MAP Decoder Research Articles

Robust Indoor Positioning with Smartphone by Utilizing Encoded Chirp Acoustic Signal.

Recently, indoor positioning has been one of the hot topics in the field of navigation and positioning. Among different solutions on indoor positioning, positioning with acoustic signals has its promise due to its relatively high accuracy in the line of sight scenarios, low cost, and ease of being implemented in smartphones. In this work, a novel acoustic positioning method, called RATBILS, is proposed, in which encoded chirp acoustic signals are modulated and transmitted by different acoustic base stations. The smartphones receive the signals and perform the following three steps: (1) preprocessing; (2) time of arrival (TOA) estimation; and (3) time difference of arrival (TDOA) calculation and location estimation. In the preprocessing stage, we use band pass filters to filter out low-frequency noise from the environment. At the same time, we perform a signal decoding function in order to lock onto the positioning source. In the TOA estimation stage, we conduct both coarse and fine detection to enhance the accuracy and robustness of TOA estimation. The primary goal of coarse detection is to establish a noise range for fine detection. The main objective of fine detection is to emphasize the intensity of the first arrival diameter and resistance with multipath and non-line-of-sight (NLOS) caused by human body obstruction. In the TDOA calculation and location estimation stage, we estimate the TDOA based on the TOA estimation and then use the TDOA results for position estimation. In order to evaluate the performance of the proposed RATBILS system, two indoor field tests are carried out. The test results show that the RATBILS system achieves a positioning error of 0.23 m at 92% in region 1 of scene 1 and is superior to the traditional threshold method. The RATBILS system achieves a positioning error of 0.56 m at 92% in region 2 of scene 1 and is superior to the traditional threshold method. In scene 2, the maximum average positioning error was 1.26 m, which is better than the 3.33 m and 3.87 m of the two traditional threshold methods.

Dental Caries Segmentation using Deformable Dense Residual Half U-Net for Teledentistry System

Clinical practitioners’ workload and challenges are significantly reduced by classifying, predicting, and localizing lesions or dental caries. In recent research, a high-reliability diagnostic system within deep learning models has been implemented in a clinical teledentistry system. In order to construct an efficient, precise, and lightweight deep learning architecture, it is dynamically structured. In this paper, we present an efficient, accurate, and lightweight deep learning architecture for augmenting spatial locations and improving the transformation modeling abilities of fixed-structure CNNs. Deformable Dense Residual (DDR) enhances the efficacy of the residual convolution block by optimizing its structure, thereby mitigating model redundancy and ameliorating the challenge of vanishing gradients encountered during the training stages. DDR Half U-Net presents notable advancements to the simplified U-Net framework across three pivotal domains: the encoder, decoder, and loss function. Specifically, the encoder integrates deformable convolutions, thereby enhancing the model's capacity to discern features of diverse scales and configurations. In the decoder, a sophisticated arrangement of dense residual connections facilitates the fusion of low-level and high-level features, contributing to comprehensive feature extraction. Moreover, the utilization of a weight-adaptive loss function ensures equitable consideration of both caries and non-caries samples, thereby promoting balanced optimization during training.

Logic Computing Field-Effect Transistors Based on a Monolayer WSe2 Homojunction for the Semi-adder and Decoder.

Two-dimensional reconfigurable field-effect transistors (FETs) are promising candidates for next-generation computing hardware. However, exploring the cascade design of FETs for logic computing remains challenging. Here, by using density functional theory combined with the nonequilibrium Green's function method, we design a 5 nm split-gate FET based on a monolayer WSe2 homojunction, which can implement dynamic polarity control in different gate configurations. The series array of two FETs shows a functional family of logic gates (NOR, AND, XOR, A̅B, and AB̅), and the semi-adder designed by the logic functions AND and XOR reduces the number of transistors by 66.7%. The parallel array of two FETs demonstrates reconfigurable logic gates with NAND/OR/A̅+B/A+B̅ quadruple functions, which can realize the decoding function of 00-11 in the decoder. The cascade design of the electrically tunable FETs helps to tackle the logic device downscaling and integration dilemmas.

A biased random-key genetic algorithm for the knapsack problem with forfeit sets

This work addresses the Knapsack Problem with Forfeit Sets, a recently introduced variant of the 0/1 Knapsack Problem considering subsets of items associated with contrasting choices. Some penalty costs need to be paid whenever the number of items in the solution belonging to a forfeit set exceeds a predefined allowance threshold. We propose an effective metaheuristic to solve the problem, based on the Biased Random-Key Genetic Algorithm paradigm. An appropriately designed decoder function assigns a feasible solution to each chromosome, and improves it using some additional heuristic procedures. We show experimentally that the algorithm outperforms significantly a previously introduced metaheuristic for the problem.

Digital Image Forgery Detection And Localization Using The Innovated U-Net

A reliable image copy–move forgery detection approach adaptable to different scenarios of tampering with color images is crucial for many applications. Different methods and solutions have been effectively proposed, but they are still subject to false positive/negative detections and cannot handle the variety of copy–move forgeries. In this paper, a machine learning model that combines ResNet 50 and U-net architectures for automatic image forgery detection in color image(s) is presented. The proposed system is inspired by the ResNet 50 architecture as an encoder and the U-Net architecture as a decoder. The encoder function implies applying convolution and normalizing for feature extraction. Conversely, the decoder functions is locating the spatial features. The decoder in the U-Net network comprises multiple decoder blocks, which are connected to corresponding encoder blocks by employing concatenate layers. A binary mask is then produced to represent the tampered regions in the image. Quantitative experimental results on two standard public datasets and a comparison with state-of-the-art methods demonstrate the effectiveness and robustness of the proposed model.

Extraction of crop canopy features and decision-making for variable spraying based on unmanned aerial vehicle LiDAR data

Implementation of precision agriculture aerial applications using unmanned aerial vehicles (UAVs) represents a pivotal technological aspect in precision agriculture. However, current UAV applications are still far from realizing true precision variable spraying. The use of UAVs to analyze and model crop growth, pest and disease conditions, and other pertinent information to enable targeted precision spraying poses a formidable challenge. Herein, a UAV variable-rate spray system with adaptive flow control based on crop canopy morphology was developed using a UAV equipped with a light detection and ranging (LiDAR) sensor to support precision spraying of cotton. Point cloud data captured by the LiDAR sensor initially undergo processing using the simple morphological filter (SMRF) algorithm and feature extraction function. Subsequently, cotton canopy volumes measured by the alpha shape algorithm, convex hull by slices shape algorithm, and voxel-based method were compared with manual measurements with coefficient of determination R2 values of 0.89, 0.78, and 0.82, respectively. The results of the validation experiments denote that the cotton canopy volume obtained using the alpha shape algorithm is in good agreement with that obtained using manual measurements; thus, this algorithm is employed for volume calculations in this design. Models were constructed to relate UAV flight parameters, cotton canopy volume, and spraying parameters to the duty cycle of variable control signals, which enabled the UAV to adjust the flow rate in real time to match the cotton canopy structure. In addition, a polygonal prescription map decoding algorithm based on the cotton canopy morphology was introduced. This algorithm is used for real-time decoding of prescription maps and extraction of flow, latitude, and longitude information. Finally, field experiments were conducted, and the results indicate that the UAV variable-rate spray system designed in this study exhibits biological efficacy (effective application thresholds provided by the pesticide manufacturer) comparable to that of the constant-rate spray system at a lower application rate. Furthermore, it exhibited superior spray deposition efficiency and coverage compared with the constant-rate spray system. Notably, the use of the variable-rate spray system in cotton crops resulted in a 43.37% reduction in spray volume while maintaining high application quality, providing an opportunity for pesticide and labor cost savings.

Design of a Biohybrid Materials Circuit with Binary Decoder Functionality (Adv. Mater. 14/2024)

Design of a Biohybrid Materials Circuit with Binary Decoder Functionality (Adv. Mater. 14/2024)

Design of a Biohybrid Materials Circuit with Binary Decoder Functionality.

Synthetic biology applies concepts from electrical engineering and information processing to endow cells with computational functionality. Transferring the underlying molecular components into materials and wiring them according to topologies inspired by electronic circuit boards has yielded materials systems that perform selected computational operations. However, the limited functionality of available building blocks is restricting the implementation of advanced information-processing circuits into materials. Here, a set of protease-based biohybrid modules the bioactivity of which can either be induced or inhibited is engineered. Guided by a quantitative mathematical model and following a design-build-test-learn (DBTL) cycle, the modules are wired according to circuit topologies inspired by electronic signal decoders, a fundamental motif in information processing. A 2-input/4-output binary decoder for the detection of two small molecules in a material framework that can perform regulated outputs in form of distinct protease activities is designed. The here demonstrated smart material system is strongly modular and can be used for biomolecular information processing for example in advanced biosensing or drug delivery applications.

MODELING UNKNOWN STOCHASTIC DYNAMICAL SYSTEM VIA AUTOENCODER

We present a numerical method to learn an accurate predictive model for an unknown stochastic dynamical system from its trajectory data. The method seeks to approximate the unknown flow map of the underlying system. It employs the idea of autoencoder to identify the unobserved latent random variables. In our approach, we design an encoding function to discover the latent variables, which are modeled as unit Gaussian, and a decoding function to reconstruct the system's future states. Both the encoder and decoder are expressed as deep neural networks (DNNs). Once the DNNs are trained by the trajectory data, the decoder serves as a predictive model for the unknown stochastic system. Through an extensive set of numerical examples, we demonstrate that the method is able to produce long-term system predictions by using short bursts of trajectory data. It is also applicable to systems driven by non-Gaussian noises.

Multifunctional optical logic device based on nanoscale rectangular ring resonator

Integrated optical logic devices are essential building blocks for implementing all-optical arithmetic and logic unit. In this paper, an ultra-compact multifunctional optical logic device consisting of a rectangular ring resonator coupled with two parallel metal–insulator–metal waveguides is presented. The transmission characteristics of the structure are analyzed in detail via temporal coupled-mode theory. The finite-difference time-domain simulation results reveal that multiple logic functions can be implemented with the aid of the wavelength division multiplexing technique at different output ports. Specifically, all seven basic types of logic gates, half-adder, half-subtractor, and 2*4 decoder can be implemented by monitoring the transmission of through and drop ports at different wavelengths. More importantly, among these functions, six logic gates (OR, XNOR, NAND, NOR, XOR, and AND) and half-adder functions can be performed simultaneously; the NOT logic operation is performed with controllable output ports and selectable working wavelengths; the half-subtractor and 2*4 decoder functions can be operated simultaneously. The proposed logic device is characterized by a small area overhead, multifunctionality, fast response time, and ultrahigh-speed information processing. It may potentially be applied in on-chip universal and parallel photonic computing units.

Learning the Geodesic Embedding with Graph Neural Networks

We present GEGNN, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on computing the geodesic distance between a single source and all destinations, which has linear complexity at least or require a long precomputation time. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space and compute the geodesic distance between a pair of points using the corresponding embedding vectors and a lightweight decoding function. To facilitate the learning of the embedding, we propose novel graph convolution and graph pooling modules that incorporate local geodesic information and are verified to be much more effective than previous designs. After training, our method requires only one forward pass of the network per mesh as precomputation. Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude while achieving comparable or better accuracy. Additionally, our method exhibits robustness on noisy and incomplete meshes and strong generalization ability on out-of-distribution meshes. The code and pretrained model can be found on https://github.com/IntelligentGeometry/GeGnn.

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Federated learning (FL) provides a promising solution to meet the requirements of data privacy and security in intelligent transportation systems (ITS), which enables edge devices and road side units (RSUs) to collaboratively train learning models without exposing the raw data. However, the deep leakage from gradients (DLG) still leads to the risk of divulging the original data. Meanwhile, the existing gradient protection methods based on secure multi-party computation (SMC) result in huge communication overheads and latency, which are difficult to satisfy the real-time demands of both FL and the diverse services in ITS. Focusing on improving edge data security in ITS, this paper proposes an enhanced federated learning (FL) model (SemBroc-RF) with reinforcement learning, which considers the advantages of both end-to-end homomorphic encryption (HE) and SMC. To reduce communication overheads and strengthen data security in RSUs and end devices simultaneously, a partially encrypted secure multi-party broadcast computation algorithm (SemBroc) is designed, which achieves the time complexity O(n) by constructing the decoding function and sharing the gradients among the local models. To improve the model accuracy by gradients aggregation, a FL algorithm (GreFLa) with reinforcement learning is proposed based on the adaptive assigned weight of the local gradients. Theoretical analysis and detailed simulation results verify that SemBroc-RF can effectively prevent gradient leakage. On the MNIST and CIFAR-10 datasets, compared with the benchmark, the accuracy of SemBroc-RF is increased by 3.63% and 1.35%, and the training round of SemBroc-RF is reduced by 70.8% and 45.6%, respectively.

Reduced‐order modeling framework using two‐level neural networks

AbstractEstablished reduced‐order modeling (ROM) methods, for instance, Galerkin‐projection, approximate the solution by linearly projecting high‐dimensional spaces to a lower‐dimensional space spanned by the reduced basis. However, the accuracy of these methods may be insufficient for complex and multiscale simulations due to the restriction to a linear space. Alternatively, autoencoders (AEs) can be used for nonlinear dimensionality reduction. We combine nonlinear dimensionality reduction techniques with time series prediction to build data‐driven ROMs. The presented framework consists of two‐level neural networks. The high‐dimensional space is nonlinearly compressed in the first level using the encoder function of the AE. Subsequently, the temporal evolution of the latent vector is predicted in the second level. The original solution can be easily reconstructed using the decoder function of the AE. In comparison with the projection‐based ROMs, for example, proper orthogonal decomposition (POD) with Galerkin projection, this framework allows naturally to include parameters in the prediction without nonlinear interpolation of the linear basis. We demonstrate the framework on a two‐dimensional flow field simulation around circular bodies parameterized with the inlet fluid velocity.

Private simultaneous messages based on quadratic residues

Private Simultaneous Messages (PSM) model is a minimal model for secure multiparty computation. Feige, Kilian, and Naor (STOC 1994) and Ishai (Cryptology and Information Security Series 2013) constructed PSM protocols based on quadratic residues. In this paper, we define QR-PSM protocols as a generalization of these protocols. A QR-PSM protocol is a PSM protocol whose decoding function outputs the quadratic residuosity modulo p of what is computed from messages. We design a QR-PSM protocol for any symmetric function f: {0,1}^n rightarrow {0,1} of communication complexity O(n^2). As far as we know, it is the most efficient PSM protocol for symmetric functions since the previously known best PSM protocol was of O(n^2log n) (Beimel et al., CRYPTO 2014). We also study the sizes of the underlying finite fields mathbb {F}_p in the protocols since the communication complexity of a QR-PSM protocol is proportional to the bit length of the prime p. We show that there is a prime p le (1+o(1))N^22^{2N-2} such that any length-N pattern of quadratic (non)residues appears modulo p (and hence it can be used for general QR-PSM protocols), which improves the Peralta’s known result (Mathematics of Computation 1992) by a constant factor (1+sqrt{2})^2.

Improving the Thresholds of Generalized LDPC Codes With Convolutional Code Constraints

CC-GLPDC codes are a class of generalized low-density parity-check (GLDPC) codes where the constraint nodes (CNs) represent convolutional codes. This allows for efficient decoding in the trellis with the forward-backward algorithm, and the strength of the component codes easily can be controlled by the encoder memory without changing the graph structure. In this letter, we extend the class of CC-GLDPC codes by introducing different types of irregularity at the CNs and investigating their effect on the BP and MAP decoding thresholds for the binary erasure channel (BEC). For the considered class of codes, an exhaustive grid search is performed to find the BP-optimized and MAP-optimized ensembles and compare their thresholds with the regular ensemble of the same design rate. The results show that irregularity can significantly improve the BP thresholds, whereas the thresholds of the MAP-optimized ensembles are only slightly different from the regular ensembles. Simulation results for the AWGN channel are presented as well and compared to the corresponding thresholds.

Maternal education as an environmental factor related to reading in children with reading difficulties: A functional magnetic resonance imaging study.

The expanded simple view of reading (SVR) model suggests that word decoding, language comprehension and executive functions are necessary for reading comprehension. Children with reading difficulties (RDs) often have deficits in critical components of reading established in the expanded SVR model and alterations in brain function of reading-related regions. Maternal education could provide children with advantageous educational opportunities or resources that support reading acquisition. The primary goal of this study was to examine the contributions of maternal education to the behavioural and neurobiological correlates of the expanded SVR model. Seventy-two 8- to 12-year-old children with RDs and typical readers (TRs) completed reading, behavioural and an functional magnetic resonance imaging stories-listening task to determine the functional connectivity of the receptive language network to the whole brain in association with maternal education. Higher maternal education was associated with better vocabulary in children with RDs and positive functional connectivity between the receptive language network and regions related to visual processing in children with RDs versus TRs. These data suggest that maternal education supports the ability to comprehend oral language and engagement of neural networks that support imagination/visualization in children with RDs.

Neural-network decoders for measurement induced phase transitions

Open quantum systems have been shown to host a plethora of exotic dynamical phases. Measurement-induced entanglement phase transitions in monitored quantum systems are a striking example of this phenomena. However, naive realizations of such phase transitions requires an exponential number of repetitions of the experiment which is practically unfeasible on large systems. Recently, it has been proposed that these phase transitions can be probed locally via entangling reference qubits and studying their purification dynamics. In this work, we leverage modern machine learning tools to devise a neural network decoder to determine the state of the reference qubits conditioned on the measurement outcomes. We show that the entanglement phase transition manifests itself as a stark change in the learnability of the decoder function. We study the complexity and scalability of this approach in both Clifford and Haar random circuits and discuss how it can be utilized to detect entanglement phase transitions in generic experiments.

Selective attention decoding in bimodal cochlear implant users.

The growing group of cochlear implant (CI) users includes subjects with preserved acoustic hearing on the opposite side to the CI. The use of both listening sides results in improved speech perception in comparison to listening with one side alone. However, large variability in the measured benefit is observed. It is possible that this variability is associated with the integration of speech across electric and acoustic stimulation modalities. However, there is a lack of established methods to assess speech integration between electric and acoustic stimulation and consequently to adequately program the devices. Moreover, existing methods do not provide information about the underlying physiological mechanisms of this integration or are based on simple stimuli that are difficult to relate to speech integration. Electroencephalography (EEG) to continuous speech is promising as an objective measure of speech perception, however, its application in CIs is challenging because it is influenced by the electrical artifact introduced by these devices. For this reason, the main goal of this work is to investigate a possible electrophysiological measure of speech integration between electric and acoustic stimulation in bimodal CI users. For this purpose, a selective attention decoding paradigm has been designed and validated in bimodal CI users. The current study included behavioral and electrophysiological measures. The behavioral measure consisted of a speech understanding test, where subjects repeated words to a target speaker in the presence of a competing voice listening with the CI side (CIS) only, with the acoustic side (AS) only or with both listening sides (CIS+AS). Electrophysiological measures included cortical auditory evoked potentials (CAEPs) and selective attention decoding through EEG. CAEPs were recorded to broadband stimuli to confirm the feasibility to record cortical responses with CIS only, AS only, and CIS+AS listening modes. In the selective attention decoding paradigm a co-located target and a competing speech stream were presented to the subjects using the three listening modes (CIS only, AS only, and CIS+AS). The main hypothesis of the current study is that selective attention can be decoded in CI users despite the presence of CI electrical artifact. If selective attention decoding improves combining electric and acoustic stimulation with respect to electric stimulation alone, the hypothesis can be confirmed. No significant difference in behavioral speech understanding performance when listening with CIS+AS and AS only was found, mainly due to the ceiling effect observed with these two listening modes. The main finding of the current study is the possibility to decode selective attention in CI users even if continuous artifact is present. Moreover, an amplitude reduction of the forward transfer response function (TRF) of selective attention decoding was observed when listening with CIS+AS compared to AS only. Further studies to validate selective attention decoding as an electrophysiological measure of electric acoustic speech integration are required.

Deformable Density Estimation via Adaptive Representation.

Crowd counting is the basic task of crowd analysis and it is of great significance in the field of public safety. Therefore, it receives more and more attention recently. The common idea is to combine the crowd counting task with convolutional neural networks to predict the corresponding density map, which is generated by filtering the dot labels with specific Gaussian kernels. Although the counting performance is promoted by the newly proposed networks, they all suffer one conjunct problem, which is due to the perspective effect, there is significant scale contrast among targets in different positions within one scene, but the existing density maps can not represent this scale change well. To address the prediction difficulties caused by target scale variation, we propose a scale-sensitive crowd density map estimation framework, which focuses on dealing with target scale change from density map generation, network design, and model training stage. It consists of the Adaptive Density Map (ADM), Deformable Density Map Decoder (DDMD), and Auxiliary Branch. To be specific, the Gaussian kernel size variates adaptively based on target size to generate ADM that contains scale information for each specific target. DDMD introduces the deformable convolution to fit the Gaussian kernel variation and boosts the model's scale sensitivity. The Auxiliary Branch guides the learning of deformable convolution offsets during the training phase. Finally, we construct experiments on different large-scale datasets. The results show the effectiveness of the proposed ADM and DDMD. Furthermore, the visualization demonstrates that deformable convolution learns the target scale variation.

Symmetric Saliency-Based Adversarial Attack to Speaker Identification

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this letter, we propose a novel generation-network-based approach, called symmetric saliency-based encoder-decoder (SSED), to generate adversarial voice examples to speaker identification. It contains two novel components. First, it uses a novel saliency map decoder to learn the importance of speech samples to the decision of a targeted speaker identification system, so as to make the attacker focus on generating artificial noise to the important samples. It also proposes an angular loss function to push the speaker embedding far away from the source speaker. Our experimental results demonstrate that the proposed SSED yields the state-of-the-art performance, i.e. over 97% targeted attack success rate and a signal-to-noise level of over 39 dB on both the open-set and close-set speaker identification tasks, with a low computational cost.