Standard Architecture Research Articles

Low‐Temperature, Scalable, Reactive Deposition of Tin Oxide for Perovskite Solar Cells

Perovskite Solar Cells In article number 2200263, David George Lidzey and co-workers fabricated SnOx electron-extraction layers via a reactive electron-beam evaporation process from a metal source under a partial pressure of oxygen. These are then used in standard (n-i-p) architecture perovskite solar cells and achieve power conversion efficiencies up to 19.3%. The SnOx deposition process is performed onto substrates maintained at low temperature compared to similar techniques, with films not requiring any subsequent high-temperature post-deposition annealing. This demonstrates the potential compatibility of reactive electron-beam evaporation with roll-to-roll processing onto flexible polymeric substrates.

A Novel Smart Lightweight Visual Attention Model for Fine-Grained Vehicle Recognition

Vehicle Make and Model Recognition (VMMR) requires fast and accurate recognition of a vehicle’s information. Generally, the vision-based VMMR method recognizes different vehicle models that mainly rely on locating and extracting the discriminative part features of a vehicle. In this paper, we propose a Lightweight Recurrent Attention Unit (LRAU) to enhance the feature extraction ability of the standard Convolutional Neural Network (CNN) architectures for VMMR. The proposed LRAU extracts the discriminative part features by generating attention masks to locate the keypoints of a vehicle (e.g., logo, headlight). The attention mask is generated based on the feature maps received by the LRAU and the preceding attention state generated by the preceding LRAU. By adding LRAUs to receive the multi-scale feature maps generated by the standard CNN architecture, discriminative features of different scales can be efficiently extracted and combined. We conduct comprehensive experiments on three challenging VMMR datasets to evaluate the proposed VMMR models. Experimental results show our models have a stable performance under different environmental conditions. Our models achieve state-of-the-art results with 93.94% accuracy on the Stanford Cars dataset, 98.31% accuracy on the CompCars dataset, and 99.41% accuracy on the NTOU-MMR dataset. Moreover, we demonstrate that our models outperform the traditional machine learning-based VMMR models in terms of recognition accuracy and processing speed. In addition, we construct a one-stage Vehicle Detection and Fine-grained Recognition (VDFR) model by combining our LRAU with the general object detection model. Results show the proposed VDFR model can achieve excellent performance with real-time processing speed.

Estimating Gridded Monthly Baseflow From 1981 to 2020 for the Contiguous US Using Long Short‐Term Memory (LSTM) Networks

AbstractAccurate baseflow estimation is essential for ecological protection and water resources management. Past studies have used environmental predictors to extend baseflow from gauged basins to ungauged basins, publishing several regional or global datasets on mean annual baseflow. However, time series datasets of baseflow are still lacking due to the complexity of baseflow generation processes. Here, we developed a monthly baseflow data set using a Deep learning model called the long short‐term memory (LSTM) networks. To better train the networks across basins, we compared the standard LSTM architecture using 8 time series as inputs with four variant architectures using 16 additional static properties as inputs. Dividing the contiguous United States into nine ecoregions, we used baseflow calculated from 1,604 gauged basins as training targets to calibrate the five LSTM architectures for each ecoregion separately. Results show that three variant architectures (Joint, Front, and Entity‐Aware‐LSTM) perform better than the standard LSTM, with median Kling‐Gupta Efficiencies across basins greater than 0.85. Based on Front LSTM, the monthly baseflow data set with 0.25° spatial resolution across the contiguous United States from 1981 to 2020 was obtained. Potential applications of the data set include analyzing baseflow trends under global change and estimating large‐scale groundwater recharge.

The Language of Mass Architectural Postmodernity

Setting itself off against the architecture of the capitalist West, allegedly tangled in styles, Soviet architecture claimed its origins in the social realm. If one is to trace the intrinsic nature of changes in the architecture of the 1980s in the USSR, it is to be done not through the borrowed concept of postmodernism, but through the analysis of the developments in the design of its most social manifestation—mass housing. So far, Soviet architecture has primarily been whittled down to the evolution of styles. A more advanced reading focuses on the shift from Socialist Realism to the complex design of the human habitat following Khrushchev’s reforms in construction. However, even this transformation took place within the framework of building systematization, represented by the all-Union system of naming for standard architecture, or the Nomenclature. The system, implemented since 1947, assigned indexes to type designs of all building types; within it, every type design was allocated its specific position. The Nomenclature could thus describe the whole human habitat. In the mid-1980s, the naming system made further steps to meet the growing diversification of type designs by assigning new indexes which were longer and codified more parameters, undermining vested geographical and temporal hierarchies. The diversity was treated as a quantitative problem, which the Nomenclature successfully solved. It proved flexible enough to consistently ascribe an index to any—not necessarily type—design. Although mass housing disappeared from the architectural discourse during perestroika, standardized architecture enjoyed the most fruitful and systematic time in its history. So all-encompassing and everlasting, the Nomenclature nevertheless collapsed with the fall of the Soviet Union. The centralization of design proved its most fundamental precondition, which in the post-Soviet world was impossible to retain.

Over-the-air firmware update for IoT devices on the wild

Internet of Things (IoT) has been gaining a lot of attention in the last few years and despite the large amount of investments, there is still much to be developed and refined. Software and firmware updates over-the-air (OTA) are a crucial part for IoT solutions longevity. This paper presents the design and implementation of an OTA firmware update method based on the standard architecture recently proposed by the Internet Engineering Task Force (IETF). The proposed solution is evaluated through a testbed using 20 constrained IoT devices and an open source IoT cloud platform, as well as on a set of devices deployed in a real world application. Results show that the proposed solution is suitable for constrained devices and has little impact on the network traffic.

Neural-network quantum state tomography

We revisit the application of neural networks to quantum state tomography. We confirm that the positivity constraint can be successfully implemented with trained networks that convert outputs from standard feed-forward neural networks to valid descriptions of quantum states. Any standard neural-network architecture can be adapted with our method. Our results open possibilities to use state-of-the-art deep-learning methods for quantum state reconstruction under various types of noise.

Low‐Temperature, Scalable, Reactive Deposition of Tin Oxide for Perovskite Solar Cells

Tin oxide (SnO x ) electron‐extraction layers are fabricated via a reactive electron‐beam evaporation process from a metal source under a partial pressure of oxygen. These are then used in standard (n‐i‐p) architecture perovskite solar cells and achieve power conversion efficiencies up to 19.3%. The SnO x deposition process is performed onto substrates maintained at low temperature compared to similar techniques, with films not requiring any subsequent high‐temperature post‐deposition annealing. This demonstrates the potential compatibility of reactive electron‐beam evaporation with roll‐to‐roll processing onto flexible polymeric substrates.

A comparitive analysis of mobilenet and xception architecture for classification of endoscopy images

The deep architectures have been making their significant mark in solving the image classification problems. The usage of the standard deep learning architectures has been increasing at a greater pace because of the outcome of the state-of-the art accuracy and precision by incorporating these architectures in image classification problems. The classification of medical images from variety of modalities is also possible with better accuracy by using these deep architectures. The standard architectures that have achieved substantial results in general object classification can be used and their learning can be transferred to the required domain. Further, these architectures can be used in an ensemble structure thereby creating a customized architecture for solving the classification problem. Some of the challenges in including these architectures include, the enormous memory and processing power requirement. Current trends are focused towards generating optimized deep structures that has relatively lesser memory and processing capacity requirement. To this end, the two benchmark architectures that have obtained momentous results in object classification namely the MobileNetV2 and Xception are included in this study to perform binary classification of capsule endoscopy images to detect the presence of abnormality. Capsule endoscopy (CE) is a medical procedure where the patient swallows the pill-based camera that traverses the entire gastrointestinal (GI) path capturing numerous images. These images are to be assessed for detecting the presence of any abnormality. The architectures included in this work have been trained on the images from the publicly available CE datasets and an ablation study on the hyperparameter tuning of the architecture have been conducted. The results are compared, analyzed and presented here. The MobileNetV2 and Xception architecture have achieved a maximum accuracy of 85% and 82% in the abnormality detection in CE images.

MBSE approach for complex industrial organization program

AbstractAs Model Based System Engineering (MBSE) becomes THE standard approach for system engineering, it is applied for large programs development based on complex industrial organizations.The purpose of this paper is to present the various rules and mechanisms supporting this model interoperability across industries and agencies in terms of: Modeling structuration (or multi‐layer) Data object in a tool agnostic's representation (data model) These rules have been worked out and agreed within a common working group gathering European Aerospace Prime industries ‐ namely the EUREcA (EURopean Ecosystem for Aerospace and Defense) initiative ‐ to elaborate a standard architecture aiming to become a European Aerospace standard for all main Defense & Aerospace contracts .This solution is implemented at Airbus level within the MBSE framework initiative to provide a company‐wide flexible and configurable solution supporting the entire Airbus program portfolio (e.g. satellite, helicopter, commercial/military aircraft, drone or ground segment).It is under deployment on several programs, in particular Future Combat Air System (FCAS), the main military European program.

Neural Networks Classify through the Class-Wise Means of Their Representations

In this paper, based on an asymptotic analysis of the Softmax layer, we show that when training neural networks for classification tasks, the weight vectors corre sponding to each class of the Softmax layer tend to converge to the class-wise means computed at the representation layer (for specific choices of the representation activation). We further show some consequences of our findings to the context of transfer learning, essentially by proposing a simple yet effective initialization procedure that significantly accelerates the learning of the Softmax layer weights as the target domain gets closer to the source one. Experiments are notably performed on the datasets: MNIST, Fashion MNIST, Cifar10, and Cifar100 and using a standard CNN architecture.

Zero-Shot Audio Source Separation through Query-Based Learning from Weakly-Labeled Data

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a single model to target multiple sources, they have difficulty generalizing to unseen sources. In this paper, we propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet. First, we propose a transformer-based sound event detection system for processing weakly-labeled training data. Second, we devise a query-based audio separation model that leverages this data for model training. Third, we design a latent embedding processor to encode queries that specify audio targets for separation, allowing for zero-shot generalization. Our approach uses a single model for source separation of multiple sound types, and relies solely on weakly-labeled data for training. In addition, the proposed audio separator can be used in a zero-shot setting, learning to separate types of audio sources that were never seen in training. To evaluate the separation performance, we test our model on MUSDB18, while training on the disjoint AudioSet. We further verify the zero-shot performance by conducting another experiment on audio source types that are held-out from training. The model achieves comparable Source-to-Distortion Ratio (SDR) performance to current supervised models in both cases.

A robust deep attention dense convolutional neural network for plant leaf disease identification and classification from smart phone captured real world images

Plant diseases cause significant food loss and hence economic loss around the globe. Therefore, automatic plant disease identification is a primary task to take proper medications for controlling the spread of the diseases. Large variety of plants species and their dissimilar phytopathological symptoms call for the implementation of supervised machine learning techniques for efficient and reliable disease identification and classification. With the development of deep learning strategies, convolutional neural network (CNN) has paved its way for classification of multiple plant diseases by extracting rich features. However, several characteristics of the input images especially captured in real world environment, viz. complex or indistinguishable background, presence of multiple leaves with the diseased leaf, small lesion area, solemnly affect the robustness and accuracy of the CNN modules. Available strategies usually applied standard CNN architectures on the images captured in the laboratory environment and very few have considered practical in-field leaf images for their studies. However, those studies are limited with very limited number of plant species. Therefore, there is need of a robust CNN module which can successfully recognize and classify the dissimilar leaf health conditions of non-identical plants from the in-field RGB images. To achieve the above goal, an attention dense learning (ADL) mechanism is proposed in this article by merging mixed sigmoid attention learning with the basic dense learning process of deep CNN. The basic dense learning process derives new features at higher layer considering all lower layer features and that provides fast and efficient training process. Further, the attention learning process amplifies the learning ability of the dense block by discriminating the meaningful lesion portions of the images from the background areas. Other than adding an extra layer for attention learning, in the proposed ADL block the output features from higher layer dense learning are used as an attention mask to the lower layers. For an effective and fast classification process, five ADL blocks are stacked to build a new CNN architecture named DADCNN-5 for obtaining classification robustness and higher testing accuracy. Initially, the proposed DADCNN-5 module is applied on publicly available extended PlantVillage dataset to classify 38 different health conditions of 14 plant species from 54,305 images. Classification accuracy of 99.93% proves that the proposed CNN module can be used for successful leaf disease identification. Further, the efficacy of the DADCNN-5 model is checked after performing stringent experiments on a new real world plant leaf database, created by the authors. The new leaf database contains 10,851 real-world RGB leaf images of 17 plant species for classifying their 44 distinguished health conditions. Experimental outcomes reveal that the proposed DADCNN-5 outperforms the existing machine learning and standard CNN architectures, and achieved 97.33% accuracy. The obtained sensitivity, specificity and false positive rate values are 96.57%, 99.94% and 0.063% respectively. The module takes approximately 3235 min for training process and achieves 99.86% of training accuracy. Visualization of Class activation mapping (CAM) depicts that DADCNN-5 is able to learn distinguishable features from semantically important regions (i.e. lesion regions) on the leaves. Further, the robustness of the DADCNN-5 is established after experimenting with augmented and noise contaminated images of the practical database.

Abstract 6233: A deep learning pipeline to capture the prognostic immune responses in lymph nodes of breast cancer patients

Abstract Capturing tumor infiltrating leucocytes (TILS) and systemic immune responses in breast cancer informs disease progression and optimal treatment management. We have previously shown that morphological alterations in axillary lymph nodes (LNs), namely the formation of germinal centers in cancer-free LNs, adds prognostic value to TILs in triple negative breast cancer patients (TNBC) for the development of distant metastasis. Extending manual assessment of LNs beyond the detection of cancer requires the integration of robust deep learning pipelines into the digital pathology workflow. In this retrospective study, we used 1,100 Haematoxylin & Eosin-stained (H&E) Whole Slide Images (WSI) from Guy’s Hospital (London, UK) of metastatic and cancer-free LNs from 151 patients (100 N+) enriched for triple-negative or HER2-positive breast cancer to implement a supervised deep learning pipeline. A subset of 114 WSI, along with 5 breast cancer LN WSIs from each of Barts Hospital (London, UK) and Tianjin University Hospital (Tianjin, China), and 5 head and neck squamous cell carcinomas LN WSI (Guy’s Hospital) were used to develop, train and evaluate the segmentation task. For training Fully Convolutional Networks (FCNs), WSIs manually annotated for both germinal centers and sinuses formed a ground-truth set. Three FCNs were implemented: (i) a standard U-Net architecture; (ii) a U-Net model with an attention gate mechanism; and (iii) a multiscale-U-Net network (MSA-U-Net) that encodes, in parallel, a feature representation of the image at multiple resolutions. The MSA-U-Net achieved the best performance with an average dice score of 0.85 for germinal centers and 0.75 for sinuses. In comparison, the average dice score amongst 4 pathologists assessing 25 LN WSI for germinal centers and sinuses, was 0.67 and 0.61 respectively, demonstrating the robustness of the MSA-U-Net model. To quantify germinal centers and sinuses in LNs across the entire cohort, the trained MSA-U-Net was used in an inference step on all 1,100 WSI. The detected morphological features were initially localized within LNs using image thresholding and contouring techniques, and quantitatively assessed based on their number, area, shape, and Shannon diversity. We found significant morphological differences in metastatic and cancer-free LNs between N0 and N+ patients, with the latter displaying larger germinal centers with more irregular shapes especially in their metastatic LNs. In addition, we found differences in the Sinus area between LNs containing GCs and those without. Here, we propose a robust deep learning pipeline based on a multiscale FCN framework to automatically detect, localize and quantify histopathological immune features in WSI of LNs. By applying our pipeline to LNs of cancer patients, such as breast or head and neck, in prospective studies or clinical trials, we will further evaluate their prognostic and predictive values. Citation Format: Gregory Verghese, Mengyuan Li, Amit Lohan, Nikhil Cherian, Swapnil Rane, Fangfang Liu, Aekta Shah, Pat Gazinska, Selvam Thavaraj, Amit Sethi, Anita Grigoriadis. A deep learning pipeline to capture the prognostic immune responses in lymph nodes of breast cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6233.

Traffic offloading model in a multilevel edge computing system for autonomous vehicles

Research subject is autonomous control networks for unmanned vehicles. Research method – study of the main functional elements and their locations for MEC, Fog technologies; studying the types of interaction between devices in vehicle networks; identification of the main problems arising in vehicle networks. Main results – MEC, V2X technologies are described in detail; considered a system that will be implemented using edge computing, and will also support ultra-low latency and high density for unmanned vehicles; a model was created for the VANET environment, demonstrating signal processing at two levels of edge computing. Practical significance – The presented architecture will reduce the load on the core network and ensure the provision of ultra-low transmission delays, which can also contribute to the introduction of unmanned vehicle networks into
 mass use in the future. The proposed architecture can be used as part of the «Smart City» concept. It is also worth noting that a multi-level system, due to its closer location to the user, will be more effective in forming a Fog cluster than with a standard network architecture, when a remote server will be used to form a cluster.

Towards fully automated segmentation of rat cardiac MRI by leveraging deep learning frameworks

Automated segmentation of human cardiac magnetic resonance datasets has been steadily improving during recent years. Similar applications would be highly useful to improve and speed up the studies of cardiac function in rodents in the preclinical context. However, the transfer of such segmentation methods to the preclinical research is compounded by the limited number of datasets and lower image resolution. In this paper we present a successful application of deep architectures 3D cardiac segmentation for rats in preclinical contexts which to our knowledge has not yet been reported. We developed segmentation models that expand on the standard U-Net architecture and evaluated models separately trained for systole and diastole phases (2MSA) and a single model trained for all phases (1MSA). Furthermore, we calibrated model outputs using a Gaussian process (GP)-based prior to improve phase selection. The resulting models approach human performance in terms of left ventricular segmentation quality and ejection fraction (EF) estimation in both 1MSA and 2MSA settings (Sørensen-Dice score 0.91 ± 0.072 and 0.93 ± 0.032, respectively). 2MSA achieved a mean absolute difference between estimated and reference EF of 3.5 ± 2.5%, while 1MSA resulted in 4.1 ± 3.0%. Applying GPs to 1MSA enabled automating systole and diastole phase selection. Both segmentation approaches (1MSA and 2MSA) were statistically equivalent. Combined with a proposed cardiac phase selection strategy, our work presents an important first step towards a fully automated segmentation pipeline in the context of rat cardiac analysis.

Hot-carrier multijunction solar cells: sensitivity and resilience to nonidealities

The resilience against non-idealities of hot-carrier multijunction solar cells (HCMJSCs) is assessed and compared with two references, namely a multijunction solar cell (MJSC) and a hot carrier solar cell (HCSC). We investigate the impact on the efficiency of three deviations from the ideal case: nonoptimal design, internal limitations, and nonstandard operation conditions. We show that the HCMJSC maintains a high efficiency even when materials with nonoptimal bandgaps are considered, broadening the range of candidate materials for its implementation. We also show that the requirement for hot carriers’ thermalization is much less stringent than with the standard HCSC architecture, allowing to surpass the best MJSC efficiency with currently achievable thermalization coefficients. Finally, we estimate the influence of nonstandard illumination by varying the AM spectrum and estimate numerically the yearly averaged efficiency of devices installed in two different locations. Preliminary results on temperature dependence are also presented.

Low-Bitwidth Convolutional Neural Networks for Wireless Interference Identification

Wireless interference identification (WII) is critical for non-cooperative communication systems in both civilian and military scenarios. Recently, deep learning (DL) based WII methods have been proposed with impressive performances. However, these methods did not consider the quantization problem for DL based methods of WII, which is an indispensable process when deploying deep neural networks into hardware units. This paper addresses the problem of training quantized convolutional neural networks (CNNs), with low-precision weights as well as activations for WII. Optimizing a low-bit width network is very challenging due to the non-differentiable quantization function. To mitigate the difficulty of training, we propose three effective approaches. Firstly, we propose to train the quantized network with the guidance of the full-precision counterpart. The quantized network can learn from the full-precision counterpart. Unfortunately, training an extra full-precision network to assist a quantized model is cumbersome and computationally expensive. To this end, we further propose a training mechanism which makes use of the manually designed probability distributions to provide a virtual full-precision counterpart for guiding the training of the quantization network without extra computational cost. Thirdly, to make the gradient back-propagates more easily, we propose novel auxiliary output modules, which can be seamlessly incorporated into the proposed quantization networks. Experimental results validate the effectiveness of the proposed methods. Furthermore, it is shown that training 3-bit and 4-bit precision networks with the proposed methods leads to performance improvement as compared to their full precision counterparts with standard network architectures.

Processing-in-Memory Technology for Machine Learning: From Basic to ASIC

Due to the need for computing models that can process large quantities of data efficiently and with high throughput in many state-of-the-art machine learning algorithms, the processing-in-memory (PIM) paradigm is emerging as a potential replacement for standard digital architectures on these workloads. In this tutorial, we review the progress of PIM technology in recent years, at both the circuit and architecture level. We further present an analysis of when and how PIM technology surpasses the performance of conventional architectures. Finally, we outline our vision for the future of PIM technology.

Comparative Analysis Between High Level Architecture (HLA) and Service Oriented Architecture (SOA) in the Field of Military Modelling and Simulation

Abstract Modelling and simulation is a major area of interest for states and international organizations in the context of the operational environment characterized by complexity, dynamism and unpredictability. At the moment, in NATO, the standard architecture for the field of modelling and simulation is High Level Architecture (HLA), but lately the concept of Service Oriented Architecture (SOA) has aroused the interest of specialists within the Alliance. In this paper, a comparative analysis is performed between the two types of architectures in order to determine the optimal variant for the field of military modelling and simulation. Following the analysis, it was concluded that a combined approach of the two types of architectures is needed to maximize the efficiency of modelling and simulation applications.

SEVA-Cpf1, a CRISPR-Cas12a vector for genome editing in cyanobacteria

BackgroundCyanobacteria are photosynthetic autotrophs that have tremendous potential for fundamental research and industrial applications due to their high metabolic plasticity and ability to grow using CO2 and sunlight. CRISPR technology using Cas9 and Cpf1 has been applied to different cyanobacteria for genome manipulations and metabolic engineering. Despite significant advances with genome editing in several cyanobacteria strains, the lack of proper genetic toolboxes is still a limiting factor compared to other model laboratory species. Among the limitations, it is essential to have versatile plasmids that could ease the benchwork when using CRISPR technology.ResultsIn the present study, several CRISPR-Cpf1 vectors were developed for genetic manipulations in cyanobacteria using SEVA plasmids. SEVA collection is based on modular vectors that enable the exchangeability of diverse elements (e.g. origins of replication and antibiotic selection markers) and the combination with many cargo sequences for varied end-applications. Firstly, using SEVA vectors containing the broad host range RSF1010 origin we demonstrated that these vectors are replicative not only in model cyanobacteria but also in a new cyanobacterium specie, Chroococcidiopsis sp., which is different from those previously published. Then, we constructed SEVA vectors by harbouring CRISPR elements and showed that they can be easily assimilated not only by conjugation, but also by natural transformation. Finally, we used our SEVA-Cpf1 tools to delete the nblA gene in Synechocystis sp. PCC 6803, demonstrating that our plasmids can be applied for CRISPR-based genome editing technology.ConclusionsThe results of this study provide new CRISPR-based vectors based on the SEVA (Standard European Vector Architecture) collection that can improve editing processes using the Cpf1 nuclease in cyanobacteria.