Small Amount Of Memory Research Articles

Hybrid LBM-FVM solver for two-phase flow simulation

In this paper, we introduce a hybrid LBM-FVM solver for two-phase fluid flow simulations in which interface dynamics is modeled by a conservative phase-field equation. Integrating fluid equations over time is achieved through a velocity-based lattice Boltzmann solver which is improved by a central-moment multiple-relaxation-time collision model to reach higher accuracy. For interface evolution, we propose a finite-volume-based numerical treatment for the integration of the phase-field equation: we show that the second-order isotropic centered stencils for diffusive and separation fluxes combined with the WENO-5 stencils for advective fluxes achieve similar and sometimes even higher accuracy than the state-of-the-art double-distribution-function LBM methods as well as the DUGKS-based method, while requiring less computations and a smaller amount of memory. Benchmark tests (such as the 2D diagonal translation of a circular interface), along with quantitative evaluations on more complex tests (such as the rising bubble and Rayleigh-Taylor instability simulations) allowing comparisons with prior numerical methods and/or experimental data, are presented to validate the advantage of our hybrid solver. Moreover, 3D simulations (including a dam break simulation) are also compared to the time-lapse photography of physical experiments in order to allow for more qualitative evaluations.

Data Communication for Low Resources IoT Devices: RS485 Over Electrical Wires

The Internet of Things is a paradigm that has been widely deployed in various areas, connecting commonly used devices, from home to industry and health, among others. IoT devices generally have a small amount of memory, low processing resources, and it is often required that they have low energy consumption. Therefore, one objective of this research is to try to take advantage of a classic cable communications standard, RS485, so as to allow the connection of simple devices to the TCP/IP network through an intermediary node. Thus, the IoT device would only require an asynchronous serial port and an interface to the electrical network. To that end, data transmission tests have been carried out over interfaces based on the THVD8000 integrated circuit. The achieved results encourage to continue working on this issue.

Subspace Culling for Ray-Box Intersection

Ray tracing is an essential operation for realistic image synthesis. The acceleration of ray tracing has been studied for a long period of time because algorithms such as light transport simulations require a large amount of ray tracing. One of the major approaches to accelerate the intersections is to use bounding volumes for early pruning for primitives in the volume. The axis-aligned bounding box is a popular bounding volume for ray tracing because of its simplicity and efficiency. However, the conservative bounding volume may produce extra empty space in addition to its content. Especially, primitives that are thin and diagonal to the axis give false-positive hits on the box volume due to the extra space. Although more complex bounding volumes such as oriented bounding boxes may reduce more false-positive hits, they are computationally expensive. In this paper, we propose a novel culling approach to reduce false-positive hits for the bounding box by embedding a binary voxel data structure to the volume. As a ray is represented as a conservative voxel volume as well in our approach, the ray--voxel intersection is cheaply done by bitwise AND operations. Our method is applicable to hierarchical data structures such as bounding volume hierarchy (BVH). It reduces false-positive hits due to the ray--box test and reduces the number of intersections during the traversal of BVH in ray tracing. We evaluate the reduction of intersections with several scenes and show the possibility of performance improvement despite the culling overhead. We also introduce a compression approach with a lookup table for our voxel data. We show that our compressed voxel data achieves significant false-positive reductions with a small amount of memory.

Fuzzy based optimized itemset mining in high dimensional transactional database using adaptable FCM

One of the extremely deliberated data mining processes is HUIM (High Utility Itemset Mining). Its applications include text mining, e-learning bioinformatics, product recommendation, online click stream analysis, and market basket analysis. Likewise lot of potential applications availed in the HUIM. However, HUIM techniques could find erroneous patterns because they don’t look at the correlation of the retrieved patterns. Numerous approaches for mining related HUIs have been presented as an outcome. The computational expense of these methods continues to be problematic, both in terms of time and memory utilization. A technique for extracting weighted temporal designs is therefore suggested to rectify the identified issue in HUIM. Preprocessing of time series-based information into fuzzy item sets is the first step of the suggested technique. These feed the Graph Based Ant Colony Optimization (GACO) and Fuzzy C Means (FCM) clustering methodologies used in the Improvised Adaptable FCM (IAFCM) method. The suggested IAFCM technique achieves two objectives: optimal item placement in clusters using GACO; and ii) IAFCM clustering and information decrease in FCM cluster. The proposed technique yields high-quality clusters by GACO. Weighted sequential pattern mining, which considers facts of patterns with the highest weight and low frequency in a repository that is updated over a period, is used to locate the sequential patterns in these clusters. The outcomes of this methodology make evident that the IAFCM with GACO improves execution time when compared to other conventional approaches. Additionally, it enhances information representation by enhancing accuracy while using a smaller amount of memory.

Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm

ABSTRACT The Feldkamp, Davis and Kress algorithm is a computationally efficient reconstruction method for three-dimensional cone-beam computed tomography. However, it suffers from severe artefacts when the number of projections is insufficient. Although recent deep learning–based methods have succeeded in reconstructing such sparse-view projections, it is still challenging to reconstruct a large 3D volume efficiently because of heavy memory consumption and difficulty in obtaining sufficient training data. Therefore, we propose a deep learning method to overcome these drawbacks. Our method consecutively reconstructs short bars in 3D CT volume using the intensities of pixels on the moving trajectory projected on the detector of these bars. Then, we feed such pixel intensities into a neural network and train it to simulate the filtering and back-projection processes of the FDK algorithm. Since the reconstruction volume is separated into bars, the neural network can be used with only a small amount of memory. Furthermore, the network can be trained sufficiently with only a few training samples because plenty of bar data can be extracted even from a single CT image. We experimentally demonstrate that our approach works efficiently for both simulated and actual sparse-view CBCT data using training data extracted from only a single CT image.

Optimal vs rotation heuristics in the role of cluster-head for routing in IoT constrained devices

Wireless Sensor Networks (WSNs) are crucial for implementing the Internet of Things (IoT) vision. A WSN can include distributed devices that can be battery powered, have a small amount of memory, have limited CPU processing capabilities and limited transmission range. WSNs are categorised into two main types that are homogeneous and heterogeneous. Homogeneous WSNs are composed of nodes that are all equal while heterogeneous ones are composed of nodes that can have different transmission rate and different initial energy. Collecting data in an energy efficient manner is one of the main goals when building wireless sensor networks since devices are battery powered and battery replacement can be difficult or impossible to be performed. Clustering protocols are one of the main approaches that have been used in order to collect data in an energy efficient way. A clustering protocol groups nodes into a set of clusters. Each cluster has a representative node that is referred to as Cluster Head (CH). This collects data from its cluster members and forwards them to an external Base Station, possibly in a multi-hop way among cluster heads. A rotation strategy for electing the cluster head is often used together with clustering in order to prolong the network lifetime. Rotation eliminates the overhead traffic that is needed for leader election and cluster formation since the old cluster heads directly designate new ones. In this work, we describe an Optimum Rotation Scheduling (ORS) that uses Integer Linear Programming in order to find the optimum rotation strategy. ORS assumes the WSN clusters are already formed by using some clustering protocol. A novel integer linear programming formulation is then used in order to define a cluster head rotation that produces the optimum cluster lifetime. Comparisons with existing heuristics and the provided optimum are then shown and discussed by means of extended simulations involving both homogeneous and heterogeneous WSNs.

Joint leaf-refinement and ensemble pruning through L_1 regularization

Ensembles are among the state-of-the-art in many machine learning applications. With the ongoing integration of ML models into everyday life, e.g., in the form of the Internet of Things, the deployment and continuous application of models become more and more an important issue. Therefore, small models that offer good predictive performance and use small amounts of memory are required. Ensemble pruning is a standard technique for removing unnecessary classifiers from a large ensemble that reduces the overall resource consumption and sometimes improves the performance of the original ensemble. Similarly, leaf-refinement is a technique that improves the performance of a tree ensemble by jointly re-learning the probability estimates in the leaf nodes of the trees, thereby allowing for smaller ensembles while preserving their predictive performance. In this paper, we develop a new method that combines both approaches into a single algorithm. To do so, we introduce L_1 regularization into the leaf-refinement objective, which allows us to jointly prune and refine trees at the same time. In an extensive experimental evaluation, we show that our approach not only offers statistically significantly better performance than the state-of-the-art but also offers a better accuracy-memory trade-off. We conclude our experimental evaluation with a case study showing the effectiveness of our method in a real-world setting.

In-Network Processing of Skyline Join Queries in Wireless Sensor Networks Using Synopses of Skyline Attribute Value Ranges.

We investigate the in-network processing of a skyline join query in wireless sensor networks (WSNs). While much research was conducted on processing skyline queries in WSNs, skyline join queries were dealt with only in traditional centralized or distributed database environments. However, such techniques cannot be applied to WSNs. Carrying out join filtering, as well as skyline filtering using them in WSNs, is infeasible due to limited memory in senor nodes and to excessive energy consumption in wireless communications. In this paper, we propose a protocol to process a skyline join query in WSNs energy efficiently with only a small amount of memory in each sensor node. It uses a synopsis of skyline attribute value ranges, which is a very compact data structure. The range synopsis is used both in the search of anchor points for skyline filtering and in 2-way semijoins for join filtering. We describe the structure of a range synopsis and present our protocol. To optimize our protocol, we solve some optimization problems. Through implementation and a set of detailed simulations, we show the effectiveness of our protocol. The range synopsis is confirmed to be compact enough for our protocol to work well with the limited memory and energy in each sensor node. For the correlated and random distributions, our protocol significantly outperforms other possible protocols, confirming the effectiveness of an in-network skyline as well as the join filtering capabilities of our protocol.

K-means-G*: Accelerating k-means clustering algorithm utilizing primitive geometric concepts

The k-means is the most popular clustering algorithm, but, as it needs too many distance computations, its speed is dramatically fall down against high-dimensional data. Although, there are some quite fast variants proposed in literature, but, there is still much room for improvement against high-dimensional large-scale datasets.What proposed here, k-means-g*, is based on a simple geometric concept. For four distinct points, if distance between all pairs except one pair are known, then, a lower bound can be determined for the unknown distance. Utilizing this technique in the assignment step of the k-means, many high-dimensional distance computations can be easily ignored, where small amount of memory is used.Both theoretical and experimental results approves speed of the k-means-g* against recently published fast variants. For over than 50 cases, out of 70 cases of performed experiments, it is faster than other algorithms. The C++ source code for k-means-g* is publicly available.

SP-SLAM: Surfel-Point Simultaneous Localization and Mapping

In this article, a novel method for simultaneous localization and mapping (SLAM) named surface elements (surfel) point SLAM (SP-SLAM) is proposed using an RGB-D camera. The key idea of SP-SLAM is to use not only keypoints but also surfels as features to cope with both high texture and low texture environments. By decomposing a surface into a small number of surfels, the method can represent spacious environments using a relatively small amount of memory. To optimize the poses of points, surfels, and cameras altogether, new objective functions are proposed, and a new bundle adjustment using these objective functions is developed. The proposed SP-SLAM runs in real time on a central processing unit as in other feature-based visual SLAM methods but works better than them not only in high texture but also in low texture environments, overcoming well-known drawbacks of feature-based visual SLAM with degradation in low texture environments. The proposed method is applied to benchmark datasets and its effectiveness is demonstrated by comparing against those of previous methods in terms of localization accuracy.

Data stream clustering for low-cost machines

Nowadays, the operations performed by the Internet of Things (IoT) systems are no more trivial since they rely on more sophisticated devices than in the past. The IoT system is physically composed of connected computing, digital, mechanical devices such as sensors or actuators. Most of the time, each of them incorporates a logical arithmetic unit that can pre-compute or compute on the device. To extract value from the data produced at the edge, processing power offered by cloud computing is still utilized. However, streaming data to the cloud exposes some limitations related to the increased communication and data transfer, which introduces delays and consumes network bandwidth. Clustering data is one example of a treatment that can be executed in the cloud. In this paper, we propose a methodology for solving the data stream clustering problem at the edge. Data Stream clustering is defined as the clustering of data that arrive continuously, such as telephone records, multimedia data, sensors data, financial transactions, etc. Since we use low-cost and low-capacity devices, the objective is, given a sequence of points, to construct a good clustering of the stream using a small amount of memory and time. We propose a ‘windowing’ scheme, coupled with a sampling scheme to respect the objective. Under the experimental conditions, experiments show that the clustering solutions can be controlled, with difficulties for time-stamped data but not for random data or data with well-delimited clusters. The main advantage of our schema is that we are clustering data “on the fly” with no knowledge or assumption regarding the available data. We do not assume that all the data are known before a treatment batch by batch. Our schema also has the potential to be adapted to other classes of machine learning algorithms.

Smart City Rail Automatic Fare Collection System Under the Background of Big Data

With the rapid development of Internet technology, the process of urban construction is accelerating and the level of urbanization is further improved. In the smart city rail automatic fare collection system, there are a large number of data information and data that need to be processed manually. The traditional manual method not only consumes human, material and financial resources, but also has low efficiency. Therefore, this paper proposes a smart city rail automatic fare collection system based on big data design. Firstly, this paper expounds the concept of smart city rail transit and studies the function of automatic fare collection system. Then it studies the definition and characteristics of big data, designs the method of system development, and tests the performance of the system. The test results show that the system runs smoothly, accounts for a relatively small amount of memory, has a fast response speed and low delay. Most passengers are satisfied with the system.

Identifying Hierarchies for Fast Optimal Search

For some search problems, the graph is known beforehand and there is time to preprocess the graph to make the search faster. One such example is video games, where one can often preprocess maps before a game is released or while a map is loaded into memory. The data produced by preprocessing should use only a small amount of memory, and, in case they are generated during runtime, preprocessing should be fast. Search with Subgoal Graphs (Uras, Koenig, and Hernandez 2013) was a non-dominated optimal path-planning algorithm in the Grid-Based Path Planning Competitions 2012 and 2013. During a preprocessing phase, it computes a Simple Subgoal Graph from a given grid, which is analogous to a visibility graph for continuous terrain, and then partitions the vertices into global and local subgoals to obtain a Two-Level Subgoal Graph. During the path-planning phase, it performs an A* search over the subgoal graph that ignores local subgoals that are not relevant to the search, which significantly reduces the size of the graph being searched. This paper is an abstract of (Uras and Koenig 2014), which generalizes this partitioning process to any undirected graph and shows that it can be recursively applied to generate more than two levels, which reduces the size of the graph being searched even further. We call these graphs N-Level Graphs.

Titchy: Online Time-Series Compression With Random Access for the Internet of Things

We introduce Titchy, which is a compression method for time-series data generated by the Internet of Things. Our proposed method is flexible and has several advantages when applied in the IoT ecosystem: 1) it is able to compress even when only a small amount of memory can be allocated to it; 2) it compresses data in tiny chunks, so it introduces very little latency during online operation and thus, enables frequent and timely updates with compressed data; and 3) it facilitates efficient data storage and retrieval by enabling low-cost random access to the compressed data, eliminating the need to decompress large chunks when only a small amount of data is requested. To evaluate each of these advantages, we have implemented the compressor and conducted extensive experiments with long-term real-world data captured over days or weeks. We also present results for seven state-of-the-art compression methods to act as a baseline. Our evaluation shows that Titchy not only outperforms all seven on random access capability and for frequent transmissions but also provides great compression ratios as well as high compression and decompression speeds.

Cryptographic algorithm for protection of communication in drones control

The paper below presents an optimised cryptographic algorithm, designed to protect communication in the management of drones. In this communication the need for the data to be protected as much as possible and (in case) stored reliably rises. The use of microcontrollers requires an optimised algorithm in terms of number and type of operations, due to lower computing power and a small amount of memory. The algorithm is built on DES algorithm, according to the Feistel scheme. It is a 64-bits symmetric block cryptographic algorithm, using a 512-bits cryptographic key.

Methods for constructing effective neural networks for low-power systems

Formulation of the problem. The problem of using large neural networks with complex architectures on modern devices is considered. They work well, but sometimes their speed is unacceptably low and the amount of memory required to place them on the device is not always available. Briefly describes how to solve these problems by using pruning and quantization. It is proposed to consider an unconventional type of neural networks that can meet the requirements for the occupied memory space, speed and quality of work and describe approaches to training this type of networks. The aim of the work is to describe modern approaches to reducing the size of neural networks with minimal loss of the quality of their work and to propose an alternative type of networks of small size and high accuracy. Results. The proposed type of neural network has a large number of advantages in terms of the size and flexibility of layer settings. By varying the parameters of the layers, you can control the size, speed and quality of the network. However, the greater accuracy, the greater the memory volume. To train such a small network, it is proposed to use specific techniques that allow learning complex dependencies based on a more complex and voluminous network. As a result of this learning procedure, it is assumed that only a small network is used, which can then be placed on low-power devices with a small amount of memory. Practical significance. The described methods allow the use techniques to reduce the size of networks with minimal loss of quality of their work. The proposed architecture makes it possible to train simpler networks without using their size reduction techniques. These networks can work with various data, be it pictures, text, or other information encoded in a numerical vector.

A Mechanism to Secure the Transaction of IoT Devices Using Blockchain Technology

Currently, Internet of Things (IoT) is one of the rapidly growing technologies. It becomes popular because IoT devices are helpful in day to day work of humans. IoT devices have a small amount of memory, computation power, and energy by which they work like smart devices. Due to fewer resources, it is very difficult to apply any security mechanism efficiently, which makes these devices vulnerable and easy target to the attacker. Thus, there is a need for an efficient mechanism to secure the data of IoT devices from attackers. Blockchain technology is popular for providing security in a decentralized environment and it uses the distributed database. In this study, a mechanism is designed to secure the transactions of IoT devices using Blockchain technology. This mechanism will help to protect the data of IoT devices from unauthorized access.

CATTmew: Defeating Software-Only Physical Kernel Isolation

All the state-of-the-art rowhammer attacks can break the MMU-enforced inter-domain isolation because the physical memory owned by each domain is adjacent to each other. To mitigate these attacks, physical domain isolation, introduced by CATT, physically separates each domain by dividing the physical memory into multiple partitions and keeping each partition occupied by only one domain. CATT implemented physical kernel isolation as the first generic and practical software-only defense to protect kernel from being rowhammered as kernel is one of the most appealing targets. In this paper, we develop a novel exploit that could effectively defeat the physical kernel isolation and gain both root and kernel privileges. Our exploit can work without exhausting the page cache or the system memory, or relying on the information of the virtual-to-physical address mapping. The exploit is motivated by our key observation that the modern OSes have double-owned kernel buffers (e.g., video buffers and SCSI Generic buffers) owned concurrently by the kernel and user domains. The existence of such buffers invalidates the physical kernel isolation and makes the rowhammer-based attack possible again. Existing conspicuous rowhammer attacks achieving the root/kernel privilege escalation exhaust the page cache or even the whole system memory. Instead, we propose a new technique, named memory ambush. It is able to place the hammerable double-owned kernel buffers physically adjacent to the target objects (e.g., page tables) with only a small amount of memory. As a result, our exploit is stealthier and has fewer memory footprints. We also replace the inefficient rowhammer algorithm that blindly picks up addresses to hammer with an efficient one. Our algorithm selects suitable addresses based on an existing timing channel.

First encounters on Bethe lattices and Cayley trees

In this work we consider the first encounter problems between a fixed and/or mobile target A and a moving trap B on Bethe lattices and Cayley trees. The survival probabilities (SPs) of the target A on the both kinds of structures are considered analytically and compared. On Bethe lattices, the results show that the fixed target will still prolong its survival time, whereas, on Cayley trees, there are some initial positions where the target should move to prolong its survival time. The mean first encounter time (MFET) for mobile target A is evaluated numerically and compared with the mean first passage time (MFPT) for the fixed target A. Different initial settings are addressed and clear boundaries are obtained. These findings are helpful for optimizing the strategy to prolong the survival time of the target or to speed up the search process on Cayley trees, in relation to the target’s movement and the initial position configuration of the two walkers. We also present a new method, which uses a small amount of memory, for simulating random walks on Cayley trees.

A guided FP-Growth algorithm for mining multitude-targeted item-sets and class association rules in imbalanced data

Identifying frequent item-sets is a popular data-mining task. It consists of finding sets of items frequently appearing in data. Yet, finding all frequent item-sets in large or dense datasets may be time-consuming, and a user may be interested merely in some specific item-sets rather than all of them. Recently, methods have been proposed for targeted item-set mining; that is to calculate the support of some item-sets of interest. Though this approach is often more suitable for real applications than traditional item-set mining approaches, performance remains an issue. To address that issue, this paper presents a novel algorithm for multitude-targeted mining, named Guided Frequent Pattern-Growth (GFP-Growth). The GFP-Growth algorithm is designed to quickly mine a given set of item-sets using a small amount of memory. This paper proves that GFP-Growth yields the exact frequency-counts for each item-set of interest. It further shows that GFP-Growth can boost the performance for several problems requiring item-set mining. We specifically study the problem of generating minority-class rules from imbalanced data and develop the Minority-Report Algorithm (MRA) that uses GFP-Growth to solve this problem efficiently. We prove several theoretical properties of MRA and present experimental results showing substantial performance gain.