Search Results (24)

The vast volume of media content, combined with the costs of manual annotation, challenges scalable codebook analysis and risks reducing decision-making accuracy. This study evaluates the effectiveness of large language models (LLMs) and multi-agent teams in structured media content analysis based on codebook-driven annotation. We construct a dataset of 200 news articles on U.S. tariff policies, manually annotated using a 26-question codebook encompassing 122 distinct codes, to establish a rigorous ground truth. Seven state-of-the-art LLMs, spanning low- to high-capacity tiers, are assessed under a unified zero-shot prompting framework incorporating role-based instructions and schema-constrained outputs. Experimental results show weighted global F1-scores between 0.636 and 0.822, with Claude-3-7-Sonnet achieving the highest direct-prompt performance. To examine the potential of agentic orchestration, we propose and develop a multi-agent system using Meta’s Llama 4 Maverick, incorporating expert role profiling, shared memory, and coordinated planning. This architecture improves the overall F1-score over the direct prompting baseline from 0.757 to 0.805 and demonstrates consistent gains across binary, categorical, and multi-label tasks, approaching commercial-level accuracy while maintaining a favorable cost–performance profile. These findings highlight the viability of LLMs, both in direct and agentic configurations, for automating structured content analysis. Full article

In modern (5G) and future Multi-User (MU) wireless communication systems Beyond 5G (B5G) using Multiple-Input Multiple-Output (MIMO) technology, base stations with a large number of antennas communicate with many mobile stations. This technology is becoming especially relevant in modern multi-user wireless sensor networks in various application scenarios. The problem of organizing an MU mode on the downlink has arisen, which can be solved by precoding at the Base Station (BS) without using additional channel frequency–time resources. In order to utilize an efficient precoding algorithm at the base station, full Channel State Information (CSI) is needed for each mobile station. Transmitting this information for massive MIMO systems normally requires the allocation of high-speed channel resources for the feedback. With limited feedback, reduced information (partial CSI) is used, for example, the codeword from the codebook that is closest to the estimated channel vector (or matrix). Incomplete (or inaccurate) CSI causes interference from the signals, transmitted to neighboring mobile stations, that ultimately results in a decrease in the number of active users served. In this paper, we propose a new downlink precoding approach for MU-MIMO systems that also uses codebooks to reduce the information transmitted over a feedback channel. A key aspect of the proposed approach, in contrast to the existing ones, is the transmission of new, uncorrelated information in each cycle, which allows for accumulating CSI with higher accuracy without increasing the feedback overhead. The proposed approach is most effective in systems with dynamic user selection. In such systems, increasing the accuracy of CSI leads to an increase in the number of active users served, which after a few cycles, can reach a maximum value determined by the number of transmit antennas at the BS side. This approach appears to be promising for addressing the challenges associated with current and future massive MIMO systems, as evidenced by our statistical simulation results. Various methods for extracting and transmitting such uncorrelated information over a feedback channel are considered. In many known publications, the precoder, codebooks, CSI estimation methods and other aspects of CSI transmission over a feedback channel are separately optimized, but a comprehensive approach to jointly solving these problems has not yet been developed. In our paper, we propose to fill this gap by combining a new approach of precoding and CSI estimation with CSI accumulation and transmission over a feedback channel. Full article

Encryption of images is an important method that can effectively improve the security and privacy of crucial image data. Existing methods generally encrypt an image with a combination of scrambling and encoding operations. Currently, many applications require highly secure results for image encryption. New methods that can achieve improved randomness for both the scrambling and encoding processes in encryption are thus needed to further enhance the security of a cipher image. This paper proposes a new method that can securely encrypt color images. As the first step of the proposed method, a complete bit-level operation is utilized to scramble the binary bits in a color image to a full extent. For the second step, the bits in the scrambled image are processed with a sweeping operation to improve the encryption security. In the final step of encryption, a codebook that varies with evolutionary operations based on several chaotic systems is utilized to encrypt the partially encrypted image obtained in the second step. Experimental results on benchmark color images suggest that this new approach can securely encrypt color images and generate cipher images that remain secure under different types of attacks. The proposed approach is compared with several other state-of-the-art encryption approaches and the results show that it can achieve improved encryption security for cipher images. Experimental results thus suggest that this new approach can possibly be utilized practically in applications where color images need to be encrypted for content protection. Full article

Beam management is a key functionality in establishing and maintaining reliable communication in cellular and vehicular networks, and it becomes more critical at millimeter-wave (mmWave) frequencies and for high-mobility scenarios. Traditional approaches consume wireless resources and incur high beam training overheads in finding the best beam pairings, thus necessitating alternative approaches such as position-aided, vision-aided, or, more generally, sensing-aided beam prediction approaches. Current systems are also leveraging artificial intelligence/machine learning (ML) to optimize the beam management procedures; however, the majority of the proposed ML frameworks have been applied to synthetic datasets, leading to overestimated performances. In this work, in the context of vehicle-to-infrastructure (V2I) communication and using the real-world DeepSense6G experimental datasets, we investigate the performance of four ML algorithms on beam prediction accuracy for mmWave V2I scenarios. We compare the performance of K-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), and naïve Bayes (NB) algorithms on position-aided beam prediction accuracy and related metrics such as precision, recall, specificity, and F1-score. The impacts of different beam codebook sizes and dataset split ratios on five different scenarios’ datasets were investigated, independently and collectively. Confusion matrices and area under the receiver operating characteristic curves were also employed to visualize the (mis)classification statistics of the considered ML algorithms. The results show that SVM outperforms the other three algorithms, for the most part, on the scenario-per-scenario cases. However, for the combined scenario with larger data samples, DT outperforms the other three algorithms for both the different codebook sizes and data split ratios. The results also show comparable performance for the different data split ratios considered for the different algorithms. However, with respect to the codebook sizes, the results show that the higher the codebook size, the lower the beam prediction accuracy. With the best accuracy results around 70% for the combined scenario in this study, multi-modal sensing-aided approaches can be explored to increase the beam prediction performance, although at the expense of higher system complexity when compared to the position-aided approach considered in this study. Full article

Vector Quantization (VQ) is a technique with a wide range of applications. For example, it can be used for image compression. The codebook design for VQ has great significance in the quality of the quantized signals and can benefit from the use of swarm intelligence. Initialization of the Linde–Buzo–Gray (LBG) algorithm, which is the most popular VQ codebook design algorithm, is a step that directly influences VQ performance, as the convergence speed and codebook quality depend on the initial codebook. A widely used initialization alternative is random initialization, in which the initial set of codevectors is drawn randomly from the training set. Other initialization methods can lead to a better quality of the designed codebooks. The present work evaluates the impacts of initialization strategies on swarm intelligence algorithms for codebook design in terms of the quality of the designed codebooks, assessed by the quality of the reconstructed images, and in terms of the convergence speed, evaluated by the number of iterations. Initialization strategies consist of a combination of codebooks obtained by initialization algorithms from the literature with codebooks composed of vectors randomly selected from the training set. The possibility of combining different initialization techniques provides new perspectives in the search for the quality of the VQ codebooks. Nine initialization strategies are presented, which are compared with random initialization. Initialization strategies are evaluated on the following algorithms for codebook design based on swarm clustering: modified firefly algorithm—Linde–Buzo–Gray (M-FA-LBG), modified particle swarm optimization—Linde–Buzo–Gray (M-PSO-LBG), modified fish school search—Linde–Buzo–Gray (M-FSS-LBG) and their accelerated versions (M-FA-LBGa, M-PSO-LBGa and M-FSS-LBGa) which are obtained by replacing the LBG with the accelerated LBG algorithm. The simulation results point out to the benefits of the proposed initialization strategies. The results show gains up to 4.43 dB in terms of PSNR for image Clock with M-PSO-LBG codebooks of size 512 and codebook design time savings up to 67.05% for image Clock, with M-FF-LBGa codebooks with size $N=512$, by using initialization strategies in substitution to Random initialization. Full article

Millimeter wave (mmWave) and terahertz (THz) massive MIMO architectures are pivotal in the advancement of mobile communications. These systems conventionally utilize codebooks to facilitate initial connection and to manage information transmission tasks. Traditional codebooks, however, are typically composed of numerous single-lobe beams, thus incurring substantial beam training overhead. While neural network-based approaches have been proposed to mitigate the beam training load, they sometimes fail to adequately consider the minority users dispersed across various regions. The fairness of the codebook coverage relies on addressing this problem. Therefore, we propose an imbalanced learning (IL) methodology for beam codebook construction, explicitly designed for scenarios characterized by an imbalanced user distribution. Our method begins with a pre-clustering phase, where user channels are divided into subsets based on their power response to combining vectors across distinct subareas. Then, each subset is refined by a dedicated sub-model, which contributes to the global model within each IL iteration. To facilitate the information exchange among sub-models during global updates, we introduce the focal loss mechanism. Our simulation results substantiate the efficacy of our IL framework in enhancing the performance of mmWave and THz massive MIMO systems under the conditions of imperfect channel state information and imbalanced user distribution. Full article

The frequent consumption of sugary beverages is associated with many health risks. This study examined how persuasive appeals and graphics were used in different media campaigns to encourage and discourage sugary beverages and water in the United States (U.S.) The investigators developed a codebook, protocol and systematic process to conduct a qualitative content analysis for 280 media campaigns organized into a typology with six categories. SPSS version 28.0 was used to analyze rational and emotional appeals (i.e., positive, negative, coactive) for campaign slogans, taglines and graphic images (i.e., symbols, colors, audiences) for 60 unique campaigns across the typology. Results showed that positive emotional appeals were used more to promote sugary beverages in corporate advertising and marketing (64.7%) and social responsibility campaigns (68.8%), and less to encourage water in social marketing campaigns (30%). In contrast, public awareness campaigns used negative emotional appeals (48.1%), and advocacy campaigns combined rational (30%) and emotional positive (50%) and negative appeals (30%). Public policy campaigns used rational (82.6%) and positive emotional appeals (73.9%) to motivate support or opposition for sugary beverage tax legislation. Chi-square analyses assessed the relationships between the U.S. media campaign typology categories and graphic elements that revealed three variables with significant associations between the campaign typology and race/ethnicity (χ²(103) = 32.445, p = 0.039), content (χ²(103) = 70.760, p < 0.001) and product image (χ²(103) = 11.930, p = 0.036). Future research should examine how positive persuasive appeals in text and graphics can promote water to reduce sugary beverage health risks. Full article

Reliable detection of COVID-19 from cough recordings is evaluated using bag-of-words classifiers. The effect of using four distinct feature extraction procedures and four different encoding strategies is evaluated in terms of the Area Under Curve (AUC), accuracy, sensitivity, and F1-score. Additional studies include assessing the effect of both input and output fusion approaches and a comparative analysis against 2D solutions using Convolutional Neural Networks. Extensive experiments conducted on the COUGHVID and COVID-19 Sounds datasets indicate that sparse encoding yields the best performances, showing robustness against various combinations of feature type, encoding strategy, and codebook dimension parameters. Full article

Recently, extensive research efforts have been dedicated to view-based 3D object retrieval, owing to its advantage of using a set of 2D images to represent 3D objects. Some existing image processing technologies can be employed. In this paper, we adopt Bag-of-Words for view-based 3D object retrieval. Instead of SIFT, DSP-SIFT is extracted from all images as object features. Moreover, two codebooks of the same size are generated by approximate k-means. Then, we combine two codebooks to correct the quantization artifacts and improve recall. Bayes merging is applied to address the codebook correlation (overlapping among different vocabularies) and to provide the benefit of high recall. Moreover, Approximate Nearest Neighbor (ANN) is used to quantization. Experimental results on ETH-80 datasets show that our method improves the performance significantly compared with the state-of-the-art approaches. Full article

The spherical-cap approximation of vector quantization (SCVQ) is an analytical model used for the mathematical analysis of multiple-input multiple-output (MIMO) systems with limited feedback. SCVQ closely emulates the distribution of the quantization error induced by the finite-rate quantization of a channel using a simple and analytically tractable approach. However, the conventional SCVQ model is not applicable when antenna-combining schemes such as quantization-based combining (QBC) are considered. Because QBC is an effective antenna-combining method that minimizes channel quantization errors, it can be adopted for various practical MIMO broadcast systems. Nevertheless, evaluating the performance of QBC-based MIMO systems with an explicit codebook can be extremely difficult, depending on the system complexity. To resolve this, this study generalizes the conventional SCVQ to be compatible with the QBC. The proposed generalized version of the SCVQ effectively emulates the quantization error obtained using QBC, while enabling a simple simulation independent of the number of feedback bits and mathematically tractable analysis. We validate the effectiveness of the proposed model by presenting a wireless communication application based on a dense cellular network. Full article

The juvenile variant of Neuronal Ceroid Lipofuscinosis (CLN3 disease/Batten disease) is a rare progressive brain disease in children and young adults, characterized by vision loss, decline in cognitive and motor capacities and epilepsy. Children with CLN3 disease often show disturbed behaviour and emotions. The aim of this study is to gain a better understanding of the behaviour and emotions of children with CLN3 disease and to examine the support that the children and their parents are receiving. A combination of qualitative and quantitative analysis was used to analyse patient files and parent interviews. Using a framework analysis approach a codebook was developed, the sources were coded and the data were analysed. The analysis resulted in overviews of (1) typical behaviour and emotions of children as a consequence of CLN3 disease, (2) the support children with CLN3 disease receive, (3) the support parents of these children receive, and (4) the problems these parents face. For a few children their visual, physical or cognitive deterioration was found to lead to specific emotions and behaviour. The quantitative analysis showed that anxiety was reported for all children. The presented overviews on support contain tacit knowledge of health care professionals that has been made explicit by this study. The overviews may provide a lead to adaptable support-modules for children with CLN3 disease and their parents. Full article

This paper focuses on a block cipher adaptation of the Galois Extension Fields (GEF) combination technique for PRNGs and targets application in the Internet of Things (IoT) space, an area where the combination technique was concluded as a quality stream cipher. Electronic Codebook (ECB) and Cipher Feedback (CFB) variations of the cryptographic algorithm are discussed. Both modes offer computationally efficient, scalable cryptographic algorithms for use over a simple combination technique like XOR. The cryptographic algorithm relies on the use of quality PRNGs, but adds an additional layer of security while preserving maximal entropy and near-uniform distributions. The use of matrices with entries drawn from a Galois field extends this technique to block size chunks of plaintext, increasing diffusion, while only requiring linear operations that are quick to perform. The process of calculating the inverse differs only in using the modular inverse of the determinant, but this can be expedited by a look-up table. We validate this GEF block cipher with the NIST test suite. Additional statistical tests indicate the condensed plaintext results in a near-uniform distributed ciphertext across the entire field. The block cipher implemented on an MSP430 offers a faster, more power-efficient alternative to the Advanced Encryption Standard (AES) system. This cryptosystem is a secure, scalable option for IoT devices that must be mindful of time and power consumption. Full article

The precoding scheme based on codebooks is used to save the same set of codebook in advance at the transmitter and the receiver, then, the receiver selects the most appropriate precoding matrix from codebooks according to different channel state information (CSI). Therefore, the design of codebook plays an important role in the performance of the whole scheme. The symmetry-based hybrid precoder and combiner is a highly energy efficient structure in the millimeter-wave massive multiple-input multiple-output (MIMO) system, but at the same time, it also has the problems of high bit error rate and low spectral efficiency. In order to improve the spectral efficiency, we formulate the codebook design as a joint optimization problem and propose an iteration algorithm to obtain the enhanced codebook by combining the compressive sampling matching pursuit (CoSaMP) algorithm with the dictionary learning algorithm. In order to prove the validity of the proposed algorithm, we simulate and analyze the change of the spectral efficiency of the algorithm with the signal-to-noise ratio (SNR) and the number of radio frequency (RF) chains of different precoding schemes. The simulation results demonstrate that the spectral efficiency of the algorithm is obviously outstanding compared with that of the OMP-based joint codebook algorithm and the hybrid precoding algorithm with quantization algorithm under low SNR and different numbers of RF chains. Particularly, when SNR is lower than 0 dB, the proposed algorithm performs very close to the optimal unconstrained precoding algorithm. Full article

With the ubiquity of smartphones, the interest in indoor localization as a research area grew. Methods based on radio data are predominant, but due to the susceptibility of these radio signals to a number of dynamic influences, good localization solutions usually rely on additional sources of information, which provide relative information about the current location. Part of this role is often taken by the field of activity recognition, e.g., by estimating whether a pedestrian is currently taking the stairs. This work presents different approaches for activity recognition, considering the four most basic locomotion activities used when moving around inside buildings: standing, walking, ascending stairs, and descending stairs, as well as an additional messing around class for rejections. As main contribution, we introduce a novel approach based on analytical transformations combined with artificially constructed sensor channels, and compare that to two approaches adapted from existing literature, one based on codebooks, the other using statistical features. Data is acquired using accelerometer and gyroscope only. In addition to the most widely adopted use-case of carrying the smartphone in the trouser pockets, we will equally consider the novel use-case of hand-carried smartphones. This is required as in an indoor localization scenario, the smartphone is often used to display a user interface of some navigation application and thus needs to be carried in hand. For evaluation the well known MobiAct dataset for the pocket-case as well as a novel dataset for the hand-case were used. The approach based on analytical transformations surpassed the other approaches resulting in accuracies of 98.0% for pocket-case and 81.8% for the hand-case trained on the combination of both datasets. With activity recognition in the supporting role of indoor localization, this accuracy is acceptable, but has room for further improvement. Full article

Human action recognition has gathered significant attention in recent years due to its high demand in various application domains. In this work, we propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The proposed scheme develops a discriminative codebook and a hybrid feature vector by encoding the features extracted from CNNs (convolutional neural networks). We explore different CNN architectures for extracting spatio-temporal features. We employ an agglomerative clustering approach for codebook generation, which intends to combine the advantages of global and class-specific codebooks. We propose a Residual Vector of Locally Aggregated Descriptors (R-VLAD) and fuse it with locality-based coding to form a hybrid feature vector. It provides a compact representation along with high order statistics. We evaluated our work on two publicly available standard benchmark datasets HMDB-51 and UCF-101. The proposed method achieves 72.6% and 96.2% on HMDB51 and UCF101, respectively. We conclude that the proposed scheme is able to boost recognition accuracy for human action recognition. Full article