Increase In Hardware Cost Research Articles

Multispectral and hyperspectral image fusion via multi-model deep prior regularization

ABSTRACT Due to the difficulty of collecting a sufficient number of photons within a narrow spectral window, hyperspectral images often have low spatial resolution. In order to solve this problem without increasing hardware costs, a large number of image super-resolution algorithms have been proposed and have shown promising results. However, the performance of these algorithms is inconsistent in different datasets. To fix this situation, we proposed a multi-model deep prior regularization method for multispectral and hyperspectral image fusion. This method leverages mechanistic knowledge to combine various super-resolution results into a single algorithm, significantly improving the quality of the hyperspectral images. Specifically, we first proposed a variable residual mixed attention network. This network takes a low-resolution hyperspectral image and a high-resolution multispectral image as inputs, producing deep prior results from three different modes by adjusting spatial and channel attention. Then, we reconstructed the prior results along the spectral dimension and used them as regularization terms in our mechanistic model. We transformed the problem of finding the optimal solution of the model into solving the Sylvester equation and applied a fast solver for this equation to create the high-resolution hyperspectral images. Additionally, we used a genetic algorithm to determine the best hyperparameters for different deep prior results. Through validation on three datasets, we have demonstrated that our method performs better than existing methods in both quantitative and qualitative comparisons.

Glioma Identification Based on Digital Multimodal Spectra Integrated With Deep Learning Feature Fusion Using a Miniature Raman Spectrometer.

The miniature fiber Raman spectroscopy detection technology can reflect the properties of biomolecules through spectral characteristics and has the advantages of noninvasiveness, real-time, safety, label-free operation, and potential for early cancer diagnosis. This technology holds promise for developing portable, low-cost, intraoperative tumor detection instruments. Glioma is one of the most common malignant tumors of the central nervous system with rapid growth and a short disease course. However, the considerable heterogeneity of the glioma sample leads to substantial intraclass variance in collected spectra, coupled with the miniature Raman spectrometer's low signal-to-noise ratio. These factors diminish the accuracy of the brain glioma recognition model. To address this issue, a glioma identification method based on digital multimodal spectra integrated with deep learning features fusion (DMS-DLFF) using the miniature Raman spectrometer is proposed. Different from existing multimodal tumor detection methods employing multiple spectral instruments, DMS-DLFF enhances tumor identification accuracy without increasing hardware costs. The method mathematically decomposes the original spectra to Raman and fluorescence spectra, so as to augment the biospectral information. Then, the deep learning method is used to extract the feature information of the two kinds of spectra, respectively, and the digital multimodal spectral fusion is realized at the feature level. Moreover, a two-layer pattern recognition model is constructed based on the ensemble strategy, amalgamating the strengths of diverse classifiers. Meanwhile, the bagging strategy is introduced to improve support vector machine algorithms, one of the basic classifiers. Compared with traditional methodologies, DMS-DLFF operates at both the feature level and decision level, employing high-information-density feature vectors to train ensemble classification models for increasing overall recognition accuracy. This study collected 260 Raman spectra of glioma and 151 Raman spectra of normal brain tissue. The accuracy, sensitivity, and specificity were 91.9%, 96.7%, and 80.8%, respectively. The proposed method outperforms traditional algorithms in brain glioma detection, which helps doctors formulate precise surgical plans and thereby improve patient prognosis.

JOA‐GAN: An improved single‐image super‐resolution network for remote sensing based on GAN

AbstractImage super‐resolution (SR) has been widely applied in remote sensing to generate high‐resolution (HR) images without increasing hardware costs. However, SR is a severe ill‐posed problem. As deep learning advances, existing methods have solved this problem to a certain extent. However, the complex spatial distribution of remote sensing images still poses a challenge in effectively extracting abundant high‐frequency details from the images. Here, a single‐image super‐resolution (SISR) network based on the generative adversarial network (GAN) for remote sensing is presented, called JOA‐GAN. Firstly, a joint‐attention module (JOA) is proposed to focus the network on high‐frequency regions in remote sensing images to enhance the quality of image reconstruction. In the generator network, a multi‐scale densely connected feature extraction block (ERRDB) is proposed, which acquires features at different scales using MSconv blocks containing multi‐scale convolutions and automatically adjusts the features by JOA. In the discriminator network, the relative discriminator is used to compute the relative probability instead of the absolute probability, which helps the network learn clearer and more realistic texture details. JOA‐GAN is compared with other advanced methods, and the results demonstrate that JOA‐GAN has improved objective evaluation metrics and achieved superior visual effects.

Indoor unknown radio transmitter localization using improved RSSD and grey correlation degree

Abstract Accurate location of unknown radio transmitter (URT) is the key to secure wireless communication. Since the fingerprint positioning methods based on received signal strength difference (RSSD) can adapt to the diversity of transmitting power and frequency, RSSD has become a popular scheme for locating the unknown radio transmitter. However, the RSSD is obtained by subtracting the RSS from two different access points (APs), so the interference of noise on the RSS is inherited and amplified by the RSSD. Besides, the need for more APs to ensure positioning accuracy leads to an increase in hardware costs. In this paper, a RSSD-based fuzzy weight grey correlation degree positioning algorithm, called FUZZY-GREY, is proposed to reduce the interference of noise, save AP hardware cost and improve the positioning accuracy. Firstly, online RSSD vector is improved by using fuzzy weight to reduce the noise interference. Secondly, the RSSD-based grey correlation coefficient is designed to calculate the correlation degree of the corresponding RSSD and ensure data integrity. Finally, a RSSD-based grey correlation degree scheme combining with fuzzy weight is proposed to select optimal reference points (RPs). Simulation and experimental results show that the proposed algorithm has better positioning performance than weighted k-nearest neighbor (WKNN), maximum correlation coefficient estimation (MCORE), Naive Bayes and support vector machine (SVM) in the case of different selected K numbers, grid distances, noise levels and AP numbers.

Use of information redundancy to increase the reliability of devices for storing, processing and transmitting information

In modern information transmission systems, a special place is occupied by telecommunication systems (TS), which include digital data transmission systems (DSTS) containing specialized computers (SEVMs). The systems under consideration must ensure fast and reliable transmission of discrete data over communication lines. In this case, the loss of even one transmitted character is unacceptable; therefore, the main indicator of the reliability of a computer is the probability of failure-free operation. To increase the probability of failure-free operation of a storage device (MS), corrective codes and duplication are used, and to increase the probability of failure-free operation of the arithmetic-logical unit (ALU) of a computer, majority redundancy is used. The disadvantage of the majority method is the high hardware costs for redundancy, which reduces the efficiency of its use. The disadvantages of using correction codes include: as a rule, they are used for separate redundancy (detection and correction of errors that occur in storage devices; majority redundancy is used to detect and correct errors in the ALU); not all arithmetic and logical operations can be controlled based on existing correcting codes; a sharp increase in hardware costs when using algebraic linear codes to detect and correct multiple errors. Detection of errors in the ALU of a computer processor can be achieved on the basis of duplication in a loaded mode with replacement, however, this is associated with solving the main problem of computer duplication: - selection of monitoring tools for determining a failed channel (detection of errors in storage and information processing devices). The purpose of the research is to develop a scientific and methodological apparatus for computer backup using the duplication method with error detection in backup channels based on the use of an algebraic linear code, which makes it possible to detect errors not only in storage devices, but also adapted for detecting errors when performing arithmetic and logical operations. Results. An analysis of operation and selection of reliability indicators for specialized computers (SEVMs) of telecommunication systems was carried out. Requirements for computer backup methods are formulated. A comparative assessment of the detecting ability and hardware costs was carried out when implementing the majority redundancy method, the duplication method and the use of correcting codes. The expediency of using the duplication method is substantiated to increase the probability of failure-free operation and survivability of self-healing digital computers, using algebraic linear codes to determine the faulty channel, which allows to significantly reduce hardware costs for constructing monitoring equipment and use 10-30% of backup equipment for these purposes. It is proposed to use an algebraic linear code, in which, unlike well-known codes, the values of the check bits correspond to the direct and inverse values of the information bits, which makes it possible to detect errors when reading information from the inverse outputs of the memory, correct single errors, detect double errors and control the logical inversion operation , necessary to represent a negative number in two's complement code, which makes it possible to adapt the code to control arithmetic and logical operations of the computer processor. An assessment was made of the probability of failure-free operation of a duplicated computer, with its general redundancy, with detection and correction of single errors in the backup memory channels and detection of errors in the backup channels of the processor ALU based on the proposed code, and an assessment of the probability of failure-free operation of the computer, with its separate redundancy, with error detection in the backup channels of the duplicated memory based on the Hamming code and error correction in the backup channels of the processor ALU based on the majority method. A comparative assessment of the probabilities of failure-free operation allows us to conclude that the general redundancy of the computer based on the proposed code, in comparison with the separate redundancy of the memory and ALU of the computer processor, allows for a gain in the probability of failure-free operation of the computer and its functional devices throughout the entire period of operation. The practical significance lies in the fact that the proposed scientific and methodological apparatus provides: reduction of hardware costs for identifying a faulty channel when organizing duplication; detection of errors in the memory and ALU of the computer processor with time costs not exceeding the time of error detection when using standard methods of monitoring the computer system.

Low-biased probabilistic multipliers using complementary inaccurate compressors

This paper proposes low-biased probabilistic multipliers and applies the proposed designs to the inference stage of convolutional neural networks (CNNs). Highly inaccurate compressors in the probabilistic multiplier make the error distribution unbalanced and produce significant relative errors. We describe design rules for applying different compressors to the probabilistic multiplier. Besides, the proposed design rules enhance the error characteristics by determining the input values of each compressor, suppressing the significant relative error. Notably, motivated by the design rules, we propose a novel inaccurate 4:2 compressor suitable for our new design. The design rules and proposed 4:2 compressor are adopted in 8-bit probabilistic multipliers. The error analysis shows that the new designs can enhance error characteristics without increasing hardware costs. Furthermore, the proposed approximate multipliers are applied to the convolutional layers of CNNs. We describe the fine-tuning scheme to reduce the retraining time of approximation-aware training. The experiments show that proposed designs can produce acceptable classification results compared with those using the floating-point and 8-bit exact multiplications on CIFAR and ImageNet datasets.

Methane gas spectral imaging method based on dual wedge scanning mirrors

With the increase in the number of oil and gas pipelines laid in China, more attention needs to be paid to pipeline maintenance work. At present, the main methods of detecting natural gas leaks in oil and gas transmission stations include manual inspections, opposing natural gas detection equipment, and cloud desktop natural gas detection equipment. Hand held natural gas detection equipment is used for manual inspection, which requires regular manual inspection. However, the response speed is poor and gas leaks cannot be detected in a timely manner. The opposed laser gas detection method can only detect the presence of gas on the beam path. If a larger area of leakage detection is desired, more equipment needs to be installed, resulting in a greatly increase in hardware costs. The existing cloud desktop laser gas detection method controls the deflection of the laser beam through the cloud platform to achieve leak detection at various points in the area to be tested. However, the rotation speed of the cloud platform is slow, and a complete detection cycle takes dozens of minutes, and only the presence of gas can be detected. For accurate leak location, manual on-site survey is also required to further determine the leak location. In order to meet the needs of the real-time monitoring and rapid positioning of oil and gas pipeline leaks, in this work, a fast and accurately controlled dual wedge scanning mirror system is designed, which combines tunable semiconductor laser absorption spectroscopy technology to convert the gas measurement laser beam from point measurement to surface measurement, thereby obtaining the two-dimensional distribution of gas, which is conducive to subsequent analysis and positioning of gas leakage sources. By using the inverse solution iterative optimization algorithm, the angle of the wedge mirror is controlled to obtain an efficient and uniform beam scanning trajectory. The deflection direction and detection position of the laser beam are fused with the corresponding methane concentration information, and a methane concentration data containing position information is constructed. In order to quantitatively verify the measurement accuracy and spatial resolution in the experiment, a standard air bag is used to simulate the methane leakage distribution. The results show that the minimum detection limit of the system can be lower than 5×10<sup>–4</sup> m, and the spatial resolution can be less than 6 cm. At the same time, this method can adjust the scanning step node based on the measurement distance of the oil from gas station, thereby achieving adjustable imaging resolution. This imaging method provides a new idea for accurately positioning and detecting the methane leakage location and amount.

Using AI-Powered Vehicle Identification System in Gas Stations (AI-VIS)

In many countries around the world, retail fuel sales have to be recorded and monitored with specific vehicle information such as license plate by government institutions and station managers. Different hardware methods are utilized to achieve this goal such as UHF (Ultra high frequency) vehicle identification tags installed on the vehicles. To extract data from the tags, RFID-UHF antennas need to be installed on the nozzle for the recognition of vehicles today, which implies an increase in hardware costs per vehicle. Additionally, the electronic waste generated by the hardware used for vehicle recognition hurts the environment. In this study, the aim is to provide a comprehensive solution that enhances the modern automotive world's efficiency, security, and convenience. The core objective of this study is to design and implement a cutting-edge Vehicle Identification System (VIS) that leverages the power of Artificial Intelligence and Computer Vision. The proposed system has the ability to recognize various critical attributes of vehicles at gas stations, including the vehicle make, license plate, vehicle type, color, and fueling information. The system utilizes advanced Image Processing and Deep Learning techniques to achieve precise identification and classification, improving security, and law enforcement.

Training-Free Stuck-At Fault Mitigation for ReRAM-Based Deep Learning Accelerators

Although Resistive RAMs can support highly efficient matrix-vector multiplication, which is very useful for machine learning and other applications, the non-ideal behavior of hardware such as stuck-at fault and IR drop is an important concern in making ReRAM crossbar array-based deep learning accelerators. Previous work has addressed the nonideality problem through either redundancy in hardware, which requires a permanent increase of hardware cost, or software retraining, which may be even more costly or unacceptable due to its need for a training dataset as well as high computation overhead. In this paper we propose a very light-weight method that can be applied on top of existing hardware or software solutions. Our method, called FPT (Forward-Parameter Tuning), takes advantage of a certain statistical property existing in the activation data of neural network layers, and can mitigate the impact of mild nonidealities in ReRAM crossbar arrays for deep learning applications without using any hardware, a dataset, or gradientbased training. Our experimental results using MNIST, CIFAR-10, CIFAR-100, and ImageNet datasets in binary and multibit networks demonstrate that our technique is very effective, both alone and together with previous methods, up to 20rate, which is higher than even some of the previous remapping methods. We also evaluate our method in the presence of other nonidealities such as variability and IR drop. Further, we provide an analysis based on the concept of effective fault rate, which not only demonstrates that effective fault rate can be a useful tool to predict the accuracy of faulty RCA-based neural networks, but also explains why mitigating the SAF problem is more difficult with multi-bit neural networks.

Decompressor for hardware applications

The use of lossless compression in the application specific computers provides such advantages as minimized amount of memory, increased bandwidth of interfaces, reduced energy consumption, and improved self-testing systems. The article discusses known algorithms of lossless compression with the aim of choosing the most suitable one for implementation in a hardware-software decompressor. Among them, the Lempel-Ziv-Welch (LZW) algorithm makes it possible to perform the associative memory of the decompressor dictionary in the simplest way by using the sequential reading the symbols of the decompressed word. The analysis of the existing hardware implementations of the decompressors showed that the main goal in their development was to increase the bandwidth at the expense of increasing hardware costs and limited functionality. It is proposed to implement the LZW decompressor in a hardware module based on a microprocessor core with a specialized instruction set. For this, a processor core with a stack architecture was selected, which is developed by the authors for the tasks of the file grammar analyzing. Additional memory block for the dictionary storing and an input buffer which converts the byte stream of the packed file into a sequence of unpacked codes are added to it. The processor core instruction set is adjusted to both speed up decompression and reduce hardware costs. The decompressor is described by the Very high-speed integral circuit Hardware Description Language and is implemented in a field programable gate array (FPGA). At a clock frequency of up to two hundred megahertz, the average throughput of the decompressor is more than ten megabytes per second. Because of the hardware and software implementation, an LZW decompressor is developed, which has approximately the same hardware costs as that of the hardware decompressor and has a lower bandwidth at the costs of flexibility, multifunctionality, which is provided by the processor core software. In particular, a decompressor of the Graphic Interchange Format files is implemented on the basis of this device in FPGA for the application of dynamic visualization of patterns on the embedded system display

Monocular depth estimation network with single-pixel depth guidance.

Due to the scale ambiguity problem, the performance of monocular depth estimation (MDE) is inherently restricted. Multi-camera systems, especially those equipped with active depth cameras, have addressed this problem at the expense of increased hardware costs and space. In this Letter, we adopt a similar but cost-effective solution using only single-pixel depth guidance with a single-photon avalanche diode. To this end, we design a single-pixel guidance module (SPGM) that combines the global information from the single-pixel depth guidance with the spatial information from the image at the feature level. By integrating SPGMs into an MDE network, we introduce PhoMoNet, the first, to the best of our knowledge, end-to-end MDE network with single-pixel depth guidance. Experimental results show the effectiveness and superiority of PhoMoNet over state-of-the-art MDE networks on synthetic and real-world datasets.

RESEARCH ON THE PRINCIPLES OF ARTIFICIAL NEURAL NETWORK CONSTRUCTION AND PARAMETER MODELING

Studies show that neural networks with multilayer direct propagation have be-come more widespread, which is due to the simplicity of their implementation, the availability of advanced learning methods, and the parallel execution of calculations. In these networks, the computational complexity increases proportionally to the square of the data size, which leads to a decrease in performance and an increase in hardware costs. The main problems of synthesis of artificial neural networks, criteria for evaluating the effectiveness of artificial neural networks, issues of choosing layers and the number of neurons in each layer are investigated. In the work, the mean square error, mean absolute error and mean absolute percentage error criteria are considered for evaluating the efficiency of neural networks. In general, one hidden layer of a neu-ral network is sufficient for most problems, two hidden layers can represent a function of any shape, and adding a third and more layers results in very little improvement in network performance. Expressions are given for the total number of parameters de-pending on the number, and the number of inputs from the binary sequence, as well as the minimum and maximum values of the training examples depending on the total number of parameters and the number of outputs. The studies have shown that the se-lection of the statistical model efficiency evaluation criteria depends on the problem to be solved. The results of the simulations performed using the MATLAB package are presented.

Snapshot of Photovoltaics − May 2023

In 2022 the cumulative installed photovoltaic electricity generation capacity increased to over 1 TW, 10 years after it reached the 100 GW level in 2012. In 2022, overall investment in renewable energy has increased by 16% to USD 499 billion compared to USD 953 billion for fossil fuels, which saw an increase of 6%. Investments in solar photovoltaics accounted for USD 301.5 billion or 60% of the renewable energy investments. The annual installations of solar photovoltaic electricity generation systems increased by about 40% to over 230 GWp in 2022. Compared to 2021, the number of countries which installed 1 GWp/year or more has increased by almost 80% to 32. Despite the increase in hardware costs for solar photovoltaic systems and battery storage, both markets had a strong growth, driven by the soaring energy prices in 2022. The increase of the levelised costs for solar photovoltaic electricity was well below the increase of electricity generated with fossil fuels. The electrification of heating, transport and industry will create additional demand for renewable electricity, including solar, if we want to stay on track for not more than 1.5 °C global temperature increase.

Server Consolidation Algorithms for Cloud Computing

In recent years, companies and researchers have hosted and rented computer resources over ‎the ‎‎internet due to cloud computing, which led to an increase in the energy consumed by ‎data centers. This ‎‎consumption is considered one of the world's highest, ‎which pushed many ‎researchers to propose ‎several techniques such as server ‎consolidation (SC) to solve the‎‏ ‏trade‏-‏off‏ ‏‏‎between energy saving and ‎quality of service ‎‎(QoS). SC requires maintaining service level ‎agreements (SLA) violations and ‎minimizing ‎the number of active physical machines (PMs). ‎Furthermore, to achieve this balance and ‎‎avoid ‎increasing hardware costs, the SC challenge targets ‎placing new virtual machines ‎‎(VMs) in ‎suitable PMs. This work explored the existing SC algorithms ‎that include ‎CloudSim as a simulator ‎environment and PlanetLab as a dataset. The authors compared ‎the well-known optimization methods ‎and extracted the weaknesses of the main three deployed ‎‎approaches involved in the consolidation ‎process: bin-packing model, metaheuristics, ‎and machine ‎learning-based solutions.‎

P‐7.3: Research on Touch Input System Based on In‐Graphic Identification

In response to the high hardware requirements of traditional touch input systems, this paper proposes a new system for touch input based on In‐Graphic recognition. Unlike In‐Cell, On‐Cell and other hardware‐based touch input systems, this system uses the method of hiding the input information in the graphic (In‐Graphic), and then uses an algorithm to identify the content with the logo in the display image and complete the input function, which is a touch input system that relies on software algorithms. The system can make a medium to large size screen into a smart screen with touch input function with little increase in hardware cost, and realize a multi‐purpose screen, greatly enhancing the user experience.

Localization of Lamb wave source with a single transmitter-receiver combination by elastic metamaterials

Many nondestructive testing and structural health monitoring systems utilize Lamb wave transducer arrays for identification and localization of scattering wave sources. A large number of transducers are usually required during array signal processing and source localization, which increases hardware cost and reduces system reliability. To overcome this limitation, a metamaterial structure is designed in this study to realize source localization with a single transmitter-receiver combination. The basic design principle is the utilization of local resonators to customize propagation characteristics of Lamb waves. In particular, amplitude-frequency modulation and velocity dispersion are customized during metamaterial design. Uncorrelated amplitude-frequency modulation is extracted from signal frequency spectrum for orientation identification. Velocity dispersion is extracted from signal time-frequency spectrum for distance evaluation. After orientation identification and distance evaluation, wave source localization is then realized. Finally, the metamaterial structure is 3D printed using PA2200 nylon and bonded to the aluminum specimen to experimentally demonstrate the effectiveness of source localization with a single transmitter-receiver combination.

Attention mechanism feedback network for image super-resolution

The number of photosensitive elements in the image sensor determines the resolution of the original image. One promising method for increasing the resolution of an image without increasing hardware cost is image super-resolution. Many existing image super-resolution methods based on deep learning lack feedback mechanisms and deal with feature channels equally, which hinders the expressive ability of deep learning networks and makes it difficult to resolve the dependence between high- and low-resolution (LR) images. An image super-resolution method based on an attention mechanism feedback network was presented in this study. First, the proposed multiscale separable convolution layer is used to extract the characteristics of the input image. Second, a feedback module is designed to process the feedback connections between subnetworks and generate richer high-level representations through densely connected upper and lower projection units, enabling the recovery of high-resolution (HR) images from LR images. Subsequently, an attention mechanism is introduced in the feedback module to redistribute channel attention resources, enhance interdependence between channels, and focus the network on learning high-frequency information. Finally, the reconstructed image was gradually generated using the reconstruction layer through an iterative network. The experimental results for ×2 to ×8 image super-resolution on five standard datasets showed that the quality of the reconstructed image of the proposed method outperforms that of the comparative image super-resolution methods in terms of subjective perception and objective evaluation indices. It can retain more detail for super-resolution and obtain better HR images.

Authenticated encryption chip implementation against side-channel attack

An authenticated encryption chip with novel nonce generation circuit was developed. This circuit associates the nonce generation with the contents and receiving time of plaintext. It will also generate overlapping power compensation for the whole chip. The integrated chip was fabricated under SMIC 180nm technology. Under 1.8V VDD, 100MHz global clock, the power consumption is about 14mW within 50k gates. The test result exhibits more than 10 times the strength in resistance to side-channel attack than the unprotected version without increasing hardware cost.

Polarization Estimation With Vector Sensor Array in the Underdetermined Case

Ship target detection using radar is an important application in military and civilian fields. For the polarization estimation of scattering waves in the underdetermined case, i.e., the number of scattering waves from ships is larger than the number of sensors, this paper proposes two estimation methods with different measurement models. 1) For the single-vector-sensor model, this paper proposes the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">polarization-invariant</i> ESPRIT-based method. This method can estimate the polarization of signals containing target echo, interference, and noise, which can cure the problem that the accuracy of existing method is poor under low interference signal ratio. 2) For the multi-vector-sensor model, this paper proposes an improved ESPRIT method based on the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">spatial-invariant and time-invariant</i> simultaneously, which can increase the degree of freedom without increasing hardware cost. As for another problem of multi-vector-sensor, i.e., almost all existing methods assume that the number of scattering waves is known, this paper introduces <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">the polarization spectrum</i> for the first time, which can estimate the polarization parameters when the number of scattering waves is unknown. Finally, we analyze the two proposed ESPRIT-based methods comparing with some existing methods through Monte Carlo simulation, which results demonstrate the efficience of the proposed methods.

In-/Near-Memory Computing

This book provides a structured introduction of the key concepts and techniques that enable in-/near-memory computing. For decades, processing-in-memory or near-memory computing has been attracting growing interest due to its potential to break the memory wall. Near-memory computing moves compute logic near the memory, and thereby reduces data movement. Recent work has also shown that certain memories can morph themselves into compute units by exploiting the physical properties of the memory cells, enabling in-situ computing in the memory array. While in- and near-memory computing can circumvent overheads related to data movement, it comes at the cost of restricted flexibility of data representation and computation, design challenges of compute capable memories, and difficulty in system and software integration. Therefore, wide deployment of in-/near-memory computing cannot be accomplished without techniques that enable efficient mapping of data-intensive applications to such devices, without sacrificing accuracy or increasing hardware costs excessively. This book describes various memory substrates amenable to in- and near-memory computing, architectural approaches for designing efficient and reliable computing devices, and opportunities for in-/near-memory acceleration of different classes of applications.