Search

The surface temperature of a workpiece during abrasive belt grinding directly affects its surface quality and determines whether the workpiece surface burns. However, the surface temperature of the workpiece during the grinding process is determined by the total heat and the heat carried away by the chips. Under certain grinding parameters, accurately obtaining the heat removed by the chips is one of the key factors to accurately obtain the workpiece surface quality. Therefore, a new method for chip heat monitoring based on audio-visual information decision fusion is proposed in this study. By obtaining visual sparks and sound signals directly related to the chip, a real-time chip quality (i.e., material removal rate, MRR) monitoring model based on convolutional neural network (CNN) and multilayer perceptron (MLP) was established. The heat taken away by the chips in real time was calculated through theoretical formula. The results show that the RMSE of the proposed method for the material removal rate does not exceed 0.006, and the coefficient of determination R2 is not less than 99.4%. The maximum error between the predicted maximum temperature of the grinding surface and the experimental measurement value is 10 °C. The proposed method provides the theoretical basis for the prediction and control of workpiece grinding temperature. [ABSTRACT FROM AUTHOR]

Optical coherence tomography (OCT) imaging technology has significant advantages in in situ and noninvasive monitoring of biological tissues. However, it still faces the following challenges: including data processing speed, image quality, and improvements in three-dimensional (3D) visualization effects. OCT technology, especially functional imaging techniques like optical coherence tomography angiography (OCTA), requires a long acquisition time and a large data size. Despite the substantial increase in the acquisition speed of swept source optical coherence tomography (SS-OCT), it still poses significant challenges for data processing. Additionally, during in situ acquisition, image artifacts resulting from interface reflections or strong reflections from biological tissues and culturing containers present obstacles to data visualization and further analysis. Firstly, a customized frequency domain filter with anti-banding suppression parameters was designed to suppress artifact noises. Then, this study proposed a graphics processing unit (GPU)-based real-time data processing pipeline for SS-OCT, achieving a measured line-process rate of 800 kHz for 3D fast and high-quality data visualization. Furthermore, a GPU-based real-time data processing for CC-OCTA was integrated to acquire dynamic information. Moreover, a vascular-like network chip was prepared using extrusion-based 3D printing and sacrificial materials, with sacrificial material being printed at the desired vascular network locations and then removed to form the vascular-like network. OCTA imaging technology was used to monitor the progression of sacrificial material removal and vascular-like network formation. Therefore, GPU-based OCT enables real-time processing and visualization with artifact suppression, making it particularly suitable for in situ noninvasive longitudinal monitoring of 3D bioprinting tissue and vascular-like networks in microfluidic chips. [ABSTRACT FROM AUTHOR]

The Network-on-Chip (NoC) is a communication infrastructure designed to integrate various components of a System-on-Chip (SoC) and connect multi-core processors. In on-chip networks, routing is a process that determines how a data packet should move from the source node to the destination node. Essentially, a routing algorithm configures the internal connections of a switch to establish communication towards the destination node by examining the source, destination and the current node addresses. After routing, multiple input channels may simultaneously request access to an output channel based on the routing results. In such cases, an arbitration strategy needs to prioritize access to the output channel for the requesting input channels. This research presents an arbitration strategy called HTPA (Hybrid Traffic Pattern-Aware arbitration) that utilizes local and global information. HTPA also uses a hybrid arbitration scheme consisting of a simple arbitration and a complex switch arbitration. Additionally, it uses age-related techniques to increase the fairness of arbitration and prevent starvation. The proposed method considers certain priorities for accessing output channels based on the distance to the destination, the number of available paths from the current node to the destination, and the traffic intensity parameter. Evaluations were conducted under uniform, transient, hot spot, and MPEG4 traffic patterns and the proposed method demonstrated a reduction in average packet delay compared to RoundRobin, CAIS, and DTIS methods by 79.46%, 71.35%, and 19.91%, respectively, across various traffic patterns. [ABSTRACT FROM AUTHOR]

Copyright of Acta Scientiarum Naturalium Universitatis Pekinensis is the property of Editorial Office of Acta Scientiarum Naturalium Universitatis Pekinensis and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Multimodal deep learning plays a pivotal role in supporting the processing and learning of diverse data types within the realm of artificial intelligence generated content (AIGC). However, most photonic neuromorphic processors for deep learning can only handle a single data modality (either vision or audio) due to the lack of abundant parameter training in optical domain. Here, we propose and demonstrate a trainable diffractive optical neural network (TDONN) chip based on on-chip diffractive optics with massive tunable elements to address these constraints. The TDONN chip includes one input layer, five hidden layers, and one output layer, and only one forward propagation is required to obtain the inference results without frequent optical-electrical conversion. The customized stochastic gradient descent algorithm and the drop-out mechanism are developed for photonic neurons to realize in situ training and fast convergence in the optical domain. The TDONN chip achieves a potential throughput of 217.6 tera-operations per second (TOPS) with high computing density (447.7 TOPS/mm2), high system-level energy efficiency (7.28 TOPS/W), and low optical latency (30.2 ps). The TDONN chip has successfully implemented four-class classification in different modalities (vision, audio, and touch) and achieve 85.7% accuracy on multimodal test sets. Our work opens up a new avenue for multimodal deep learning with integrated photonic processors, providing a potential solution for low-power AI large models using photonic technology. Most photonic processors can only handle a single data modality due to the lack of abundant parameter training in optical domain. Here, authors propose and demonstrate a trainable diffractive optical neural network chip based on on-chip diffractive optics with tunable elements to address these constraints. [ABSTRACT FROM AUTHOR]

Aiming to address the issues of low data execution efficiency and slow storage speed on traditional tourism cloud service platforms, a rural tourism management cloud service platform based on an embedded system is proposed. The embedded device components, such as the ARM processor, NOR Flash memory, and RTL network chip, are utilized to optimize the hardware structure of the cloud service platform. This optimization aims to enhance data processing and storage efficiency, as well as improve the reliability and durability of system operation. The unstructured feature grasping algorithm is employed to gather rural tourism resource data for target demand characterization. Associated algorithms are then utilized to develop data analysis, service recommendation, and tourism management modules, creating a comprehensive tourism cloud service platform. Additionally, the shortest path algorithm is used to enhance database storage speed, improve business docking efficiency, establish a big data monitoring center, comprehensively monitor changes in the scenic area and related industries, and enhance platform service efficiency. It has been proven through experiments that the latency of the tourism management cloud service platform, based on the embedded system, is reduced by almost 46.7% compared to the traditional approach, and the throughput is increased to 0.69 b/s. The practical application effect is positive, as it contributes to the development of tourism resources and the economic growth of rural areas. It also brings about economic and social benefits. [ABSTRACT FROM AUTHOR]

This comprehensive review explores the advancements in processing-in-memory (PIM) techniques and chiplet-based architectures for deep neural networks (DNNs). It addresses the challenges of monolithic chip architectures and highlights the benefits of chiplet-based designs in terms of scalability and flexibility. This review emphasizes dataflow-awareness, communication optimization, and thermal considerations in PIM-enabled manycore architectures. It discusses tailored dataflow requirements for different machine learning workloads and presents a heterogeneous PIM system for energy-efficient neural network training. Additionally, it explores thermally efficient dataflow-aware monolithic 3D (M3D) NoC architectures for accelerating CNN inferencing. Overall, this review provides valuable insights into the development and evaluation of chiplet and PIM architectures, emphasizing improved performance, energy efficiency, and inference accuracy in deep learning applications. [ABSTRACT FROM AUTHOR]

RASopathies are a group of genetic disorders caused by mutations in genes encoding components and regulators of the RAS/MAPK signaling pathway, resulting in overactivation of signaling. RASopathy patients exhibit distinctive facial features, cardiopathies, growth and skeletal abnormalities, and varying degrees of neurocognitive impairments including neurodevelopmental delay, intellectual disabilities, or attention deficits. At present, it is unclear how RASopathy mutations cause neurocognitive impairment and what their neuronspecific cellular and network phenotypes are. Here, we investigated the effect of RASopathy mutations on the establishment and functional maturation of neuronal networks. We isolated cortical neurons from RASopathy mouse models, cultured them on multielectrode arrays and performed longitudinal recordings of spontaneous activity in developing networks as well as recordings of evoked responses in mature neurons. To facilitate the analysis of large and complex data sets resulting from long-term multielectrode recordings, we developed MATLAB-based tools for data processing, analysis, and statistical evaluation. Longitudinal analysis of spontaneous network activity revealed a convergent developmental phenotype in neurons carrying the gain-of-function Noonan syndrome-related mutations Ptpn11D61Y and KrasV14l. The phenotype was more pronounced at the earlier time points and faded out over time, suggesting the emergence of compensatory mechanisms during network maturation. Nevertheless, persistent differences in excitatory/inhibitory balance and network excitability were observed in mature networks. This study improves the understanding of the complex relationship between genetic mutations and clinical manifestations in RASopathies by adding insights into functional network processes as an additional piece of the puzzle. [ABSTRACT FROM AUTHOR]

Multidimensional torus networking topology has become widespread recently in the domain of high-performance computers, clusters, and grids, as well as in the domain of networks on chip. Torus represents an ideal communication structure with the shortest distance and multitude of alternative shortest paths between a pair of nodes. We study simple and powerful local packet forwarding (switching) rules that provide packet delivery with quasi-optimal load balancing and do not use tables of addresses (routes). Implementation of these rules in the form of micro-program code within switching nodes increases considerably network performance, security, and QoS. We use infinite Petri nets and reenterable models in the form of colored Petri nets for prototyping the multi-dimensional torus interconnect simulator to study and compare the packet forwarding rules. Then, an ad-hoc simulator of torus interconnect ts is implemented in the C language to provide high performance and the possibility of simulation over prolonged intervals of time. The simulation results acknowledge the advantages of local packet forwarding rules. [ABSTRACT FROM AUTHOR]

Data acquisition based on network-on-chip (NoC) technology is a high-sampling-rate data acquisition scheme using low-sampling-rate analog–digital conversion (ADC) chips. It has the characteristics of multi-task parallel communication, being global asynchronous, local synchronous clock distribution, high throughput, low transmission latency, and strong scalability. High-speed data acquisition is realized through the combination of an on-chip network and time-interleaved data acquisition technology. In the time-interleaved sampling technique, the precision of clock synchronization directly affects the precision of sampling. Based on the proposed NOC data acquisition scheme, an improved White Rabbit clock synchronization protocol is applied to high-speed data acquisition to achieve high-precision synchronization of multi-channel time-interleaved sampling clocks. Firstly, the offset of the master clock and slave clock is determined by the PTP protocol, and the offset is corrected to achieve rough synchronization between the master clock and slave clock. Secondly, a digital dual-mixer time difference (DDMTD) is used to measure the phases of the master and slave clocks. After that, the phase of the slave clock is corrected through the dynamic phase-shift function of the clock's phase-locked loop (PLL). Finally, according to the simulation results in Modelsim, the average absolute error of a TI-ADC sampling clock can be less than 20 ps. [ABSTRACT FROM AUTHOR]

Modern microtechnology methods are widely used to create neural networks on a chip with a connection architecture demonstrating properties of modularity and hierarchy similar to brain networks. Such in vitro networks serve as a valuable model for studying the interplay of functional architecture within modules, their activity, and the effectiveness of inter-module interaction. In this study, we use a two-chamber microfluidic platform to investigate functional connectivity and global activity in hierarchically connected modular neural networks. We found that the strength of functional connections within the module and the profile of network spontaneous activity determine the effectiveness of inter-modular interaction and integration activity in the network. The direction of intermodular activity propagation configures the different densities of inhibitory synapses in the network. The developed microfluidic platform holds the potential to explore function-structure relationships and efficient information processing in two- or multilayer neural networks, in both healthy and pathological states. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-temporal dynamics in SNNs, neuromorphic chips are highly desired to execute SNNs in hardware-based neuron and synapse circuits directly. This paper presents a large-scale neuromorphic chip named Darwin3 with a novel instruction set architecture, which comprises 10 primary instructions and a few extended instructions. It supports flexible neuron model programming and local learning rule designs. The Darwin3 chip architecture is designed in a mesh of computing nodes with an innovative routing algorithm. We used a compression mechanism to represent synaptic connections, significantly reducing memory usage. The Darwin3 chip supports up to 2.35 million neurons, making it the largest of its kind on the neuron scale. The experimental results showed that the code density was improved by up to 28.3× in Darwin3, and that the neuron core fan-in and fan-out were improved by up to 4096× and 3072× by connection compression compared to the physical memory depth. Our Darwin3 chip also provided memory saving between 6.8× and 200.8× when mapping convolutional spiking neural networks onto the chip, demonstrating state-of-the-art performance in accuracy and latency compared to other neuromorphic chips. [ABSTRACT FROM AUTHOR]

In the DC-6 GHz band, low-insertion-loss packaging materials were investigated to effectively reduce the heat generated during the working process of the attenuation chip. Based on the working principle of the attenuation chip, when the signal passes through the attenuation chip resistor network, it results in energy loss. This means that the insertion loss of the chip generates heat, which leads to an uneven heat dissipation of the chip and thus functional failure. The microwave characteristics of the packaged joints were investigated using different packaging techniques. The results show that the S21 and S11 of the attenuation chip after nano-silver and Au80Sn20 packaging are optimal in the frequency band of DC-6 GHz, and the insertion loss is low compared with the commonly used packaging materials Sn60Pb40 and Sn96.5Ag3.5, which reduces the heat loss and improves the reliability of the attenuation chip packaging. [ABSTRACT FROM AUTHOR]

Scaling technology and shrinking transistor size have enabled the integration of multicore modules on a single chip for high-performance computing. Wireless Network-On-Chips has been demonstrated to be a viable choice for on-chip communication compared with wired communication, considering latency, energy, and data rate as performance metrics. Limitations in on–off keying modulation schemes have been addressed using OFDM modulation methods. In this paper, a new method based on the compressed sensing integrated dual tree complex wavelet transform (CS-DTCWT) is presented for OFDM modulation and demodulation operating in the mm-wave band. The CS-DTCWT-based OFDM model is developed in MATLAB and evaluated for its performance in the mm-wave operating frequency band of 20–60 GHz and for subcarriers of 128–1024. The BER performances of CS-DTCWT-based OFDM are demonstrated to be an improvement of 80% compared to FFT-based OFDM techniques. In addition, it can save 3.11% more energy than existing works. The proposed OFDM model is suitable for wireless NOC applications. [ABSTRACT FROM AUTHOR]

Several works report on overcoming the challenge of complex general-purpose signal processing algorithms that result in quick utilization of chip area resources (like FPGA in implementing system on chip or network on chip). However, with the advent of machine learning and deep learning algorithms, reducing this complexity and immense use of resources is a challenging task that can improve the system's performance in real time. One of the approaches is algorithm optimization, which consumes fewer resources and produces an equivalent performance. This approach may likely be accepted in less-sensitive applications, like voice or video processing. Recently, an optimized algorithm of correlation-less Wiener–Hopf-based adaptive channel equalizer is reported, in which the overall complexity of the system is reduced by employing a more compact way of weight optimization. This paper is the continuation of that work that reports the modification in the Steepest-Descent-based adaptive channel equalizer algorithm by keeping the autocorrelation matrix out of the algorithm. The proposed design is simulated and tested at equivalent spectral performance and produces comparable performance with fewer chip resources when translated on FPGA. The proposed design supports that algorithm-level optimization may be accepted extensively for the optimal hardware-based design of DSP systems. [ABSTRACT FROM AUTHOR]

Background: The study focused on exploring Erzhi Pill's molecular mechanism in treating lupus nephritis (LN) for the first time by means of network pharmacology, combined with molecular docking (MD) and GEO database analysis. Materials and Methods: Multiple databases were utilized to select compounds and targets of Erzhi Pill and targets of LN. We built a protein-protein interaction network which was later imported into Cytoscape to screen core regulatory genes. The GEO chip was analyzed to verify the key targets and apply Discovery Studio for MD of those screened effective components with hub targets. The drug-disease intersection targets were performed Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment. Results: CASP3 and MMP9 had significant differences by GEO chip analysis. Luteolin and MMP9 have the highest binding affinity through MD. GO and KEGG analysis suggested that Erzhi Pill effect on LN were closely related to cell apoptosis, oxidative stress, and lipid metabolism. Conclusions: Erzhi Pill has been found to treat LN in various ways through multi-component, multi-target interaction, and multi-pathway. [ABSTRACT FROM AUTHOR]

How do states' positions across multiple and interconnected economic networks affect their power? The Weaponized Interdependence (WI) scholarship emphasizes that states centrally located in global economic networks have access to new sources of coercion. In this paper, we look at how their positions across multiple networks interact with each other to create new opportunities and vulnerabilities. We use network analysis to map the semiconductor supply chain and show that it can be viewed as four interrelated networks: (1) design, (2) raw material, (3) manufacturing equipment, and (4) assembled chips. We then highlight how states' centrality varies across these networks and how it shapes their respective opportunities for coercion. Looking specifically at the United States, we emphasize how its centrality in the design network enables it to weaponize chokepoints in the trade network of assembled chips. In so doing the paper makes three contributions. First, it highlights how interactions among multiple economic networks provide new opportunities for states to weaponize interdependence. Second, it contributes to recent attempts using network analysis to analyze structural power on the global stage. Last, it demonstrates how network methodology can help detect potential (ab)uses of WI and how the potential for weaponization evolves over time. [ABSTRACT FROM AUTHOR]

Network on Chip (NoC) has emerged as a potential substitute for the communication model in modern computer systems with extensive integration. Among the numerous design challenges, application mapping on the NoC system poses one of the most complex and demanding optimization problems. In this research, we propose a hybrid improved whale optimization algorithm with enhanced genetic properties (IWOA-IGA) to optimally map real-time applications onto the 2D NoC Platform. The IWOA-IGA is a novel approach combining an improved whale optimization algorithm with the ability of a refined genetic algorithm to optimally map application tasks. A comprehensive comparison is performed between the proposed method and other state-of-the-art algorithms through rigorous analysis. The evaluation consists of real-time applications, benchmarks, and a collection of arbitrarily scaled and procedurally generated large-task graphs. The proposed IWOA-IGA indicates an average improvement in power reduction, improved energy consumption, and latency over state-of-the-art algorithms. Performance based on the Convergence Factor, which assesses the algorithm's efficiency in achieving better convergence after running for a specific number of iterations over other efficiently developed techniques, is introduced in this research work. These results demonstrate the algorithm's superior convergence performance when applied to real-world and synthetic task graphs. Our research findings spotlight the superior performance of hybrid improved whale optimization integrated with enhanced GA features, emphasizing its potential for application mapping in NoC-based systems. [ABSTRACT FROM AUTHOR]

Real-time heterogeneous parallel embedded digital signal processor (DSP) systems process multiple data streams in parallel in a stringent time interval. This type of system on chip (SoC) requires the network on chip (NoC) to establish multiple symbiotic parallel data transmission paths with ultra-low transmission latency in real time. Our early NoC research PCCNOC meets this need. The PCCNOC uses packet routing to establish and lock a transmission circuit, so that PCCNOC is perfectly suitable for ultra-low latency and high-bandwidth transmission of long data packets. However, a parallel multi-data stream DSP system also needs to transmit roughly the same number of short data packets for job configuration and job execution status reports. While transferring short data packets, the link establishment routing delay of short data packets becomes relatively obvious. Our further research, thus, introduced PaCHNOC, a hybrid NoC in which long data packets are transmitted through a circuit established and locked by routing, and short data packets are attached to the routing packet and the transmission is completed during the routing process, thus avoiding the PCCNOC setup delay. Simulation shows that PaCHNOC performs well in supporting real-time heterogeneous parallel embedded DSP systems and achieves overall latency reduction 65% compared with related works. Finally, we used PaCHNOC in the baseband subsystem of a real 5G base station, which proved that our research is the best NoC for baseband subsystem of 5G base stations, which reduce 31% comprehensive latency in comparison to related works. [ABSTRACT FROM AUTHOR]

The development of vascular networks in microfluidic chips is crucial for the long-term culture of three-dimensional cell aggregates such as spheroids, organoids, tumoroids, or tissue explants. Despite rapid advancement in microvascular network systems and organoid technologies, vascularizing organoids-on-chips remains a challenge in tissue engineering. Most existing microfluidic devices poorly reflect the complexity of in vivo flows and require complex technical set-ups. Considering these constraints, we develop a platform to establish and monitor the formation of endothelial networks around mesenchymal and pancreatic islet spheroids, as well as blood vessel organoids generated from pluripotent stem cells, cultured for up to 30 days on-chip. We show that these networks establish functional connections with the endothelium-rich spheroids and vascular organoids, as they successfully provide intravascular perfusion to these structures. We find that organoid growth, maturation, and function are enhanced when cultured on-chip using our vascularization method. This microphysiological system represents a viable organ-on-chip model to vascularize diverse biological 3D tissues and sets the stage to establish organoid perfusions using advanced microfluidics. Vascularization remains a significant challenge in organoid technology. Here, the authors develop a microfluidic platform that enhances organoid growth, function and maturation, by establishing functional perfusable vascular networks. [ABSTRACT FROM AUTHOR]

Given the complexity and wide range of applications being developed for the Internet of Things (IoT) requiring an efficient mapping of application tasks in hardware resources, especially embedded systems, it is necessary to address the problem of resource optimization, taking into account constraints for energy consumption, latency, and bandwidth, among others. This paper proposes a population based multi-objective heuristic algorithm to solve the task mapping for an application into a hierarchical hardware architecture known as Wireless Network on Chip using a mathematical modeling, as well as Artificial Intelligence algorithms, that combine the strategies of neural networks and genetic algorithms. A Population Based Incremental Learning (PBIL) algorithm is used in this research to solve the task mapping problem oriented to IoT applications, allowing heterogeneous systems to be involved with different bandwidths, latencies and technologies. The optimization goals addressed in this paper are bandwidth, speedup, power consumption and communication cost. The PBIL algorithm was tested on synthetic applications with heavy workload, where performance is measured taking into account the combination of low power consumption and maximum speedup and bandwidth. Other tests carried out with the PBIL algorithm were aimed to reduce the cost of communication in task mapping for real applications such as Multi-Window Display (MWD) and MPEG4 decoder. The results obtained in both synthetic and real applications showed an improvement when Escort entropy was used compared to Renyi and Shannon. In the case of real applications, when using a 2D Mesh topology, an improvement of 15.25% for MWD and 40.32% for MPEG-4 was observed when compared to the ISFL algorithm. Also, when the Mesh-Star topology was used, better results were obtained compared to ISFL (48.74% MWD and 62.06% MPEG-4). [ABSTRACT FROM AUTHOR]

In recent years, with the expansion of information, artificial intelligence technology has been developed and used in various fields. Among them, optical neural network provides a new type of special neural network accelerator chip solution, which has the advantages of high speed, high bandwidth, and low power consumption. In this paper, we construct an optical neural network based on Mach-Zehnder interferometer. The experimental results on the image classification of MNIST handwritten digitals show that the optical neural network has high accuracy, fast convergence and good scalability. [ABSTRACT FROM AUTHOR]

Application mapping is a difficult and crucial topic of research in Networks on Chip (NoC). Mapping of NoC is an NP-hard issue and various types of heuristics have been adopted to deal these issues. Therefore, in this research, Hesitant Fuzzy Linguistic Bi-objective Clustering Method (HFLBCM) with Evolutionary Multi-objective Seagull Optimisation Algorithm (EMSOA) is proposed for application mapping in 3D-NoC. The robustness of proposed method is confirmed by experiments conducted on certain benchmarks, like VOPD and MPEG-4 in NoC. At first, the HFLBCM approach selects the core and calculates the weight of each core. Subsequently, EMSOA method performs the application mapping with standard topologies, like mesh and torus. The implementation of the proposed method is done in Python and the parameters, like power, delay and computation time for VOPD and MPEG-4 benchmarks. The proposed approach has attained 45.175%, 65.319%, 71.226% lower power consumption for mesh topology and 30.141%, 19.211%, 32.727% lower power consumption for torus topology in VOPD benchmark than existing methods, like Knowledge-base multiple objective application mapping approach (AM-3D NoC-KBMA), self-adaptive mapping approach for NoC with low power consumption (AM-3D NoC-SKNNCM-SACSOA) and Ant lion optimised buffer less routing design for low power application specific NoC (AM-3D NoC-ALOA), respectively. [ABSTRACT FROM AUTHOR]

Soft matter‐based microlasers are widely regarded as excellent building blocks for realizing photonic interconnected networks in optoelectronic chips, owing to their flexibility and functional network topology. However, the potential of these devices is hindered by challenges such as poor lasing stability, high lasing threshold, and gaps in knowledge regarding cavity interconnection characteristics. In this study, the first demonstration of a high‐quality, low‐threshold nanoplatelets (NPLs)‐based polymer microfiber laser fabricated using capillary immersion techniques and its photonic interconnected networks are presented. CdSe/CdS@Cd1‐xZnxS core/buffer shell@graded‐shell NPLs with high optical gain characteristics are adopted as the gain medium. The study achieves a lasing threshold below 14.8 µJ cm−2, a single‐mode quality (Q)‐factor of ≈5500, and robust lasing stability in the fabricated NPLs‐based microfibers. Furthermore, the study pioneers the exploration of polygonal self‐coupling microlasers and the optical characteristics of their interconnected fiber network. Based on the signal generation mechanism observed in the photonic networks, an interconnected NPLs‐based fiber network structure achieving single‐mode lasing emission and laser mode modulation is successfully designed. The work contributes a novel method for realizing microlasers fabricated via soft‐matter technologies and provides a key foundation and new insights for unit design and programming for future photonic network systems. [ABSTRACT FROM AUTHOR]

A network on a chip is a solitary silicon chip utilized to perform the communication characteristics of large-scale (LSI) to very large-scale integration (VLSI) systems. Network-on-chip (NoC) architecture includes links, network interfaces (NI), and routers to unite with external memories or processors. NoC is designed to flow messages from the source module to the destination module through several links involving routing decisions. The design of NoC is complex and the buffer section's expensiveness creates problems while providing secured data service. Moreover, routers and links in NoC setups are liable to faults. This work introduces a minimal buffered router, and the faults in the network are optimized using moth flame optimized (MFO) fault-tolerant technique. The software named Xilinx ISE design suite 14.5 is employed for the minimum buffered router model. The suggested scheme is operated with less area, low power (0.241 mW), and high speed (965.261 Megahertz (MHz)) when matched with previous works. [ABSTRACT FROM AUTHOR]

3D ICs, a novel technology, might significantly impact multicore NoCs with hundreds or thousands of processing components on a single chip. Multiple 2D chips can be stacked vertically to create multiple active processing elements at various levels. Adding active device layers to 3D ICs can enhance system performance, increase functionality, and increase packing density. New architectural and IC technology advancements hinder energy-efficient design research. Achieving a balance between chip power and performance is crucial. This paper describes the "Dynamic Low Power Management Method in 3DWiNoC" (DLPM 3DWiNoC) architecture, which enables self-organized, centrally managed service management using Smart Master Agents. The approach utilizes SMA's ODA DD module for self-organized, centrally managed service management. To improve power regulation, data flow across vertical interconnects (TSVs) is reconfigured based on a dynamic evaluation of channel link use. SMA aims to reduce congestion by increasing connection utilization through high-frequency, bi-directional vertical channels via TSVs. The suggested system is modeled in MATLAB Simulink. Compared to 3D stacking, TSV stacking of vertical interconnects with the SMA method ensures low parasitic (latency and power) and higher bandwidth with higher vertical wire densities. Experimental results show that the proposed architecture decreases area overhead by 5%-7%, network latency by 12%-15%, and NoC power consumption by 15%-20% compared to the present multi-NoC design. [ABSTRACT FROM AUTHOR]

Systems-on-chips need numerous predesigned cores to advance. NoC enables Multi-Core SoCs (MC_SoCs). Conventional NoC cores use power and latency on multi-hop wired connections. An effective Wireless Network-on-Chip (WiNoC) architecture can overcome NoC difficulties. On-chip antennas, transceivers, and routers replace multi-hop cable connections with high-bandwidth single-hop wireless networks using WiNoC. Nanotechnology development demands fast data transfer to overcome performance bottlenecks from sharing memory modules and connecting fabrics. This research offers a new Proactive Flow control using Adaptive Beam formation for Smart Intra-layer Data Communication technique(PF_SDC) to optimally use network resources and assure QoS in Wireless Network-on-Chip for next-generation nano-domain technology. Hybrid NoC architecture optimises application admission for data transfer over wired and wireless interconnects. Data traffic is managed by a fuzzy inference-based Intelligent Head Agent (IHA). Queue load predicts router status for the fittest path selection. IHA initiates beams at angles to admit data flow towards the target while utilising the least amount of network power and resources. A simulation model shows that the proposed system may be applied in real-world applications and consumes little power with good throughput. [ABSTRACT FROM AUTHOR]

Intelligent monitoring of machine chips can help the machine tool to remove chip accumulation in time. Based on chip shape information, real-time monitoring of the machine tool is also possible. Although image segmentation algorithms have been widely used in industry, they still need to improve. These methods still have some limitations in effectively combining global and local information of industrial images, and there needs to be an image segmentation algorithm specifically for machine tool chips. In this paper, we propose a deep learning-based algorithm for lightweight chip image segmentation named Hybridformer. First, the algorithm generates scale-aware semantic features using feature maps of different scales as the input part. Then, we use the cross specification and SelfNorm to improve the generalization robustness of the model in terms of distribution bias. Finally, the network extracts global contextual information fusing EfficientNetv2 features to achieve accurate localization. Widespread experimental results show that Hybridformer outperforms both CNN and Transformer algorithms in terms of comprehensive performance on multiple chip image datasets, and it can achieve a good balance between accuracy and size of parameters. [ABSTRACT FROM AUTHOR]

Summary: Network on Chip (NoC) is an evolving platform for communications related applications, which are executed on a single silicon chip. There are several routing models in NoC architectures, but the accuracy of these models is limited, and the existing models are degraded because of over and under fitting issues. This research introduces the new deep learning‐based latency aware predictive routing model for on‐chip networks to route packets with better performance and power efficiency. The deep learning model used in this research is a new convolutional residual gated recurrent unit (CRGRU) with queuing theory. Moreover, the source and channel queuing delay is comprised of features to learn spatial and sequential information that improves the overall prediction accuracy. This router is modified by the intrusion of the Router States Monitor unit and the CRGRU hardware engine. The work is executed using the Xilinx platform, and the performance measures like latency and throughput are obtained by varying the network size as 4×4, 8×8, and 12×12 and also varying the buffer space and length as L=4,B=9, L=9,B=4, and L=14,B=3, respectively. In addition, the squared correlation coefficient (SCC) and normalized root mean square error (NRMSE) are evaluated and compared with existing learning models to validate the proposed model. [ABSTRACT FROM AUTHOR]

In this work, we report the monolithic three-dimensional integration (M3D) of hybrid memory architecture based on resistive random-access memory (RRAM), named M3D-LIME. The chip featured three key functional layers: the first was Si complementary metal-oxide-semiconductor (CMOS) for control logic; the second was computing-in-memory (CIM) layer with HfAlOx-based analog RRAM array to implement neural networks for feature extractions; the third was on-chip buffer and ternary content-addressable memory (TCAM) array for template storing and matching, based on Ta2O5-based binary RRAM and carbon nanotube field-effect transistor (CNTFET). Extensive structural analysis along with array-level electrical measurements and functional demonstrations on the CIM and TCAM arrays was performed. The M3D-LIME chip was further used to implement one-shot learning, where ~96% accuracy was achieved on the Omniglot dataset while exhibiting 18.3× higher energy efficiency than graphics processing unit (GPU). This work demonstrates the tremendous potential of M3D-LIME with RRAM-based hybrid memory architecture for future data-centric applications. Designing efficient 3D artificial neural networks chip remains a challenge. Here, the authors report a M3D-LIME chip with monolithic three-dimensional integration of hybrid memory architecture based on resistive random-access memory, which achieves a high classification accuracy of 96% in one-shot learning task while exhibiting 18.3× higher energy efficiency than GPU. [ABSTRACT FROM AUTHOR]

The 'Astrocyte Network' and the understanding of its communication has been posed as a new grand challenge to be investigated by contemporary science. However, communication studies in astrocyte networks have investigated traditional petri-dish in vitro culture models where cells are closely packed and can deviate from the stellate form observed in the brain. Using novel cell patterning approaches, highly organised, regular grid networks of astrocytes on chip, to single-cell fidelity are constructed, permitting a stellate-like in vitro network model to be realised. By stimulating the central cell with a single UV nanosecond laser pulse, the initiation/propagation pathways of stellate-like networks are re-explored. The authors investigate the mechanisms of intercellular Ca2+ communication and discover that stellate-like networks of adult human astrocytes in vitro actually exploit extracellular ATP release as their dominant propagation pathway to cells in the network locally; being observed even down to the nearest neighbour and next nearest neighbouring cells—contrary to the reported gap junction. This discovery has significant ramifications to many neurological conditions such as epilepsy, stroke and aggressive astrocytomas where gap junctions can be targeted. In cases where such gap junction targeting has failed, this new finding suggests that these conditions should be re-visited and the ATP transmission pathway targeted instead. [ABSTRACT FROM AUTHOR]

Data prefetching efficiently reduces the memory access latency in NUCA architectures as the Last Level Cache (LLC) is shared and distributed across multiple cores. But cache pollution generated by prefetcher reduces its efficiency by causing contention for shared resources such as LLC and the underlying network. The paper proposes Zero Pollution Prefetcher (ZPP) that eliminates cache pollution for NUCA architecture. For this purpose, ZPP uses L1 prefetcher and places the prefetched blocks in the data locations of LLC where modified blocks are stored. Since modified blocks in LLC are stale and request for such blocks are served from the exclusively owned private cache, their space unnecessary consumes power to maintain such stale data in the cache. The benefits of ZPP are (a) Eliminates cache pollution in L1 and LLC by storing prefetched blocks in LLC locations where stale blocks are stored. (b) Insufficient cache space is solved by placing prefetched blocks in LLC as LLCs are larger in size than L1 cache. This helps in prefetching more cache blocks, thereby increasing prefetch aggressiveness. (c) Increasing prefetch aggressiveness increases its coverage. (d) It also maintains an equivalent lookup latency to L1 cache for prefetched blocks. Experimentally it has been found that ZPP increases weighted speedup by 2.19x as compared to a system with no prefetching while prefetch coverage and prefetch accuracy increases by 50%, and 12%, respectively compared to the baseline. [ABSTRACT FROM AUTHOR]

In vitro model networks could provide cellular models of physiological relevance to reproduce and investigate the basic function of neural circuits on a chip in the laboratory. Several tools and methods have been developed since the past decade to build neural networks on a chip; among them, microfluidic circuits appear to be a highly promising approach. One of the numerous advantages of this approach is that it preserves stable somatic and axonal compartments over time due to physical barriers that prevent the soma from exploring undesired areas and guide neurites along defined pathways. As a result, neuron compartments can be identified and isolated, and their interconnectivity can be modulated to build a topological neural network (NN). Here, we have assessed the extent to which the confinement imposed by the microfluidic environment can impact cell development and shape NN activity. Toward that aim, microelectrode arrays have enabled the monitoring of the short- and mid-term evolution of neuron activation over the culture period at specific locations in organized (microfluidic) and random (control) networks. In particular, we have assessed the spike and burst rate, as well as the correlations between the extracted spike trains over the first stages of maturation. This study enabled us to observe intense neurite communications that would have been weaker and more delayed within random networks; the spiking rate, burst and correlations being reinforced over time in terms of number and amplitude, exceeding the electrophysiological features of standard cultures. Beyond the enhanced detection efficiency that was expected from the microfluidic channels, the confinement of cells seems to reinforce neural communications and cell development throughout the network. [ABSTRACT FROM AUTHOR]

An artificial neural network (ANN) is a computational system that is designed to replicate and process the behavior of the human brain using neuron nodes. ANNs are made up of thousands of processing neurons with input and output modules that self-learn and compute data to offer the best results. The hardware realization of the massive neuron system is a difficult task. The research article emphasizes the design and realization of multiple input perceptron chips in Xilinx integrated system environment (ISE) 14.7 software. The proposed single-layer ANN architecture is scalable and accepts variable 64 inputs. The design is distributed in eight parallel blocks of ANN in which one block consists of eight neurons. The performance of the chip is analyzed based on the hardware utilization, memory, combinational delay, and different processing elements with targeted hardware Virtex-5 field-programmable gate array (FPGA). The chip simulation is performed in Modelsim 10.0 software. Artificial intelligence has a wide range of applications, and cutting-edge computing technology has a vast market. Hardware processors that are fast, affordable, and suited for ANN applications and accelerators are being developed by the industries. The novelty of the work is that it provides a parallel and scalable design platform on FPGA for fast switching, which is the current need in the forthcoming neuromorphic hardware. [ABSTRACT FROM AUTHOR]

Following Moore's law, the density of integrated circuits is increasing in all dimensions, for instance, in 3D stacked chip networks. Amongst other electro-optic solutions, multimode optical interconnects on a silicon interposer promise to enable high throughput for modern hardware platforms in a restricted space. Such integrated architectures require confidential communication between multiple chips as a key factor for high-performance infrastructures in the 5G era and beyond. Physical layer security is an approach providing information theoretic security among network participants, exploiting the uniqueness of the data channel. We experimentally project orthogonal and non-orthogonal symbols through 380 μ m long multimode on-chip interconnects by wavefront shaping. These interconnects are investigated for their uniqueness by repeating these experiments across multiple channels and samples. We show that the detected speckle patterns resulting from modal crosstalk can be recognized by training a deep neural network, which is used to transform these patterns into a corresponding readable output. The results showcase the feasibility of applying physical layer security to multimode interconnects on silicon interposers for confidential optical 3D chip networks. [ABSTRACT FROM AUTHOR]

Network‐on‐Chip (NoC) is a key component in chip multiprocessors (CMPs) as it supports communication between many cores. NoC is a network‐based communication subsystem on an integrated circuit, most typically between modules in a system on a chip (SoC). Designing a reliable NoC against failures that can prevent failure using some measures or preventing error or system failure while failure happens and proper performance became a significant concern. For a reliable design against failures, first, the system should be analysed to discover the critical points. Hence, in this research, it is tried first to investigate the scale of fault tolerance effect on the mechanism in the router on the network by injecting simulated errors, and then these errors are prevented. As the major novelty, the authors implemented a router on a synchronised network and calculated the network buffering fault tolerance by injecting error in the buffer. Specifically, a new method for improving fault tolerance is proposed, which uses the existing resources efficiently. So, it does not impose any overhead on hardware and improves the error tolerance scale. The authors also evaluate it from different perspectives to show its superior performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Engineering (17264073) is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Neuronal networks receive and deliver information to regulate bodily functions while the vascular network provides oxygen, nutrients, and signaling molecules to tissues. Neurovascular interactions are vital for both tissue development and maintaining homeostasis in adulthood; these two network systems align and reciprocally communicate with one another. Although communication between network systems has been acknowledged, the lack of relevant in vitro models has hindered research at the mechanistic level. For example, the current used in vitro neurovascular models are typically established to be short-term (≤ 7 days) culture models, and they miss the supporting vascular mural cells. Methods: In this study, we utilized human induced pluripotent stem cell (hiPSC) -derived neurons, fluorescence tagged human umbilical vein endothelial cells (HUVECs), and either human bone marrow or adipose stem/stromal cells (BMSCs or ASCs) as the mural cell types to create a novel 3D neurovascular network-on-a-chip model. Collagen 1–fibrin matrix was used to establish long-term (≥ 14 days) 3D cell culture in a perfusable microphysiological environment. Results: Aprotinin-supplemented endothelial cell growth medium-2 (EGM-2) supported the simultaneous formation of neuronal networks, vascular structures, mural cell differentiation, and the stability of the 3D matrix. The formed neuronal and vascular networks were morphologically and functionally characterized. Neuronal networks supported vasculature formation based on direct cell contacts and by dramatically increasing the secretion of angiogenesis-related factors in multicultures in contrast to cocultures without neurons. Both utilized mural cell types supported the formation of neurovascular networks; however, the BMSCs seemed to boost neurovascular networks to greater extent. Conclusions: Overall, our study provides a novel human neurovascular network model that is applicable for creating in vivo-like tissue models with intrinsic neurovascular interactions. The 3D neurovascular network model on chip forms an initial platform for the development of vascularized and innervated organ-on-chip and further body-on-chip concepts and offers the possibility for mechanistic studies on neurovascular communication both under healthy and in disease conditions. DtMPMfM_nPvk_pFj8pUo8r Video Abstract [ABSTRACT FROM AUTHOR]

In Network-on-Chip architecture, wired structure and multi-step communication increase consumption power and latency. Combining wired media for a regular transmission and high-bandwidth wireless media for multi-step communication is a way to reduce latency and consumption of power. Wireless nodes are prone to error in on-chip wireless networks due to their complexity and relatively high usage; they are also crowded due to their sharing between several nodes, but their job is to increase efficiency. However, the presence of wireless nodes in wireless networks on the chip increases the cost and area. Therefore, finding an optimal structure for communication between cores is necessary. In this paper, a new three-dimensional architecture for a Wireless Network on Chip is presented, which has two levels; depending on the location of the error in the second level, the wireless routers in the first level are assigned to the processing elements. The demand matrix is used to optimize different traffic patterns. The performance of 3D architecture has been compared under different traffic patterns. The obtained results show that the proposed structure has a relatively good performance and increases the network's reliability. [ABSTRACT FROM AUTHOR]

This paper presents a novel architecture of femto power-delay super threshold voltage level shifter (LS) for network on-chip voltage control, developed using feedback topology for error aware interconnections data transmission. The proposed LS utilises eight MOS transistors with low aspect ratios for level up or level down. The developed LS can shift as low as 0.12–1.25 V with a tremendous reduction in delay and power consumption. Implemented in 65 nm CMOS technology, the post-layout simulation substantiates the achievement of voltage translation. The proposed LS incurs energy per cycle of 44 fJ during up shift; the average of level up and level down static power consumption is 3.61 nW, while VDDL is 0.3 V and VDDH is 1.2 V at a frequency of 1 MHz. The layout area of the proposed LS is 3.21 µm × 2.13 µm. [ABSTRACT FROM AUTHOR]

The super power of deep learning in image classification problems have become very popular and applicable in many areas like medical sciences. Some of the medical applications are real-time and may be implemented in embedded devices. In these cases, achieving the highest level of accuracy is not the only concern. Computation runtime and power consumption are also considered as the most important performance indicators. These parameters are mainly evaluated in hardware design phase. In this research, an energy efficient deep learning accelerator for endoscopic images classification (DLA-E) is proposed. This accelerator can be implemented in the future endoscopic imaging equipments for helping medical specialists during endoscopy or colonoscopy in order of making faster and more accurate decisions. The proposed DLA-E consists of 256 processing elements with 1000 bps network on chip bandwidth. Based on the simulation results of this research, the best dataflow for this accelerator based on MobileNet v2 is kcp_ws from the weight stationary (WS) family. Total energy consumption and total runtime of this accelerator on the investigated dataset is 4.56 × 109 MAC (multiplier–accumulator) energy and 1.73 × 107 cycles respectively, which is the best result in comparison to other combinations of CNNs and dataflows. [ABSTRACT FROM AUTHOR]

As a fundamental building block for photonic integrated circuits, waveguide crossing is playing an essential role for routing the increasingly complex network on chip. Driven by the demands for carrying a large capacity of data per waveguide, wavelengths and guiding modes are emerging as important degrees of freedom for optical multiplexing to embrace the advantages of signal parallelism. Although various waveguide crossing structures are proposed to either support broad spectra of wavelengths or a large number of modes, none of these are simultaneously achieved. Here, an ultra‐broadband multimode waveguide crossing based on subwavelength transmitarray (SWTA) is proposed. The SWTA is well designed for high transmittance in the propagation direction and excellent confinement in its orthogonal direction by creation of a bound state. A three‐mode crossing is designed and fabricated on silicon on insulator with a compact footprint of only 5.05 µm × 5.05 µm. The crossing is able to operate over a large bandwidth from 1.4 to 2.1 µm with an excess loss of less than 0.77 dB. For a proof‐of‐concept demonstration of the structure scalability, the crossing is predicted to support up to ten modes. The ultra‐broadbandwidth and compactness of this multimode crossing make it possible to densely cross connect the waveguides with large data capacity via wavelength and mode division multiplexing. [ABSTRACT FROM AUTHOR]

Wireless network-on-chip (WiNoC) face serious reliability challenges, and the fault-tolerant design of wireless routers (WRs) has a significant impact on the transmission efficiency of the overall on-chip network. Due to the continuous shrinking of CMOS technology and the integration of wireless technology in complex circuits, WRs appear to become more prevalent. In this paper, we propose a dynamic detection strategy for wireless interface faults in WiNoC, which classifies the fault scenarios of wireless interfaces in WRs, implements wireless interface fault detection in WiNoC operation, and updates the fault scenarios. Meanwhile, a fault-free WR table-based nearest route algorithm is also presented to maximize the network performance. The Evaluations show that the proposed scheme can effectively guarantee the network performance when WR faults occur in the network and is also effective under the case of moderate WR fault rate. • We propose two mechanisms to ensure efficient communication in wireless network. • First, we propose a dynamic detection mechanism for potential faults in the wireless interface. • Next, we propose a WI fault-tolerant routing algorithm to select the optimal routing path. • Finally, the evaluation results show that the proposed scheme maintains low latency and large throughput under moderate faults. [ABSTRACT FROM AUTHOR]

This paper proposes an energy-efficient hybrid Networks-on-Chip architecture called SaHNoC, which is more self adaptive with respect to selection of Wi-Fi positions in a Mesh topology. In comparison with wired on-chip interconnect NoC, wireless interconnect NoC offers a promising performance with respect to communication speed. However, the wireless switch occupies a larger area and has higher power-energy consumption than the wired switch. In this paper, we develop an optimal energy-efficient wire-wireless NoC structure called Hybrid NoC. The proposed hybrid NoC approach explores the self-adaptive technique for the selection of wireless switching positions in a suitable location against topology with respect to network diameter and average hop count. The effectiveness of the proposed SaHNoC is validated with a modified version of Booksim 2.0 in mutual with Orion 3.0. [ABSTRACT FROM AUTHOR]

Circuits based on quantum technology process data significantly quicker than circuits based on standard transistor-based technologies. The polarization of electrons provides digital information in Quantum-Dot Cellular Automata (QCA) technology. Making effective electronic circuits is one of the applications of this QCA technology in the field of nano communications. A nanonetwork, also known as a nano-scale network, is a collection of interconnected nanomachines capable of computation, data storage, sensing, and actuation. They can be built in various ways, with different phases of switching components and connecting links. On the other hand, manufacturing flaws and variances continue to be a concern with QCA-based circuits. Designing a fault-tolerant circuit for a banyan network is one of the most appealing topics in QCA nanotechnology because the banyan network is one of the most common and multistage communication architecture operations that are needed in all computing systems. The banyan network can be highly beneficial and supportive in designing any switching circuit. In the present article, we provide a novel circuit design technique for fault-tolerant banyan network circuits utilizing QCA technology, which is a new method for implementing the nano communications circuit. Furthermore, we used QCADesigner-E software to check simulated findings for a suggested circuit with other researchers for results and analysis. The fault-tolerant banyan network circuit that has been proposed employs 516 QCA cells, an area of 0.38 µm2, and has a 1.5 clock cycle delay in achieving its goal. Furthermore, simulation outcomes show that the recommended banyan network circuit with a fault-tolerant can achieve a 70% fault tolerance against four faults: cell missing, cell displacement, extra cell, and cell rotation. These findings enrich the literature on digital transformation, fault-tolerant designs in nano-based technologies, and nano communication and provide implications for the transformation of nanonetworks and networks on the chip. [ABSTRACT FROM AUTHOR]