Existing on-device AI architectures for resource-constrained environments face two critical limitations: they lack compactness, with parameter requirements scaling proportionally to task complexity, and they exhibit poor generalizability, performing effectively only on specific application domains (e.g., models designed for regression tasks cannot adapt to natural language processing (NLP) applications). In this paper, we propose CURA, an architecture inspired by analog audio signal processing circuits that provides a compact and lightweight solution for diverse machine learning tasks across multiple domains. Our architecture offers three key advantages over existing approaches: (1) Compactness: it requires significantly fewer parameters regardless of task complexity; (2) Generalizability: it adapts seamlessly across regression, classification, complex NLP, and computer vision tasks; and (3) Complex pattern recognition: it can capture intricate data patterns while maintaining extremely low model complexity. We evaluated CURA across diverse datasets and domains. For compactness, it achieved equivalent accuracy using up to 2,500 times fewer parameters compared to baseline models. For generalizability, it demonstrated consistent performance across four NLP benchmarks and one computer vision dataset, nearly matching specialized existing models (achieving F1-scores up to 90%). Lastly, it delivers superior forecasting accuracy for complex patterns, achieving 1.6 times lower mean absolute error and 2.1 times lower mean squared error than competing models.

This study measures the long memory of investor-segregated cash flows within the Korean equity market from 2015 to 2024. Applying detrended fluctuation analysis (DFA) to BUY, SELL, and NET aggregates, we estimate the Hurst exponent ($H$) using both a static specification and a 250-day rolling window. All series exhibit heavy tails, with complementary cumulative distribution exponents ranging from approximately 2 to 3. As a control, time-shuffled series yield $H \approx 0.5$, confirming that the observed persistence originates from the temporal structure rather than the distributional shape. Our analysis documents long-range dependence and reveals a clear ranking of persistence across investor types. Persistence is strongest for retail BUY and SELL flows, intermediate for institutional flows, and lowest for foreign investor flows. For NET flows, however, this persistence diminishes for retail and institutional investors but remains elevated for foreign investors. The rolling $H$ exhibits clear regime sensitivity, with significant level shifts occurring around key events: the 2018--2019 tariff episode, the COVID-19 pandemic, and the period of disinflation from November 2022 to October 2024. Furthermore, regressions of daily volatility on the rolling $H$ produce positive and statistically significant coefficients for most investor groups. Notably, the $H$ of retail NET flows demonstrates predictive power for future volatility, a characteristic not found in institutional NET flows. These findings challenge the canonical noise-trader versus informed-trader dichotomy, offering a model-light, replicable diagnostic for assessing investor persistence and its regime shifts.

Osteoporosis silently erodes skeletal integrity worldwide; however, early detection through imaging can prevent most fragility fractures. Artificial intelligence (AI) methods now mine routine Dual-energy X-ray Absorptiometry (DXA), X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI) scans for subtle, clinically actionable markers, but the literature is fragmented. This survey unifies the field through a tri-axial framework that couples imaging modalities with clinical tasks and AI methodologies (classical machine learning, convolutional neural networks (CNNs), transformers, self-supervised learning, and explainable AI). Following a concise clinical and technical primer, we detail our Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-guided search strategy, introduce the taxonomy via a roadmap figure, and synthesize cross-study insights on data scarcity, external validation, and interpretability. By identifying emerging trends, open challenges, and actionable research directions, this review provides AI scientists, medical imaging researchers, and musculoskeletal clinicians with a clear compass to accelerate rigorous, patient-centered innovation in osteoporosis care. The project page of this survey can also be found on Github.

Leveraging received signal strength (RSS) measurements for indoor localization is highly attractive due to their inherent availability in ubiquitous wireless protocols. However, prevailing RSS-based methods often depend on complex computational algorithms or specialized hardware, rendering them impractical for low-cost access points. To address these challenges, this paper introduces buffer-aided RMSProp (BARProp), a fast and memory-efficient localization algorithm specifically designed for RSS-based tasks. The key innovation of BARProp lies in a novel mechanism that dynamically adapts the decay factor by monitoring the energy variations of recent gradients stored in a buffer, thereby achieving both accelerated convergence and enhanced stability. Furthermore, BARProp requires less than 15% of the memory used by state-of-the-art methods. Extensive evaluations with real-world data demonstrate that BARProp not only achieves higher localization accuracy but also delivers at least a fourfold improvement in convergence speed compared to existing benchmarks.

Deep learning (DL) has revolutionized wireless communication systems by introducing datadriven end-to-end (E2E) learning, where the physical layer (PHY) is transformed into DL architectures to achieve peak optimization. Leveraging DL for E2E optimization in PHY significantly enhances its adaptability and performance in complex wireless environments, meeting the demands of advanced network systems such as 5G and beyond. Furthermore, this evolution of data-driven PHY optimization has also enabled advanced semantic applications across various modalities, including text, image, audio, video, and multimodal transmissions. These applications elevate communication from bit-level to semantic-level intelligence, making it capable of discerning context and intent. Although the PHY, as a DL architecture, plays a crucial role in enabling semantic communication (SemCom) systems, comprehensive studies that integrate both E2E communication and SemCom systems remain significantly underexplored. This highlights the novelty and potential of these integrative fields, marking them as a promising research domain. Therefore, this article provides a comprehensive review of the emerging field of data-driven PHY for E2E communication systems, emphasizing their role in enabling semantic applications across various modalities. It also identifies key challenges and potential research directions, serving as a crucial guide for future advancements in DL for E2E communication and SemCom systems.

Image captioning by the encoder-decoder framework has shown tremendous advancement in the last decade where CNN is mainly used as encoder and LSTM is used as a decoder. Despite such an impressive achievement in terms of accuracy in simple images, it lacks in terms of time complexity and space complexity efficiency. In addition to this, in case of complex images with a lot of information and objects, the performance of this CNN-LSTM pair downgraded exponentially due to the lack of semantic understanding of the scenes presented in the images. Thus, to take these issues into consideration, we present CNN-GRU encoder decode framework for caption-to-image reconstructor to handle the semantic context into consideration as well as the time complexity. By taking the hidden states of the decoder into consideration, the input image and its similar semantic representations is reconstructed and reconstruction scores from a semantic reconstructor are used in conjunction with likelihood during model training to assess the quality of the generated caption. As a result, the decoder receives improved semantic information, enhancing the caption production process. During model testing, combining the reconstruction score and the log-likelihood is also feasible to choose the most appropriate caption. The suggested model outperforms the state-of-the-art LSTM-A5 model for picture captioning in terms of time complexity and accuracy.

To provide a comprehensive view for dynamics of and on many real-world temporal networks, we investigate the interplay of temporal connectivity patterns and spreading phenomena, in terms of the susceptible-infected-removed (SIR) model on the modified activity-driven temporal network (ADTN) with memory. In particular, we focus on how the epidemic threshold of the SIR model is affected by the heterogeneity of nodal activities and the memory strength in temporal and static regimes, respectively. While strong ties (memory) between nodes inhibit the spread of epidemic to be localized, the heterogeneity of nodal activities enhances it to be globalized initially. Since the epidemic threshold of the SIR model is very sensitive to the degree distribution of nodes in static networks, we test the SIR model on the modified ADTNs with the possible set of the activity exponents and the memory exponents that generates the same degree distributions in temporal networks. We also discuss the role of spatiotemporal scaling properties of the largest cluster and the maximum degree in the epidemic threshold. It is observed that the presence of highly active nodes enables to trigger the initial spread of epidemic in a short period of time, but it also limits its final spread to the entire network. This implies that there is the trade-off between the spreading time of epidemic and its outbreak size. Finally, we suggest the phase diagram of the SIR model on ADTNs and the optimal condition for the spread of epidemic under the circumstances.

Hand gesture recognition using multichannel surface electromyography (sEMG) is challenging due to unstable predictions and inefficient time-varying feature enhancement. To overcome the lack of signal based time-varying feature problems, we propose a lightweight squeeze-excitation deep learning-based multi stream spatial temporal dynamics time-varying feature extraction approach to build an effective sEMG-based hand gesture recognition system. Each branch of the proposed model was designed to extract hierarchical features, capturing both global and detailed spatial-temporal relationships to ensure feature effectiveness. The first branch, utilizing a Bidirectional-TCN (Bi-TCN), focuses on capturing long-term temporal dependencies by modelling past and future temporal contexts, providing a holistic view of gesture dynamics. The second branch, incorporating a 1D Convolutional layer, separable CNN, and Squeeze-and-Excitation (SE) block, efficiently extracts spatial-temporal features while emphasizing critical feature channels, enhancing feature relevance. The third branch, combining a Temporal Convolutional Network (TCN) and Bidirectional LSTM (BiLSTM), captures bidirectional temporal relationships and time-varying patterns. Outputs from all branches are fused using concatenation to capture subtle variations in the data and then refined with a channel attention module, selectively focusing on the most informative features while improving computational efficiency. The proposed model was tested on the Ninapro DB2, DB4, and DB5 datasets, achieving accuracy rates of 96.41%, 92.40%, and 93.34%, respectively. These results demonstrate the capability of the system to handle complex sEMG dynamics, offering advancements in prosthetic limb control and human-machine interface technologies with significant implications for assistive technologies.

This paper introduces a novel method for image colorization that utilizes a color transformer and generative adversarial networks (GANs) to address the challenge of generating visually appealing colorized images. Conventional approaches often struggle with capturing long-range dependencies and producing realistic colorizations. The proposed method integrates a transformer architecture to capture global information and a GAN framework to improve visual quality. In this study, a color encoder that utilizes a random normal distribution to generate color features is applied. These features are then integrated with grayscale image features to enhance the overall representation of the images. Our method demonstrates superior performance compared with existing approaches by utilizing the capacity of the transformer, which can capture long-range dependencies and generate a realistic colorization of the GAN. Experimental results show that the proposed network significantly outperforms other state-of-the-art colorization techniques, highlighting its potential for image colorization. This research opens new possibilities for precise and visually compelling image colorization in domains such as digital restoration and historical image analysis.

A technique for object localization based on pose estimation and camera calibration is presented. The 3-dimensional (3D) coordinates are estimated by collecting multiple 2-dimensional (2D) images of the object and are utilized for the calibration of the camera. The calibration steps involving a number of parameter calculation including intrinsic and extrinsic parameters for the removal of lens distortion, computation of object's size and camera's position calculation are discussed. A transformation strategy to estimate the 3D pose using the 2D images is presented. The proposed method is implemented on MATLAB and validation experiments are carried out for both pose estimation and camera calibration.

Differentiating malware is important to determine their behaviors and level of threat; as well as to devise defensive strategy against them. In response, various anti-malware systems have been developed to distinguish between different malwares. However, most of the recent malware families are Artificial Intelligence (AI) enable and can deceive traditional anti-malware systems using different obfuscation techniques. Therefore, only AI-enabled anti-malware system is robust against these techniques and can detect different features in the malware files that aid in malicious activities. In this study we review two AI-enabled techniques for detecting malware in Windows and Android operating system, respectively. Both the techniques achieved perfect accuracy in detecting various malware families.

Homomorphic encryption is one of the representative solutions to privacy-preserving machine learning (PPML) classification enabling the server to classify private data of clients while guaranteeing privacy. This work focuses on PPML using word-wise fully homomorphic encryption (FHE). In order to implement deep learning on word-wise homomorphic encryption (HE), the ReLU and max-pooling functions should be approximated by some polynomials for homomorphic operations. Most of the previous studies focus on HE-friendly networks, where the ReLU and max-pooling functions are approximated using low-degree polynomials. However, for the classification of the CIFAR-10 dataset, using a low-degree polynomial requires designing a new deep learning model and training. In addition, this approximation by low-degree polynomials cannot support deeper neural networks due to large approximation errors. Thus, we propose a precise polynomial approximation technique for the ReLU and max-pooling functions. Precise approximation using a single polynomial requires an exponentially high-degree polynomial, which results in a significant number of non-scalar multiplications. Thus, we propose a method to approximate the ReLU and max-pooling functions accurately using a composition of minimax approximate polynomials of small degrees. If we replace the ReLU and max-pooling functions with the proposed approximate polynomials, well-studied deep learning models such as ResNet and VGGNet can still be used without further modification for PPML on FHE. Even pre-trained parameters can be used without retraining. We approximate the ReLU and max-pooling functions in the ResNet-152 using the composition of minimax approximate polynomials of degrees 15, 27, and 29. Then, we succeed in classifying the plaintext ImageNet dataset with 77.52% accuracy, which is very close to the original model accuracy of 78.31%.

The internet of things refers to the network of devices connected to the internet and can communicate with each other. The term things is to refer non-conventional devices that are usually not connected to the internet. The network of such devices or things is growing at an enormous rate. The security and privacy of the data flowing through these things is a major concern. The devices are low powered and the conventional encryption algorithms are not suitable to be employed on these devices. In this correspondence a survey of the contemporary lightweight encryption algorithms suitable for use in the IoT environment has been presented.

Antifreeze proteins (AFPs) are the sub-set of ice binding proteins indispensable for the species living in extreme cold weather. These proteins bind to the ice crystals, hindering their growth into large ice lattice that could cause physical damage. There are variety of AFPs found in numerous organisms and due to the heterogeneous sequence characteristics, AFPs are found to demonstrate a high degree of diversity, which makes their prediction a challenging task. Herein, we propose a machine learning framework to deal with this vigorous and diverse prediction problem using the manifolding learning through composition of k-spaced amino acid pairs. We propose to use the deep neural network with skipped connection and ReLU non-linearity to learn the non-linear mapping of protein sequence descriptor and class label. The proposed antifreeze protein prediction method called AFP-CKSAAP has shown to outperform the contemporary methods, achieving excellent prediction scores on standard dataset. The main evaluater for the performance of the proposed method in this study is Youden's index whose high value is dependent on both sensitivity and specificity. In particular, AFP-CKSAAP yields a Youden's index value of 0.82 on the independent dataset, which is better than previous methods.

Millimeter wave (mmWave)-enabled unmanned aerial vehicle (UAV) swarm networks (UAVSNs) can utilize a large spectrum of resources to provide low latency and high data transmission rate. Additionally, owing to the short wavelength, UAVs equipped with large antenna arrays can form secure narrow directive beam to establish communication with less interference. However, due to the high UAV mobility, limited beam coverage, beam misalignment, and high path loss, it is very challenging to adopt the mmWave communication in UAVSNs. In this article, we present a comprehensive survey on neighbor discovery and beam alignment techniques for directional communication in mmWave-enabled UAVSNs. The existing techniques are reviewed and compared with each other. We also discuss key open issues and challenges with potential research direction.

We demonstrate phase-coherent transport in suspended long-channel Cd3As2 nanowire devices using both direct current (DC) transport and radio-frequency (RF) reflectometry measurements. By integrating Cd3As2 nanowires with on-chip superconducting LC resonators, we achieve sensitive detection of both resistance and quantum capacitance variations. In a long-channel device (L ~ 1.8 {\mu}m), clear Fabry-Pérot (FP) interference patterns are observed in both DC and RF measurements, provide strong evidence for ballistic electron transport. RF reflectometry reveals gate-dependent modulations of the resonance frequency, arising from quantum capacitance oscillations induced by changes in the density of states and FP interference. These oscillations exhibit a quasi-periodic structure that closely correlates with the FP patterns in DC transport measurements. In another device of a Cd3As2 nanowire Josephson junction (L ~ 730 nm, superconducting Al contacts), FP interference patterns are too weak to be resolved in DC conductance but are detectable using RF reflectometry. These results demonstrate the high quality of our Cd3As2 nanowires and the versatility of RF reflectometry, establishing their potential for applications in topological quantum devices, such as Andreev qubits or gatemon architectures.

Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model's layer response, and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single weight values, which may lead to over generalized saliency map. To address this issue, we use a global guidance map to rectify the weighted aggregation operation during saliency estimation, where resultant interpretations are comparatively clean er and instance-specific. We obtain the global guidance map by performing elementwise multiplication between the feature maps and their corresponding gradient maps. To validate our study, we compare the proposed study with eight different saliency visualizers. In addition, we use seven commonly used evaluation metrics for quantitative comparison. The proposed scheme achieves significant improvement over the test images from the ImageNet, MS-COCO 14, and PASCAL VOC 2012 datasets.

Graphene matter in a strong magnetic field, realizing one-dimensional quantum Hall channels, provides a unique platform for studying electron interference. Here, using the Landauer-B\"uttiker formalism along with the tight-binding model, we investigate the quantum Hall (QH) effects in unipolar and bipolar monolayer-bilayer graphene (MLG-BLG) junctions. We find that a Hall bar made of an armchair MLG-BLG junction in the bipolar regime results in valley-polarized edge-channel interferences and can operate a fully tunable Mach-Zehnder (MZ) interferometer device. Investigation of the bar-width and magnetic-field dependence of the conductance oscillations shows that the MZ interference in such structures can be drastically affected by the type of (zigzag) edge termination of the second layer in the BLG region [composed of vertical dimer or non-dimer atoms]. Our findings reveal that both interfaces exhibit a double set of Aharonov-Bohm interferences, with the one between two oppositely valley-polarized edge channels dominating and causing a large-amplitude conductance oscillation ranging from 0 to $2 e^2 / h$. We explain and analyze our findings by analytically solving the Dirac-Weyl equation for a gated semi-infinite MLG-BLG junction.

The smart mobile terminal operator platform Android is getting popular all over the world with its wide variety of applications and enormous use in numerous spheres of our daily life. Considering the fact of increasing demand of home security and automation, an Android based control system is presented in this paper where the proposed system can maintain the security of home main entrance and also the car door lock. Another important feature of the designed system is that it can control the overall appliances in a room. The mobile to security system or home automation system interface is established through Bluetooth. The hardware part is designed with the PIC microcontroller.