Recognition Module Research Articles

Modified receiver architecture in software-defined radio for real-time modulation classification

Automatic modulation classification (AMC) is an important process for future communication systems with prominent applications from spectrum management, and secure communication, to cognitive radio. The requirement for an efficient AMC classifier is due to its capability in blind modulation recognition, which is a difficult task in real scenarios where the limitations of traditional hardware and the complexity of channel impairments are involved. Therefore, this paper proposes a complete real-time AMC system based on software-defined radio and deep learning architecture. The system demodulation performance is verified through simulations and real channel impairment conditions to ensure reliability. With at most 6 times reduced number of parameters, two proposed models convolutional long short-term memory deep neural network and residual long short-term memory neural network also show a general improvement in classification accuracy compared with reference studies. The performance of these models at real-time AMC is tested with suitable processing time for practical applications.

YPL-SLAM: A Simultaneous Localization and Mapping Algorithm for Point-line Fusion in Dynamic Environments.

Simultaneous Localization and Mapping (SLAM) is one of the key technologies with which to address the autonomous navigation of mobile robots, utilizing environmental features to determine a robot's position and create a map of its surroundings. Currently, visual SLAM algorithms typically yield precise and dependable outcomes in static environments, and many algorithms opt to filter out the feature points in dynamic regions. However, when there is an increase in the number of dynamic objects within the camera's view, this approach might result in decreased accuracy or tracking failures. Therefore, this study proposes a solution called YPL-SLAM based on ORB-SLAM2. The solution adds a target recognition and region segmentation module to determine the dynamic region, potential dynamic region, and static region; determines the state of the potential dynamic region using the RANSAC method with polar geometric constraints; and removes the dynamic feature points. It then extracts the line features of the non-dynamic region and finally performs the point-line fusion optimization process using a weighted fusion strategy, considering the image dynamic score and the number of successful feature point-line matches, thus ensuring the system's robustness and accuracy. A large number of experiments have been conducted using the publicly available TUM dataset to compare YPL-SLAM with globally leading SLAM algorithms. The results demonstrate that the new algorithm surpasses ORB-SLAM2 in terms of accuracy (with a maximum improvement of 96.1%) while also exhibiting a significantly enhanced operating speed compared to Dyna-SLAM.

Biophysical and structural analyses of the interaction between the SHANK1 PDZ domain and an internal SLiM.

The PDZ (Postsynaptic density protein-95[PSD-95]/Discs-large) domain, prevalent as a recognition module, has attracted significant attention given its ability to specifically recognize ligands with consensus motifs (also termed PDZ binding motifs [PBMs]). PBMs typically bear a C-terminal carboxylate as a recognition handle and have been extensively characterized, whilst internal ligands are less well known. Here we characterize a short linear motif (SLiM) - EESTSFQGP - as an internal PBM based on its strong binding affinity towards the SHANK1 PDZ domain (SHANK1656-762 hereafter referred to as SHANK1). Using the acetylated analogue Ac-EESTSFQGP-CONH2 as a competitor for the interaction of SHANK1 with FAM-Ahx-EESTSFQGP-CONH2 or a typical fluorophore-labelled C-terminal PBM - GKAP - FITC-Ahx-EAQTRL-COOH - the internal SLiM was demonstrated to show comparable low-micromolar IC50 by competition fluorescent anisotropy. To gain further insight into the internal ligand interaction at the molecular level, we obtained the X-ray co-crystal structure of the Ac-EESTSFQGP-CONH2/SHANK1 complex and compared this to the Ac-EAQTRL-COOH/SHANK1 complex. The crystallographic studies reveal that the SHANK1 backbones for the two interactions overlap significantly. The main structural differences were shown to result from the flexible loops which reorganize to accommodate the two PBMs with distinct lengths and terminal groups. In addition, the two C-terminal residues Gly and Pro in Ac-EESTSFQGP-CONH2 were shown not to participate in interaction with the target protein, implying further truncation and structural modification using peptidomimetic approaches on this sequence may be feasible. Taken together, the SLiM Ac-EESTSFQGP-CONH2 holds potential as an internal ligand for targeting SHANK1.

FACE RECOGNITION BASED OFFICE RESOURCE CONTROLLING

In contemporary office environments, effective resource management and access control are essential for maintaining security and optimizing productivity. Traditional methods of resource management and access control, such as manual logging and key- based systems, are often cumbersome, prone to errors, and lack real-time monitoring capabilities. In this paper, we propose a Face Recognition-Based Office Resource Controlling (FROC) system that leverages the capabilities of facial recognition technology to automate resource management and access control processes. The FROC system utilizes advanced deep learning algorithms to accurately identify individuals based on facial biometrics, granting or restricting access to office resources accordingly. By integrating facial recognition technology with centralized resource management software, the FROC system enables seamless and efficient control over office facilities, equipment, and confidential information. Additionally, the system offers real-time monitoring and logging of resource usage, enhancing security and accountability within the office environment. Through a combination of hardware components, including surveillance cameras and access control devices, and software modules for facial recognition and resource tracking, the FROC system provides a comprehensive solution for modern office resource management. We evaluate the performance and effectiveness of the FROC system through extensive testing in simulated office environments, demonstrating its potential to streamline operations, improve security, and optimize resource utilizationin office settings. Keywords: Convolutional Neural Networks, image recognition, Tensor Flow, Deep Learning, Teachable Machine,

Multiview Spatial-Temporal Meta-Learning for Multivariate Time Series Forecasting.

Multivariate time series modeling has been essential in sensor-based data mining tasks. However, capturing complex dynamics caused by intra-variable (temporal) and inter-variable (spatial) relationships while simultaneously taking into account evolving data distributions is a non-trivial task, which faces accumulated computational overhead and multiple temporal patterns or distribution modes. Most existing methods focus on the former direction without adaptive task-specific learning ability. To this end, we developed a holistic spatial-temporal meta-learning probabilistic inference framework, entitled ST-MeLaPI, for the efficient and versatile learning of complex dynamics. Specifically, first, a multivariate relationship recognition module is utilized to learn task-specific inter-variable dependencies. Then, a multiview meta-learning and probabilistic inference strategy was designed to learn shared parameters while enabling the fast and flexible learning of task-specific parameters for different batches. At the core are spatial dependency-oriented and temporal pattern-oriented meta-learning approximate probabilistic inference modules, which can quickly adapt to changing environments via stochastic neurons at each timestamp. Finally, a gated aggregation scheme is leveraged to realize appropriate information selection for the generative style prediction. We benchmarked our approach against state-of-the-art methods with real-world data. The experimental results demonstrate the superiority of our approach over the baselines.

Sign Tone: A Deep Learning-Based Deaf Companion System for Two Way Communication Between Deaf and Non-Deaf Individuals

Communication is essential to express and receive information, knowledge, ideas, and views among people, but it has been quite a while to be an obstruction for people with hearing and mute disabilities. Sign language is one method of communicating with deaf people. Though there is sign language to communicate with non-sign people it is difficult for everyone to interpret and understand. The performance of existing sign language recognition approaches is typically limited. Developing an assistive device that will translate the sign language to a readable format will help the deaf-mutes to communicate with ease to the common people. Recent advancements in the development of deep learning, deep neural networks, especially Temporal convolutional networks (TCNs) have provided solutions to the communication of deaf and mute individuals. In this project, the main objective is to design Deaf Companion System for that to develop SignNet Model to provide two-way communication of deaf individuals and to implement an automatic speaking system for deaf and mute people. It provides two-way communication for all classes of people (deaf-and-mute, hard of hearing, visually impaired, and non-signers) and can be scaled commercially. The proposed system, consists of three modules; the sign recognition module (SRM) that recognizes the signs of a deaf individual using TCN, the speech recognition using Hidden Marko Model and synthesis module (SRSM) that processes the speech of a non-deaf individual and converts it to text, and an Avatar module (AM) to generate and perform the corresponding sign of the non-deaf speech, which were integrated into the sign translation companion system called deaf companion system to facilitate the communication from the deaf to the hearing and vice versa. The proposed model is trained on Indian Sign Language. Then developed a web-based user interface to deploy SignNet Model for ease of use. Experimental results on MNIST sign language recognition datasets validate the superiority of the proposed framework. The TCN model gives an accuracy of 98.5%..

Tackling Few-Shot Challenges in Automatic Modulation Recognition: A Multi-Level Comparative Relation Network Combining Class Reconstruction Strategy.

Automatic Modulation Recognition (AMR) is a key technology in the field of cognitive communication, playing a core role in many applications, especially in wireless security issues. Currently, deep learning (DL)-based AMR technology has achieved many research results, greatly promoting the development of AMR technology. However, the few-shot dilemma faced by DL-based AMR methods greatly limits their application in practical scenarios. Therefore, this paper endeavored to address the challenge of AMR with limited data and proposed a novel meta-learning method, the Multi-Level Comparison Relation Network with Class Reconstruction (MCRN-CR). Firstly, the method designs a structure of a multi-level comparison relation network, which involves embedding functions to output their feature maps hierarchically, comprehensively calculating the relation scores between query samples and support samples to determine the modulation category. Secondly, the embedding function integrates a reconstruction module, leveraging an autoencoder for support sample reconstruction, wherein the encoder serves dual purposes as the embedding mechanism. The training regimen incorporates a meta-learning paradigm, harmoniously combining classification and reconstruction losses to refine the model's performance. The experimental results on the RadioML2018 dataset show that our designed method can greatly alleviate the small sample problem in AMR and is superior to existing methods.

MobileNetV2 with Spatial Attention module for traffic congestion recognition in surveillance images

Traffic congestion recognition is essential for road traffic condition monitoring and improving transportation operation efficiency. Recent works have proposed using computer vision to develop cost-effective traffic congestion detection systems. This paper proposed a custom framework for recognizing traffic congestion using a trained advanced CNNs model on highway surveillance images. The proposed CNNs model uses an attention mechanism that significantly helps the network performing better. Specifically, a spatial attention module is proposed to aggregate model features and increase representational power. Exploring the optimal model choice for edge device deployment: MobileNetV2 is considered the best model choice for this task due to its lowest FLOPs and params. Furthermore, the accuracy of MobileNetV2 with attention module on the test set exceeds that of several advanced CNNs models such as VGG16, GoogLeNet, ResNet50, Efficientnetb0, DenseNet121. For a selected dataset of real-world traffic congestion images, test accuracy of 98.58% strongly supports the model’s efficiency in recognizing traffic congestion rendering image samples. In addition, proposed model also achieves 98.82% on the UCSD dataset, which as same as sort-of-the-art method. In summary, we have developed a congestion detection framework equipped with spatial attention module. Extensive experimental validation has demonstrated that using MobileNetV2 as the backbone network achieves state-of-the-art performance. The framework also uses the Grad-CAM approach for visual interpretability and localization of traffic congestion in surveillance images. Judging from the results of Grad-CAM, attention-integrated models can localize traffic congestion in surveillance images better. Our model is developed under the Pytorch framework using python3.8.

CNN-BiLSTM-DNN-Based Modulation Recognition Algorithm at Low SNR

Radio spectrum resources are very limited and have become increasingly tight in recent years, and the exponential growth of various frequency-using devices has led to an increasingly complex and changeable electromagnetic environment. Wireless channel complexity and uncertainty have increased dramatically, and automated modulation recognition (AMR) performs poorly at low signal-to-noise ratios. It is proposed to use convolutional bidirectional long short-term memory deep neural networks (CNN-BiLSTM-DNNs) as a deep learning framework to extract features from single and mixed in-phase/orthogonal (I/Q) symbols in modulated data. The framework combines the capabilities of one- and two-dimensional convolution, a bidirectional long short-term memory network, and a deep neural network more efficiently, extracting characteristics from the perspective of time and space to enhance the accuracy of automatic modulation recognition. Modulation recognition experiments on the benchmark datasets RML2016.10b and RML2016.10a show that the average recognition accuracies of the proposed model from −20 dB to 18 dB are 64.76% and 62.73%, respectively, and the improvement ranges of modulation recognition accuracy are 0.29−5.56% and 0.32−4.23% when the signal-to-noise ratio (SNR) is −10 dB to 4 dB, respectively. The CNN-BiLSTM-DNN model outperforms classical models such as MCLDNN, MCNet, CGDNet, ResNet, and IC-AMCNet in terms of modulation type recognition accuracy.

RNSC: A hierarchical deep learning model for net promoter scoring understanding by combining review and note through semantic consistency

The Net Promoter Score (NPS) is a widely-used metric for measuring customer loyalty and is an essential element in customer service analysis. To understand and analyze NPS effectively, customer-generated content, such as customer reviews, is commonly employed. Nevertheless, the information provided in customer-generated content may sometimes be inadequate. In this paper, we aim to enhance NPS understanding by incorporating a valuable employee-generated content known as employee notes, which provide insights into the internal operations of the enterprise's customer service. Considering the different standpoints of the two pieces of textual information, the semantic consistency is defined to calculate the semantic relationship between them, which helps better understand and analyze NPS. To effectively capture the crucial semantic consistency relationship and enhance the understanding of NPS, we propose a hierarchical deep learning approach, called RNSC (Review, Note and Semantic Consistency), which employs a bidirectional LSTM (BiLSTM) and a semantic consistency recognition module to encode and identify the local relationship between customer reviews and employee notes. Based on the trained model, the attention mechanism can detect and output the keywords that significantly contribute to the NPS through semantic consistency, showing its potential for supporting diagnostic analysis and further service optimization. Extensive data experiments, such as comparison with baseline methods, ablation experiments, and sparse data experiments, verify the superiority of the proposed RNSC approach.

Localización de robots basada en red neural utilizando características visuales

This paper outlines the development of a module capable of constructing a map-building algorithm using inertial odometry and visual features. It incorporates an object recognition module that leverages local features and unsupervised artificial neural networks to identify non-dynamic elements in a room and assign them positions. The map is modeled using a neural network, where each neuron corresponds to an absolute position in the room. Once the map is constructed, capturing just a couple of images of the environment is sufficient to estimate the robot's location. The experiments were conducted using both simulation and a real robot. The Webots environment with the virtual humanoid robot NAO was used for the simulations. Concurrently, results were obtained using a real NAO robot in a setting with various objects. The results demonstrate notable precision in localization within the two-dimensional maps, achieving an accuracy of ± (0.06, 0.1) m in simulations contrasted with the natural environment, where the best value achieved was ± (0.25, 0.16) m.

ClST: A Convolutional Transformer Framework for Automatic Modulation Recognition by Knowledge Distillation

ClST: A Convolutional Transformer Framework for Automatic Modulation Recognition by Knowledge Distillation

Incomplete handwritten Dongba character image recognition by multiscale feature restoration

Incomplete handwritten Dongba character often appears in heritage documents and its recognition is significant for heritage and philology. However, all previous methods always suppose that a complete Dongba character is used as input, and thus fail to achieve satisfactory performance when applied to incomplete Dongba character recognition. In this paper, an end-to-end network (DB2RNet) is proposed for incomplete handwritten Dongba character image recognition by multiscale feature restoration. Specifically, we first develop datasets that contain different levels of incomplete Dongba characters. A restoration module is proposed to restore the input incomplete Dongba character, and then a recognition module is employed to recognize Dongba character. By introducing an inter-module residual connection between the restoration module and recognition module, the DB2RNet can strengthen feature information transmission and boost the recognition performance. In addition, novel multiscale feature blocks are introduced, which can provide more effective texture and contextual information transmission for Dongba character image restoration, and thus yielding better restoration effects and better recognition results. Extensive experiments are conducted on Dongba character, Chinese character and Oracle character datasets and validate the effectiveness, superiority and robustness of our methods. Experiments results demonstrate that our proposed DB2RNet achieves competitive Dongba character restoration and recognition performance and outperforms the current state-of-the-art methods.

A Novel Dual-Component Radar-Signal Modulation Recognition Method Based on CNN-ST

Dual-component radar-signal modulation recognition is a challenging yet significant technique for electronic reconnaissance systems. To improve the lower recognition performance and the higher computational costs of the conventional methods, this paper presents a randomly overlapping dual-component radar-signal modulation recognition method based on a convolutional neural network–swin transformer (CNN-ST) under different signal-to-noise ratios (SNRs). To enhance the feature representation ability and decrease the loss of the detailed features of dual-component radar signals under different SNRs, the swin transformer is adopted and integrated into the designed CNN model. An inverted residual structure and lightweight depthwise convolutions are used to maintain the powerful representational ability. The results show that the dual-component radar-signal recognition accuracy of the proposed CNN-ST is up to 82.58% at −8 dB, which shows the better recognition performance of the CNN-ST over others. The dual-component radar-signal recognition accuracies under different SNRs are all more than 88%, which verified the fact that the CNN-ST achieves better recognition accuracy under different SNRs. This work offers essential guidance in enhancing dual-component radar signal recognition under different SNRs and in promoting actual applications.

Palindrome sequence mediated target recycling integrating with self-priming assisted signal reaction for sensitive miRNA detection

The development of a sensitive and isothermal technique with a greatly enhanced miRNA detection signal is still technically problematic due to the low abundance of miRNA and high sequence similarities with homologous miRNAs. Herein, we propose a novel fluorescence approach for sensitive and reliable miRNA detection by integrating the palindrome sequence mediated target recycling with self-priming assisted signal reaction. In this method, a dual toehold DNA nano-probe (HT) with two functional arms is designed to mediate specific target recognition and signal amplification. In the presence of target miRNA, it binds to the recognition module of HT probe, releasing the “2” sequence to initiate strand displacement amplification (SDA) and a self-priming-induced signal reaction. Based on the elegant design, the proposed method exhibits a wide linear response range exceeding five orders of magnitude and a low limit of detection of 0.96 fM according to the 3δ rule. The non-specific signal is below 5 % for non-target miRNA detection. Taking the merits of excellent sensitivity, desirable specificity, and superior anti-interference ability, the proposed approach shows a promising prospect for detecting miRNAs in complicated biological environments and early diagnosis of diseases.

A video object segmentation-based fish individual recognition method for underwater complex environments

Currently, aquaculture methods tend to combine scale and intelligence, which saves manpower and improves the survival rate of seafood at the same time. High-precision and high-efficiency fish individual recognition can provide key technical support for fish disease detection, feeding habits, body condition, etc. In the realm of intelligent aquaculture, it provides robust data support for precision fish farming. However, the current research methods for individual fish recognition struggle to maintain the network model's focus on the fish body in real marine underwater complex environments (e.g., environmental background interference such as coral reefs, overlap between fish bodies, light noise, etc.), leading to unsatisfactory recognition results. To this end, this paper proposes a method for fish individual recognition in underwater complex environments based on video object segmentation, which consists of three parts, including a fish individual segmentation detection module, a fish individual recognition module, and an all-in-one visualization module. The work adopts a combination of deep learning methods and video object segmentation algorithms to solve the problem of low attention and poor detection accuracy of fish individuals in real underwater complex environments, which effectively improves the accuracy and efficiency of fish individual recognition, and analyzes and discusses the comparison of recognition effects using different weights. The results of the simulation experiments show that the key metric Rank1 value of the method achieves more than 96% accuracy on the public datasets DlouFish, WideFish, and the Fish-seg dataset produced in this paper, and improves over the state-of-the-art methods for fish individual recognition by 2.23%, 1.33%, and 1.25%, respectively.

A Complex-Valued Transformer for Automatic Modulation Recognition

A Complex-Valued Transformer for Automatic Modulation Recognition

Adversarial training for signal modulation classification based on Ulam stability theory

The modulation classification of radar, communication, and other radiation source signals under complex electromagnetic conditions is an important task in the field of military electronic countermeasures. Deep learning is an important tool for automatic modulation classification (AMC) tasks. However, AMC models based on deep neural networks are easily attacked by adversarial methods such as gradient attacks, and even under small perturbations, the model may exhibit significant differences in prediction. To address adversarial attacks, we proposed a Ulam stability adversarial training method, which could improve the robust accuracy and the natural accuracy of the adversarial training model. We introduced a class of Jensen type Ulam stability theorem, which transforms the Jensen condition into a special class of stability preserving regularization terms for adversarial training models, enhancing the model's adversarial robustness. More importantly, our method provided a framework for improving the stability of adversarial training, which can be combined with existing adversarial training methods to effectively enhance their adversarial defense capabilities. In the experimental section, we compared four types of adversarial training methods on three types of modulation recognition datasets, and the results showed that Ulam adversarial training improved robust accuracy by an average of 4.8% and natural accuracy by an average of 2.2% on three datasets. The difference between the best and final accuracies of the models decreased by an average of 4.5%.

TCN-Inception: Temporal Convolutional Network and Inception modules for sensor-based Human Activity Recognition

The field of Human Activity Recognition (HAR) has experienced a significant surge in interest due to its essential role across numerous areas, including human–computer interaction (HCI), healthcare, smart homes, and various Internet of Things (IoT) applications. The power of deep learning methods in performing various classification tasks, including HAR, has been well-demonstrated. In light of this, our paper presents an efficient HAR system developed using a unique deep-learning architecture called TCN-Inception, which is designed for multivariate time series tasks like HAR data, by combining Temporal Convolutional Network (TCN) and Inception modules. The network starts with an Inception module that uses parallel convolution layers with various kernel sizes for feature extraction. It then includes a TCN module with dilated convolutions to grasp extended temporal patterns. Features are merged from different channels, and the use of residual connections and batch normalization improves training and deepens the architecture. We use four public datasets, UCI-HAR, MobiAct, Daphnet, and DSADS to assess the performance of the TCN-Inception model, and it obtains an average accuracy of 96.15%, 98.86%, 92.63%, and 99.50% for each dataset, respectively. Moreover, we compare the TCN-Inception to several deep learning frameworks to verify its performance. Finally, we implement an ablation study using several architectural configurations of the TCN-Inception model.

NETosis-Inspired Cell Surface-Constrained Framework Nucleic Acids Traps (FNATs) for Cascaded Extracellular Recognition and Cellular Behavior Modulation.

Upon pathogenic stimulation, activated neutrophils release nuclear DNA into the extracellular environment, forming web-like DNA structures known as neutrophil extracellular traps (NETs), which capture and kill bacteria, fungi, and cancer cells. This phenomenon is commonly referred to as NETosis. Inspired by this, we introduce a cell surface-constrained web-like framework nucleic acids traps (FNATs) with programmable extracellular recognition capability and cellular behavior modulation. This approach facilitates dynamic key chemical signaling molecule recognition such as adenosine triphosphate (ATP), which is elevated in the extracellular microenvironment, and triggers FNA self-assembly. This, in turn, leads to in situ tightly interwoven FNAs formation on the cell surface, thereby inhibiting target cell migration. Furthermore, it activates a photosensitizer-capturing switch, chlorin e6 (Ce6), and induces cell self-destruction. This cascade platform provides new potential tools for visualizing dynamic extracellular activities and manipulating cellular behaviors using programmable in situ self-assembling DNA molecular devices.