Psychotic disorders pose a significant public health concern, and early detection of relapse is a crucial aspect of their management. In this study, we investigate the effectiveness of unsupervised learning-based anomaly detection approaches for relapse detection in psychotic disorders, using data from wearable sensors as a proposed solution for the ICASSP Signal Processing Grand Challenge e-Prevention track 2 Relapse Detection. We explore both a global scheme, where a single model is trained on data from all patients, and a personalized scheme, where a unique model is trained for each patient. To evaluate the performance of different anomaly detection models, we extract features related to sleep, heart rate, accelerometer and gyroscope data, physical activity, and percentage of time the sensor is worn. Additionally, we examine the influence of the time window size used for feature extraction. Our findings suggest that the autoencoder is the best-performing model in the global scheme while personalized models show significant variability in performance across patients and on average outperform the general model. These results highlight the potential of unsupervised learning approaches for relapse detection in psychotic disorders and underscore the importance of personalized approaches for optimal assessment of these conditions

The upcoming sixth generation (6G) is expected to support a wide range of applications that require efficient sensing, accurate localization, and reliable communication capabilities. Furthermore, 6G is expected to catalyze the development of new use cases that will require working in extreme environmental and hazardous conditions and have ultra-small size and low-cost wireless devices. Thus, developing sustainable multi-functional wireless networks that are capable of incorporating billions of low-power devices and supporting their sensing and communication requirements on top of energy harvesting capability is of paramount importance. Motivated by this, we consider in this work a rate-splitting multiple access (RSMA)-based multifunctional wireless network with sensing, energy harvesting, and communication capabilities. We employ trust region policy optimization (TRPO), a deep  reinforcement learning (DRL) algorithm, to efficiently allocate the available resources and manage the interference between the three functionalities. TRPO/DRL is capable to learn a near-optimal policy for the resource allocation problem in a complex and dynamic environment. This enables us to obtain near-optimal transmit precoders, power splitting ratios, and ratesplitting among the common and private rates in a multiple access setting. Simulation results demonstrate the effectiveness of RSMA in mitigating the interference in such multi-functional networks and its capability to accommodate the rate and energy harvesting requirements of the devices while still capable of sensing multiple targets.

The transition from 5G to 6G networks necessitates network automation to meet the escalating demands for high data rates, ultra-low latency, and integrated technology. Recently, Zero-Touch Networks (ZTNs), leveraging AI and ML, have emerged as a promising solution for enhancing automation in 5G/6G networks but face significant challenges. Specifically, they are vulnerable to cyber-attacks, and the development of AI/ML-based cybersecurity mechanisms requires substantial specialized expertise and encounters model drift issues. Therefore, this paper proposes an automated security framework targeting Physical Layer Authentication (PLA) and Cross-Layer Intrusion Detection Systems (CLIDS) to address security concerns at multiple Internet protocol layers. The proposed framework employs drift-adaptive online learning techniques and a novel enhanced Successive Halving (SH)-based Automated ML (AutoML) method to automatically generate optimized ML models for dynamic networking environments. Experimental results illustrate that the proposed framework achieves high performance on the public ORACLE RF fingerprinting and CICIDS2017 datasets, showcasing its effectiveness in addressing PLA and CLIDS tasks within dynamic and complex networking environments. Furthermore, the paper explores open challenges and research directions in the 5G/6G cybersecurity domain. This framework represents a significant advancement towards fully autonomous and secure 6G networks, paving the way for future innovations in network automation and cybersecurity.

The phase-locked loop (PLL) is a commonly used synchronization control method for grid-tied inverters. The PLL-synchronized inverters tend to have poor stability robustness with weak grid interconnections, especially when the PLL is designed with a high control bandwidth. To tackle this challenge, this paper proposes an enhanced q-axis voltage integral damping (Q-VID) control, which not only stabilizes PLL-synchronized inverters in weak grids but also lifts the restriction on PLL bandwidth. This superior feature enables inverters to operate stably in ultraweak grids and with a superior transient response. Experimental tests confirm the performance of the method with 400-Hz PLL bandwidth under a short circuit ratio of 1.28 of the grids.

BER expressions for an uplink SCMA using joint Hybrid Interference Cancellation and Log MPA are derived under sorted channel conditions. Power allocation is done based on these BER expressions to achieve a Target BER for all users in the SCMA uplink scenario.

In Binary multiplications, the number of ones in the multiplier indicates how many addition operations are needed. Instead of using all the ones in the multiplier, Booth algorithm uses only the bit transitions. Any string of consecutive ones has two bit transitions; one transition at the least significant bit and the second one follows the most significant bit of the stirng. Booth algorithm converts any string of ones in the multiplier into two operations; a subtraction of the multiplicand shifted to the least significant bit of the string followed by an addition at the zero bit that terminates the string, regardless of the string length. Booth algorithm performance is excellent when the number of bit transitions is small. However, the performance of Booth algorithm deteriorates when the binary string contains double transitions; either a single one between two zeros or single zero between two ones. Applying Booth algorithm in this case requires two operations; an addition and a subtraction instead of one operation in comparison to the binary multiplier. A new method is described here that avoids using the algorithm for double-transition strings by flipping the bits of the leading transition thus reducing the double transition string into single transition. The flipping achieves the same outcome of Booth algorithm while saving half the number of partial products. Experimental results show the effectiveness of this approach in overcoming the drawbacks of the traditional Booth algorithm, while maintaining its decoding simplicity in comparison to radix-4 algorithm. The proposed algorithm is guaranteed to reduce the number of partial products to no more than N/2 for N bit operands. The proposed algorithm has been realized with considerable saving in hardware complexity in comparison to Radix-4 Booth lagorithm.

This study investigates the long-term effects of temperature variations on economic growth using a data-driven approach. Leveraging machine learning techniques, we analyze global land surface temperature data from Berkeley Earth and economic indicators, including GDP and population data, from the World Bank. Our analysis reveals a significant relationship between average temperature and GDP growth, suggesting that climate variations can substantially impact economic performance. This research underscores the importance of incorporating climate factors into economic planning and policymaking, and it demonstrates the utility of machine learning in uncovering complex relationships in climate-economy studies.

A method for incorporating synchronous generator capability curves (GCC) into the constraints of the optimal power flow (OPF) problem is proposed. The steady-state equivalent circuit of the synchronous machine in qd variables is added as a branch in the branch flow model (BFM) of the nonlinear power system equations. Semi-definite programming is used to formulate a computationally efficient, convex relaxation of the BFM-based OPF with the GCC constraints. This enables the inclusion of nonlinear GCC equations, which vary with terminal voltage magnitude and include the impact of rotor saliency and stator resistance, in the OPF. Numerical verification and case studies are provided.

Memristor technology has grown rapidly since its beginnings and become a potential candidate to revolutionize how data is stored and processed throughout all of the circuit theory. The memristor-based digital logic circuits can be a promising alternative to traditional integrated circuit technology when examining any advanced computer systems. In this work, we propose a hardware design for memristor-based resistive random access memory (RRAM) using Verilog hardware description language (Verilog HDL). The implementation results of a 256-byte memory on Xilinx Vivado targeted for the Artix-7 FPGA board demonstrate that the memristor-based RRAM outperforms the conventional RAM in terms of power consumption. Furthermore, the proposed architectures use less than 8% of the available hardware resources on the Artix-7 board. Hence, the proposed approach can be integrated into Internet of Things (IoT) applications with limited hardware resources or extended to memory systems in memory systems with larger capacities.

Smart grid applications heavily rely on communication infrastructures that offer flexibility, scalability, and cost-effectiveness to enable bi-directional information exchange across geographically distributed grid elements. Wireless cellular networks, such as LTE cat-M, provide extensive coverage at a reduced cost, both in terms of installation and power consumption. This paper presents a multi-node testbed to assess the suitability of LTE cat-M technology for a variety of smart grid applications, with distributed nodes collecting and transmitting data at a variable rate, from 0.25 to 100 frames per second (fps). Based on field experiments, an extensive performance analysis is presented with Key Performance Indicators (KPIs), such as delay, jitter, and frame loss. The impact of the number of smart grid nodes and propagation quality are also considered in the analysis. Finally, a calibration method to optimize the packet transmission time is presented with a 33.91% delay reduction under different conditions.

Polyphone disambiguation has long been a crucial problem for Chinese text-to-speech (TTS) systems. Researchers have greatly improved the performance of neural disambiguation models by leveraging pre-trained BERT models. However, the vast computation of BERT makes its deployment on edge devices extremely hard. To mitigate this problem, we present a hybrid model compression strategy incorporating both network pruning and knowledge distillation for polyphone disambiguation. In contrast to previous methods that compressed the model only through knowledge distillation, our approach can produce compact alternatives by directly pruning an existing BERT, thus remarkably reducing the training cost. Besides, we also provide a new dataset for common Chinese polyphonic characters (CCPC) to facilitate future research. Experimental results demonstrate that our approach can offer efficient disambiguation models with highly comparable performance to the BERT-based baseline.

As wireless sensor network (WSN) continues to evolve, the need for efficient and reliable throughput is becoming increasingly important. With the demand for data transmission and size growing, it is important to find ways to maintain expected throughput while also minimizing computational complexity. One promising approach is the use of multichannel technology. By generating multiple data channels, this technology enables the transmission of more data simultaneously, which can help to improve network reliability and reduce the risk of data loss. In this paper, we provide a comprehensive analysis of multichannel in wireless sensor network (WSN). Our investigation shows that multichannel technology offers promising performance for wireless technology innovations, with improved throughput and reduced collision probability. This technology could be a game-changer for the world of wireless communication, helping to drive innovation and progress in this important field.

With increased variable renewable generation and retirements of dispatchable thermal plants, net load variability and forecast error will increase. Many ISOs and RTOs have implemented or are considering implementing ramp products in their real-time markets to maintain both reliability and efficiency with the changing resource base. The design of any real-time market enhancement, however, must account for the fact that ISOs and RTOs use separate real-time engines for commitment, dispatch, and pricing. Depending on which engine is modified, there will be different impacts on reliability, system dynamics, system cost and prices. We present a rolling horizon simulation framework for the PJM Real-Time Market, consisting of a day-ahead model and real-time commitment, dispatch, and pricing engines that account for generator outages, net load variability and rolling short-term forecast error for a 2050 future capacity scenario. We compare the impacts across ramp product designs on system costs, reliability, prices, generation mix and generator revenues. We analyze the sensitivity of these results to the quantity of ramp product procured in the real-time commitment vs. dispatch and show that a balanced requirement added to both the commitment and dispatch engines provides the best performance across multiple metrics.

In the age of rapid technological evolution, synthetic realities and AI-generated content are transforming the very fabric of digital interaction. This article delves into the multifaceted landscape of artificial intelligence's role in the creation of auto-generated content, spanning text, images, videos, and 3D mediums. The challenges posed by such developments---ranging from misinformation campaigns to threats against traditional forensics---are examined in depth. At the same time, the article highlights emergent opportunities in the realms of security, privacy, and digital forensics that are spurred by these AI advancements. Within this discourse, the paper seeks to propose robust policies and regulatory frameworks that can uphold the integrity of digital media while ensuring societal safety. Balancing ethical considerations, the article underscores the necessity of international cooperation, technological innovation, and public awareness to navigate the transformative potential of synthetic media. Through a blend of case studies, future projections, and policy discussions, the article offers a comprehensive perspective on the intricate interplay between AI-enabled content and societal implications.

The digital landscape of the modern world has witnessed a remarkable evolution over the past few decades, with technological advancements permeating every facet of our lives. While these innovations have brought forth unprecedented convenience and connectivity, they have also exposed society to new vulnerabilities. Cybercrimes have surged in both frequency and sophistication, punctuating the digital era with high-profile incidents that have shaken industries and nations. Recent history serves as a stark reminder of the potential havoc that cybercriminals can unleash upon critical infrastructure, as exemplified by the notorious Colonial Pipeline breach, where a malevolent actor manipulated digital systems to demand ransom in the form of cryptocurrency. Traditionally, cybercriminal endeavors necessitated a specialized skill set and an in-depth understanding of intricate technological nuances. However, the landscape has transformed dramatically with the emergence of Generative Artificial Intelligence (AI). Previously the domain of highly specialized engineers, the tools required to orchestrate cybercrimes have become increasingly accessible due to the proliferation of advanced AI models such as ChatGPT and other modern Large Language Models (LLMs). These AI-driven capabilities have lowered the entry barrier for potential wrongdoers, enabling individuals with even basic technical aptitude to partake in cybercriminal activities. A cursory glance at contemporary news headlines underscores the growing ubiquity of cybercrimes. A relentless surge in cyberattacks serves as an alarming indication of the escalating threat posed by malicious actors in the digital realm. As each year unfolds, instances of cybercrime proliferate, impacting individuals, corporations, and governments alike. This trend signals a pressing need to comprehend the intersection between Generative AI and cybersecurity – a convergence that holds the potential to reshape the dynamics of digital malfeasance and defense. This research paper embarks on a journey to explore the intricate relationship between Generative AI and cybersecurity. Delving into the realm of AI-driven creativity and manipulation, we examine how the advent of Generative AI technologies has facilitated a paradigm shift in the landscape of cyber threats. As we navigate through this exploration, we unravel the challenges and opportunities that arise from this dynamic interplay. By delving into case studies, examining emerging trends, and scrutinizing potential countermeasures, this paper aims to shed light on the novel dimensions of cybersecurity in the era of Generative AI. Through a comprehensive analysis, we aim to equip readers with an informed understanding of the evolving cybersecurity landscape and the critical role that Generative AI plays therein.

Digital technologies in present day interconnect globally, providing a dynamic environment to support the educational needs of any learner within a novel technological ecosystem. The paper discusses the identified aspects of providing relevant digital accessibility to learners with various needs by this ecosystem, such as sensor support, knowledge provision from a variety of digital and non-digital repositories, and support to the motivation of the learner to acquire better knowledge in the classroom, museum, or in rehabilitation. A novel tool for assessment of such technological ecosystems, called Accessibility Barometer, is described.

This paper presents the development and implementation of a low-cost, portable scale utilizing a smartphone and image  processing technology. The main objective of this research is to explore the potential of using a compliant mechanism, markers, and  image processing techniques to accurately determine the weight of an object. We designed a 3D printed platform fitted with a  webcam to capture images of white markers on a black surface. The Image Processing Toolbox on MATLAB was used to detect  two parameters, the number of white pixels and the centroid positions of the white pixels with respect to the centre of the image in  each marker. Calibration is carried out to convert these two parameters into weight, hence accurately estimating the weight of an  object placed on the platform.

A fast analytical model for prediction of antenna S11 in presence of a layered medium; This model is based on plane wave expansion of antenna field and has two appriximations. The first is neglecting the evanescent modes of plane wave and the second is neglecting the multiple reflections from the antenna to the multilayer.