Low Resource Consumption Research Articles

Design and Implementation of a Highly Efficient Quasi-Cyclic Low-Density Parity-Check Transceiving System Using an Overlapping Decoder.

The traditional LDPC encoding and decoding system is characterized by low throughput and high resource consumption, making it unsuitable for use in cost-efficient, energy-saving sensor networks. Aiming to optimize coding complexity and throughput, this paper proposes a combined design of a novel LDPC code structure and the corresponding overlapping decoding strategies. With regard to structure of LDPC code, a CCSDS-like quasi-cyclic parity check matrix (PCM) with uniform distribution of submatrices is constructed to maximize overlap depth and adapt the parallel decoding. In terms of reception decoding strategies, we use a modified 2-bit Min-Sum algorithm (MSA) that achieves a coding gain of 5 dB at a bit error rate of 10-6 compared to an uncoded BPSK, further mitigating resource consumption, and which only incurs a slight loss compared to the standard MSA. Moreover, a shift-register-based memory scheduling strategy is presented to fully utilize the quasi-cyclic characteristic and shorten the read/write latency. With proper overlap scheduling, the time consumption can be reduced by one third per iteration compared to the non-overlap algorithm. Simulation and implementation results demonstrate that our decoder can achieve a throughput up to 7.76 Gbps at a frequency of 156.25 MHz operating eight iterations, with a two-thirds resource consumption saving.

Peak Cancellation Method With IIR Filters and Its FPGA Implementation

To improve the efficiency of power amplifiers (PA) in communication transmitters, peak cancellation (PC) in the time domain is often implemented on a Field-programmable gate array (FPGA) to reduce the peak-to-average power ratio (PAPR) of the baseband signals. However, to reduce the out-of-band radiation, the existing techniques tend to use high-order finite impulse response (FIR) filters, which increases the input-to-output delay and resource consumption of FPGA. To address this issue, a PC method with the infinite impulse response (IIR) filter is proposed in this brief. The design criteria of the IIR filter for PC is given. The FPGA implementation scheme and resource optimization are discussed. To verify the performance of the proposed method, MATLAB simulation and FPGA implementation are made with a 5G NR signal. The comparison with the state-of-the-art PC methods shows that the proposed technique can reduce the total time delay greatly, with good PC performance and low resource consumption.

Efficient On-Chip Learning of Multi-Layer Perceptron Based on Neuron Multiplexing Method

An efficient on-chip learning method based on neuron multiplexing is proposed in this paper to address the limitations of traditional on-chip learning methods, including low resource utilization and non-tunable parallelism. The proposed method utilizes a configurable neuron calculation unit (NCU) to calculate neural networks in different degrees of parallelism through multiplexing NCUs at different levels, and resource utilization can be increased by reducing the number of NCUs since the resource consumption is predominantly determined by the number of NCUs and the data bit-width, which are decoupled from the specific topology. To better support the proposed method and minimize RAM block usage, a weight segmentation and recombination method is introduced, accompanied by a detailed explanation of the access order. Moreover, a performance model is developed to facilitate parameter selection process. Experimental results conducted on an FPGA development board demonstrate that the proposed method has lower resource consumption, higher resource utilization, and greater generality compared to other methods.

Defect detection and classification on semiconductor wafers using two-stage geometric transformation-based data augmentation and SqueezeNet lightweight convolutional neural network

The manufacturing industry is evolving in line with the principles of Industry 4.0, with the aim of achieving higher levels of automation and digitization. In particular, deep learning algorithms such as convolutional neural networks (CNNs) are key enabling technologies to achieve this goal. The semiconductor industry is a particular case where CNNs are used to assist inspection systems and human operators in defect classification of wafers. However, deep CNN models are time consuming and resource intensive. It is therefore necessary to look for alternatives. One of these alternatives is the use of lightweight models, which provide competitive classification performance with low time and resource consumption. Therefore, the motivation of this work is to apply these lightweight models to semiconductor defect classification and compare their performance with that obtained by deep CNN models in similar work. In this line, this paper introduces an efficient two-step approach combining traditional computer vision techniques and a lightweight SqueezeNet CNN for defect detection and classification. The lightweight SqueezeNet model is tuned using a grid search algorithm. After obtaining the optimal model, its metrics are presented and compared with results from related work. Using a semiconductor surface defect dataset from a multinational semiconductor company, our lightweight model can achieve really competitive classification results (99.356% versus 99.443% obtained by ResNet50) while consuming significantly less time than other heavyweight models (80.146% less time than ResNet50).

Passive frustrated nanomagnet reservoir computing

Reservoir computing (RC) has received recent interest because reservoir weights do not need to be trained, enabling extremely low-resource consumption implementations, which could have a transformative impact on edge computing and in-situ learning where resources are severely constrained. Ideally, a natural hardware reservoir should be passive, minimal, expressive, and feasible; to date, proposed hardware reservoirs have had difficulty meeting all of these criteria. We, therefore, propose a reservoir that meets all of these criteria by leveraging the passive interactions of dipole-coupled, frustrated nanomagnets. The frustration significantly increases the number of stable reservoir states, enriching reservoir dynamics, and as such these frustrated nanomagnets fulfill all of the criteria for a natural hardware reservoir. We likewise propose a complete frustrated nanomagnet reservoir computing (NMRC) system with low-power complementary metal-oxide semiconductor (CMOS) circuitry to interface with the reservoir, and initial experimental results demonstrate the reservoir’s feasibility. The reservoir is verified with micromagnetic simulations on three separate tasks demonstrating expressivity. The proposed system is compared with a CMOS echo state network (ESN), demonstrating an overall resource decrease by a factor of over 10,000,000, demonstrating that because NMRC is naturally passive and minimal it has the potential to be extremely resource efficient.

Physical-Layer Secret Key Generation Based on Bidirectional Convergence Feature Learning Convolutional Network

Physical layer secret key generation (PLKG) is a new research area that has emerged in recent years. It is aimed at scenarios where legitimate IoT devices communicate directly, interacting with confidential information for lower overhead and higher security by using wireless channel. When applying it to wireless feature extraction, noise removal is not taken into account in current deep learning networks. To address these problems, the PLKG scheme based on bidirectional convergence feature learning convolutional network (BCFL-based scheme) is proposed, which consists of neural network called BCFL and a new quantization method to achieve better secret key generation. Unlike existing PLKG schemes that enabling both parties to communicate for obtaining higher channel feature similarities, when training it, channel state information (CSI) obtained by channel estimation for two legitimate devices during coherent time is used as inputs; and mean square error (MSE) between two outputs is used as result of loss function for iterative training. Thus, it can obtain better denoising ability with guaranteed low computational resource consumption, and two legitimate devices can obtain highly correlated channel features. Multiple quantization method is also proposed to address low secret key generation rate (KGR) and low secret key randomness (KR). The results show that the proposed BCFL-based scheme has a lower MSE than other schemes in different scenarios, indicating that it has better capability to learn channel reciprocity; and secret key error rate (KER) and time consumption are only about 50% of other schemes, which is a significant performance improvement.

The Intel neuromorphic DNS challenge

A critical enabler for progress in neuromorphic computing research is the ability to transparently evaluate different neuromorphic solutions on important tasks and to compare them to state-of-the-art conventional solutions. The Intel Neuromorphic Deep Noise Suppression Challenge (Intel N-DNS Challenge), inspired by the Microsoft DNS Challenge, tackles a ubiquitous and commercially relevant task: real-time audio denoising. Audio denoising is likely to reap the benefits of neuromorphic computing due to its low-bandwidth, temporal nature and its relevance for low-power devices. The Intel N-DNS Challenge consists of two tracks: a simulation-based algorithmic track to encourage algorithmic innovation, and a neuromorphic hardware (Loihi 2) track to rigorously evaluate solutions. For both tracks, we specify an evaluation methodology based on energy, latency, and resource consumption in addition to output audio quality. We make the Intel N-DNS Challenge dataset scripts and evaluation code freely accessible, encourage community participation with monetary prizes, and release a neuromorphic baseline solution which shows promising audio quality, high power efficiency, and low resource consumption when compared to Microsoft NsNet2 and a proprietary Intel denoising model used in production. We hope the Intel N-DNS Challenge will hasten innovation in neuromorphic algorithms research, especially in the area of training tools and methods for real-time signal processing. We expect the winners of the challenge will demonstrate that for problems like audio denoising, significant gains in power and resources can be realized on neuromorphic devices available today compared to conventional state-of-the-art solutions.

Lightweight and flexible hardware implementation of authenticated encryption algorithm SIMON‐Galois/Counter Mode

SummaryThis brief proposes a new lightweight authenticated encryption algorithm SIMON‐GCM for Internet of Things (IoT) security, which realizes the combination of SIMON block cipher and Galois/Counter Mode (GCM). The designed SIMON circuit supports 128/192/256‐bit key size, which improves the flexibility and enlarges the range of applications. Moreover, the scheme of 32‐cycle Galois field (GF) multiplier in GF(2128) is adopted to effectively reduce the hardware cost of the Galois Hash (GHASH) function in GCM. At the same time, a finite state machine (FSM) is used to run the SIMON and GHASH modules in parallel, thus shortening the authenticated encryption time. The whole circuit is designed and implemented in field programmable gate array (FPGA) platforms. It is measured to yield a throughput of 32.4 Gbps when consuming 331 slices in Artix‐7. Compared with the existing authenticated encryption algorithms, the proposed algorithm achieves lower resource consumption and better flexibility.

Kalman Filtresi ve Küresel En Yakın Komşu Yöntemi ile Çok Kişili Gerçek Zamanlı Poz Takibi

Poz tahmini, kamera ile çekilen görüntülerde insan iskeletindeki anahtar noktaların piksel konumlarının tespit edilmesi amacıyla ortaya çıkmıştır. Poz tahmini yöntemlerinin çıktıları görüntüde tespit edilen tüm eklem noktalarının piksel değerlerini ilişkilendirdiği kişiye göre vermektedir. Videolarda kişilerin hareketlerini anlamlandırmak için ardışık görüntü kareleri boyunca kimliklendirilmeleri gerekir. Böylece kişilerin video boyunca ne zaman hangi hareketleri yaptığı tespit edilebilir. Bu çalışmada sabit hızlı ve sabit ivmeli hareket modeline göre Kalman filtresi kullanarak küresel en yakın komşu (KEYK) algoritması ile tasarlanan çok kişili poz takibi yönteminin verdiği sonuçlar incelenmiştir. Geliştirilen ön işleme adımlarının poz tahmini yöntemlerinin kalitesini artırarak poz takibine etkisi de tespit edilmiştir. Bu amaçla PoseTrack veri kümesi üzerinde DCPose ve OpenPose poz tahmini yöntemlerinin başarımı değerlendirilmiştir. Ön işleme adımları ile sistemin başarımının her iki yöntem için de yükseldiği görülmüştür. Gerçek zamanlı çalışabilen, başarılı bir poz tahmini yöntemi olan ve düşük kaynak tüketimine sahip OpenPose yöntemi ile literatürde en iyi sonuçları veren DCPose yönteminin sonuçları incelendiğinde çok kişili poz takibi konusunda DCPose yönteminin daha başarılı sonuçlar verdiği görülmüştür. 550 farklı video ile elde edilen sonuçlar ön işleme adımları uygulandığında başarımı sabit hızlı ve sabit ivmeli hareket modellerinde aşağıdan yukarı yöntemi OpenPose için %22.6 ve %16.02, yukarıdan aşağı yöntemi DCPose için %21.2 ve %21.8 artırmıştır.

Towards Persistent Detection of DDoS Attacks in NDN: A Sketch-Based Approach

As a promising architectural design for future Internet, Named Data Networking (NDN) relies on data names, instead of destination IP addresses, to deliver data. NDN supports data authenticity and integrity by making public key signatures mandatory on data content and data names. This handles the primary security concern in NDN, but is still vulnerable to new DDoS attacks, including Cache Pollution attacks and Interest Flooding attacks, which degrade NDN transmission significantly, by violating the crucial components of NDN routers. To defend against DDoS attacks in NDN, the most effective way is to persistently detect the malicious traffic and then throttle them. Except for the usual concern of the accuracy and efficiency in attack detection, since these attacks themselves have already imposed a huge burden on victims, to avoid exhausting the remaining resources on the victims for detection purpose, a lightweight detection solution is highly desired. We study DDoS attacks and propose a persistent detection solution based on an observed malicious traffic pattern, which leverages a novel sketch to monitor the malicious traffic in a timely and lightweight way. Additionally, our analysis and experiments demonstrate that, with fixed low resource consumption, the proposed solution can persistently detect DDoS attacks in NDN.

Coriolis: enabling metagenomic classification on lightweight mobile devices.

The introduction of portable DNA sequencers such as the Oxford Nanopore Technologies MinION has enabled real-time and in the field DNA sequencing. However, in the field sequencing is actionable only when coupled with in the field DNA classification. This poses new challenges for metagenomic software since mobile deployments are typically in remote locations with limited network connectivity and without access to capable computing devices. We propose new strategies to enable in the field metagenomic classification on mobile devices. We first introduce a programming model for expressing metagenomic classifiers that decomposes the classification process into well-defined and manageable abstractions. The model simplifies resource management in mobile setups and enables rapid prototyping of classification algorithms. Next, we introduce the compact string B-tree, a practical data structure for indexing text in external storage, and we demonstrate its viability as a strategy to deploy massive DNA databases on memory-constrained devices. Finally, we combine both solutions into Coriolis, a metagenomic classifier designed specifically to operate on lightweight mobile devices. Through experiments with actual MinION metagenomic reads and a portable supercomputer-on-a-chip, we show that compared with the state-of-the-art solutions Coriolis offers higher throughput and lower resource consumption without sacrificing quality of classification. Source code and test data are available from http://score-group.org/?id=smarten.

Studies advanced in chatbots based on deep learning

Chatbots have always been a hot research topic in the field of human-computer interaction research, which aims to build a conversational intelligent response model to simulate human dialogue. Thanks to the rapid development of natural language processing technology and the continuous accumulation of dialogue data, the research of chat robots have made remarkable progress, which has gradually been widely used in various fields such as e-commerce and smart home. According to different technical frameworks, existing chatbots are mainly divided into two types: retrieval chatbots and generative chatbots. As the primary means of implementing chatbots in the industry, retrieval chatbots have smooth responses and low computational resource consumption. In contrast, generative chatbots do not require a predefined knowledge base and can dynamically generate responses based on the dialogue content. In this paper, focusing on the above two types of frameworks, we introduce the latest research progress in the field of deep learning-based chatbots in detail, including the representative algorithms and corresponding pipelines. Second, we compare the performance of representative algorithms on different datasets. We also summarize the problems chatbot technology research faces and give an outlook on its future development trends.

An event-driven Spike-DBN model for fault diagnosis using reward-STDP

Deep neural networks (DNNs) have shown high accuracy in fault diagnosis, but they struggle to effectively capture changes over time in multivariate time-series data and suffer from resource consumption issues. Spike deep belief networks (spike-DBNs) address these limitations by capturing the change in time-varying signals and reducing resource consumption, but they sacrifice accuracy. To overcome these limitations, we propose integrating an event-driven approach into spike-DBNs through the Latency-Rate coding method and the reward-STDP learning rule. The encoding method enhances the event representation capability, while the learning rule focuses on the global behavior of spiking neurons triggered by events. Our proposed method not only maintains low resource consumption but also improves the fault diagnosis ability of spike-DBNs. We conducted a series of experiments to verify our model’s performance, and the results demonstrate that our proposed method improves the accuracy of fault classification of manipulators and reduces learning time by nearly 76% compared to spike-CNN under the same conditions.

XRecon: An Explainbale IoT Reconnaissance Attack Detection System Based on Ensemble Learning.

IoT devices have grown in popularity in recent years. Statistics show that the number of online IoT devices exceeded 35 billion in 2022. This rapid growth in adoption made these devices an obvious target for malicious actors. Attacks such as botnets and malware injection usually start with a phase of reconnaissance to gather information about the target IoT device before exploitation. In this paper, we introduce a machine-learning-based detection system for reconnaissance attacks based on an explainable ensemble model. Our proposed system aims to detect scanning and reconnaissance activity of IoT devices and counter these attacks at an early stage of the attack campaign. The proposed system is designed to be efficient and lightweight to operate in severely resource-constrained environments. When tested, the implementation of the proposed system delivered an accuracy of 99%. Furthermore, the proposed system showed low false positive and false negative rates at 0.6% and 0.05%, respectively, while maintaining high efficiency and low resource consumption.

Application of finite element analysis in maxillofacial surgery biomechanics

ABSTRACT Finite element analysis method is one of the important tools in biomechanics research, which has the characteristics of high efficiency, convenience, accuracy, low resource consumption, individuation, and repeatability. At present, it is widely used in maxillofacial surgery, such as the biomechanics of normal jaw, the mechanical research of temporomandibular joint disease, and the surgical effect of jaw fracture and of orthognathic surgery. In this paper, the application of finite element analysis in maxillofacial surgery is summarized by combining the principle of finite element analysis, and the shortcomings of finite element analysis in clinical application are explained to provide suggestions for future research.

Research on Optimizing the Communication Efficiency of NAT Penetration Technology Based on STUN Protocol

NAT (Network Address Translator) technology solves the problem of IP address shortage, but this technology can prevent P2P (Peer-to-Peer) communication between hosts. NAT penetration is the technical means to find a way to allow external datagrams to pass through the NAT device according to the mapping rules of the device, thus establishing a stable P2P connection. In order to ensure that the nodes in a P2P network complete high-quality communication, this paper investigates the entire P2P communication process and proposes an optimisation strategy based on STUN (Simple Traversal of UDP Through NATs) protocol penetration to address the problems of complex and tedious NAT type detection process and low success rate of the penetration process. By reclassifying NAT types, improving NAT type detection methods, introducing network state detection algorithms and optimising the communication flow, the strategy ensures smooth and high-quality communication between nodes in a P2P network. The experimental results show that the STUN protocol-based NAT penetration strategy proposed in this paper has lower resource consumption, stronger anti-interference capability and higher penetration success rate, avoiding performance bottlenecks in the server and providing high-quality network services for the whole communication process.

GLASS: Generator for Large Scale Structure

We present GLASS, the Generator for Large Scale Structure, a new code for the simulation of galaxy surveys for cosmology, which iteratively builds a light cone with matter, galaxies, and weak gravitational lensing signals as a sequence of nested shells. This allows us to create deep and realistic simulations of galaxy surveys at high angular resolution on standard computer hardware and with low resource consumption. GLASS also introduces a new technique to generate transformations of Gaussian random fields (including lognormal) to essentially arbitrary precision, an iterative line-of-sight integration over matter shells to obtain weak lensing fields, and flexible modelling of the galaxies sector. We demonstrate that GLASS readily produces simulated data sets with per cent-level accurate two-point statistics of galaxy clustering and weak lensing, thus enabling simulation-based validation and inference that is limited only by our current knowledge of the input matter and galaxy properties. The code described in this paper is available <a href="https://github.com/glass-dev/glass">here</a>.

GLASS: Generator for Large Scale Structure

We present GLASS, the Generator for Large Scale Structure, a new code for the simulation of galaxy surveys for cosmology, which iteratively builds a light cone with matter, galaxies, and weak gravitational lensing signals as a sequence of nested shells. This allows us to create deep and realistic simulations of galaxy surveys at high angular resolution on standard computer hardware and with low resource consumption. GLASS also introduces a new technique to generate transformations of Gaussian random fields (including lognormal) to essentially arbitrary precision, an iterative line-of-sight integration over matter shells to obtain weak lensing fields, and flexible modelling of the galaxies sector. We demonstrate that GLASS readily produces simulated data sets with per cent-level accurate two-point statistics of galaxy clustering and weak lensing, thus enabling simulation-based validation and inference that is limited only by our current knowledge of the input matter and galaxy properties.

Time-Series Representation Learning in Topology Prediction for Passive Optical Network of Telecom Operators

The passive optical network (PON) is widely used in optical fiber communication thanks to its low cost and low resource consumption. However, the passiveness brings about a critical problem that it requires manual work to identify the topology structure, which is costly and prone to bringing noise to the topology logs. In this paper, we provide a base solution firstly introducing neural networks for such problems, and based on that solution we propose a complete methodology (PT-Predictor) for predicting PON topology through representation learning on its optical power data. Specifically, we design useful model ensembles (GCE-Scorer) to extract the features of optical power with noise-tolerant training techniques integrated. We further implement a data-based aggregation algorithm (MaxMeanVoter) and a novel Transformer-based voter (TransVoter) to predict the topology. Compared with previous model-free methods, PT-Predictor is able to improve prediction accuracy by 23.1% in scenarios where data provided by telecom operators is sufficient, and by 14.8% in scenarios where data is temporarily insufficient. Besides, we identify a class of scenarios where PON topology does not follow a strict tree structure, and thus topology prediction cannot be effectively performed by relying on optical power data alone, which will be studied in our future work.

How does remote education facilitate student performance? Appraising a sustainable learning perspective midst of COVID-19

The COVID-19 pandemic has brought the concept of a "new normal" to our daily lives and fundamentally affects how we live, learn, and work. In these extraordinary times, the quick move from traditional (face-to-face) learning to online learning is viewed as a paradigm change affecting social, economic, and ecological factors. In this vein, the current study investigates the linkages among system quality, instructor quality, campus learning climate, student satisfaction, and online learning success. We have collected questionnaire-based data from 302 students enrolled in different programs and employed the structural equation modelling (SEM) approach. The results indicate that system and instructor quality is vital in accomplishing campus learning climate and student satisfaction. Manifestly, campus learning climate and student satisfaction also significantly affect online learning success, which helps achieve institutional excellence and positive word of mouth. Virtual learning offers many technological advantages and leads to lower resource consumption than physical learning models. Enlightening the quality of education systems and instructors is crucial in producing value in modern societies for institutional superiority.