networks to learn optimally and achieve the same learning efficiency as humans on complex reinforcement learning (RL) tasks like Atari games. In fact, the sparse recurrent connections cause these networks to retain fading memory of past inputs, thereby enabling them to perform temporal integration across successive RL time-steps and learn with partial state inputs. The spike-based approach using small random recurrent networks provides a computationally efficient alternative to state-of-the-art deep reinforcement learning networks with several layers of trainable parameters.

Ecotoxicological QSAR modelling of organic chemicals against Pseudokirchneriella subcapitata using consensus predictions approach

The present study provides robust consensus quantitative structure-activity relationship (QSAR) models developed from 334 organic chemicals covering a wide chemical domain for the prediction of effective concentrations of chemicals for 50% and 10% inhibition of algal growth. Only 2D descriptors with definite physicochemical meaning were employed for QSAR model building, whereas development, validation and interpretation were achieved following the strict Organization for Economic Co-operation and Development (OECD) recommended guidelines. Genetic algorithm along with stepwise approach was used in feature selection while the final QSAR models were derived using partial least squares regression technique. The applicability domain of the developed models was also checked. The obtained consensus models were then used to predict 64 organic chemicals having no definite observed responses while the confidence of predictions was checked by the 'prediction reliability indicator' tool. The developed models should be applicable for data gap filling in case of new or untested organic chemicals provided they fall within the domain of the model and can also be implemented to design safer alternatives to the environment.

Alpha Globin Gene Mutation: A Major Determinant of Hydroxyurea Response in Transfusion-Dependent HbE-β-Thalassaemia

Thalassaemias are the most common inherited autosomal recessive single gene disorders characterised by chronic hereditary haemolytic anaemia due to absence or reduced synthesis of one or more of the globin chains. Haemoglobin E (HbE)-β-thalassaemia is the genotype responsible for approximately one-half of all cases of severe β-thalassaemia worldwide. This study proposes to evaluate response of hydroxyurea in reducing transfusion requirements of severe HbE-β-thalassaemia patients, and its correlation with foetal haemoglobin (HbF) level and α-mutation. Hydroxyurea was started at a baseline dose in 82 transfusion-dependent HbE-β-thalassaemia patients. HbF levels and %F-cells were measured. β-Thalassaemia mutations and α-globin gene deletions and triplications were detected by amplification refractory mutation system (ARMS)-polymerase chain reaction (PCR) and Gap-PCR, respectively. Patients were categorised as good (41.5%), moderate (31.7%), and poor responders (26.8%) based on their decrease in transfusion requirements. Nine patients were excellent responders who became transfusion independent. The mean increase in HbF levels and %F-cells after therapy was correlated with decrease in transfusion requirements. Patients having a deletion of the α-globin gene were better responders. The response was proportional to the number of α-globin gene deletions. We conclude that hydroxyurea treatment decreases transfusion requirements, and the response correlates with α-globin gene deletions.

A rare case of tuberculoma masquerading as CP Angle neoplasm

Tuberculoma involving the cerebellopontine angle is very rare. Preoperative neuroradiological features of such lesions may mimic neoplastic lesions. Our case presented with cerebellar features and multiple cranial nerve palsy. Neuroimaging mimicked CP angle neoplastic lesion. Antitubercular therapy and steroids resulted in significant clinical improvement and marked radiological reduction in size of the lesion. In our subcontinent a treatable infective cause like tuberculosis should be ruled out in CP angle lesions. Although rare but definitely a possibility to be considered.

Synthesizing Images From Spatio-Temporal Representations Using Spike-Based Backpropagation

Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series of spike trains over time. In this paper, we propose a method to synthesize images from multiple modalities in a spike-based environment. We use spiking auto-encoders to convert image and audio inputs into compact spatio-temporal representations that is then decoded for image synthesis. For this, we use a direct training algorithm that computes loss on the membrane potential of the output layer and back-propagates it by using a sigmoid approximation of the neuron's activation function to enable differentiability. The spiking autoencoders are benchmarked on MNIST and Fashion-MNIST and achieve very low reconstruction loss, comparable to ANNs. Then, spiking autoencoders are trained to learn meaningful spatio-temporal representations of the data, across the two modalities-audio and visual. We synthesize images from audio in a spike-based environment by first generating, and then utilizing such shared multi-modal spatio-temporal representations. Our audio to image synthesis model is tested on the task of converting TI-46 digits audio samples to MNIST images. We are able to synthesize images with high fidelity and the model achieves competitive performance against ANNs.

Analysis of Liquid Ensembles for Enhancing the Performance and Accuracy of Liquid State Machines

Liquid state machine (LSM), a bio-inspired computing model consisting of the input sparsely connected to a randomly interlinked reservoir (or liquid) of spiking neurons followed by a readout layer, finds utility in a range of applications varying from robot control and sequence generation to action, speech, and image recognition. LSMs stand out among other Recurrent Neural Network (RNN) architectures due to their simplistic structure and lower training complexity. Plethora of recent efforts have been focused toward mimicking certain characteristics of biological systems to enhance the performance of modern artificial neural networks. It has been shown that biological neurons are more likely to be connected to other neurons in the close proximity, and tend to be disconnected as the neurons are spatially far apart. Inspired by this, we propose a group of locally connected neuron reservoirs, or an ensemble of liquids approach, for LSMs. We analyze how the segmentation of a single large liquid to create an ensemble of multiple smaller liquids affects the latency and accuracy of an LSM. In our analysis, we quantify the ability of the proposed ensemble approach to provide an improved representation of the input using the Separation Property (SP) and Approximation Property (AP). Our results illustrate that the ensemble approach enhances class discrimination (quantified as the ratio between the SP and AP), leading to better accuracy in speech and image recognition tasks, when compared to a single large liquid. Furthermore, we obtain performance benefits in terms of improved inference time and reduced memory requirements, due to lowered number of connections and the freedom to parallelize the liquid evaluation process.

Consensus QSPR modelling for the prediction of cellular response and fibrinogen adsorption to the surface of polymeric biomaterials

In the current study, we have developed predictive quantitative structure-activity relationship (QSAR) models for cellular response (foetal rate lung fibroblast proliferation) and protein adsorption (fibrinogen adsorption (FA)) on the surface of tyrosine-derived biodegradable polymers designed for tissue engineering purpose using a dataset of 66 and 40 biodegradable polymers, respectively, employing two-dimensional molecular descriptors. Best four individual models have been selected for each of the endpoints. These models are developed using partial least squares regression with a unique combination of six and four descriptors for cellular response and protein adsorption, respectively. The generated models were strictly validated using internal and external metrics to determine the predictive ability and robustness of proposed models. Subsequently, the validated individual models for each response endpoints were used for the generation of 'intelligent' consensus models ( http://teqip.jdvu.ac.in/QSAR_Tools/DTCLab/ ) to improve the quality of predictions for the external data set. These models may help in prediction of virtual polymer libraries for rational design/optimization for properties relevant to biomedical applications prior to their synthesis.

Surgical outcome of intradural extramedullary meningiomas without dural resection – A study on 75 cases

Background: Spinal tumor is a common cause of morbidity in otherwise healthy population, timely diagnosis and treatment of spinal tumor gives excellent outcome. Aims and Objective: We report experience and clinical outcomes of 75 cases with Intradural extramedullary meningiomas operated in last 21 years. Materials and Methods: All the patients were clinically assessed with Nurick’s Grading (both pre and post operatively). MRI was the main armamentarium for operating planning. In all the patients dural attachments were coagulated without any dural excision. Results: Out of 75 patients, 65% were female. Peak incidence was noted in 4th & 5th decade and majority of patients having tumor in the thoracic spine and lateral to the cord. The entire patient showed remarkable clinical improvement according to Nurick’s grade. Total removal was achieved in 69 (90.2%) patients. Two patients had re-growth of tumor in 1 yr. follow up. No postoperative mortality noted in the present series. Conclusion: Spinal meningioma excision without dural resection did not show any increase in recurrences.

Primary spinal peripheral primitive neuroectodermal tumor with acute presentation: A case report and review of literature

Primary spinal primitive neuroectodermal tumors (PNET) is a rare occurrence and carries a poor prognosis. A 13-year old female patient acutely presented with pain in the thoracic region, bilateral lower limb weakness, bladder and bowel dysfunction. Clinically paraplegia with truncal weakness, lower limb deep tendon reflexes of both side were absent and planter reflexes equivocal bilaterally. Preoperative MRI of thoracic spine revealed D4-D6 extradural SOL. A D4-D5 Laminectomy and left Cortico transversectomy done. Pathological findings were consistent with PNET. The clinical, histopathological, and radiological findings of the patient are presented.

ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing

In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs. We propose Spike Timing Dependent Plasticity (STDP) based probabilistic learning algorithm, referred to as Hybrid-STDP (HB-STDP), incorporating Hebbian and anti-Hebbian learning mechanisms, to train the binary kernels forming ReStoCNet in a layer-wise unsupervised manner. We demonstrate the efficacy of ReStoCNet and the presented HB-STDP based unsupervised training methodology on the MNIST and CIFAR-10 datasets. We show that residual connections enable the deeper convolutional layers to self-learn useful high-level input features and mitigate the accuracy loss observed in deep SNNs devoid of residual connections. The proposed ReStoCNet offers >20 × kernel memory compression compared to full-precision (32-bit) SNN while yielding high enough classification accuracy on the chosen pattern recognition tasks.

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain.

A study assessing the outcome of endoscopic endonasal transsphenoidal excision of pituitary adenoma at a tertiary care institutions- An Initial experience of 30 cases

Background: Endoscopic Endonasal Transphenoidal Pituitary Surgery (EETS), has been proved to be a preferred alternative to conventional surgery because of its salient features like wider, more panoramic field of visualization, improved illumination and mobility of instruments, and an ability to look around anatomical corners using angled lens and minimal invasiveness.The current study was done to analyse the effectiveness and morbidity in the patients operated in our centre by Endoscopic Endonasal Transphenoidal Pituitary Surgery (EETS) done by single team in single centre in15 months. Aims and Objective: To describe a case series of patients with pituitary adenomas with endoscopic endonasaltranssphenoidal approach, the technique performed and complications in our centre. Materials and Methods: The technique performed in a series of 30 consecutive patients, and description of their complications and the protocol followed to treat these complications. Results: The tumor removal was gross total in 18 (60.0%) patients, subtotal in 8 (30.7%), and partial in 4 (7.7%) patient. Two patients with growth hormone-secreting adenomas had normalization of hormonal status. Four patients developed temporary diabetes insipidus. Four patients developed post-operative CSF rhinorrhea and were managed conservatively.Two patient had recurrence of tumor.one patient had meningitis and one patient expired in perioperative periods. Conclusions: Our experience suggests that the Endoscopic transsphenoidal approach offers a potentially viable and cost economic treatment option in pituitary tumors which are difficult to remove by the standard microscopic approaches. In past one and half year we have witnessed encouraging results without much of the anticipated complications.

QSPR modelling for prediction of glass transition temperature of diverse polymers

The glass transition temperature is a vital property of polymers with a direct impact on their stability. In the present study, we built quantitative structure-property relationship models for the prediction of the glass transition temperatures of polymers using a data set of 206 diverse polymers. Various 2D molecular descriptors were computed from the single repeating units of polymers. We derived five models from different combinations of six descriptors in each case by employing the double cross-validation technique followed by partial least squares regression. The selected models were subsequently validated by methods such as cross-validation, external validation using test set compounds, the Y-randomization (Y-scrambling) test and an applicability domain study of the developed models. All of the models have statistically significant metric values such as r² ranging from 0.713-0.759, Q² ranging from 0.662-0.724 and [Formula: see text] ranging 0.702-0.805. Finally, a comparison was made with recently published models, though the previous models were based on a much smaller data set with limited diversity. We also used a true external set to demonstrate the performance of our developed models, which may be used for the prediction and design of novel polymers prior to their synthesis.