Nuclei segmentation and classification of hematoxylin and eosin-stained histology images is a challenging task due to a variety of issues, such as color inconsistency that results from the non-uniform manual staining operations, clustering of nuclei, and blurry and overlapping nuclei boundaries. Existing approaches involve segmenting nuclei by drawing their polygon representations or by measuring the distances between nuclei centroids. In contrast, we leverage the fact that morphological features (appearance, shape, and texture) of nuclei in a tissue vary greatly depending upon the tissue type. We exploit this information by extracting tissue specific (TS) features from raw histopathology images using the proposed tissue specific feature distillation (TSFD) backbone. The bi-directional feature pyramid network (BiFPN) within TSFD-Net generates a robust hierarchical feature pyramid utilizing TS features where the interlinked decoders jointly optimize and fuse these features to generate final predictions. We also propose a novel combinational loss function for joint optimization and faster convergence of our proposed network. Extensive ablation studies are performed to validate the effectiveness of each component of TSFD-Net. The proposed network outperforms state-of-the-art networks such as StarDist, Micro-Net, Mask-RCNN, Hover-Net, and CPP-Net on the PanNuke dataset, which contains 19 different tissue types and 5 clinically important tumor classes, achieving 50.4% and 63.77% mean and binary panoptic quality, respectively. The code is available at: https://github.com/Mr-TalhaIlyas/TSFD.

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.

In this paper, we propose a complex neuro-memristive synapse that exhibits the physiological acts of synaptic potentiation and depression of the human-brain. Specifically, the proposed neuromorphic synapse efficiently imitates the synaptic plasticity, especially long-term potentiation (LTP) and depression (LTD), and short-term facilitation (STF) and depression (STD), phenomena of a biological synapse. Similar to biological synapse, the short- or long-term potentiation (STF and LTP) or depression (STD or LTD) of the memristive synapse are distinguished on the basis of time or repetition of input cycles. The proposed synapse is also designed to exhibit the effect of reuptake and neurotransmitters diffusion processes of a bio-synapse. In addition, it exhibits the distinct bio-realistic attributes, i.e., strong stimulation, exponentially decaying conductance trace of synapse, and voltage dependent synaptic responses, of a neuron. The neuro-memristive synapse is designed in SPICE and its bio-realistic functionalities are demonstrated via various simulations.

Humans experience a variety of emotions throughout the course of their daily lives, including happiness, sadness, and rage. As a result, an effective emotion identification system is essential for electroencephalography (EEG) data to accurately reflect emotion in real-time. Although recent studies on this problem can provide acceptable performance measures, it is still not adequate for the implementation of a complete emotion recognition system. In this research work, we propose a new approach for an emotion recognition system, using multichannel EEG calculation with our developed entropy known as multivariate multiscale modified-distribution entropy (MM-mDistEn) which is combined with a model based on an artificial neural network (ANN) to attain a better outcome over existing methods. The proposed system has been tested with two different datasets and achieved better accuracy than existing methods. For the GAMEEMO dataset, we achieved an average accuracy±standard deviation of 95.73±0.67 for valence and 96.78±0.25 for arousal. Moreover, the average accuracy percentage for the DEAP dataset reached 92.57±1.51 in valence and 80.23±1.83 in arousal.

This article reviews the nonlinear dynamical attributes, switching kinetics, bifurcation analysis, and physical realization of a family of generic memristors, namely, Chua corsage memristors (CCM). CCM family contains three 1-st order generic memristor dubbed as 2-lobe, 4-lobe, and 6-lobe Chua corsage memristors and can be distinguished in accordance with their asymptotic stable states. The 2-lobe CCM has two asymptotically stable equilibrium states and regarded as a binary memory device. In contrast, the versatile 4-lobe CCM and 6-lobe CCM are regarded as a multi-bit-per-cell memory device as they exhibit three and four asymptotic stable states, respectively, on their complex and diversified dynamic routes. Due to the diversified dynamic routes, the CC memristors exhibit a highly nonlinear DC V-I curve. Unlike most published highly-nonlinear DC V-I curves with several disconnected branches, the DC V-I curves of CCMs are contiguous along with a locally active negative slope region. Moreover, the DC V-I curves and parametric representations of the CCMs are explicitly analytical. Switching kinetics of the CCM family can be demonstrated with universal formulas of exponential state trajectories x_n(t), time period t_fn, and applied minimum pulse amplitude V_A and width Δw. These formulas are regarded universal as they can be applied to any piecewise linear dynamic routes for any DC or pulse input and with any number of segments. When local activity, and bifurcation and chaos theorems are employed, CMMs exhibit unique stable limit cycles spawn from a supercritical Hopf bifurcation along with static attractors. In addition, the nonlinear circuit and system theoretic approach is applied to explain the asymptotic stability behavior of CCMs and to design real memristor emulators using off-the-shelf circuit components.

Efforts are being made to design a brain-like intelligence due to its robustness, synaptic modification (i.e., learning and memory), analog synaptic multiplication, multi-state storage, ultra-low power consumption, and parallel computation. However, current bioelectronic and biomedical technologies have yet to fully replicate brain-like intelligence. In particular, devices that can emulate both homosynaptic and heterosynaptic plasticity remain extremely limited. This work presents a neuromemristive synapse capable of replicating key biological features, including homosynaptic and heterosynaptic plasticity. The proposed synapse uses a memristor, a promising candidate for achieving bio-realistic features of synapse due to its low power consumption, multi-state operation, analog behavior, high data storage durability, and CMOS compatibility. The artificial synapse is designed as a composite 1-port structure consisting of a memristor (M) and a controlled capacitor (CCon). The memristor is responsible for emulating synaptic plasticity in response to distinct brainwave patterns, while the capacitor modulates the discharge rate through the memristor. During the active input phase (synaptic potentiation), the composite 1-port charges up. During the inactive phase (synaptic depression), CCon governs the discharging of the memristor, enabling full or partial discharging through memory fading or homosynaptic and heterosynaptic depression pathways. We designed the proposed synapse in SPICE and validated its bio-functionalities through various simulations. The proposed synapse demonstrates low power consumption and replicates key neurobiological processes for learning and memory such as heterosynaptic homeostasis, modular input specificity, associativity, and homosynaptic long-term and short-term potentiation and depression (LTP, LTD, STF, STD), along with memory fading effect (MFE), and strong stimulation (SST). The proposed synapse bio-realistically mimics synaptic plasticity, neurotransmitter dynamics, and neuronal responses. Implemented using off-the-shelf components, it supports both volatile and non-volatile modes, making it suitable for CMOS integration. This enables advancements in spiking neural networks, brain function analysis, and scalable neuromorphic computing systems.