Many people use online platforms such as Instagram and Facebook on a daily basis. These applications often feature comment sections where users can express their opinions. Unfortunately, it is common for this feature to be used inappropriately, with people posting offensive comments towards individuals or groups. Defining what represents offensive content is difficult, as it varies by context, making AI removal challenging. In order to offer additional awareness on hateful and abusive conduct in social media, this work focuses on the SemEval-2023 task of binary sexism detection. Our data analysis indicates that adding a new label would be beneficial for enhancing the dataset's alignment with real-world applications. Towards this end, this work presents a simple baseline model using cosine similarity to assess comment alignment with different platform guidelines to highlight how these comments differ from the community guidelines.

Neck pain or cervicalgia is the discomfort in or around the cervical spine which is the region of spine located just below the head. One of the most common causes for neck pain is poor posture. Excessive use of electronic devices like computers, cell phones, etc aggravates the neck posture. This research focused on the development of a device that monitors cervical spine posture and provides feedback to the user to help them maintain a good neck posture. The device uses three flex sensors to measure neck bending and an MPU6050 IMU sensor for measuring acceleration and rotation in the neck movements. It employs an ERM motor to provide haptic feedback to the user about their neck posture. HC-05 Bluetooth modules have been used for wireless communication and a LiPo battery powers the device. A Bluetooth adapter, which contains a HC-05 and a USB-to-TTL converter, transmits sensor data to a computer running the Python script that feeds this data to a Long Short Term Memory (LSTM) Network to predict the user’s neck posture type. The neck band containing the sensors has a diameter of 110 mm and height of 120 mm. It is made up of flexible Thermo Polyurethane and has a velcro for easy wear. An enclosure made up of Polylactic Acid with its dimensions as 56 mm x 56 mm x 58 mm houses all the components of the device including the vibration motor. The enclosure has a push button, ports for uploading code and charging the battery, and a hole for sensor wires coming from the neck band. The LSTM model was trained on a dataset containing 3400 data samples. The device uses Python to feed the sensor data to the trained LSTM model which classifies the neck postures into 2 categories, good and bad. The Python script also sends the posture type predictions back to the device via Bluetooth. Real-time sensor data for every user wearing the device is saved in CSV files along with the predicted posture labels. Based on the LSTM model predictions about the neck posture type received from the python script, the Arduino code running on the device controls the vibration motor and alerts the user with two vibrations for bad posture and no vibrations for good posture. The LSTM model’s classification performance was evaluated using accuracy. Over 100 epochs, validation loss decreased from 70% to 28.51%, and validation accuracy increased from 40.59% to 95%. The accuracy obtained on the test set was 82%. User testing with 20 participants showed that the device accurately distinguished between good and bad neck postures with an overall accuracy of 79%, which varied by activity: 81% at a desk, 82% while walking, and 78% while sitting in different postures. User feedback indicated 75% found the device comfortable for extended wear, 85% found the neck band to be non-intrusive, 65% participants could easily set it up, and 40% reported minor discomfort from the vibration motor. Additionally, 80% felt the device feedback helped them correct their neck posture with 75% finding the vibration alert effective, and 70% agreeing that the usage of the device improved their neck posture awareness.

We present an unique approach to demonstrating probabilistic bits (p-bit) leveraging perimeter-gated single-photon avalanche diodes (pg-SPADs). By exploiting the pg-SPAD's dark count rate (DCR) modulation property, we show a compact circuit design approach for probabilistic computing. Measured results from an array of pg-SPAD-based p-bits fabricated in 0.35 µm CMOS validate the tunable random number generation capability of these devices. In addition, experimentally calibrated circuit simulations-based on measured device data-confirm that these pg-SPAD-based p-bits can scale efficiently to form large probabilistic circuits (p-circuits). This work highlights an viable route toward building energy-efficient, CMOScompatible p-circuits for resource-constrained and largescale applications alike.

In this paper we continue our previous investigation about the use of stress function in the flow of generalized Newtonian fluids through conduits of circular and noncircular (or/and multiply connected) cross sections where we inspect the flow of Ellis fluids in tubes of elliptical cross sections. We derive analytical expressions for the flow velocity profile and for the volumetric flow rate. The obtained analytical expressions were tested against the available analytical expressions for the special cases of Newtonian flow in circular tubes, Newtonian flow in elliptical tubes and Ellis flow in circular tubes and the results were identical. The obtained analytical expressions were also tested for sensible trends, tendencies and correlations and they passed all these tests.

This article presents a comprehensive exploration of the architecture and various approaches in the domain of cloud computing and software-defined networks. The salient points addressed in this article encompass: Foundational Concepts: An overview of the foundational concepts and technologies of cloud computing, including software-defined cloud computing. Algorithm Evaluation: An introduction and evaluation of various algorithms aimed at enhancing network performance. These algorithms include Intelligent Rule-Based Metaheuristic Task Scheduling (IRMTS), reinforcement learning algorithms, task scheduling algorithms, and Priority-aware Semi-Greedy (PSG). Each of these algorithms contributes uniquely to optimizing Quality of Service (QoS) and data center efficiency. Resource Optimization: An introduction and examination of cloud network resource optimization based on presented results and practical experiments, including a comparison of the performance of different algorithms and approaches. Future Challenges: An investigation and presentation of challenges and future scenarios in the realm of cloud computing and software-defined networks. In conclusion, by introducing and analyzing simulators like Mininet and CloudSim, the article guides the reader in choosing the most suitable simulation tool for their project. Through its comprehensive analysis of the architecture, methodologies, and prevalent algorithms in cloud computing and software-defined networking, this article aids the reader in achieving a deeper understanding of the domain. Additionally, by presenting the findings and results of conducted research, it facilitates the discovery of the most effective and practical solutions for optimizing cloud network resources.

The shift to battery electric vehicles (BEVs) is a key step towards reducing greenhouse gas (GHG) emissions and decreasing dependence on fossil fuels, ultimately achieving Sustainability Development Goals and more specifically, a more sustainable form of transportation. However, while BEVs help eliminate tailpipe emissions, understanding and consequently optimizing their energy efficiency is still an ongoing task, as battery life is often affected by various driving conditions, including driving behavior, terrain and sometimes weather. Traditional linear modeling techniques often lack the ability to capture the non-linear and complex relationships found in real-world scenarios. For this reason, this study introduces a more sophisticated statistical framework for energy consumption profiling for BEVs, through an in-depth exploratory analysis on key influencing factors and the implementation of both a linear and a custom generalized additive model (GAM) for data modeling. The experimental results showcase that the integration of smoothing splines instead of linear regression modeling further refines the proposed model by offering improved accuracy of the order of 20%.

A novel, compact MIMO antenna design is introduced, measuring only 23x38 mm², suitable for ultrawideband (UWB) applications. The antenna features two square-shaped elements and a T-shaped stub with a vertical slot to minimize mutual coupling. Additional strips between the monopole elements create a band notch in the 5.15-5.85 GHz WLAN frequency range. The antenna’s performance is evaluated based on impedance matching, mutual coupling, VSWR, and correlation coefficient (ECC). Simulation results demonstrate an impedance bandwidth of 2.7-13.4 GHz (S11 ≤ -10 dB) and an envelope correlation coefficient of less than 0.002 across the frequency band. The isolation between the two antenna elements exceeds -20 dB throughout the band, covering WCDMA, WLAN, WiMax, and UWB frequency ranges.

Theater performers express emotions while acting through a variety of facial expressions and vocal techniques. To improve their skills or while preparing for performances, actors rehearse their scripts and practice their facial expressions and dialogue delivery. Computer vision tools can be utilized to detect emotions from facial expressions. Audio processing tools can be used to analyze vocal characteristics like tone, pitch, loudness, etc providing insights into the emotional delivery of actors through their speech. This research focuses on developing an application that combines computer vision and audio analysis for emotion recognition, aimed at helping actors enhance their skills and performances. The emotion detection tool utilizes deep learning models to predict emotions based on actors’ facial expressions and speech. The emotion conveyed by the user through facial expressions is predicted by utilizing Mediapipe’s FaceMesh model and Blendshapes. A pre-trained wav2vec2 based audio emotion classification model predicts the emotion conveyed in the user’s speech. The emotions detected in the user’s video and speech are logged into a PDF report which also contains a customized list of links of tutorials which a particular user could learn from to improve their acting skills. The proposed emotion recognition system was tested with 20 volunteers for detecting emotions in both video and audio data. 65% of the participants confirmed the system accurately identified their facial expressions, and 75% found it useful for assessing their dialogue delivery. Participants appreciated the immediate feedback and detailed PDF reports, which proved to be helpful for them to identify their mistakes and enhance their acting skills. This multimodal approach shows promise as a valuable resource for beginner actors trying to improve their skills.

This paper explores the integration of Artificial Intelligence Generated Content (AIGC) with human-machine intelligence (HMI) to enhance the functionality of Intelligent Transportation Systems (ITS). Adaptive decision-making mechanisms are crucial as transportation networks become increasingly complex, generating vast real-time data from vehicles, infrastructure, and users. AIGC plays a transformative role in optimizing traffic flow through dynamic routing and real-time traffic management. At the same time, human intelligence ensures that these systems remain responsive to ever-changing real-world conditions. In terms of safety, AIGC is employed to simulate complex driving scenarios for autonomous vehicle training and detect traffic anomalies, with human oversight providing contextual decisionmaking in unexpected or ambiguous situations. For sustainability, AIGC develops data-driven strategies to reduce emissions and energy consumption, while human expertise ensures alignment with ethical and environmental goals. This synergy between AIGC and human intelligence is vital for refining real-time decision-making, ensuring both accuracy and adaptability across diverse ITS scenarios. This paper offers a comprehensive literature review on core and supporting AIGC technologies and their applications in key ITS domains. Case studies and initiatives from industry leaders demonstrate practical implementations of AIGC-driven HMI collaboration in ITS. We also address challenges such as compatibility with legacy systems, data privacy, model bias, and scalability. The paper concludes by outlining future research directions, emphasizing the need for scalable, interpretable, and ethically compliant AIGC models. By prioritizing humanmachine intelligence, this work advances the safe, efficient, and sustainable deployment of AIGC-driven HMI solutions in modern transportation networks.

In the era of personalized communication, effective marketing email campaigns hinge on the ability to predict and tailor content to individual recipients’ preferences. This paper explores innovative approaches to text prediction by leveraging idiolect and sociolect modeling derived from social media interactions, specifically Twitter. By analyzing the linguistic patterns of individual users (idiolect) and their social circles (sociolect), we aim to enhance the accuracy of word predictions, thus saving keystrokes and improving message relevance. Our methodology incorporates context-sensitive and context-insensitive prediction modules trained on user-generated tweets, evaluating their performance through keystroke savings metrics. The findings highlight the potential of personalized text prediction in optimizing marketing strategies, ultimately fostering more engaging and effective email communications. This research contributes to the field of digital marketing by providing insights into how linguistic modeling can drive personalization in automated messaging systems.

Gradient-based flux observers offer promise in permanent magnet synchronous motor (PMSM) encoderless control due to their computational efficiency and adaptability but face challenges in gain tuning and noise sensitivity. This paper proposes a robust optimized flux observer combining the huber loss function (HLF) and root mean square propagation (RMSProp) algorithm to overcome these limitations. Firstly, a robust nonlinear flux observer is developed with the HLF to enhance the steady state performance of the encoderless control by leveraging its smoothness and noise suppression capabilities. Secondly, the RMSProp algorithm is employed to optimize the gradient search process, dynamically adjusting the step size in real-time based on historical gradient information to ensure improved dynamic response. Additionally, the Lyapunov stability criterion is utilized to analyze the stability of the proposed controller and prove the bounds of its observation error. Finally, experimental results confirm the proposed control strategy, achieving high-precision position estimation. Angular estimation errors under no-load and load conditions are reduced to below-0.09 rad and-0.08 rad, respectively, compared to-0.22 rad and-0.15 rad with conventional methods.

Ferrite plates are essential elements in wireless power transmission systems. Their presence is critical to achieving adequate magnetic coupling and minimizing stray magnetic field. At the same time, reducing the volume of ferrite used in the vehicle assembly (VA) offers significant benefits in terms of cost and weight reduction. Topology optimization methods are particularly effective tools for applications like Wireless Power Transfer, where the magnetic field is not confined to a well-defined volume, unlike in classical electrical machines. In the present work, the Solid Isotropic Material with Penalization (SIMP) methodology is used to achieve an optimized reduced-volume design of the ferrite plate of a SAE-compliant VA that maintains magnetic interoperability with the starting design. The optimized plate was manufactured and its performance was experimentally validated and compared to the original VA. The results show that the fabricated plate is able to maintain a mutual inductance reduction of less than 10% with a 55% reduction in material volume, thus meeting the magnetic interoperability requirements outlined in the SAE J2954 standard. The impact of the material reduction on the system's losses was also evaluated, revealing that the proposed solution results in a 2% increase in losses when tested on a 3.3 kW test bench.

High-temperature superconductors (HTS) could enable a new paradigm for lightweight and efficient electric machine designs. While superconducting rotors have been successfully implemented, the adoption of superconducting armatures has been hindered by high AC losses, leading to impractically high cryogenic cooling demands. This paper introduces a slotted torus axial flux machine (AFM) topology to address this challenge, leveraging toroidal windings to align HTS tapes with slot leakage flux, avoiding complex end-windings while achieving AC losses at least an order of magnitude below HTS armatures with tooth-coil tape orientation. A 1-MW proof-of-concept aviation motor design demonstrates the feasibility of this approach, achieving an active torque density of 51.1 Nm/kg with HTS AC losses below 0.03 % of the output power and total cryogenic losses slightly exceeding 0.1 % when including the steel losses. The study highlights the importance of HTS tape orientation within the slot and using flux diverters for the end-windings to minimize losses. Further, it illustrates how an even higher cryogenic efficiency can be reached by lowering the electrical frequency. The promising results motivate further development and optimization of superconducting machines with this topology.

Generative Artificial Intelligence (GenAI) has the potential to transform higher education by generating human-like content. The advancement in GenAI has revolutionised several aspects of education, especially subject and assessment design. In this era, it is crucial to design assessments that challenge students and cannot be solved using GenAI tools. This makes it necessary to update the educational content with rapidly evolving technology. The assessment plays a significant role in ensuring the students' learning, as it encourages students to engage actively, leading to the achievement of learning outcomes. The paper intends to determine how effectively GenAI can design a subject, including lectures, labs and assessments, using prompts and custom-based training. This paper aims to elucidate the direction to educators so they can leverage GenAI to create subject content. Additionally, we provided our experiential learning for educators to develop content, highlighting the importance of prompts and fine-tuning to ensure output quality. It has also been observed that expert evaluation is essential for assessing the quality of GenAI-generated materials throughout the content generation process.

Adversarial examples undermine the robustness of deep neural networks (DNNs), posing a major challenge to deep learning. Although existing research has focused on external representations, such as shifts in feature distributions, internal dependencies between features, essential for model decisions, are often overlooked. Adversarial examples disrupt these dependencies, but quantifying such changes in high-dimensional feature spaces remains computationally challenging and underexplored. To address these challenges, we propose the Copula-based Adversarial Feature Index (CAFI), a novel metric that quantifies feature dependencies in the copula space. Copulas enable explicit modeling of feature interdependencies, overcoming limitations of methods that treat features as independent. By leveraging the degrees of freedom (dofs) in copula space, CAFI quantifies how adversarial perturbations destabilize these feature dependencies. Robust models maintain stable dependencies under attack, while non-robust models exhibit significant disruption. Beyond its diagnostic utility, CAFI also serves as a regularization tool to enhance adversarial training. Experimental results in multiple datasets show that incorporating CAFI regularization improves robustness by up to 8.61% against strong attacks like FWA, while preserving competitive accuracy on benign examples. The code is available at https://github.com/lynneliu-creator/CAFI.

We propose a new high-capacity photonic Ising machine (PIM) that employs ultrafast coherent optical pulse propagation in a 50 km-long passive recirculating fiber loop and analyze its performance including a new bifurcation mechanism. Although analog optical phenomena (laser oscillation) such as those provided by a degenerate optical parametric oscillator (DOPO) and an opto-electric oscillator (OEO) have been used in conventional PIMs to generate a third-order polynomial bifurcation, in other words a Van der Pol type bifurcation with the rotating wave approximation, we newly adopted a passive recirculating fiber loop and digital feedback nonlinearity for the generation of a pitchfork-type bifurcation. The present PIM has no laser oscillation. The generation of the bifurcation can be very stably realized by introducing a digital nonlinearity, for example a tanh function, which enabled us to solve a max-cut problem of 100,000 nodes. We further describe the first result obtained for a 1 million node max-cut problem by employing the present PIM software in a high-performance computer (HPC).

To detect contaminants accidentally included in packaged foods, food industries use an array of systems ranging from metal detectors to X-ray imagers. Low density plastic or glass contaminants, however, are not easily detected with standard methods. If the dielectric contrast between the packaged food and these contaminants in the microwave spectrum is sensible, Microwave Sensing (MWS) can be used as a contactless detection method, which is particularly useful when the food is already packaged. In this paper we propose using MWS combined with Machine Learning (ML). In particular, we report on experiments we did with packaged cocoa-hazelnut spread and show the accuracy of our approach. We also present an FPGA acceleration that runs the ML processing in real-time so as to keep up with the throughput of a production line.

Congestion due to morning and evening traffic peaks has caused economic losses amounting to billions of dollars annually. Thus, accurately predicting the departure time of commuters is of interest to transportation planners, engineers, and elected officials alike. We develop a statistically-informed deep learning approach to improve commuter departure time prediction models. Specifically, we leverage elements of the proportional hazards model, a class of time-to-event prediction approaches, to augment vanilla deep neural network (DNN) architectures. The proposed approach also employs collaborative filtering to segment the commuter population into distinct behavioral classes, allowing tailored predictions for specific commuter profiles. We find that our class of survival analysis-enhanced DNNs outperforms conventional neural networks in predicting trip departure times, while also offering more interpretability through the hazard coefficients.