Limited Memory Research Articles

Online_XKD: An online knowledge distillation model for underwater object detection

Underwater object detection in the field of computer vision faces unique challenges such as color distortion, reduced visibility, and blurred edges caused by aquatic conditions, which decrease the efficiency of traditional methods. Furthermore, the limited memory and computational power of underwater equipment necessitate the development of lightweight and efficient real-time monitoring algorithms. To address these issues, this paper designs an online knowledge distillation(KD) framework based on mutual knowledge transfer, named Online-XKD, which aims to enhance the efficiency and generalizability of knowledge distillation through mutual knowledge exchange while maintaining model lightweightness. The core idea of Online-XKD is an internally designed mutual knowledge transfer structure for online distillation within the detection head, which enhances learning outcomes by optimizing distillation efficiency and broadening generalizability. Additionally, we introduce a mask generation feature knowledge distillation architecture based on the backbone network, which significantly enhances the feature extraction capability of the student model by integrating mask masking and feature generation techniques. Moreover, by incorporating PSA and AUGFPN attention modules, the feature extraction capability in complex underwater environments is further enhanced without adding extra parameters, thereby improving detection accuracy. Experimental results on the URPC2020 dataset demonstrate that Online-XKD enhances the detection accuracy of the student model by 3.6 mAP, exceeding initial KD models by 3.3 mAP, and outperforming most existing KD methods in underwater detection tasks. These results confirm the effectiveness and superiority of Online-XKD in applications of underwater object detection, proving its practical significance and effectiveness in enhancing the feature extraction and generalization abilities of lightweight models.

Lightweight Improved Transmission Line External Mechanical Damage Threats Detection Algorithm

In monitoring transmission line external damage prevention, due to the limited memory computing power of the equipment, the image needs to be transmitted to the data center at regular intervals, resulting in a high false negative rate. Therefore, this paper proposes a target detection method based on lightweight YOLOv5s. First, DSConv and improved E‐ELAN are used in Backbone to reduce the model's parameters. Then, GSConv and VoV‐GSCSP are introduced in Neck to reduce the complexity of the model. Finally, the Mish activation function achieves more effective feature transfer. According to the experimental findings, the proposed model's parameters are about 37% smaller than the original model's, and the calculation amount is about 53% smaller. The detection accuracy on the self‐built data set is the same, which proves that the proposed algorithm can reduce the model while maintaining high detection performance. It has specific practical significance for the terminal real‐time detection of external mechanical damage targets. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Human cognitive system privileges processing over short-term storage: Asymmetry in working memory limitations.

The continuous flow of information in which we are immersed obliges our cognitive system to maintain accessible the relevant elements for the time necessary for their processing. The present study investigated how working memory balances the resource demands of this necessary storage in the face of demanding processing. In four experiments using a complex span task, we examined the residual performance in memory and processing of individuals who performed at their best in the other component. Reciprocal dual-task costs pointed toward a resource sharing between the two functions. However, whereas prioritizing processing almost abolished participants' memory performance, more than 60% of their processing capacities were preserved while maintaining memory performance at span. We argue that this asymmetry might be adaptive in nature. Working memory might have evolved as an action-oriented system in which short-term memory capacity is structurally limited to spare the resources needed for processing the information it holds. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Introducing Mplots: scaling time series recurrence plots to massive datasets

Time series similarity matrices (informally, recurrence plots or dot-plots), are useful tools for time series data mining. They can be used to guide data exploration, and various useful features can be derived from them and then fed into downstream analytics. However, time series similarity matrices suffer from very poor scalability, taxing both time and memory requirements. In this work, we introduce novel ideas that allow us to scale the largest time series similarity matrices that can be examined by several orders of magnitude. The first idea is a novel algorithm to compute the matrices in a way that removes dependency on the subsequence length. This algorithm is so fast that it allows us to now address datasets where the memory limitations begin to dominate. Our second novel contribution is a multiscale algorithm that computes an approximation of the matrix appropriate for the limitations of the user’s memory/screen-resolution, then performs a local, just-in-time recomputation of any region that the user wishes to zoom-in on. Given that this largely removes time and space barriers, human visual attention then becomes the bottleneck. We further introduce algorithms that search massive matrices with quadrillions of cells and then prioritize regions for later examination by either humans or algorithms. We will demonstrate the utility of our ideas for data exploration, segmentation, and classification in domains as diverse as astronomy, bioinformatics, entomology, and wildlife monitoring.

Probing Postmeasurement Entanglement without Postselection

We study the problem of observing quantum collective phenomena emerging from large numbers of measurements. These phenomena are difficult to observe in conventional experiments because, in order to distinguish the effects of measurement from dephasing, it is necessary to postselect on sets of measurement outcomes with Born probabilities that are exponentially small in the number of measurements performed. An unconventional approach, which avoids this exponential “postselection problem”, is to construct cross-correlations between experimental data and the results of simulations on classical computers. However, these cross-correlations generally have no definite relation to physical quantities. We first show how to incorporate classical shadows into this framework, thereby allowing for the construction of quantum information-theoretic cross-correlations. We then identify cross-correlations that both upper and lower bound the measurement-averaged von Neumann entanglement entropy, as well as cross-correlations that lower bound the measurement-averaged purity and entanglement negativity. These bounds show that experiments can be performed to constrain postmeasurement entanglement without the need for postselection. To illustrate our technique, we consider how it could be used to observe the measurement-induced entanglement transition in Haar-random quantum circuits. We use exact numerical calculations as proxies for quantum simulations and, to highlight the fundamental limitations of classical memory, we construct cross-correlations with tensor-network calculations at finite bond dimension. Our results reveal a signature of measurement-induced criticality that can be observed using a quantum simulator in polynomial time and with polynomial classical memory. Published by the American Physical Society 2024

Online adaptation of fourier series-based acoustic transfer function model and its application to sound source localization and separation

In this paper, we propose an online adaptation method for Fourier series-based acoustic transfer function (FS-ATF) models for robot audition systems using microphone array signal processing. The ATF represents the characteristics of signal propagation from a sound source to a microphone, which is essential for sound source localization (SSL) and sound source separation (SSS). For practical applications in dynamically changing real-world environments, ATF models must satisfy two criteria: (1) they must be adaptable to changes in the acoustic environment; and (2) they must be lightweight to be suitable for resource-constrained systems, such as robots with limited memory and computational capacity. The proposed method addresses these challenges using Fourier series expansions for interpolation, which reduces the memory footprint of the ATF model and facilitates online adaptation to acoustic environmental changes. The experimental results demonstrate that the proposed online adaptation method both improves the SSL and SSS performance while reducing the size of the ATF model, which represents a significant improvement over existing online ATF adaptation methods.

Split_ Composite: A Radar Target Recognition Method on FFT Convolution Acceleration.

Synthetic Aperture Radar (SAR) is renowned for its all-weather and all-time imaging capabilities, making it invaluable for ship target recognition. Despite the advancements in deep learning models, the efficiency of Convolutional Neural Networks (CNNs) in the frequency domain is often constrained by memory limitations and the stringent real-time requirements of embedded systems. To surmount these obstacles, we introduce the Split_ Composite method, an innovative convolution acceleration technique grounded in Fast Fourier Transform (FFT). This method employs input block decomposition and a composite zero-padding approach to streamline memory bandwidth and computational complexity via optimized frequency-domain convolution and image reconstruction. By capitalizing on FFT's inherent periodicity to augment frequency resolution, Split_ Composite facilitates weight sharing, curtailing both memory access and computational demands. Our experiments, conducted using the OpenSARShip-4 dataset, confirm that the Split_ Composite method upholds high recognition precision while markedly enhancing inference velocity, especially in the realm of large-scale data processing, thereby exhibiting exceptional scalability and efficiency. When juxtaposed with state-of-the-art convolution optimization technologies such as Winograd and TensorRT, Split_ Composite has demonstrated a significant lead in inference speed without compromising the precision of recognition.

On languaging a simulation engine: Rapid modeling of nanoporous media sorption by hierarchical language model

Language model intelligence is revolutionizing the way we program materials simulations. However, the diversity of simulation scenarios renders it challenging to precisely transform human language into a tailored simulator. Here, using three types of expert language model, we propose a language-to-simulation (Lang2Sim) framework that enables interactive navigation on languaging a simulation engine, by taking a scenario instance of water sorption in porous matrices. Unlike line-by-line coding of a target simulator, the language models interpret each simulator as an assembly of invariant tool function and its variant input–output pair. Lang2Sim enables the precise transform of textual description by functionalizing and sequentializing the language models of, respectively, rationalizing the tool categorization, customizing its input–output combinations, and distilling the simulator input into executable format. Importantly, depending on its expert type, each language model features a distinct processing of chat history to best balance its memory limit and information completeness, thus leveraging the model intelligence to unstructured nature of human request. Overall, this work establishes language model as an intelligent platform to unlock the era of languaging a simulation engine.

Efficient Management of Containers for Software Defined Vehicles

Containerization technology, such as Docker, is gaining in popularity in newly established software-defined vehicle architectures (SDVA). However, executing those containers can quickly become computationally expensive in constrained environments, given the limited CPU, memory, and energy resources in the Electric Control Units (ECU) of SDVA. Consequently, the efficient management of these containers is crucial for enabling the on-demand usage of the applications in the vehicle based on the available resources while considering several constraints and priorities, including failure tolerance, security, safety, and comfort. In this paper, we propose a dynamic software container management approach for constrained environments such as embedded devices/ECUs in SDVA within smart cars. To address the conflicting objectives and constraints within the vehicle, we design a novel search-based approach based on multi-objective optimization. This approach facilitates the allocation, movement, or suspension of containers between ECUs in the cluster. Collaborating with our industry partner, Ford Motor Company, we evaluate our approach using different real-world software-defined scenarios. These scenarios involve using heterogeneous clusters of ECU devices in vehicles based on real-world software containers and use-case studies from the automotive industry. The experimental results demonstrate that our scheduler outperforms existing scheduling algorithms, including the default Docker scheduler -Spread- commonly used in automotive applications. Our proposed scheduler exhibits superior performance in terms of energy and resource cost efficiency. Specifically, it achieves a 35% reduction in energy consumption in power-saving mode compared to the scheduler employed by Ford Motor Company. Additionally, our scheduler effectively distributes workload among the ECUs in the cluster, minimizing resource usage, and dynamically adjusts to the real-time requirements and constraints of the car environment. This work will serve as a fundamental building block in the automotive industry to efficiently manage software containers in smart vehicles considering constraints and priorities in the real world.

LiteHash: Hash Functions for Resource-Constrained Hardware

The global paradigm shift towards edge computing has led to a growing demand for efficient integrity verification. Hash functions are one-way algorithms which act as a zero-knowledge proof of a datum’s contents. However, it is infeasible to compute hashes on devices with limited processing power and memory. Hence, we propose four novel LiteHash functions which are architecturally similar to SHA-512 yet simpler. By using various approximation techniques, our implementations reduce the computational costs of digesting a message into a hash. On validating our proposed designs using the NIST PRNG Test Suite, we observe SHA-512 equivalent cryptographic security while satisfying all desired hash function property requirements. We observe a minimum of 9.41% reduction in area, 20.47% reduction in power and 22.05% increase in throughput. Our designs offer a throughput of upto 2 Gbps while reducing area and power by a maximum of 16.86% and 32.48% respectively. LiteHash functions also support the computation of the entire SHA-2 family of hash functions (SHA-224/256/384/512) with minor architectural modifications.

Optimal Allocation of Water Resources Using Agro-Economic Development and Colony Optimization Algorithm

Water is an irreplaceable commodity with a high economic value. Today, water scarcity is the biggest challenge in the world, and the crises arising from lack of freshwater resources are serious threats to sustainable environmental development and human health and welfare. As the problems grow in complexity and dimensions, it becomes less possible to solve them with conventional optimization methods or explicit computational methods in a proper amount of time and with the currently limited computation memory, making it very difficult to achieve an optimal absolute solution. In this regard, metaheuristic algorithms that are generally inspired by nature are used in complex optimization problems. The Pishin Dam is an important dam in the eastern basin of Iran in the south of Sistan and Baluchestan province. This region faces severe water stress due to very low precipitation and very high evaporation on the one hand and the growing increase in urban, agricultural, and industrial demand on the other hand. The water development plans executed by the Ministry of Energy in the studied region influence water supply and demand profoundly. This research investigated the optimal allocation of water resources of this dam under management scenarios using the metaheuristic technique of the ant colony optimization algorithm (ACO). The results showed that the best value of the objective function was 82.3658 million m3. When applying the scenario of developing the cultivation area, the best value was obtained at 67.1258, which was significantly different from the base state. The results show that the ACO algorithm is suitable for the water resources of the Pishin Dam and can be used in planning and policymaking.

FDE-Net: A memory-efficiency densely connected network inspired from fractional-order differential equations for single image super-resolution

Dense connection has proved an effective way to take full advantage of hierarchical features extracted from low-resolution images using deep neural networks (DNNs) for single image super-resolution (SISR). However, existing densely connected networks are often manually designed and overly depended on practical experience, thus leading to suboptimal performance. Moreover, due to their complicated connections, they are memory-consuming and lack of interpretability. To address all these problems with one stone, we propose to construct a new densely connected network for SISR from a dynamic system perspective. Following this idea, we cast the hierarchical transformation of DNNs into the state evolution of a fractional-order dynamic system, which empowers us to automatically construct two interdependent densely connected modules based on the system solution rather manual design. They are a prediction module that controls the system to iteratively predict the next state, and a correction module that iteratively refines the predicted state to improve the prediction accuracy. With these two modules as backbone, we establish a Fractional-order Differential Equations-based network (FDE-Net) for SISR. Since the iterative computational manner requires both densely connected modules to be of the recurrent structure, FDE-Net is memory-efficiency and good interpretability. In addition, we analyze the existence and uniqueness of the solution for FDE to theoretically guarantee the feasibility of FDE-Net. Experiments on four SISR benchmark datasets demonstrate the superiority of FDE-Net over existing densely connected networks and other baselines in terms of generalization capacity, especially with limited memory.

Building Counter-Colonial Commemorative Landscapes through Indigenous Collective Remembering in Wānanga

Statues and monuments are permanent forms of commemoration that interpret and reconstruct public memory in colonial settler societies. Representation through memorialisation is attributed to a genealogy of Western collective remembering that reflects the values, narratives, and experiences of the dominant settler population. Yet, collective remembering and memory can change. This article reports on Indigenous collective remembering practices that were observed in a local government intervention in Aotearoa New Zealand. The Boulcott Memorial Research Project sought iwi Māori (Indigenous Māori tribes) perspectives of the battle of Boulcott’s Farm to change a one-sided colonial memorial that was erected to honour British militia who died in the conflict. Iwi kaipūrākau (representatives) from Te Ātiawa, Ngāti Tama, Ngāti Rangatahi, Ngāti Hāua, and Ngāti Toa Rangatira relayed their perspective of the battle through wānanga (a Māori oral tradition). In wānanga, kaipūrākau were perceived to remember relationally, outside colonial time, and through contemporary concerns and political interests, to advance tribal autonomy and self-determination. In this paper, I show how collective remembering in wānanga offers a counter-colonial ethic and intervention for building commemorative landscapes that can redirect public remembrance beyond the limitations of settler colonial memory and towards perspectives that are in tune with Indigenous peoples’ lived realities.

A limited memory subspace minimization conjugate gradient algorithm for unconstrained optimization

A limited memory subspace minimization conjugate gradient algorithm for unconstrained optimization

Design of an optimized sensor fault identification within the limited computing, memory, and energy capabilities

The main goal of this work is to design an optimized sensor-fault identification and diagnostic system for the Internet of Things (IoT) and Cyber-Physical Systems (CPS). The challenge is to accomplish this task within the sensors’ limited computing, memory, and energy capabilities. More importantly, identifying errors is time-sensitive, even though the diagnosis does not have to be made quickly. This project aims to provide an enhanced sensor-fault detection and diagnostic system for the IoT and CPS with constrained energy, memory, and computation resources. The system’s goals are to promptly detect defects, lessen the computing burden on sensors, and enhance the recall and accuracy of fault detection. This study used a hybrid approach that combined principal component analysis, autoencoder, and gated recurrent unit to create an optimal sensor-fault detection and diagnostic system. There were 1001 sensor readings in the dataset; 112 were defective, while the remaining 888 were normal. The investigation showed that the suggested method, which detected faults with an accuracy of 95% and recall of 92%, achieved high accuracy and recall in recognizing defects in IoT and CPS. With significantly shorter processing times, the system’s potential to reduce computational strain on sensors was also proved. The findings of this study indicate that the suggested optimized sensor-fault detection and diagnosis system successfully detects faults in IoT and CPS with limited computation, memory, and energy resources. The system’s ability to reduce the computing burden on sensors while improving accuracy and recall makes it an appealing choice for industrial and commercial applications.

An exhaustive review of the stream ciphers and their performance analysis

The number of internet of things (IoT) applications has increased, which has increased the demand for low-resource gadgets. The data produced by these devices must be protected to guarantee security. The devices operate in conditions with limited space, computational power, memory, and energy. High-security standards are difficult to achieve with limited resources. The detailed analysis of various stream ciphers and their performance metrics is reviewed in this manuscript. The functionality of the stream ciphers is categorized and thoroughly discussed based on both the hardware and software viewpoints. The security attacks and their countermeasure methods using stream ciphers are discussed. The performance metrics of most hardware-based stream ciphers, including the ECRYPT stream cipher project (eSTREAM) ciphers, are discussed. Each hardware stream cipher design highlights the hardware constraints such as chip area, frequency, throughput, and hardware efficiency. The work also highlights the various applications using these stream ciphers. The current trends using these stream ciphers are discussed with futuristic goals.

An improved limited memory-Sage Husa-cubature Kalman filtering algorithm for the state of charge and state of energy co-estimation of lithium-ion batteries based on hysteresis effect-dual polarization model

The accurate estimation of battery state of charge (SOC) and state of energy (SOE) are the key technologies in researching battery management systems. Due to the uncertainty of prior noise in practical engineering, traditional cubature Kalman filters (CKF) have lower filtering accuracy. This paper proposes an improved limited memory-Sage Husa-cubature Kalman (LM–SH–CKF) algorithm to estimate the SOC and SOE of lithium-ion batteries. During the filtering process, the Sage-Husa estimator is introduced to estimate the noise, correcting the statistical characteristics of the noise in real-time, thereby improving the estimation accuracy. Meanwhile, establish a filtering divergence criterion to determine whether the filtering is abnormal and ensure the real-time performance of the algorithm. To improve the accuracy of parameter identification, the Hysteresis Effect-Dual Polarization (HE-DP) model is established and the limited memory recursive least square (LMRLS) algorithm is proposed. The results show that the LM–SH–CKF has the smallest mean absolute error (MAE) and root mean square error (RMSE). Under the dynamic stress test (DST) at 15 °C, the estimated MAE and RMSE of SOC and SOE are both less than 1 %. The LM–SH–CKF has high accuracy and robustness, and short calculation time, providing a reference for battery status monitoring.

Optimize Memory usage of GO Applications by setting Memory Limit

Optimize Memory usage of GO Applications by setting Memory Limit

Nondefective Vacancy Enhanced Resistive Switching Reliability in Emergent van der Waals Metal Phosphorus Trisulfide-Based Memristive In-Memory Computing Hardware.

Two-dimensional-material-based memristors are emerging as promising enablers of new computing systems beyond von Neumann computers. However, the most studied anion-vacancy-enabled transition metal dichalcogenide memristors show many undesirable performances, e.g., high leakage currents, limited memory windows, high programming currents, and limited endurance. Here, we demonstrate that the emergent van der Waals metal phosphorus trisulfides with unconventional nondefective vacancy provide a promising paradigm for high-performance memristors. The different vacancy types (i.e., defective and nondefective vacancies) induced memristive discrepancies are uncovered. The nondefective vacancies can provide an ultralow diffusion barrier and good memristive structure stability giving rise to many desirable memristive performances, including high off-state resistance of 1012 Ω, pA-level programming currents, large memory window up to 109, more than 7-bit conductance states, and good endurance. Furthermore, a high-yield (94%) memristor crossbar array is fabricated and implements multiple image processing successfully, manifesting the potential for in-memory computing hardware.

Quantity and quality of memory and guesses in pattern recall of complex soccer scenarios

ABSTRACT In soccer, players need to keep in mind the locations of the ball and numerous teammates and opponents in complex scenarios. This study aimed to examine both the quantity and quality of players’ memory and guess in pattern recall for complex soccer scenarios. We developed an adapted pattern recall task in which participants were required to reproduce player locations in complex scenarios through two stages, allowing for the separation of memory from guesses and the subsequent analysis of accurate memory and false memory. The results showed that soccer athletes could maintain the locations of about eight players, along with the ball, in accurate memory for complex soccer scenarios, showing a greater quantity of accurate memory than non-athletes, whereas the precision of memory did not differ between the two groups. On the other hand, non-athletes falsely memorised the locations of a larger number of attacking players and tended to make more guesses about the locations of defending players than soccer athletes. Moreover, soccer athletes displayed superior precision when guessing player locations compared to non-athletes. These findings suggest that soccer athletes leverage their knowledge to enhance the chunking of individual players to be maintained in short-term memory and facilitate the inferences about player locations exceeding the limit of short-term memory, providing them with an advantage in both memory quantity and guess quality in complex soccer scenarios.