Ensemble learning of diffractive optical networks

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning.Specifically,there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization,power efficiency and computation speed.Diffractive deep neural networks(D²NNs)form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers.D²NNs have demonstrated success in various tasks,including object classification,the spectral encoding of information,optical pulse shaping and imaging.Here,we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning.After independently training 1252 D²NNs that were diversely engineered with a variety of passive input filters,we applied a pruning algorithm to select an optimized ensemble of D²NNs that collectively improved the image classification accuracy.Through this pruning,we numerically demonstrated that ensembles of N=14 and N=30 D²NNs achieve blind testing accuracies of 61.14±0.23%and 62.13±0.05%,respectively,on the classification of GFAR-10 test images,providing an inference improvennent of>16%compared to the average performance of the individual D²NNs within each ensemble.These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.     

Light Spectral Composition Modifies Polyamine Metabolism in Young Wheat Plants

Although light-emitting diode (LED) technology has extended the research on targeted photomorphogenic, physiological, and biochemical responses in plants, there is not enough direct information about how light affects polyamine metabolism. In this study, the effect of three spectral compositions (referred to by their most typical characteristic: blue, red, and the combination of blue and red [pink] lights) on polyamine metabolism was compared to those obtained under white light conditions at the same light intensity. Although light quality induced pronounced differences in plant morphology, pigment contents, and the expression of polyamine metabolism-related genes, endogenous polyamine levels did not differ substantially. When exogenous polyamines were applied, their roborative effect were detected under all light conditions, but these beneficial changes were correlated with an increase in polyamine content and polyamine metabolism-related gene expression only under blue light. The effect of the polyamines on leaf gene expression under red light was the opposite, with a decreasing tendency. Results suggest that light quality may optimize plant growth through the adjustment of polyamine metabolism at the gene expression level. Polyamine treatments induced different strategies in fine-tuning of polyamine metabolism, which were induced for optimal plant growth and development under different spectral compositions.     

Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines

This study proposes a novel prediction approach for human breast and colon cancers using different feature spaces. The proposed scheme consists of two stages: the preprocessor and the predictor. In the preprocessor stage, the mega-trend diffusion (MTD) technique is employed to increase the samples of the minority class, thereby balancing the dataset. In the predictor stage, machine-learning approaches of K-nearest neighbor (KNN) and support vector machines (SVM) are used to develop hybrid MTD-SVM and MTD-KNN prediction models. MTD-SVM model has provided the best values of accuracy, G-mean and Matthew's correlation coefficient of 96.71%, 96.70% and 71.98% for cancer/non-cancer dataset, breast/non-breast cancer dataset and colon/non-colon cancer dataset, respectively. We found that hybrid MTD-SVM is the best with respect to prediction performance and computational cost. MTD-KNN model has achieved moderately better prediction as compared to hybrid MTD-NB (Naïve Bayes) but at the expense of higher computing cost. MTD-KNN model is faster than MTD-RF (random forest) but its prediction is not better than MTD-RF. To the best of our knowledge, the reported results are the best results, so far, for these datasets. The proposed scheme indicates that the developed models can be used as a tool for the prediction of cancer. This scheme may be useful for study of any sequential information such as protein sequence or any nucleic acid sequence.     

Learning multiple experiences useful visual features for active maps localization in crowded environments

Crowded urban environments are composed of different types of dynamic and static elements. Learning and classification of features is a major task in solving the localization problem in such environments. This work presents a gradual learning methodology to learn the useful features using multiple experiences. The usefulness of an observed element is evaluated by a scoring mechanism which uses two scores – reliability and distinctiveness. The visual features thus learned are used to partition the visual map into smaller regions. The robot is efficiently localized in such a partitioned environment using two-level localization. The concept of active map (AM) is proposed here, which is a map that represents one partition of the environment in which there is a high probability of the robot existing. High-level localization is used to track the mode of the AMs using discrete Bayes filter. Low-level localization uses a bag-of-words model to retrieve images and accurately localize the robot. The pose of the robot is the one retrieved from the AM that has maximum a posteriori. Experiments have been conducted on a unique highly crowded data-set collected from Indian roads. The results support the proposed method due to speed and localization accuracy.     

Deep features-based speech emotion recognition for smart affective services

Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

     

Electrical Insulation Characteristics of Silicone and EPDM Polymeric Blends. I

The typical parts of a polymeric insulator are core, metal end fittings and polymeric housing material. The housing is intended to protect the fibre glass rod from the environment and electrical surface discharges. Since the housing materials are made of organic polymeric material, its insulation characteristics need to be studied. Amongst the many different polymers available, this work focuses on silicone rubber and ethylene propylene diene monomer (EPDM). Blends of EPDM and silicone rubber are prepared in a two roll mixing mill. Dicumyl peroxide is used as vulcanizing agent. The blends consisting of various proportions of component polymers are prepared, compression moulded into sheets, and post cured. The blends are tested for their insulation characteristics as per IEC and ASTM standards. Volume and surface resistivity, dielectric strength, dielectric constant, tan delta, tracking resistance, arc resistance, comparative tracking index, tensile strength, and percentage elongation at break of the blends are studied and discussed. The test results show that the increasing proportion of silicone enhances the electrical insulation properties whereas increasing weight percentage of EPDM improves the mechanical strength of the blends.     

Mechanical regulation of the early stages of angiogenesis

Favouring or thwarting the development of a vascular network is essential in fields as diverse as oncology, cardiovascular disease or tissue engineering. As a result, understanding and controlling angiogenesis has become a major scientific challenge. Mechanical factors play a fundamental role in angiogenesis and can potentially be exploited for optimizing the architecture of the resulting vascular network. Largely focusing on in vitro systems but also supported by some in vivo evidence, the aim of this Highlight Review is dual. First, we describe the current knowledge with particular focus on the effects of fluid and solid mechanical stimuli on the early stages of the angiogenic process, most notably the destabilization of existing vessels and the initiation and elongation of new vessels. Second, we explore inherent difficulties in the field and propose future perspectives on the use of in vitro and physics-based modelling to overcome these difficulties.     

MicroRNA Changes Up to 24 h following Induced Hypoglycemia in Type 2 Diabetes

Hypoglycemia, as a complication of type 2 diabetes (T2D), causes increased morbidity and mortality but the physiological response underlying hypoglycemia has not been fully elucidated. Small noncoding microRNA (miRNA) have multiple downstream biological effects. This pilot exploratory study was undertaken to determine if induced miRNA changes would persist and contribute to effects seen 24 h post-hypoglycemia. A parallel, prospective study design was employed, involving T2D (n = 23) and control (n = 23) subjects. The subjects underwent insulin-induced hypoglycemia (2 mmol/L; 36 mg/dL); blood samples were drawn at baseline, upon the induction of hypoglycemia, and 4 h and 24 h post-hypoglycemia, with a quantitative polymerase chain reaction analysis of miRNA undertaken. The baseline miRNAs did not differ. In the controls, 15 miRNAs were downregulated and one was upregulated (FDR < 0.05) from the induction of hypoglycemia to 4 h later while, in T2D, only four miRNAs were altered (downregulated), and these were common to both cohorts (miR-191-5p; miR-143-3p; let-7b-5p; let-7g-5p), correlated with elevated glucagon levels, and all were associated with energy balance. From the induction of hypoglycemia to 24 h, 14 miRNAs were downregulated and 5 were upregulated (FDR < 0.05) in the controls; 7 miRNAs were downregulated and 7 upregulated (FDR < 0.05) in T2D; a total of 6 miRNAs were common between cohorts, 5 were downregulated (miR-93-5p, let-7b-5p, miR-191-5p, miR-185-5p, and miR-652-3p), and 1 was upregulated (miR-369-3p). An ingenuity pathway analysis indicated that many of the altered miRNAs were associated with metabolic and coagulation pathways; however, of the inflammatory proteins expressed, only miR-143-3p at 24 h correlated positively with tumor necrosis factor-α (TNFa; p < 0.05 and r = 0.46) and negatively with toll-like receptor-4 (TLR4; p < 0.05 and r = 0.43). The MiRNA levels altered by hypoglycemia reflected changes in counter-regulatory glucagon and differed between cohorts, and their expression at 24 h suggests miRNAs may potentiate and prolong the physiological response. Trial registration: ClinicalTrials.gov {"type":"clinical-trial","attrs":{"text":"NCT03102801","term_id":"NCT03102801"}}NCT03102801.     

Pharmacophore Synergism in Diverse Scaffold Clinches in Aurora Kinase B

Aurora kinase B (AKB) is a crucial signaling kinase with an important role in cell division. Therefore, inhibition of AKB is an attractive approach to the treatment of cancer. In the present work, extensive quantitative structure–activity relationships (QSAR) analysis has been performed using a set of 561 structurally diverse aurora kinase B inhibitors. The Organization for Economic Cooperation and Development (OECD) guidelines were used to develop a QSAR model that has high statistical performance (R²_tr = 0.815, Q²_LMO = 0.808, R²_ex = 0.814, CCC_ex = 0.899). The seven-variable-based newly developed QSAR model has an excellent balance of external predictive ability (Predictive QSAR) and mechanistic interpretation (Mechanistic QSAR). The QSAR analysis successfully identifies not only the visible pharmacophoric features but also the hidden features. The analysis indicates that the lipophilic and polar groups—especially the H-bond capable groups—must be present at a specific distance from each other. Moreover, the ring nitrogen and ring carbon atoms play important roles in determining the inhibitory activity for AKB. The analysis effectively captures reported as well as unreported pharmacophoric features. The results of the present analysis are also supported by the reported crystal structures of inhibitors bound to AKB.     

Nontoxic and Naturally Occurring Active Compounds as Potential Inhibitors of Biological Targets in Liriomyza trifolii

In recent years, novel strategies to control insects have been based on protease inhibitors (PIs). In this regard, molecular docking and molecular dynamics simulations have been extensively used to investigate insect gut proteases and the interactions of PIs for the development of resistance against insects. We, herein, report an in silico study of (disodium 5′-inosinate and petunidin 3-glucoside), (calcium 5′-guanylate and chlorogenic acid), chlorogenic acid alone, (kaempferol-3,7-di-O-glucoside with hyperoside and delphinidin 3-glucoside), and (myricetin 3′-glucoside and hyperoside) as potential inhibitors of acetylcholinesterase receptors, actin, α-tubulin, arginine kinase, and histone receptor III subtypes, respectively. The study demonstrated that the inhibitors are capable of forming stable complexes with the corresponding proteins while also showing great potential for inhibitory activity in the proposed protein-inhibitor combinations.