Parameter Estimation in Multiple Dynamic Synaptic Coupling Model Using Bayesian Point Process State-Space Modeling Framework

Inferring stimulation induced short-term synaptic plasticity dynamics using novel dual optimization algorithm

Experimental evidence in both human and animal studies demonstrated that deep brain stimulation (DBS) can induce short-term synaptic plasticity (STP) in the stimulated nucleus. Given that DBS-induced STP may be connected to the therapeutic effects of DBS, we sought to develop a computational predictive model that infers the dynamics of STP in response to DBS at different frequencies. Existing methods for estimating STP–either model-based or model-free approaches–require access to pre-synaptic spiking activity. However, in the context of DBS, extracellular stimulation (e.g. DBS) can be used to elicit presynaptic activations directly. We present a model-based approach that integrates multiple individual frequencies of DBS-like electrical stimulation as pre-synaptic spikes and infers parameters of the Tsodyks-Markram (TM) model from post-synaptic currents of the stimulated nucleus. By distinguishing between the steady-state and transient responses of the TM model, we develop a novel dual optimization algorithm that infers the model parameters in two steps. First, the TM model parameters are calculated by integrating multiple frequencies of stimulation to estimate the steady state response of post-synaptic current through a closed-form analytical solution. The results of this step are utilized as the initial values for the second step in which a non-derivative optimization algorithm is used to track the transient response of the post-synaptic potential across different individual frequencies of stimulation. Moreover, in order to confirm the applicability of the method, we applied our algorithm–as a proof of concept–to empirical data recorded from acute rodent brain slices of the subthalamic nucleus (STN) during DBS-like stimulation to infer dynamics of STP for inhibitory synaptic inputs.

An Investigation on Spiking Neural Networks Based on the Izhikevich Neuronal Model: Spiking Processing and Hardware Approach

The main required organ of the biological system is the Central Nervous System (CNS), which can influence the other basic organs in the human body. The basic elements of this important organ are neurons, synapses, and glias (such as astrocytes, which are the highest percentage of glias in the human brain). Investigating, modeling, simulation, and hardware implementation (realization) of different parts of the CNS are important in case of achieving a comprehensive neuronal system that is capable of emulating all aspects of the real nervous system. This paper uses a basic neuron model called the Izhikevich neuronal model to achieve a high copy of the primary nervous block, which is capable of regenerating the behaviors of the human brain. The proposed approach can regenerate all aspects of the Izhikevich neuron in high similarity degree and performances. The new model is based on Look-Up Table (LUT) modeling of the mathematical neuromorphic systems, which can be realized in a high degree of correlation with the original model. The proposed procedure is considered in three cases: 100 points LUT modeling, 1000 points LUT modeling, and 10,000 points LUT modeling. Indeed, by removing the high-cost functions in the original model, the presented model can be implemented in a low-error, high-speed, and low-area resources state in comparison with the original system. To test and validate the proposed final hardware, a digital FPGA board (Xilinx Virtex-II FPGA board) is used. Digital hardware synthesis illustrates that our presented approach can follow the Izhikevich neuron in a high-speed state (more than the original model), increase efficiency, and also reduce overhead costs. Implementation results show the overall saving of 84.30% in FPGA and also the higher frequency of the proposed model of about 264 MHz, which is significantly higher than the original model, 28 MHz.

Ensemble Machine Learning-Based Approach for Predicting of FRP–Concrete Interfacial Bonding

Developments in fiber-reinforced polymer (FRP) composite materials have created a huge impact on civil engineering techniques. Bonding properties of FRP led to its wide usage with concrete structures for interfacial bonding. FRP materials show great promise for rehabilitation of existing infrastructure by strengthening concrete structures. Existing machine learning-based models for predicting the FRP–concrete bond strength have not attained maximum performance in evaluating the bond strength. This paper presents an ensemble machine learning approach capable of predicting the FRP–concrete interfacial bond strength. In this work, a dataset holding details of 855 single-lap shear tests on FRP–concrete interfacial bonds extracted from the literature is used to build a bond strength prediction model. Test results hold data of different material properties and geometrical parameters influencing the FRP–concrete interfacial bond. This study employs CatBoost algorithm, an improved ensemble machine learning approach used to accurately predict bond strength of FRP–concrete interface. The algorithm performance is compared with those of other ensemble methods (i.e., histogram gradient boosting algorithm, extreme gradient boosting algorithm, and random forest). The CatBoost algorithm outperforms other ensemble methods with various performance metrics (i.e., lower root mean square error (2.310), lower covariance (21.8%), lower integral absolute error (8.8%), and higher R-square (96.1%)). A comparative study is performed between the proposed model and best performing bond strength prediction models in the literature. The results show that FRP–concrete interfacial bonding can be effectively predicted using proposed ensemble method.

IoT Application of Transfer Learning in Hybrid Artificial Intelligence Systems for Acute Lymphoblastic Leukemia Classification

Acute lymphoblastic leukemia is the most common cancer in children, and its diagnosis mainly includes microscopic blood tests of the bone marrow. Therefore, there is a need for a correct classification of white blood cells. The approach developed in this article is based on an optimized and small IoT-friendly neural network architecture. The application of learning transfer in hybrid artificial intelligence systems is offered. The hybrid system consisted of a MobileNet v2 encoder pre-trained on the ImageNet dataset and machine learning algorithms performing the role of the head. These were the XGBoost, Random Forest, and Decision Tree algorithms. In this work, the average accuracy was over 90%, reaching 97.4%. This work proves that using hybrid artificial intelligence systems for tasks with a low computational complexity of the processing units demonstrates a high classification accuracy. The methods used in this study, confirmed by the promising results, can be an effective tool in diagnosing other blood diseases, facilitating the work of a network of medical institutions to carry out the correct treatment schedule.