Search

This article presents a new approach for providing an interpretation for a spiking neural network classifier by transforming it to a multiclass additive model. The spiking classifier is a multiclass synaptic efficacy function-based leaky-integrate-fire neuron (Mc-SEFRON) classifier. As a first step, the SEFRON classifier for binary classification is extended to handle multiclass classification problems. Next, a new method is presented to transform the temporally distributed weights in a fully trained Mc-SEFRON classifier to shape functions in the feature space. A composite of these shape functions results in an interpretable classifier, namely, a directly interpretable multiclass additive model (DIMA). The interpretations of DIMA are also demonstrated using the multiclass Iris dataset. Further, the performances of both the Mc-SEFRON and DIMA classifiers are evaluated on ten benchmark datasets from the UCI machine learning repository and compared with the other state-of-the-art spiking neural classifiers. The performance study results show that Mc-SEFRON produces similar or better performances than other spiking neural classifiers with an added benefit of interpretability through DIMA. Furthermore, the minor differences in accuracies between Mc-SEFRON and DIMA indicate the reliability of the DIMA classifier. Finally, the Mc-SEFRON and DIMA are tested on three real-world credit scoring problems, and their performances are compared with state-of-the-art results using machine learning methods. The results clearly indicate that DIMA improves the classification accuracy by up to 12% over other interpretable classifiers indicating a better quality of interpretations on the highly imbalanced credit scoring datasets.

Green nanotechnology, an emerging field, offers economic and social benefits while minimizing environmental impact. Nanoparticles, pivotal in medicine, pharmaceuticals, and agriculture, are now sourced from green plants and microorganisms, overcoming limitations of chemically synthesized ones. In agriculture, these green-made nanoparticles find use in fertilizers, insecticides, pesticides, and fungicides. Nanofertilizers curtail mineral losses, bolster yields, and foster agricultural progress. Their biological production, preferred for environmental friendliness and high purity, is cost-effective and efficient. Biosensors aid early disease detection, ensuring food security and sustainable farming by reducing excessive pesticide use. This eco-friendly approach harnesses natural phytochemicals to boost crop productivity. This review highlights recent strides in green nanotechnology, showcasing how green-synthesized nanomaterials elevate crop quality, combat plant pathogens, and manage diseases and stress. These advancements pave the way for sustainable crop production systems in the future., Competing Interests: The authors declare no conflict of interest., (© 2023 The Authors. Global Challenges published by Wiley‐VCH GmbH.)

Travel time estimation accounting for on-the-ground realities between the location where a need for emergency obstetric care (EmOC) arises and the health facility capable of providing EmOC is essential for improving pregnancy outcomes. Current understanding of travel time to care is inadequate in many urban areas of Africa, where short distances obscure long travel times and travel times can vary by time of day and road conditions. Here, we describe a database of travel times to comprehensive EmOC facilities in the 15 most populated extended urban areas of Nigeria. The travel times from cells of approximately 0.6 × 0.6 km to facilities were derived from Google Maps Platform's internal Directions Application Programming Interface, which incorporates traffic considerations to provide closer-to-reality travel time estimates. Computations were done to the first, second and third nearest public or private facilities. Travel time for eight traffic scenarios (including peak and non-peak periods) and number of facilities within specific time thresholds were estimated. The database offers a plethora of opportunities for research and planning towards improving EmOC accessibility., (© 2023. Springer Nature Limited.)

Background and Aims: The relative utility of self-expanding metal stent (SEMS) insertion for malignant colon obstruction (MCO) due to extra-colonic malignancy (ECM) versus intra-colonic malignancy (ICM) is understudied., Methods: A systematic search was done from inception-April 2021 to identify reports of safety and efficacy of SEMS insertion for the treatment of MCO-ECM versus MCO-ICM. A meta-analysis of proportions, comparative meta-analysis to compute relative risks (RR), and mean differences (MD) was performed. Subgroup analyses and influence analyses were conducted. The certainty in estimates of effect(s) was assessed using the GRADE approach., Results: Eight non-randomized studies were identified; 46% (39-53%) and 63% (59-67%) of patients in the ECM and ICM groups were male. Most obstructions were in the rectosigmoid colon in both ECM and ICM groups. SEMS insertion in MCO-ECM was associated with an increased risk of technical failure compared to MCO-ICM (RR 2.92; 1.13-7.54; Certainty: Very Low). Risk of clinical failure of SEMS was higher in MCO-ECM compared to MCO-ICM (RR 2.88; 1.58-2.52; Certainty: Very Low). The risk of clinical failure remained significant throughout the influence analysis, as well as on subgroup analysis. There was no significant difference in the risk of adverse events or luminal perforation with SEMS insertion among patients with MCO-ECM and MCO-ICM. On influence analysis, removal of one study unveiled a significant increase in the risk of luminal perforation in MCO-ECM (RR 3.22; 1.44-7.19; p = 0.004)., Conclusion: SEMS for MCO-ECM may have a technical success rate comparable to or questionably worse than MCO-ICM, with low certainty in estimate of effects. SEMS deployment in MCO-ECM carries a higher risk of clinical failure, with a questionably higher risk of luminal perforation., (© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

This paper presents a new time-varying long-term Synaptic Efficacy Function-based leaky-integrate-and-fire neuRON model, referred to as SEFRON and its supervised learning rule for pattern classification problems. The time-varying synaptic efficacy function is represented by a sum of amplitude modulated Gaussian distribution functions located at different times. For a given pattern, the SEFRON's learning rule determines the changes in the amplitudes of weights at selected presynaptic spike times by minimizing a new error function reflecting the differences between the desired and actual postsynaptic firing times. Similar to the gamma-aminobutyric acid-switch phenomenon observed in a biological neuron that switches between excitatory and inhibitory postsynaptic potentials based on the physiological needs, the time-varying synapse model proposed in this paper allows the synaptic efficacy (weight) to switch signs in a continuous manner. The computational power and the functioning of SEFRON are first illustrated using a binary pattern classification problem. The detailed performance comparisons of a single SEFRON classifier with other spiking neural networks (SNNs) are also presented using four benchmark data sets from the UCI machine learning repository. The results clearly indicate that a single SEFRON provides a similar generalization performance compared to other SNNs with multiple layers and multiple neurons.

This paper presents a new learning algorithm developed for a three layered spiking neural network for pattern classification problems. The learning algorithm maximizes the interclass margin and is referred to as the two stage margin maximization spiking neural network (TMM-SNN). In the structure learning stage, the learning algorithm completely evolves the hidden layer neurons in the first epoch. Further, TMM-SNN updates the weights of the hidden neurons for multiple epochs using the newly developed normalized membrane potential learning rule such that the interclass margins (based on the response of hidden neurons) are maximized. The normalized membrane potential learning rule considers both the local information in the spike train generated by a presynaptic neuron and the existing knowledge (synaptic weights) stored in the network to update the synaptic weights. After the first stage, the number of hidden neurons and their parameters are not updated. In the output weights learning stage, TMM-SNN updates the weights of the output layer neurons for multiple epochs to maximize the interclass margins (based on the response of output neurons). Performance of TMM-SNN is evaluated using ten benchmark data sets from the UCI machine learning repository. Statistical performance comparison of TMM-SNN with other existing learning algorithms for SNNs is conducted using the nonparametric Friedman test followed by a pairwise comparison using the Fisher's least significant difference method. The results clearly indicate that TMM-SNN achieves better generalization performance in comparison to other algorithms.

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental problem in children. Resting state functional magnetic resonance imaging (rs-fMRI) provides an important tool in understanding the aberrant functional mechanisms in ADHD patients and assist in clinical diagnosis. Recently, spatio-temporal decomposition via spatial filtering (Fukunaga-Koontz transform, ICA) have gained attention in the analysis of fMRI time-series data. Their ability to decompose the blood oxygen level dependent (BOLD) rs-fMRI time series data into discriminative spatial and temporal components have resulted in better classification accuracy and the ability to isolate the important brain circuits responsible for the observed differences in brain activity. However, they are prone to errors in the estimation of covariance matrices due to the significant presence of atypical samples in the ADHD dataset. In this paper, we present a regularization framework to obtain a robust estimation of the covariance matrices such that the effect of atypical samples is reduced. The resulting approach called as regularized spatial filtering method (R-SFM) further uses Mahalanobis whitening to lower the effect of two-way correlations while preserving the spatial arrangement of the data in the feature extraction process. R-SFM was evaluated on the benchmark ADHD200 dataset and not only obtained a 6% improvement in classification accuracy, but also a 66.66% decrease in standard deviation over the previously developed SFM approach. Also R-SFM produces higher specificity which results in lower misclassification of ADHD, thereby reducing the risk of misdiagnosis. These results clearly show that R- SFM provides an accurate and reliable tool for detection of ADHD from BOLD rs-fMRI time series data.

Experimentation was conducted on a single cylinder CI engine using processed colloidal emulsions of TiO 2 nanoparticle-water-diesel distillate of crude plastic diesel oil as test fuel. The test fuel was prepared with plastic diesel oil as the principal constituent by a novel blending technique with an aim to improve the working characteristics. The results obtained by the test fuel from the experiments were compared with that of commercial petro-diesel (CPD) fuel for same engine operating parameters. Plastic oil produced from high density polyethylene plastic waste by pyrolysis was subjected to fractional distillation for separating plastic diesel oil (PDO) that contains diesel range hydrocarbons. The blending process showed a little improvement in the field of fuel oil-water-nanometal oxide colloidal emulsion preparation due to the influence of surfactant in electrostatic stabilization, dielectric potential, and pH of the colloidal medium on the absolute value of zeta potential, a measure of colloidal stability. The engine tests with nano-emulsions of PDO showed an increase in ignition delay (23.43%), and decrease in EGT (6.05%), BSNO x (7.13%), and BSCO (28.96%) relative to PDO at rated load. Combustion curve profiles, percentage distribution of compounds, and physical and chemical properties of test fuels ascertains these results. The combustion acceleration at diffused combustion phase was evidenced in TiO 2 emulsion fuels under study.

We report an aqueous one-pot reaction chemistry to derivatize phosphopeptides by switching the negatively charged phosphate group to a positively charged phosphonium or ammonium moiety. The phosphonium or ammonium tagged peptides then serve as peptide or protein phosphorylation signatures allowing extended and more sensitive analyses using surface-enhanced Raman spectroscopy (SERS) and mass spectrometry.

In this paper, the recently developed Extreme Learning Machine (ELM) is used for direct multicategory classification problems in the cancer diagnosis area. ELM avoids problems like local minima, improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. We have evaluated the multi-category classification performance of ELM on three benchmark microarray datasets for cancer diagnosis, namely, the GCM dataset, the Lung dataset and the Lymphoma dataset. The results indicate that ELM produces comparable or better classification accuracies with reduced training time and implementation complexity compared to artificial neural networks methods like conventional back-propagation ANN, Linder's SANN, and Support Vector Machine methods like SVM-OVO and Ramaswamy's SVM-OVA. ELM also achieves better accuracies for classification of individual categories.

Organization of the fibers in the descending tracts of the dorsolateral funiculus of the cervical spinal cord was investigated in cats. The spinal cord was penetrated with microelectrodes at 400 mum intervals in the medio-lateral direction at the c5/c6 and c6/c7 segmental borders. Silicon substrate microelectrodes with a linear arrangement of activated iridium contacts were used. The stimulus consisted of a 20 ms train of charge balanced biphasic current pulses at 330 Hz. The evoked activities from selected forelimb muscles were acquired into computer. Only the data points with an activation threshold of less than 35 muA were considered in the analysis. Muscle contractions were mostly in the form of short twitches. In both spinal segments, an area of high threshold was found in the middle of the dorsolateral funiculus. Majority of the muscles studied had a dorsal or ventral concentration of activation points. The distal muscles were mostly activated in the ventro-lateral aspect of the funiculus, while the elbow muscle maps spread to both dorsal and ventral sides. These results show a functional organization in both cervical segments studied, with overlapping regions between the areas dedicated for each forelimb muscle.

Posttranslational modification (PTM) of proteins is likely to be the most common mechanism of altering the expression of genetic information. It is essential to characterize PTMs to establish a complete understanding of the activities of proteins. Here, we present a sensitive detection method using surface-enhanced Raman spectroscopy (SERS) that can detect PTMs from as little as zeptomoles of peptide. We demonstrate, using model peptides, the ability of SERS to detect a variety of protein modifications, such as acetylation, trimethylation, phosphorylation, and ubiquitination. In addition, we show the capability to obtain positional information for modifications such as trimethylation and phosphorylation using SERS and wavelet decomposition data analysis techniques. We further show that it is possible to apply SERS to detect PTMs from biological samples such as histones. We envision that this detection method might be a valuable technique that is complementary to mass spectrometry in obtaining orthogonal chemical and modification-specific information from biological samples at sensitive levels.

In this paper, a recently developed machine learning algorithm referred to as Extreme Learning Machine (ELM) is used to classify five mental tasks from different subjects using electroencephalogram (EEG) signals available from a well-known database. Performance of ELM is compared in terms of training time and classification accuracy with a Backpropagation Neural Network (BPNN) classifier and also Support Vector Machines (SVMs). For SVMs, the comparisons have been made for both 1-against-1 and 1-against-all methods. Results show that ELM needs an order of magnitude less training time compared with SVMs and two orders of magnitude less compared with BPNN. The classification accuracy of ELM is similar to that of SVMs and BPNN. The study showed that smoothing of the classifiers' outputs can significantly improve their classification accuracies.

We show that it is possible to use single layer soft lithography to create deformable polymer membranes within microfluidic chips for performing a variety of microfluidic operations. Single layer microfluidic chips were designed, fabricated, and characterized to demonstrate pumping, sorting, and mixing. Flow rates as high as 0.39 microl min(-1) were obtained by peristaltic pumping using pneumatically-actuated membrane devices. Sorting was attained via pneumatic actuation of membrane units placed alongside the branch channels. An active mixer was also demonstrated using single-layer deformable membrane units.

This paper presents a new sequential learning algorithm for radial basis function (RBF) networks referred to as generalized growing and pruning algorithm for RBF (GGAP-RBF). The paper first introduces the concept of significance for the hidden neurons and then uses it in the learning algorithm to realize parsimonious networks. The growing and pruning strategy of GGAP-RBF is based on linking the required learning accuracy with the significance of the nearest or intentionally added new neuron. Significance of a neuron is a measure of the average information content of that neuron. The GGAP-RBF algorithm can be used for any arbitrary sampling density for training samples and is derived from a rigorous statistical point of view. Simulation results for bench mark problems in the function approximation area show that the GGAP-RBF outperforms several other sequential learning algorithms in terms of learning speed, network size and generalization performance regardless of the sampling density function of the training data.

To obtain a coding system for multiplex detection, we have developed a method to synthesize a new type of nanomaterial called composite organic-inorganic nanoparticles (COINs). The method allows the incorporation of a broad range of organic compounds into COINs to produce surface enhanced Raman scattering (SERS)-like spectra that are richer in variety than fluorescence-based signatures. Preliminary data suggest that COINs can be used as Raman tags for multiplex and ultrasensitive detection of biomolecules.

To investigate the functional organization in the lateral corticospinal tract (LCST), the cervical white matter was stimulated with multiple penetrations in the mediolateral direction at the C5/C6 and C6/C7 segmental borders in cats. Silicon substrate microelectrodes (CNCT, University of Michigan) with a linear arrangement of activated iridium contacts were used. The stimulation current consisted of a short (10-20 ms) train of charge balanced biphasic pulses at 330 Hz. The evoked limb movements were observed and the activities from selected forelimb muscles were acquired into a computer. Only the data points with an activation threshold of less than 30 muA were considered in the analysis. The muscle contractions were usually in the form of short twitches. Sustained muscle forces were observed only rarely for certain movements such as elbow flexion and digit extension in the forelimb. There exits a region in the middle of the dorsolateral funiculus for both segments where the activation threshold was relatively high (>30 microA). A segregation of the fibers according to the muscles they innervate was not found in these segmental borders. A functional organization is being investigated with further analysis.

A complex radial basis function neural network is proposed for equalization of quadrature amplitude modulation (QAM) signals in communication channels. The network utilizes a sequential learning algorithm referred to as complex minimal resource allocation network (CMRAN) and is an extension of the MRAN algorithm originally developed for online learning in real-valued radial basis function (RBF) networks. CMRAN has the ability to grow and prune the (complex) RBF network's hidden neurons to ensure a parsimonious network structure. The performance of the CMRAN equalizer for nonlinear channel equalization problems has been evaluated by comparing it with the functional link artificial neural network (FLANN) equalizer of J.C. Patra et al. (1999) and the Gaussian stochastic gradient (SG) RBF equalizer of I. Cha and S. Kassam (1995). The results clearly show that CMRANs performance is superior in terms of symbol error rates and network complexity.

This paper presents a detailed performance analysis of the minimal resource allocation network (M-RAN) learning algorithm, M-RAN is a sequential learning radial basis function neural network which combines the growth criterion of the resource allocating network (RAN) of Platt (1991) with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The resulting network leads toward a minimal topology for the RAN. The performance of this algorithm is compared with the multilayer feedforward networks (MFNs) trained with 1) a variant of the standard backpropagation algorithm, known as RPROP and 2) the dependence identification (DI) algorithm of Moody and Antsaklis on several benchmark problems in the function approximation and pattern classification areas. For all these problems, the M-RAN algorithm is shown to realize networks with far fewer hidden neurons with better or same approximation/classification accuracy. Further, the time taken for learning (training) is also considerably shorter as M-RAN does not require repeated presentation of the training data.

This paper analyzes parallel implementation of the backpropagation training algorithm on a heterogeneous transputer network (i.e., transputers of different speed and memory) connected in a pipelined ring topology. Training-set parallelism is employed as the parallelizing paradigm for the backpropagation algorithm. It is shown through analysis that finding the optimal allocation of the training patterns amongst the processors to minimize the time for a training epoch is a mixed integer programming problem. Using mixed integer programming optimal pattern allocations for heterogeneous processor networks having a mixture of T805-20 (20 MHz) and T805-25 (25 MHz) transputers are theoretically found for two benchmark problems. The time for an epoch corresponding to the optimal pattern allocations is then obtained experimentally for the benchmark problems from the T805-20, TS805-25 heterogeneous networks. A Monte Carlo simulation study is carried out to statistically verify the optimality of the epoch time obtained from the mixed integer programming based allocations. In this study pattern allocations are randomly generated and the corresponding time for an epoch is experimentally obtained from the heterogeneous network. The mean and standard deviation for the epoch times from the random allocations are then compared with the optimal epoch time. The results show the optimal epoch time to be always lower than the mean epoch times by more than three standard deviations (3sigma) for all the sample sizes used in the study thus giving validity to the theoretical analysis.

The determination with murexide of free and protein-bound calcium in model systems of known composition, ionic strength, and pH was investigated. The spectra of calcium murexide in the presence of varying amounts of calcium ions indicated that the absorption maximum fo calcium murexide complex occurs at 480 nm while that of murexide ion is at 520 nm. The absorbance at 509 nm is independent of calcium ion concentration and, therefore, could be used to measure the total dye. The spectra are pH dependent but constant in the range 6.5 to 7.0. The apparent dissociation constant of calcium murexide is dependent upon ionic environment, ionic strength, and free calcium ion concentration. The relationship between the apparent dissociation constant and free calcium concentration was established. Whole casein had no effect on the absorption spectra of calcium murexide and no affinity for calcium murexide complex or murexide ion. Beta-casein, at the concentrations employed, did not influence the dissociation fo calcium murexide. At pH 7.0, ionic strength .1, and 2 C, Beta-casein bound calcium as if there were 8.65 binding sites per molecule, each of pK 2.23, corresponding to an intrinsic association constant of 168.9 liters per mole.