Remaining Useful Life Prediction of Lithium-Ion Batteries Using Neural Networks with Adaptive Bayesian Learning.

With smart electronic devices delving deeper into our everyday lives, predictive maintenance solutions are gaining more traction in the electronic manufacturing industry. It is imperative for the manufacturers to identify potential failures and predict the system/device's remaining useful life (RUL). Although data-driven models are commonly used for prognostic applications, they are limited by the necessity of large training datasets and also the optimization algorithms used in such methods run into local minima problems. In order to overcome these drawbacks, we train a Neural Network with Bayesian inference. In this work, we use Neural Networks (NN) as the prediction model and an adaptive Bayesian learning approach to estimate the RUL of electronic devices. The proposed prognostic approach functions in two stages-weight regularization using adaptive Bayesian learning and prognosis using NN. A Bayesian framework (particle filter algorithm) is adopted in the first stage to estimate the network parameters (weights and bias) using the NN prediction model as the state transition function. However, using a higher number of hidden neurons in the NN prediction model leads to particle weight decay in the Bayesian framework. To overcome the weight decay issues, we propose particle roughening as a weight regularization method in the Bayesian framework wherein a small Gaussian jitter is added to the decaying particles. Additionally, weight regularization was also performed by adopting conventional resampling strategies to evaluate the efficiency and robustness of the proposed approach and to reduce optimization problems commonly encountered in NN models. In the second stage, the estimated distributions of network parameters were fed into the NN prediction model to predict the RUL of the device. The lithium-ion battery capacity degradation data (CALCE/NASA) were used to test the proposed method, and RMSE values and execution time were used as metrics to evaluate the performance.

Association of serum osteoprotegerin with severity of chronic liver disease in female patients: A potential biomarker.

OBJECTIVE: To determine the association of serum osteoprotegerin (OPG) with the severity of chronic liver disease in female patients. METHODS: This case-control study was conducted in Madina Teaching Hospital from 2019-2020.An institutional review board of University Medical and Dental College, The University of Faisalabad gave the approval to conduct the study. Only female patients of age group 40 to 60 years having CLD were included in this study. Total 80 participants were enrolled after fulfilling the inclusion and exclusion criteria. Serum OPG levels were measured by enzyme linked immunosorbant assay (ELISA) supplied by ELAB Sciences, USA. The severity of disease was assessed by Child-Pugh classification. RESULTS: OPG levels were significantly different between the three Child-Pugh classes. OPG levels were significantly high in class C indicating increased level of this cytokine in CLD as compared to class A (p = <0.05). There was a positive association of OPG with splenomegaly (OR = 2.10, p = <0.001), hepatomegaly (OR = 4.41, (p = <0.05), skin pigmentation (OR = 2.06, p = <0.05), malena (OR = 1.87, p = <0.05) and prolonged bleeding (OR = 1.86, p = <0.05). CONCLUSION: The levels of serum Osteoprotegerin is increased in severe form of chronic liver disease (Class C) of Child-Pughs classification as compared to mild (Class A) and moderate (Class B) forms of Child-Pughs classification.

Serum resistin: A possible link between inflammation, hypertension and coronary artery disease.

BACKGROUND & OBJECTIVES: Inflammation is considered as the main triggering factor in evolution of atherosclerotic pathology of heart and blood vessels. Resistin, an inflammatory cytokine is proved to be a main mediator of initiation and progression of mechanisms leading to atherosclerosis, hypertension and ultimately to coronary artery disease. Our objective was to compare the levels of serum resistin, C-reactive protein and total leucocyte count in subjects of hypertension and coronary artery disease; and to observe the correlation of serum resistin with CRP and TLC in the study participants. METHODS: Eighty selected participants were divided into four equal groups including normal healthy participants, newly diagnosed cases of hypertension, stable angina pectoris and myocardial infarction, both with hypertension. The study was conducted in the physiology department of Post Graduate Medical Institute Lahore, during 2013. After consent, history and examination, fasting blood samples of the participants were collected. Serum resistin and C-reactive protein were determined by using standard techniques of enzyme linked immunosorbent assay, while total leukocyte count by automated hematology analyzer. RESULTS: The values of serum resistin, C- reactive protein and total leukocyte count were found significantly raised in patients of hypertension, angina pectoris and myocardial infarction with hypertension as compared to normal participants (p<0.001 for all). Significantly positive correlation of resistin was observed with TLC only in hypertensive patients of myocardial infarction (r = 0.459, n = 20, p = 0.042) while in other study groups correlation between resistin and TLC as well as CRP was non-significant. CONCLUSION: Serum resistin levels along with CRP and TLC are significantly raised in patients of hypertension and coronary artery disease while resistin levels revealed significantly positive correlation with TLC in hypertensive patients of myocardial infarction.

Iron deficiency anemia in reproductive age women: A survey study of district Bahawalpur, Punjab, Pakistan.

Iron deficiency anemia (IDA) is one of the foremost health issues among women of reproductive age. The study highlights to assess the level of awareness about the causes, symptoms, prevention and treatment of IDA among women of reproductive age in district Bahawalpur, province Punjab, Pakistan. A randomized study was conducted by using a self-designed standardized questionnaire disseminated to the hostels of female residents and homes in the immediate vicinity of Islamia University Bahawalpur. Females aged 18-45 years without any previous history of medical or gynecological problems were enlisted. A total number of 200 women were surveyed for awareness of iron deficiency anemia. Seventy three percent (73%) of women (n=146) were aware of the term IDA with the highest proportion of women falling in the age bracket 20-35 years. Most (66.9%) of the women were aware of the fact that their diet contains iron and its importance in health. It is concluded that, in reproductive age women the IDA can be prevented and treated through proper guidance and awareness through education.

Hardware-amenable structural learning for spike-based pattern classification using a simple model of active dendrites.

This letter presents a spike-based model that employs neurons with functionally distinct dendritic compartments for classifying high-dimensional binary patterns. The synaptic inputs arriving on each dendritic subunit are nonlinearly processed before being linearly integrated at the soma, giving the neuron the capacity to perform a large number of input-output mappings. The model uses sparse synaptic connectivity, where each synapse takes a binary value. The optimal connection pattern of a neuron is learned by using a simple hardware-friendly, margin-enhancing learning algorithm inspired by the mechanism of structural plasticity in biological neurons. The learning algorithm groups correlated synaptic inputs on the same dendritic branch. Since the learning results in modified connection patterns, it can be incorporated into current event-based neuromorphic systems with little overhead. This work also presents a branch-specific spike-based version of this structural plasticity rule. The proposed model is evaluated on benchmark binary classification problems, and its performance is compared against that achieved using support vector machine and extreme learning machine techniques. Our proposed method attains comparable performance while using 10% to 50% less in computational resource than the other reported techniques.

Predicting glaucoma progression using deep learning framework guided by generative algorithm.

Glaucoma is a slowly progressing optic neuropathy that may eventually lead to blindness. To help patients receive customized treatment, predicting how quickly the disease will progress is important. Structural assessment using optical coherence tomography (OCT) can be used to visualize glaucomatous optic nerve and retinal damage, while functional visual field (VF) tests can be used to measure the extent of vision loss. However, VF testing is patient-dependent and highly inconsistent, making it difficult to track glaucoma progression. In this work, we developed a multimodal deep learning model comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network, for glaucoma progression prediction. We used OCT images, VF values, demographic and clinical data of 86 glaucoma patients with five visits over 12 months. The proposed method was used to predict VF changes 12 months after the first visit by combining past multimodal inputs with synthesized future images generated using generative adversarial network (GAN). The patients were classified into two classes based on their VF mean deviation (MD) decline: slow progressors (< 3 dB) and fast progressors (> 3 dB). We showed that our generative model-based novel approach can achieve the best AUC of 0.83 for predicting the progression 6 months earlier. Further, the use of synthetic future images enabled the model to accurately predict the vision loss even earlier (9 months earlier) with an AUC of 0.81, compared to using only structural (AUC = 0.68) or only functional measures (AUC = 0.72). This study provides valuable insights into the potential of using synthetic follow-up OCT images for early detection of glaucoma progression.

Development of cortical orientation selectivity in the absence of visual experience with contour.

Visual cortical neurons are selective for the orientation of lines, and the full development of this selectivity requires natural visual experience after eye opening. Here we examined whether this selectivity develops without seeing lines and contours. Juvenile ferrets were reared in a dark room and visually trained by being shown a movie of flickering, sparse spots. We found that despite the lack of contour visual experience, the cortical neurons of these ferrets developed strong orientation selectivity and exhibited simple-cell receptive fields. This finding suggests that overt contour visual experience is unnecessary for the maturation of orientation selectivity and is inconsistent with the computational models that crucially require the visual inputs of lines and contours for the development of orientation selectivity. We propose that a correlation-based model supplemented with a constraint on synaptic strength dynamics is able to account for our experimental result.

High-content image generation for drug discovery using generative adversarial networks.

Immense amount of high-content image data generated in drug discovery screening requires computationally driven automated analysis. Emergence of advanced machine learning algorithms, like deep learning models, has transformed the interpretation and analysis of imaging data. However, deep learning methods generally require large number of high-quality data samples, which could be limited during preclinical investigations. To address this issue, we propose a generative modeling based computational framework to synthesize images, which can be used for phenotypic profiling of perturbations induced by drug compounds. We investigated the use of three variants of Generative Adversarial Network (GAN) in our framework, viz., a basic Vanilla GAN, Deep Convolutional GAN (DCGAN) and Progressive GAN (ProGAN), and found DCGAN to be most efficient in generating realistic synthetic images. A pre-trained convolutional neural network (CNN) was used to extract features of both real and synthetic images, followed by a classification model trained on real and synthetic images. The quality of synthesized images was evaluated by comparing their feature distributions with that of real images. The DCGAN-based framework was applied to high-content image data from a drug screen to synthesize high-quality cellular images, which were used to augment the real image data. The augmented dataset was shown to yield better classification performance compared with that obtained using only real images. We also demonstrated the application of proposed method on the generation of bacterial images and computed feature distributions for bacterial images specific to different drug treatments. In summary, our results showed that the proposed DCGAN-based framework can be utilized to generate realistic synthetic high-content images, thus enabling the study of drug-induced effects on cells and bacteria.

Digging deep into Golgi phenotypic diversity with unsupervised machine learning.

The synthesis of glycans and the sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNA interference screening offers opportunities to explore this organelle organization and the gene network underlying it. To date, image-based Golgi screens have based on a single parameter or supervised analysis with predefined Golgi structural classes. Here, we report the use of multiparametric data extracted from a single marker and a computational unsupervised analysis framework to explore Golgi phenotypic diversity more extensively. In contrast with the three visually definable phenotypes, our framework reproducibly identified 10 Golgi phenotypes. They were used to quantify and stratify phenotypic similarities among genetic perturbations. The derived phenotypic network partially overlaps previously reported protein-protein interactions as well as suggesting novel functional interactions. Our workflow suggests the existence of multiple stable Golgi organizational states and provides a proof of concept for the classification of drugs and genes using fine-grained phenotypic information.

Multiclass Classification by Adaptive Network of Dendritic Neurons with Binary Synapses Using Structural Plasticity.

The development of power-efficient neuromorphic devices presents the challenge of designing spike pattern classification algorithms which can be implemented on low-precision hardware and can also achieve state-of-the-art performance. In our pursuit of meeting this challenge, we present a pattern classification model which uses a sparse connection matrix and exploits the mechanism of nonlinear dendritic processing to achieve high classification accuracy. A rate-based structural learning rule for multiclass classification is proposed which modifies a connectivity matrix of binary synaptic connections by choosing the best "k" out of "d" inputs to make connections on every dendritic branch (k < < d). Because learning only modifies connectivity, the model is well suited for implementation in neuromorphic systems using address-event representation (AER). We develop an ensemble method which combines several dendritic classifiers to achieve enhanced generalization over individual classifiers. We have two major findings: (1) Our results demonstrate that an ensemble created with classifiers comprising moderate number of dendrites performs better than both ensembles of perceptrons and of complex dendritic trees. (2) In order to determine the moderate number of dendrites required for a specific classification problem, a two-step solution is proposed. First, an adaptive approach is proposed which scales the relative size of the dendritic trees of neurons for each class. It works by progressively adding dendrites with fixed number of synapses to the network, thereby allocating synaptic resources as per the complexity of the given problem. As a second step, theoretical capacity calculations are used to convert each neuronal dendritic tree to its optimal topology where dendrites of each class are assigned different number of synapses. The performance of the model is evaluated on classification of handwritten digits from the benchmark MNIST dataset and compared with other spike classifiers. We show that our system can achieve classification accuracy within 1 - 2% of other reported spike-based classifiers while using much less synaptic resources (only 7%) compared to that used by other methods. Further, an ensemble classifier created with adaptively learned sizes can attain accuracy of 96.4% which is at par with the best reported performance of spike-based classifiers. Moreover, the proposed method achieves this by using about 20% of the synapses used by other spike algorithms. We also present results of applying our algorithm to classify the MNIST-DVS dataset collected from a real spike-based image sensor and show results comparable to the best reported ones (88.1% accuracy). For VLSI implementations, we show that the reduced synaptic memory can save upto 4X area compared to conventional crossbar topologies. Finally, we also present a biologically realistic spike-based version for calculating the correlations required by the structural learning rule and demonstrate the correspondence between the rate-based and spike-based methods of learning.

Learning Spike Time Codes Through Morphological Learning With Binary Synapses.

In this brief, a neuron with nonlinear dendrites (NNLDs) and binary synapses that is able to learn temporal features of spike input patterns is considered. Since binary synapses are considered, learning happens through formation and elimination of connections between the inputs and the dendritic branches to modify the structure or morphology of the NNLD. A morphological learning algorithm inspired by the tempotron, i.e., a recently proposed temporal learning algorithm is presented in this brief. Unlike tempotron, the proposed learning rule uses a technique to automatically adapt the NNLD threshold during training. Experimental results indicate that our NNLD with 1-bit synapses can obtain accuracy similar to that of a traditional tempotron with 4-bit synapses in classifying single spike random latency and pairwise synchrony patterns. Hence, the proposed method is better suited for robust hardware implementation in the presence of statistical variations. We also present results of applying this rule to real-life spike classification problems from the field of tactile sensing.

Activation of protein kinase Czeta is essential for cytokine-induced metalloproteinase-1, -3, and -9 secretion from rabbit smooth muscle cells and inhibits proliferation.

Several matrix metalloproteinases (MMPs), including MMP-1, -3, and -9, mediate matrix destruction during chronic inflammatory diseases such as arthritis and atherosclerosis. MMP up-regulation by inflammatory cytokines involves interactions between several transcription factors, including activator protein-1 and nuclear factor kappaB (NF-kappaB). The upstream regulatory pathways are less well understood. We investigated the role of isoforms of protein kinase C (PKC) in basic fibroblast growth factor- and interleukin-1alpha-mediated MMP production from cultured rabbit aortic smooth muscle cells. A synthetic PKC inhibitor, RO318220, inhibited MMP-1, -3, and -9 production by 89 +/- 3, 75 +/- 18, and 89 +/- 9%, respectively. However, down-regulation of conventional and novel isoforms did not inhibit but rather increased MMP-9 production by 48 +/- 16%, implicating an atypical PKC isoform. Consistent with this, PKCzeta protein levels and activity were stimulated 3.3- and 13-fold, respectively, by basic fibroblast growth factor plus interleukin-1alpha and antisense oligonucleotides to PKCzeta significantly decreased MMP-9 formation by 62 +/- 18% compared with scrambled sequences. Moreover, adenovirus-mediated overexpression of a dominant-negative (DN) PKCzeta reduced MMP-1, -3, and -9 production by 78 +/- 9, 76 +/- 8, and 76 +/- 5%, respectively. DN-PKCzeta inhibited NF-kappaB DNA binding but did not affect ERK1/2 activation or AP-1 binding. Antisense PKCzeta oligonucleotides and DN-PKCzeta stimulated cell proliferation by 89 +/- 14% (n = 4) and 305 +/- 74% (n = 3), respectively (both p < 0.05). Our results show that PKCzeta is essential for cytokine-induced up-regulation of MMP-1, -3, and -9, most likely by activating NF-kappaB. Selective inhibition of PKCzeta is therefore a possible strategy to inhibit MMP production in inflammatory diseases such as atherosclerosis.