Exploring the growth and physiological response mechanisms of rice under continuous drought stress circumstances can provide a significant scientific foundation and technological assistance for meeting drought difficulties, improving drought resistance and rice (Oryza sativa L.) output, and ensuring food security. In this study, a rice field experiment was conducted under a rain shelter with five different treatments set up: P1 (drought stress from tillering stage), P2 (drought stress from jointing-booting stage), P3 (drought stress from heading-flowering stage), P4 (drought stress from grain filling stage), and CK (adequate water management throughout the growth stage). Continuous drought stress from different growth stages with four levels (mild, medium, serious, and extreme). The results showed that the effects of different drought stress treatments on rice growth varied significantly. Compared with the CK treatment, plant height was reduced by 12.10%, 8.14%, 3.83%, and 1.06% in the P1, P2, P3, and P4 treatments, respectively; and the number of tillers was reduced by 23.83%, 18.91%, 13.47%, and 8.68%, respectively. With the increase in drought stress levels, SPAD values and Rubisco activity of rice leaf continued to decrease; SOD activity showed a decreasing trend, but the decreasing trend of POD and CAT activities was not significant, while MDA content showed an increasing trend. For yield components, continuous drought stress significantly reduced spike length, effective number of spikes, thousand grain weight, grain number per spike, and fruiting rate of rice compared to CK treatments during the growth period. In general, continuous drought stress during the early growth period affected the effective spike number and the grain number per spike. Continuous drought stress after the grain filling stage had the least effect on yield and water use efficiency was much higher than other treatments. The results of these studies reveal the response of rice growth and physiology to continuous drought stress, which is important for agricultural practices.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

This study presents an advanced Simulated Shearer Machine Cutting Experiment System enhanced with digital twin technology. Central to this system is a simulated shearer drum, designed based on similarity theory to mirror the operational dynamics of actual mining cutters accurately. The setup incorporates a modified machining center equipped with sophisticated sensors that monitor various parameters such as cutting states, forces, torque, vibration, temperature and sound. These sensors are crucial for precisely simulating the shearer cutting actions. The integration of digital twin technology is pivotal, featuring a real-time data management layer, a dynamic simulation mechanism model layer, and an application service layer that facilitates virtual experiments and algorithm refinement. This multifaceted approach allows for in-depth analysis of simulated coal cutting, utilizing sensor data to comprehensively evaluate the shearer's performance. The study also includes tests on simulated coal samples. The system effectively conducts experiments and captures cutting condition signals via the sensors. Through time-domain analysis of these signals, gathered while cutting materials of varying strengths, it is determined that the cutting force signal characteristics are particularly distinct. By isolating the cutting force signal as a key feature, the system can effectively distinguish between different cutting modes. This capability provides a robust experimental basis for coal-rock identification research, offering significant insights into the nuances of shearer operation.

The abstract should be a total of about 250 words and structured to contain the following headings: Background/Objectives, Methods, Results, Conclusions. Background/Objectives: Place the question addressed in a broad context and highlight the purpose of the study; Methods: Describe briefly the main methods or treatments applied. Include any relevant preregistration numbers, and species and strains of any animals used; Results: Summarize the article’s main findings; Conclusions: Indicate the main conclusions or interpretations. The abstract should be an objective representation of the article: it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions. Clinical trial abstracts should include items that the CONSORT group has identified as essential.

The collaboration of multimodal transport documents is the foundation for conducting multimodal transport operations. Blockchain technology can effectively address trust issues and information sharing difficulties in current multimodal transport document collaboration. However, in current blockchain-based electronic document research, the bottleneck problem lies in the collaboration of multiparty in multimodal transport under the "one-bill coverage system". We design a blockchain platform architecture for multimodal transport, reshaping collaboration processes for different modes of transport based on the blockchain platform. It proposes a collaboration model for multimodal transport under the "one-bill coverage system" and performs model solving and case analysis. The obtained collaboration strategies are embedded into the platform's application layer. Finally, using Solidity language, it writes smart contracts related to multimodal transport under the "one-bill coverage system " and deploys and executes them on the Remix platform.

Ambulatory heart rate (HR) monitors that acquire electrocardiogram (ECG) or/and photoplethysmographm (PPG) signals from the torso, wrists, or ears are notably less accurate in tasks associated with high levels of movement compared to clinical measurements. However, reliable estimation of HR can be obtained through data fusion from different sensors. These methods are especially suitable for multimodal hearable devices, where heart rate can be tracked from different modalities, including electrical ECG, optical PPG, and sounds (heart tones). Combined information from different modalities can compensate for single source limitations. In this paper, we evaluate the possible application of data fusion methods in hearables. We assess data fusion for heart rate estimation from simultaneous in-ear ECG and in-ear PPG, recorded on eight subjects while performing 5-minute sitting and walking tasks. Our findings show that data fusion methods provide a similar level of mean absolute error as the best single-source heart rate estimation but with much lower intra-subject variability, especially during walking activities. We conclude that data fusion methods provide more robust HR estimation than a single cardiovascular signal. These methods can enhance the performance of wearable devices, especially multimodal hearables, in heart rate tracking during physical activity.

Multimodal emotion classification (MEC) involves analyzing and identifying human emotions by integrating data from multiple sources, such as audio, video, and text. This approach leverages the complementary strengths of each modality to enhance the accuracy and robustness of emotion recognition systems. However, one significant challenge is effectively integrating these diverse data sources, each with unique characteristics and levels of noise. Additionally, the scarcity of large, annotated multimodal datasets in Bangla limits the training and evaluation of models. In this work, we unveiled a pioneering multimodal Bangla dataset, MAViT-Bangla (Multimodal Audio Video Text Bangla dataset). This dataset, comprising 1002 samples across audio, video, and text modalities, is a unique resource for emotion recognition studies in the Bangla language. It features emotional categories such as anger, fear, joy, and sadness, providing a comprehensive platform for research. Additionally, we developed a framework for emotion recognition that employs a cross-modal attention mechanism among unimodal features. This mechanism fosters the interaction and fusion of features from different modalities, enhancing the model’s ability to capture nuanced emotional cues. The effectiveness of this approach was demonstrated by achieving an F1-score of 0.64, a significant improvement over unimodal methods.

Aiming at the problems of high labor intensity and high cost of manual picking, high loss rate of mechanical picking seeds, low mechanization level and difficult to guarantee the quality of picking plates in the process of picking plates of edible sunflower. Based on the principle of manual plate taking, a plate taking control system for sunflower harvesting table was designed. Through the research and analysis of the principle of taking the plate of the edible sunflower harvesting table. According to the actual operation requirements, the overall scheme of the sunflower plate control system is determined, and the control strategy of imitating artificial low loss harvesting is designed. To reduce the grain loss in the process of taking the plate and improve the control accuracy of the system on the movement speed and displacement of the key components in the process of taking the plate, a trapezoidal acceleration and deceleration control algorithm is designed as the control algorithm of taking the plate. To verify the working performance of the plate control system, with the absolute error, relative error and total loss rate of the harvest as objectives. The bench and field verification experiments were both carried out. The bench experiment showed that the speed error of the plate parts was not more than 0.028 m/s. In the bench experiments of the device, the maximum positioning error was 1.25 mm, the average relative error is only 0.94 %, and the grain loss rate was not more than 2.26 %. It result showed that the system algorithm was reliable, the positioning accuracy was high, and the taking plate operation can be completed well. The field verification experiment showed that the forward speed of the unit was in the range of 0.4~0.8 m/s, and the total loss rate of harvest was less than 5 %. When the forward speed is 0.6 m/s, the minimum harvest loss rate is 2.32 %, and which indicated the control system meets the requirements of sunflower harvesting operation.

Electric tractors have many advantages, including high torque, excellent controllability, energy efficiency, simple structure, and electric interface for expansion. However, a significant limitation lies in their endurance. This study presents the design of an extended-range power supply system to ensure continuous endurance of electric tractor. The objective is to provide a continuous power source for our self-developed electric tractor while preserving the benefits of electric propulsion. Extended-range power systems utilize a primary mover, typically an oil-fueled internal combustion engine, to drive the generator for electricity generation, and the generated AC form electricity is subsequently converted into stable DC bus voltage by a power electronic converter. The hardware and control design of the extended-range power supply system have been finalized and validated through experimental trials. Results demonstrate the system’s capability to sustain a stable DC bus voltage amidst disruptions such as sudden load shifts and fluctuations in prime mover speed. Even with 50% sudden load change, the voltage drop is within 12% and could recover to ±3% within 4 seconds. The range extender can be used alone without battery to power the electric tractor, or it can used in parallel with other extended-range extenders or battery thanks with the droop control ability for power sharing.

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual and textual features, and hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. Experimental results demonstrate that, compared to the current multimodal state-of-the-art methods, the proposed method achieves significant performance improvements in knowledge graph link prediction tasks. This proves that the proposed method effectively addresses the problem of multimodal feature fusion in knowledge graph link prediction tasks.

Improper sitting positions are known as the primary reason for back pain and the emergence of musculoskeletal disorders (MSD) among individuals who spend prolonged time working with computer screens, keyboards, and mice. At the same time, it is well understood that automated technological tools can play an important role in the process of unhealthy habit alteration, so plenty of research efforts are focused on research and technology development (RTD) activities that aim to provide support to the prevention of back pain or the development of MSD. Here, we report on creating a new resource in support of RTD activities aiming at the automated detection of improper sitting positions. It consists of multimodal multisensory recordings of 100 persons made with a video recorder, camera, and wrist-attached sensors that capture physiological signals (PPG, EDA, Skin temperature), as well as motion sensors (three-axis accelerometer). Our multimodal multisensory dataset (MMD-MSD) opens new opportunities for modeling the body stance (sitting posture and movements), physiological state (stress level, attention, emotional arousal, valence), and performance (success rate on the Stroop test) of people working with a computer. Finally, we demonstrate two use cases: improper neck posture detection from pictures and cognitive load detection from physiological signals.

The human mind is multimodal. Yet most behavioral studies rely on century-old measures of behavior—task accuracy and latency (response time). Multimodal and multisensory analysis of human behavior creates a better understanding of how the mind works. The problem is that designing and implementing these experiments is technically complex and costly. This paper introduces versatile and economical means of developing multimodal-multisensory human experiments. We provide an experimental design framework that automatically integrates and synchronizes measures including electroencephalogram (EEG), galvanic skin response (GSR), eye-tracking, virtual reality (VR), body movement, mouse/cursor motion and response time. Unlike proprietary systems (e.g., iMotions), our system is free and open-source; it integrates PsychoPy, Unity and Lab Streaming Layer (LSL). The system embeds LSL inside PsychoPy/Unity for the synchronization of multiple sensory signals—gaze motion, electroencephalogram (EEG), galvanic skin response (GSR), mouse/cursor movement, and body motion—with low-cost consumer-grade devices in a simple behavioral task designed by PsychoPy and a virtual reality environment designed by Unity. This tutorial shows a step-by-step process by which a complex multimodal-multisensory experiment can be designed and implemented in a few hours. When conducting the experiment, all of the data synchronization and recoding of the data to disk will be done automatically.

In response to the issues of sensor noise and accumulated motion errors that lead to low positioning accuracy and insufficient robustness during large maneuvers or continuous flight of small unmanned aerial vehicles (UAVs) in complex environments, this paper proposes a multi-source and multimodal data fusion method. Initially, it employs a multimodal data fusion of various sensors including GPS (Global Positioning System), IMU (Inertial Measurement Unit), and visual sensors to complement the strengths and weaknesses of each hardware component, thereby eliminating motion errors to enhance accuracy. To mitigate the impact of sudden changes in sensor data, the method introduces a digital twin UAV data source. By utilizing the Extended Kalman Filter algorithm, it fuses data from both the real UAV and its digital twin, and the filtered positional information is fed back into the control system of the real UAV. This enables real-time correction of UAV positional deviations caused by sensor noise and environmental disturbances. The multi-source multimodal fusion Kalman filter method proposed in this paper significantly improves the positioning accuracy of UAVs in complex scenarios and the overall stability of the system. This method holds significant value in maintaining high-precision positioning in variable environments and has important practical implications for enhancing UAV navigation and application efficiency.

Molecular analysis of growing teratoma syndrome has not been extensively studied. Here, we report a 14-year-old boy with a growing mass during treatment for a mixed germ cell tumor of the pineal region. Tumor markers were negative; thus, growing teratoma syndrome was suspected. A radical resection via the occipital transtentorial approach was performed, and histopathological examination revealed a teratoma with malignant features. Methylation classifier analysis confirmed the diagnosis of teratoma, and DMRT1 loss and 12p gain were identified by copy number variation analysis, potentially elucidating the cause of growth and malignant transformation of the teratoma. The patient remains in remission after intense chemoradiation treatment as a high-risk germ cell tumor.

Sepsis still remains one of the most difficult conditions to diagnose as it presents unspecific clinical signs and symptoms, which makes early detection crucial. Our study aimed to enhance the accuracy of sepsis diagnosis by integrating multimodal monitoring technologies with traditional diagnostic methods. The research involved 121 newborns, comprising 39 cases of late-onset sepsis, 35 cases of early-onset sepsis, and 47 control subjects. Biosignals including pulse oximetry (PO), near-infrared spectroscopy (NIRS), and skin temperature (ST) were continuously monitored and an algorithm was developed using Python for identifying early signs of sepsis. The model demonstrated the ability to detect sepsis 6 to 48 hours in advance with an accuracy rate of 87.67% ± 7.42%. Sensitivity and specificity were recorded at 76% and 90%, respectively, with NIRS and ST having the most significant impact on predictive accuracy. Despite the promising results, limitations such as sample size, data variability, and potential biases were noted. The findings highlight the critical role of non-invasive biosensing methods in conjunction with traditional biomarkers and cultures, offering a robust framework for early sepsis detection and improved neonatal care. Further studies are recommended to validate these results across diverse clinical settings.

Microbial foodborne pathogens can cause major risks to public health and the food industry. Rapid and accurate detection of these pathogens is crucial to prevent outbreaks and ensure food safety. Traditional single-mode biosensing approaches have their limitations in terms of specificity, sensitivity, and speed. Over the years, there has been an increasing research interest in developing multimodal biosensing strategies that integrate multiple sensing techniques to achieve enhanced accuracy, efficacy, and precision in foodborne pathogen detection. This article review paper explores the current state of multimodal biosensing technologies and their promising applications in the food industry. We discuss various integrated biosensing platforms, including optical, electrochemical, and nanomaterial-based systems, among others. The advantages, challenges, and future prospects of multimodal biosensing for foodborne pathogens are thoroughly examined, highlighting the potential impact of these advanced technologies on food safety and public health.

Federated learning (FL) has become a burgeoning and attractive research area, which provides a collaborative training scheme for distributed data sources with privacy concerns. Most existing FL studies focus on taking unimodal data, such as images and text, as the model input and resolving the heterogeneity challenge, i.e., the non-identically distributed (non-IID) challenge caused by data distribution imbalance related to data labels and data amount. In real-world applications, data are usually described by multiple modalities. However, to the best of our knowledge, only a handful of studies have been proposed to improve the system performance by utilizing multimodal data. In this survey paper, we identify the significance of this emerging research topic – multimodal federated learning (MFL) and perform a literature review on the state-of-art MFL methods. Furthermore, we categorize multi-modal federated learning into congruent and incongruent multimodal federated learning based on whether all clients possess the same modal combinations. We investigate the feasible application tasks and related benchmarks for MFL. Lastly, we summarize the promising directions and fundamental challenges in this field for future research.

In this paper, the Hafele‐Keating experiment and the geostationary orbit satellite of related physics problems of are analyzed and discussed in detail. If researchers read the paper and think about it, It will be found that the Hafele‐Keating experiment and the geostationary satellite problem prove that some of the core ideas and theories of relativity are seriously wrong. Isnʹt that a very serious problem in physics? Canʹt this cause the academic circles to pay great attention to it? Isnʹt this worthy of in‐depth analysis and research? The core of the paper is to point out that there are problems with the space concept and the reference system theory of classical physics and relativity, And that would bring up a whole host of physics problems. It takes a concerted effort from the academic community, Do furtherin‐depth analysis and research. Strive forthe further discovery and perfection of physics theory.

The paper presents a new type of hydraulic clutch operating with magnetorheological (MR) fluids and the results achieved from both theoretical analysis and experimental measurement. The hy-draulic clutch system of its own design with MR working fluid and a rotating magnetic field lo-cated is designed. The principle of this clutch is to use a rotating magnetic field created by an al-ternating current electromagnet to set the MR fluid in motion. In the tests of the hydraulic clutch with a rotating magnetic field, MR fluid produced on their own, consisting of solid iron particles of various diameters mixed with a silicone oil, are used as working fluids. The rheological properties of MR fluids are assessed on the basis of tests carried out with a Brookfield DV2T rheometer equipped with a magnetic device for generating the magnetic field of its own design. The char-acteristics of the hydraulic clutch with MR working fluid and the rotating magnetic field are tested on a specially built test stand. As a result of the research, it has been found that the torque transmitted by the clutch is the greater, the higher the rotational speed of the magnetic field and the lower the rotational speed of the beaker in which the working fluid is placed, and that the greatest torque occurs for the working fluid with the highest iron content. Based on the analysis of the structure and characteristics of the clutch in which the magnetic field is used, it has been shown that the design of the developed clutch is similar to that of an induction clutch, and its characteristics correspond to the characteristics of the eddy current clutch. Therefore, the proposed new clutch working with MR fluid and the rotating magnetic field can be applied to stationary power transmission system similarly to an eddy current clutch.

The present study analyzed the effect of temperature, pH, retention time, pretreatment and mixing ratio on the anerobic digestion process. The parameters during the anaerobic co digestion of cow manure and food waste were then optimized using the Taguchi experimental design method. ANOVA is carried out to find the significant parameters which influence the biogas production. Experimental tests were carried out at laboratory scale reactors kept at different temperatures (28 °C, 35 °C, and 50 °C). The specific methanogenic Performance (SMP) during anerobic digestion at higher temperatures was characterized with the analysis of acetate, propionate, butyrate, hydrogen, glucose, and formate. The improvement of biogas production with different pre-treatment i.e., ultrasonic, autoclave, and microwave techniques also analysed. The results showed that reactor that maintained at 35 °C showed the highest biogas production. While the reactor that maintained at lower temperature (28 °C) produced the lower volume of biogas. As the retention time increases, the amount of biogas produced increases. Methanogenic activities of microorganisms reduced at higher temperature conditions (65 °C). Biogas production increased by 28.1%, 20.23%, and 13.27 % when the of substrates treated with ultrasonic, autoclave, and microwave, respectively, compared to the untreated substrate. The optimized condition for the highest biogas production during anaerobic co digestion of food waste and cow manure is temperature of 35 °C, pH of 7 and mixing ratio (CM: FW=1.5:0.5). ANOVA showed that temperature is the most important input parameter affecting biogas production, followed by mixing ratio.

There have been multiple technological advancements that promise to gradually enable devices to measure and record signals with high resolution and accuracy in the domain of Brain Computer Interfaces (BCI). This review paper provides a comprehensive overview of fNIRS, EEG, and fMRI, including their principles, advantages, limitations, and integration with other modalities for advanced BCIs. The paper highlights the advantages of integrating multiple modalities, such as increased accuracy and reliability, and discusses the challenges and limitations of multimodal integration. Applications of advanced BCIs in clinical, assistive, gaming, and entertainment domains are also discussed. Furthermore, we explain the data acquisition approaches for each of these modalities. We also demonstrate various software programs that help in extracting, cleaning, and refining the data. We conclude this paper with discussion on the available literature on data acquisition approaches and a comparison of the ease of use for each of the modalities.

The membrane potential or resting potential of the neuron has been the subject of many studies. Although this theory explains the generation and maintenance of the membrane potential by direct or even facilitated diffusion, there are too many contradictions to doubt that these forces are sufficient or even at work in a process whose initial conditions are of rare complexity. The aim of this article is to show that already in the past, a competing theory has been developed whose hypothesis seems more scientifically sound. To confirm this last theory, Hirohisa Tamagawa carried out an experiment of great simplicity which makes it possible to invalidate the current theory and to question the teaching and the knowledge in Biology and Biophysics.

A non-steady state mathematical model of amino acid (phenylalanine (Phe)) and mineral salt (NaCl) solution separation by neutralization dialysis (ND) carried out in a batch mode is proposed. The model takes into account the characteristics of membranes (thickness, ion-exchange capacity and conductivity) and solutions (concentration, composition), as well as the flow rate of the solution in the dialyzer compartments. As compared to previously developed models, the new one considers the local equilibrium of Phe protolysis reactions in solutions and membranes and, also, the transport of all the phenylalanine forms (zwitterionic, positively and negatively charged) through membranes. A series of experiments on ND demineralization of NaCl and Phe mixed solution was carried out. In order to minimize Phe losses, the solution pH in the desalination compartment was controlled by changing the concentrations of the solutions in the acid and alkali compartments of the ND cell. The validity of the model was verified by comparison of simulated and experimental time dependencies of solution electric conductivity and pH, as well as the concentration of Na+, Cl– ions and Phe species in the desalination compartment. Based on the simulation results, the role of Phe transport mechanisms in the losses of this amino acid during ND was discussed.

The analysis of social media content plays a crucial role in uncovering intricate user behaviors and trends across diverse digital platforms. Social media is inherently multimodal, incorporating texts, images, audios, and videos, each offering unique insights into user engagement and preferences. Traditional classification methods often focus narrowly on the most prominent modality, typically neglecting the synergistic potential of integrating multiple data types. To address this gap, we introduce the Unified Multimodal Classifier (UMC), a suite of streamlined models that adeptly harness and integrate these varied modalities. UMC leverages a novel architecture that combines a pooling layer with auxiliary learning tasks, facilitating the formation of a robust and shared feature space. This integration allows UMC to not only accommodate but also capitalize on the inherent diversity of social media data. The models are designed to be inherently flexible, adjusting to the availability of data modalities and maintaining high classification accuracy under varied conditions. In emotion classification scenarios, UMC has shown exceptional performance, significantly outperforming traditional methods by effectively synthesizing information across modalities. Its robustness is highlighted in its ability to deliver consistent results, even in the absence of one or more modalities. The simplicity and efficiency of UMC make it a potent tool for social media analytics, enabling it to achieve higher accuracies and maintain effectiveness even with limited data inputs. This adaptive capability ensures that UMC can be deployed in real-world applications where data incompleteness is common, thus broadening the scope of its applicability in various analytical contexts.

In today’s Web 2.0 era, online social media has become an integral part of our lives. In the course of the information revolution, the form of information has undergone a radical change, from simple text information to today’s integrated video, image, text and audio, and there has also been a great change in the way of dissemination and access, as people nowadays do not just rely on traditional media to passively receive information, but more actively and selectively obtain information from social media. Therefore, it has become a great challenge for us to effectively utilize these massive and integrated multi-modal media information to form an effective system of retrieval, browsing, analysis and usage. Unlike movies and traditional long-form video content, micro-videos are usually short in length, between a few seconds and tens of seconds, which allows users to quickly browse different contents and make full use of the fragmented time in their lives, while users can also share their micro-videos to their friends or the public, forming a unique social way. Video contains rich multimodal information, and fusing information from multiple modalities in a video recommendation task can improve the accuracy of the video recommendation task.According to the micro-video recommendation task, a new combinatorial network model is proposed to combine the discrete features of each modality into the overall features of various modalities through the network, and then fuse the various modal features to obtain the overall video features, which will be used for recommendation. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

Batch and transport experiments were used to investigate the remediation of a loamy sand soil contaminated with Cr(VI) using zero valent iron nanoparticles (nZVI) stabilized by the carboxy methyl cellulose (CMC-nZVI). The effect of pH, ionic strength (IS), and flow rate on the removal efficiency of Cr(VI) were investigated under equilibrium (uniform transport) and non-equilibrium (Two-site sorption) transport using the Hydrus-1D model. The overall removal efficiency ranged from 70 to over 90% based on the chemical characteristics of the CMC-nZVI suspension and the transport conditions. The concentration and pH of the CMC-nZVI suspension had the most significant effect on the removal efficiency and transport of Cr(VI) in the soil. The average removal efficiency of Cr(VI) was increased from 24.1 to 75.5% when the concentration of CMC-nZVI nanoparticles was increased from 10 to 250 mg L-1, mainly because of the increased total surface area at larger particle concentration. Batch experiments showed that removal efficiency of Cr(VI) was much larger under acidic conditions. The average removal efficiency of Cr(VI) reached 90.1 and 60.5 % at pH 5 and 7, respectively. The Two-site sorption model described quite well (r2 = 0.96-0.98) the transport of Cr(VI) in soil as compared to the uniform transport model (r2 = 0.81-0.98). The average retardation of Cr(VI) was 3.51 and 1.61 at pH 5 and 7, respectively, indicating earlier arrival for the breakthrough curves and shorter time to reach maximum relative concentration at lower pH. The Hydrus-1D model has proven to be an efficient tool for assessing the removal of Cr(VI) pollutants, offering innovative, cost-effective, and environmentally friendly remediation methodologies.

A two-year field experiment (2022–2023) was carried out to investigate the impact of different sowing periods (spring and winter) and nitrogen levels (0, 30, 60 kg/ha) on the phytoextraction potential of flax. The study site is characterized by high concentrations of heavy metals (Cd, Ni, Cu, Pb, Zn) and belongs to the Mediterranean climate type. Flax (var. Calista) was sown in the spring of 2022 and in the winter of 2023, following a split plot experimental design with three rep-lications, and applying low-input practices. Results showed that spring-sown flax produced short-er but thicker plants with significantly higher biomass (5.27 tn ha-1) when treated with 30 kg ha-1 N compared to winter-sown (2.30 tn ha-1) when treated with 60 kg ha-1 N. The concentration of contaminants in the aerial biomass varied according to metal type and sowing period. The higher biomass production in spring resulted in a higher quantity of heavy metals being removed from the soil, making flax a promising crop for phytoextraction purposes, especially in soils contami-nated with multiple heavy metals.

Contact tracing is one of the oldest social network health interventions used to reduce the diffusion of various infectious diseases. However, some infectious diseases like COVID-19 amass at such a great scope that traditional methods of conducting contact tracing (e.g., face-to-face interviews) remain difficult to implement, pointing the need to develop reliable and valid survey approaches. The purpose of this research is to test the effectiveness of three different egocentric survey methods for extracting contact tracing data: (1) a baseline approach, (2) a retrieval cue approach, and (3) a context-based approach. A sample of 397 college students were randomized into one of each condition and were prompted to anonymously provide contacts and populated places visited from the past four days. After controlling for various demographic, social identity, psychological, and physiological variables, participants in the context-based condition were significantly more likely recall more contacts (medium effect size) and places (large effect size) than the other two conditions. Theoretically, the research supports suggestions by field theory that assume network recall can be significantly improved by activating relevant activity foci. Practically, the research contributes to developing innovative social network data collection methods for contract tracing survey instruments.

Sign language recognition is essential in hearing-impaired people’s communication. Sign language recognition is an important concern in computer vision and has been developed with rapid progress in image recognition technology. However, sign language recognition using a general monocular camera has problems with occlusion and recognition accuracy in sign language recognition. In this research, we aim to improve accuracy by using a 2-axis bending sensor as an aid in addition to image recognition. We aim to achieve higher recognition accuracy by acquiring hand keypoint information of sign language actions captured by a monocular RGB camera and adding sensor assist. To improve sign language recognition, we need to propose new AI models. In addition, the amount of dataset is small because it uses the original data set of our laboratory. To learn using sensor data and image data, we used MediaPipe, CNN, and BiLSTM to perform sign language recognition. MediaPipe is a method for estimating the skeleton of the hand and face provided by Google. In addition, CNN is a method that can learn spatial information, and BiLSTM can learn time series data. Combining the CNN and BiLSTM methods yields higher recognition accuracy. We will use these techniques to learn hand skeletal information and sensor data. Additionally, the 2-axis Bending sensor glove data support training AI model. Using these methods, we aim to improve the recognition accuracy of sign language recognition by combining sensor data and hand skeleton data. Our method performed better than using skeletal information, achieving 96.5% accuracy in Top-1.

According to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is raising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data. To solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, Freesurfer MRI segmentation data, and psychological data. For Alzheimer’s disease vs cognitively normal prediction, the random forest classifier provides 100% accuracy. Furthermore, Alzheimer’s disease and non-Alzheimer’s dementia should be classified properly because their symptoms are similar. To the best of our knowledge, we are the first to present a three-class classification on Alzheimer’s disease vs cognitively normal vs non-Alzheimer’s dementia and achieved 99.86% accuracy using an ensemble model. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work..

In an era where dietary habits significantly impact health, technological interventions can offer personalized and accessible food choices. This paper introduces Chef Dalle, a recipe recommen-dation system that leverages multimodal human-computer interaction (HCI) techniques to pro-vide personalized cooking guidance. The application integrates voice-to-text conversion via Whisper, ingredient image recognition through GPT-Vision, and employs TF-IDF vectorization alongside cosine similarity for personalized recipe recommendations. These methods enable users to interact with the system using voice, text, or images, accommodating various dietary re-strictions and preferences. Furthermore, the utilization of DALL-E 3 for generating recipe images enhances user engagement. User feedback mechanisms allow for the refinement of future rec-ommendations, demonstrating the system's adaptability. Chef Dalle showcases potential appli-cations ranging from home kitchens to grocery stores and restaurant menu customization, ad-dresses accessibility, promoting healthier eating habits. This paper underscores the significance of multimodal HCI in enhancing culinary experiences, setting a precedent for future developments in the field.

This study compares the performance of existing studies on multimodal emotion recognition, and proposes a model that fuses two modalities with the speaker's text and voice signals as input values and detects depression. Based on the DAIC-WOZ dataset, voice features were extracted using CNN, text features were extracted using Transformers, and two modalities were fused through a tensor fusion network. We also build a model to detect whether the speaker is depressed or not using LSTM in the final layer. This study suggests the possibility of increasing access to mental illness diagnosis by enabling patients to detect depression on their own in daily conversations. If the model proposed in this study is developed and the voice conversation system is connected, it will be easier for patients who cannot visit the hospital periodically or who are reluctant to visit the hospital to check their condition and seek recovery. Furthermore, it can be expanded to multi-label classification for various mental diseases and used as a simple self-mental disease diagnosis tool.

Excessive oxidative stress and exercise-induced fatigue reduce physical performance and can lead to dysfunction in antioxidant systems within muscular and hepatic tissues. Integrating natural substances with exercise may mitigate fatigue via anti-oxidant effects. This study aims to compare and evaluate the effects of exercise and supplementation with Sundarbans honey vs energy drinks on the strength, anxiety physiological profiles, and hepatic antioxidant capacity in mice undergoing extraneous exercise and fatigue. Forty-eight four-week-old Swiss albino mice were randomly assigned to one of eight groups: (1) Control, (2) Speed™ (Sp), (3) Royal Tiger™ (RT), (4) Sundarbans Honey (SH), (5) Exercise (Ex), (6) Exercise + Sundarbans Honey (Ex+SH), (7) Exercise + Speed™ (Ex+Sp), and (8) Exercise + Royal Tiger™ (Ex+RT). Supplements were administered via oral gavage: Sp (2.5 ml/kg BW), RT (2.5 ml/kg BW), and SH (1 g/kg BW), four times a week for 60 days. Mice in the Ex, Ex+SH, Ex+Sp, and Ex+RT groups underwent daily swimming and running. The strength, fatigue, anxiety levels, lipid profiles, and antioxidant biomarkers were evaluated post-treatment. The SH, Ex, and Ex+SH groups exhibited significantly enhanced physical performance (p<0.05). Plasma lipid profiles, including LDL, triglycerides, total cholesterol, and fatigue-related biomarkers (ALP, AST, ALT, LDH, CK, LA, BUN, and glucose) were markedly increased in the Sp and RT groups but decreased in the SH, Ex, and Ex+SH groups compared to control (p<0.05). Exercise-induced fatigue elevated the Nrf2/HO-1 antioxidant defense system in liver tissue. IL-6 levels were reduced in the SH, Ex, and Ex+SH groups (p<0.05). These findings indicate that regular exercise combined with SH supplementation increases strength and improves lipid profiles, reducing exercise-induced oxidative stress and fatigue via modulation of the Nrf2/HO-1 pathway in liver tissue. These results highlight SH supplementation’s potential as a complementary strategy to enhance exercise outcomes and mitigate exercise-induced stress.

In the paper the experimental methodology for the single-crystal circular plate deformation measurement and subsequent procedure for mechanical properties quantitation are developed. The procedure is based on a new numerical-analytical solution of nonlinear boundary-value problem for finite deformations of a circular anisotropic plate. Using the developed method, a study of the deformation of single-crystal circular plates formed on the basis of a silicon-on-insulator structure was carried out. The values of residual stresses are determined and it is shown that the presence of these stresses increases the flexural rigidity of the plate in several times.

By combining general relativity and CPT symmetry, the theory of CPT gravity predicts gravitational repulsion between matter and CPT-transformed matter, i.e. antimatter inhabiting an inverted space-time. Such repulsive gravity turned out to be an excellent candidate for explaining the accelerated expansion of the Universe, without the need for dark energy. The recent results of the ALPHA-g experiment, which show gravitational attraction between antihydrogen atoms and the Earth, seem to undermine this success in the cosmological field. Analyzing the above theory, we find two solutions that can be consistent with the experimental results, while preserving the large-scale gravitational repulsion. The first highlights how repulsive gravity can be the result of the interaction with an inverted space-time, but occupied by matter and not antimatter, and therefore the antimatter present in our space-time has no reason to exhibit gravitational repulsion. The second retains the original CPT transformation, resulting in repulsive gravity between matter and antimatter, but with the caveat that antimatter immersed in our space-time cannot exhibit the PT transformation which is the cause of the repulsion. Finally, it is shown that, in a Newtonian approximation of the geodesic equation, time reversal is not a necessary operation for repulsive gravity, therefore opening the possibility of an expanding cosmos with a single time direction.

We all have in mind Einstein's famous thought experiment in the elevator where we observe the free fall of a body, and then the trajectory of a light ray. Simply here, in addition to the qualitative aspect, we carry out the exact calculation, and for the first time the worldlines equations are given. We consider a uniformly accelerated reference frame in rectilinear translation, and we show that the trajectories of the particles are semi-ellipses with the center on the event horizon. The frame of reference is non-inertial, the space-time is flat, and the computations are performed within the framework of special relativity. Some experimental consequences are discussed, especially the experiment with the accelerated Michelson-Morley interferometer is solved, and we described an experiment where a new relativistic paradox appears --- a particle of matter seems to go faster than light. The differences, compared to the classical case, are important at large scale and close to the horizon, but they are small in the lift where the interest is above all theoretical. The concepts of metric, coordinated velocity and horizon are discussed, and the analogy with the black hole is made.

Smartphone use has changed patterns of online and offline interaction. Phubbing (i.e., looking at one’s phone instead of paying attention to others) is an increasingly recognized phenomenon in offline interaction. We examined whether people who phub are more likely to have lower social intelligence, whether phubbing is considered more annoying than being ignored due to reading a magazine, and if people describe smartphones and magazines differently as sources of social distraction. We collected two survey samples (N = 112, N = 108) for a cartoon-based role-playing experiment (the Bystander Inaccessibility Experiment) in which a smartphone user and a person reading a magazine ignored the respondents’ conversational initiatives. Annoyance in each scenario was measured, and written accounts were collected on why the respondents rated the scenarios the way they did. Other measures used included the Generic Scale of Phubbing, Generic Scale of Being Phubbed, and Tromsø Social Intelligence Scale. The results showed that participants in both samples were more annoyed by phubbing than by being ignored due to reading a magazine. Linear regression analyses showed that phubbing was associated with lower social intelligence, even after adjusting for confounding factors. The annoyingness of phubbing was explained with negative attitudes toward smartphones, which were assumed to be used for useless endeavors, while magazines were more appreciated and seen as more cultivating. The role of bystanders’ epistemic access to the smartphone user’s activities is discussed.

Materials characterised by magnetorheological properties are non-classic engineering materials. A significant increase in the interest of scientific community in materials from this group can be observed over the recent several years. The results of research presented in this article are oriented on the examination of said materials’ mechanical properties. In order to do so, stress relaxation tests were conducted on cylindrical samples of magnetorheological elastomers loaded with compressive stress for various values of magnetic induction (B1 = 0 mT, B2 = 32 mT, B3 = 48 mT, and B4 = 64 mT) and temperature (T1 = 25° C, T2 = 30° C, and T3 = 40° C). The results of these tests indicate that the stiffness of examined samples increases along with the increase of magnetic field induction and decreases along with the increase of temperature. On this basis, it has been determined that: the biggest stress amplitude change caused by the influence of magnetic field was σ0ΔB = 12.7% and the biggest stress amplitude change caused by the influence of temperature was σ0ΔT = 11.3%. As a result of applying a mathematical model, it has been indicated that the stress relaxation in the examined magnetorheological elastomer for the adopted time range (t = 3600 s) has a hyperbolic decline nature. The collected test results point to examined materials being characterised by extensive rheological properties, which leads to a conclusion that it is necessary to conduct further tests in this scope.

The eddy current loss should be optimized to be as less as possible for the stability of permanent magnet in high speed permanent magnet synchronous motor (HSPMSM) rotor and ensure the high efficiency and low temperature of the motor. This paper analyzes the eddy current distribution in rotor, with consideration of the conflict of the thickness of sleeve and diameter of the rotor, calculating the eddy current loss (ECL) and the thermal distribution via Separation of variables method for solving Maxwell's equations with analytical hieratical model of ECL constructed. The optimization result of ECL of the HSPMSM whose power and rated speed is 30kw 48000r/min can be got by multi-objective optimization method, combined weighting coefficient method and traversal algorithm based on chaotic local search particle swarm optimization (CLSPSO), utilizing ECL analytical model and other analytical constraints. Related experiment and measurement has been implemented with new approach of loss separation.

The sPHENIX experiment is a state-of-the-art jet and heavy flavor physics detector which successfully recorded its first Au + Au collision data at 200 GeV at RHIC. sPHENIX will provide heavy flavor physics measurements covering an unexplored kinematic region and unprecedented precision at RHIC to probe the parton energy loss mechanism, parton transport coefficients in quark-gluon plasma, and the hadronization process under various medium conditions. At the center of sPHENIX, the Monolithic-Active-Pixel-Sensor (MAPS) based VerTeX detector (MVTX) is a high-precision silicon pixel detector. The MVTX provides excellent position resolution and the capability of operating in continuous streaming readout mode, allowing precise vertex determination and recording a large data sample, both of which are particularly crucial for heavy flavor physics measurements. In this work, we will show the general performance of heavy-flavor hadron reconstruction. In addition, we will discuss the commissioning experience with sPHENIX. Finally, we will provide the projection of b-hadron and jet observables and discuss the estimated constraints on theoretical models.

Bell’s correlation formula is based on a classical Kolmogorov probability theory. It is tested in experiment with an estimate correlation. The latter is the raw product moment (rpm) correlation that is classical Kolmogorov based as well. We note that the famous Bell inequalities are derived from Bell’s correlation formula. The problem is that the hypothesis: “is it possible that in experiment Bell’s correlation is equal to quantum”, can only found to be false. This is not because the data generating process does not produce the required data. Or that the inequalities sufficiently show that the data cannot violate the inequalities. It is because the statistics of the Bell experiment is flawed. The rpm correlation in experiment cannot be equal to the quantum value in principle. This is because it requires the classical Kolmogorov rpm correlation to be not Kolmogorov.

We propose a phenomenological theory of spin behavior in a magnetic field, which explains from the point of view of classical physics the two-valued result of the Stern-Gerlach experiment. The behavior of the spin and intrinsic magnetic moment of an electron wave of an atom in an external magnetic field is considered. We show that in a weak magnetic field, the intrinsic magnetic moment of an electron wave is always oriented parallel to the magnetic field strength vector, while in a strong magnetic field, depending on the initial orientation of the intrinsic magnetic moment, two orientations are realized: either parallel or antiparallel to the magnetic field strength vector. Within the framework of classical electrodynamics, the calculation of the motion of an atomic beam in an inhomogeneous magnetic field is carried out, which reproduces the results of the Stern-Gerlach experiment.

Neurodegenerative diseases, such as Alzheimer’s disease and Parkinson’s disease, are caused by a combination of multiple events that damage neuronal function. A well-characterized biomarker of neurodegeneration is proteinaceous aggregates accumulation in the brain. However, the gradually worsening symptoms of neurodegenerative diseases are unlikely to be solely due to the result of a mutation in a single gene, but rather a multi-step process involving epigenetic changes. Multiple epigenetic studies have revealed that modification of histones accompanied by both the local and global remodeling of the chromatin structure and alternations in transcriptional patterns are closely associated with the pathogenesis of neurodegenerative diseases. Unlike DNA mutations, epigenetic alterations are reversible, and therefore raise the possibilities for therapeutic intervention including dietary modifications. Additionally, reactive oxygen species may contribute to the pathogenesis of Alzheimer’s disease and Parkinson’s disease. Given that the antioxidant properties of plant-derived phytochemicals are likely to exhibit pleiotropic effects against ROS-mediated epigenetic alternation, dietary intervention may be promising for the management of neurodegeneration in these diseases. In this review, the state-of-the-art applications using single-cell multi-modal omics approaches including genetics, and epigenetics, and dietary approaches for the identification of novel biomarkers and therapeutic approaches for the treatment of neurodegenerative diseases are discussed.

Multimodal user interfaces promise a natural and intuitive human machine interactions. But is the extra effort for the development of a complex multi-sensor system justified, or can users also be satisfied with one input modality already? This study investigates interactions in an industrial weld inspection workstation. Three unimodal interfaces, including spatial interaction with buttons augmented on a workpiece or a worktable, and speech commands, were tested individually and in a multimodal combination. Within the unimodal conditions, users preferred the augmented worktable, but overall, the interindividual usage of all input technologies in the multimodal condition was ranked best. Our findings indicate that the implementation and use of multiple input modalities is valuable, and that it is difficult to predict the usability of individual input modalities for complex systems.

The exponential growth of multimodal content across social media platforms, comprising text, images, audio, and video, has catalyzed substantial interest in artificial intelligence, particularly in multi-modal sentiment analysis (MSA). This study presents a comprehensive survey of 30 research papers published between 2020 and 2024 by eminent publishers such as Elsevier, ACM, IEEE, Springer, and others indexed in Google Scholar. Our analysis primarily focuses on exploring multimodal fusion techniques and features, with specific emphasis on the integration of text and image data. Additionally, the article offers an overview of the evolution, definition, and historical context of MSA. It delves into the current challenges and potential advantages of MSA, investigating recent datasets and sophisticated models. Furthermore, the study provides insights into prospective research directions. Notably, this review offers valuable recommendations for advancing research and developing more robust MSA models, thus serving as a valuable resource for both academic and industry researchers engaged in this burgeoning field.

The advent of the era of big data will bring more convenience to people and greater development to society. But at the same time, it will also bring people the problem of 'information overload', i.e., when people are faced with huge information data, there are many redundant and worthless data. The redundant and worthless data information seriously interferes with the accurate selection of information data. Even though people can use Internet search engines to access information data, they cannot meet the individual needs of specific users in specific contexts. The personalized needs of a particular user in a particular context. Therefore, how to find useful and valuable information quickly has become one of the key issues in the development of big data. With the advent of the era of big data, recommendation systems, as an important technology to alleviate information overload, have been widely used in the field of e-commerce. Recommender systems suffer from a key problem: data sparsity. The sparsity of user history rating data causes insufficient training of collaborative filtering recommendation models, which leads to a significant decrease in the accuracy of recommendations. In fact, traditional recommendation systems tend to focus on scoring information and ignore the contextual context in which users interact. There are various contextual modal information in people's real life, which also plays an important role in the recommendation process. In this paper we achieve data degradation and feature extraction, solving the problem of sparse data in the recommendation process. An interaction context-aware sub-model is constructed based on a tensor decomposition model with interaction context information to model the specific influence of interaction context in the recommendation process. Then an attribute context-aware sub-model is constructed based on the matrix decomposition model and using attribute context information to model the influence of user attribute contexts and item attribute contexts on recommendations. In the process of building the model, the method not only utilizes the explicit feedback rating information of users in the original dataset, but also utilizes the interaction context and attribute context information of the implicit feedback and the unlabeled rating data. We evaluate our model by extensive experiments. The results illustrate the effectiveness of our recommender model.

Hateful and abusive speech presents a major challenge for all online social media platforms. Recent advances in Natural Language Processing and Natural Language Understanding allow more accurate detection of hate speech in textual streams. This study presents a multimodal approach to hate speech detection by combining Computer Vision and Natural Language processing models for abusive context detection. Our study focuses on Twitter messages and, more specifically, on hateful, xenophobic and racist speech in Greek aimed at refugees and migrants. In our approach we combine transfer learning and fine-tuning of Bidirectional Encoder Representations from Transformers (BERT) and Residual Neural Networks (Resnet). Our contribution includes the development of a new dataset for hate speech classification, consisting of tweet ids, along with the code to obtain their visual appearance, as they would have been rendered in a web browser. We have also released a pre-trained Language Model trained on Greek tweets, which has been used in our experiments. We report a consistently high level of accuracy (accuracy score=0.970, f1-score=0.947 in our best model) in racist and xenophobic speech detection.

Globally, there is massive uptake and explosion of data and challenge is to address issues like scale, pace, velocity, variety, volume and complexity of this big data. Considering the recent epidemic in China, modeling of COVID-19 epidemic for cumulative number of infected cases using data available in early phase was big challenge. Being COVID-19 pandemic during very short time span, it is very important to analyze the trend of these spread and infected cases. This chapter presents medical perspective of COVID-19 towards epidemiological triad and the study of state-of-the-art. The main aim this chapter is to present different predictive analytics techniques available for trend analysis, different models and algorithms and their comparison. Finally, this chapter concludes with the prediction of COVID-19 using Prophet algorithm indicating more faster spread in short term. These predictions will be useful to government and healthcare communities to initiate appropriate measures to control this outbreak in time.

Affordances are an important concept in cognition, which can be applied to robots in order to perform a successful human-robot interaction (HRI). In this paper we explore and discuss the idea of emotional affordances and propose a viable model for implementation into HRI. We consider “2-ways” affordances: perceived object triggering an emotion, and perceived human emotion expression triggering an action. In order to make the implementation generic, the proposed model includes a library that can be customised depending on the specific robot and application’s scenario. We present the AAA (Affordance-Appraisal-Arousal) model, which incorporates Plutchik’s Wheel of Emotions, and show some examples of simulation and possible scenarios.

The recent availability of commercial platforms for behavioral analysis in zebrafish larvae based on video-tracking technologies has exponentially increased the number of studies analyzing different behaviors in this model organism to assess neurotoxicity. Among the most commonly used assays in zebrafish larvae are basal locomotor activity (BLA) and visual motor response (VMR). However, the effect of different intrinsic and extrinsic factors that can significantly alter the outcome of these assays is still not well understood. In this work we have analyzed in 143 larvae the influence of age (5-8 days post-fertilization), time of day (8:00, 10:00, 12:00, 14:00; 16:00, 18:00, and 20:00 h), and experiment (three experiments performed at different days) on BLA and VMR results (4,004 analyses for each behavior). Results from both behaviors were adjusted to a Random-Effects linear regression model using generalized least squares (GLS), including in the model the effect of the three variables, the second-way interactions between them and the three-way interaction. The results presented in this manuscript show a specific effect of all three intrinsic factors and their interactions on both behaviors, supporting the view that the most stable time period for performing these behavioral assays is from 10:00 am to 04:00 pm, with some differences depending on age of the larva and the behavioral test.

A galvalume corrugated sheet was utilized as formwork for a reinforced concrete beam in flexure. A numerical model was validated to the experimentally obtained data, and further adopted to simulate the behavior of this composite structure under elevated temperatures. The properties and constitutive stress-strain data of the basic materials were obtained from experiments, and superimposed into the finite element model. The study concluded that the load carrying capacity of the member decreased as a direct function on temperature increase, and the cracking moment was very sensitive to the temperature fluctuation. The elevated temperatures also altered the failure mode.

Understanding and preventing the “great obstetrical syndromes” has been the focus of pregnancy research for decades. The combined global impact from these syndromes on maternal and perinatal morbidity and mortality is compounded by increased long-term risk of adverse health effects following pregnancy. Accumulating evidence indicates that conditions such as pre-eclampsia, fetal growth restriction, spontaneous preterm labour, and stillbirth, are syndromes with etiologic heterogeneity that share common pathophysiologic pathways involving placental dysfunction. Recently, the importance of the interaction between fetal and maternal genomes has been extended to include the epigenetic impact of pre-existing maternal pathophysiology on placental development and highlights the importance of nutritional and environmental factors in altered placentation. Validated first-trimester screening algorithms for preeclampsia can identify high-risk women and prophylactic treatment with low-dose aspirin can be initiated. High-risk women can be monitored during the second trimester using clinical assessment, ultrasound, and biochemical markers, that are able to predict complications prior to the development of clinical signs and symptoms. The integration of lifestyle interventions, pregnancy screening, and medical management represents a conceptual advance in pregnancy care. This approach has the potential to significantly reduce pregnancy complications, maternal and perinatal morbidity and mortality, adverse health outcomes later in life, and health-care costs.

Emotion detection holds significant importance in facilitating human-computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers for profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

The study combines two critical aspects of climate research in Nigeria. The first segment focuses on improving predictive performance of global circulation models (GCMs) employing ensemble techniques. ANN ensemble displayed significant improvement in the accuracy of climate projections, particularly in high-altitude geographic areas where traditional models exhibit limitations. Performance evaluation metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Nash–Sutcliffe Efficiency (NSE) demonstrate the effectiveness of the ANN multimodal ensemble. Building on the improved climate modelling, the second segment delves into a spatial and temporal analysis of rainfall and mean temperature patterns under climate change in Nigeria. By considering two Representative Concentration Pathways (RCPs), namely RCP4.5 and RCP8.5, the study utilizes dynamically downscaled GCMs obtained from the Coupled Model Intercomparison Project phase 5 (CMIP5). The Mann-Kendall test reveals significant spatiotemporal variations in climate trends across the country. The warming trend is particularly pronounced in the northern regions, with RCP8.5 showing more severe impacts compared to RCP4.5. This integrated approach not only highlights the importance of multimodal ensembles in climate modelling but also provides valuable insights into the spatial and temporal patterns of climate change to inform effective adaptation and mitigation strategies for Nigeria.

This study aims to enhance multimodal transportation systems by mitigating CO2 emissions and enhancing operational efficiency. It introduces a novel centralized cargo concentration approach tailored for regions facing geographical challenges. The method proposes for direct transportation of cargo from its loading origin to export ports, bypassing intermediate hubs. The mathematical model determines the most efficient means of transport for each route, factoring in variables like distance, volume, and cargo type. Research results indicate that, in scenarios with a high concentration of cargo, multiple hubs may not be necessary, which could streamline transportation and logistics operations. Modal preferences vary based on regional dynamics and cargo characteristics, with rail and sea transport emerging as preferable options under specific circumstances, surpassing the efficacy of road transport. The proposed model showcases reductions in both logistics costs and CO2 emissions compared to road-centric scenarios. It underscores the strategic integration of diverse transportation modes as pivotal for enhancing efficiency and sustainability. This study furnishes a framework adaptable to optimizing multimodal transportation systems in regions sharing similar geographical and logistical attributes.

We present a new vision on the double-slit experiment (DSE), that does not use any waves or the so-called wave-particle duality. It is based on particles, viewed as localized vibrations. Rather than being illogical, or mysterious, the approach reproduces logically the interference patterns observed externally, using the well-known ``amplification of stimulated emission'' (ASE). The conservation of particle number is not observed. Different particles can present ASE with in-phase or counter-phase behavior, making the patterns observed for electrons, other particles, even atoms. The Law of the Excluded Middle (LEM) is not broken illogically in two-states macroscopically, but broken naturally in three or more states, microscopically, using ASE. Any particle supporting ASE, in-phase or counter-phase, can enter a DSE, and provide an external interference pattern. Frequency plays a role, while amplitude is not considered. This work is important in quantum computing, possibly saving cost, time, and welcoming more participants.

We present an ontology log-OLOG- representation of the classical Miller-Urey experiment, usually considered as a paradigm for spontaneous generation of biomolecules on the prebiotic Earth and also, as a key in understanding the chemical evolution phenomena linked to the origins of life. Ologging The Miler-Urey experiment enables us, through the categorical notion of fibre product or pullback, to define the concept of Biogenic Space, as a space containing low complexity biogenic units subjected to appropriate physical and chemical conditions, facilitating the synthesis of highly complex organic molecules. Also, we characterize the Biogenic Space as a concrete universal object that could be associated with the preconditions for life inside various structures in the universe such as exoplanets and exomoons located in habitable zones, but also in interstellar and intergalactic organic clouds.

Coalbed Methane(CBM) production enhancement for single wells is a big problem to CBM industrialization. Low production is due to insufficient gas generation by thermogenic. Luckily, Biogenic gas was found in many areas and its supply is assumed to improve coalbed methane production. Therefore, microbial simulation experiment will demonstrate the effectiveness of the assumption. From microbial simulation experiment on different coal ranks, it is found that microbes can use coals to produce biogas under laboratory conditions. With different temperatures for different experiments, it turns out that the gas production at 35 ℃ is greater than that at 15℃,indicating that 35℃ is more suitable for microbes to produce gas. According to quantitative experiments, adding exogenous nutrients or exogenous bacteria can improve CBM production. Moreover, the production enhancement ratio can reach up to 115% under the condition of adding exogenous bacterial species, while the ratio for adding nutrients can be up to 144%.

Though the cancer research community has used mouse xenografts for decades more than zebrafish xenografts, zebrafish have much to offer: they are cheap, easy to work with, and the embryonic model is relatively easy to use in high-throughput assays. Zebrafish can be imaged live, allowing us to observe cellular and molecular processes in vivo in real time. Opponents dismiss the zebrafish model due to the evolutionary distance between zebrafish and humans, as compared to mice, but proponents argue for the zebrafish xenograft’s superiority to cell culture systems and its advantages in imaging. This review places the zebrafish xenograft in the context of current views on cancer and gives an overview of how several aspects of this evolutionary disease can be addressed in the zebrafish model. Zebrafish are missing homologs of some human proteins and (of particular interest) several members of the matrix metalloproteinase (MMP) family of proteases, which are known for their importance in tumour biology. This review draws attention to the implicit evolutionary experiment taking place when the molecular ecology of the xenograft host is significantly different than that of the donor.

The rapidly evolving domain of multimodal sentiment analysis is crucial for unraveling the intricate layers of emotional expression in social media content, customer service interactions, and personal vlogs. This research introduces a cutting-edge Advanced Cross-Modal Gating (ACMG) framework that significantly enhances the precision of sentiment analysis by refining the interplay among textual, auditory, and visual modalities. Our approach addresses three foundational aspects of sentiment analysis: (1) Advanced learning of cross-modal interactions, which focuses on extracting and synthesizing sentiment from varied modal inputs, thus providing a holistic view of expressed emotions; (2) Mastery over the temporal dynamics of multimodal data, enabling the model to maintain context and sentiment continuity over extended interactions; and (3) Deployment of a novel fusion strategy that not only integrates unimodal and cross-modal cues but also dynamically adjusts the influence of each modality based on its contextual relevance to the sentiment being expressed. The exploration of these dimensions reveals that the nuanced modeling of cross-modal interactions is crucial for enhancing model responsiveness and accuracy. By applying the ACMG model to two highly regarded datasets—CMU Multimodal Opinion Level Sentiment Intensity (CMU-MOSI) and CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI)—we achieve groundbreaking accuracies of 83.9\% and 81.1\%, respectively. These results represent significant improvements of 1.6\% and 1.34\% over the current state-of-the-art, showcasing the superior performance and potential of our approach in navigating the complexities of multimodal sentiment analysis.

In cardiac surgery, post-sternotomy pain is a significant issue, peaking within 48 hours and requiring proper analgesia for both acute relief and to avoid chronicization. Opioids are commonly used for pain management post-surgery but pose risks like adverse effects and dependency. Post-cardiac surgery pain can stem from various sources - somatic, visceral, and neuropathic, making opioid reliance a concern. Multimodal analgesia, combining different medications and regional anesthesia techniques, is increasingly recommended to decrease opioid use and its related problems. Strategies include acetaminophen, gabapentinoids, NMDA antagonists, alpha-2 agonists, intravenous lidocaine, anti-inflammatory drugs, and regional anesthesia. Implementing these approaches can enhance pain control, lessen opioid reliance, and improve cardiac surgery outcomes. The ERAS® Cardiac Society strongly advocates for an opioid-sparing multimodal approach to benefit patient recovery by reducing complications and enhancing satisfaction. This review aims to consolidate current evidence to assist healthcare providers in customizing pain management for patients post-cardiac surgery, emphasizing reduced opioid use and optimizing the recovery process.

Syringomyelia can be associated with multiple etiologies. The treatment of the underlying causes is the first-line therapy, however, a direct approach to the syrinx is accepted as rescue treatment. Any direct intervention on the syrinx requires a myelotomy, posing a significant risk of iatrogenic spinal cord (SC) injury. Intraoperative neurophysiological monitoring (IONM) is crucial to detect and prevent surgically induced damage in neural SC pathways. We retrospectively reviewed the perioperative and intraoperative neurophysiological data and perioperative neurological examinations in ten cases of syringomyelia surgery. All monitored modalities remained stable throughout the surgery in six cases, correlating with no new postoperative neurological deficits. In two patients, significant transitory attenuation, or loss of motor evoked potentials (MEPs), were observed and recovered after a corrective surgical maneuver, with no new postoperative deficit. In two cases, a significant MEP decrement was noted, which lasted until the end of the surgery and was associated with postoperative weakness. A transitory train of neurotonic electromyography (EMG) discharges was reported in one case, the surgical plan was adjusted and the patient showed no postoperative deficit. The dorsal nerve roots were stimulated and identified in the seven cases where the myelotomy was performed via the dorsal root entry zone. Dorsal column mapping guided the myelotomy entry zone in four cases. In conclusion, multimodal IONM is feasible and reliable and may help prevent iatrogenic SC injury during syringomyelia surgery.

Document classification is one of the most critical steps in the document analysis pipeline. There are two types of approaches for document classification, known as image-based and multimodal approaches. The image-based document classification approaches are solely based on the inherent visual cues of the document images. In contrast, the multimodal approach co-learns the visual and textual features, and it has proved to be more effective. Nonetheless, these approaches require a huge amount of data. This paper presents a novel approach for document classification that works with a small amount of data and outperforms other approaches. The proposed approach incorporates a hierarchical attention network(HAN) for the textual stream and the EfficientNet-B0 for the image stream. The hierarchical attention network in the textual stream uses the dynamic word embedding through fine-tuned BERT. HAN incorporates both the word level and sentence level features. While the earlier approaches rely on training on a large corpus (RVL-CDIP), we show that our approach works with a small amount of data (Tobacco-3482). To this end, we trained the neural network at Tobacco-3428 from scratch. Thereby, we outperform state-of-the-art by obtaining an accuracy of 90.3%. This results in a relative error reduction rate of 7.9%.

This paper is an interdisciplinary study of novel applications of techniques and tools of an area of brain science, known as Synesthesia (involving associations and/or confusion between distinct senses), to area of Computer Science known as Immersive Virtual Reality (VR), that makes the subject’s awareness of physical self be diminished by being surrounded in an engrossing artificial environment. Natural Synesthesia has for the last decade been an important emerging area in brain science but is present in only a small proportion of the population. For example a person with Natural Synesthesia, when viewing a grapheme, may perceive a color additionally to be associated to the grapheme. In contrast, Artificial synesthesia (also known as virtual synesthesia or synthetic synesthesia) has been defined as the sensory joining due a cross-modal mapping device, where information of one sense is accompanied by an induced perception in another sense. In particular, we propose use of a multimodal manner of displaying information in VR to increase and concentrate attention. Artificial Synesthesia to synthetically create induced associations between senses, allowing Artificial Synesthesia to be experienced by anyone using a VR system. The paper describes the enhancement of immersive VR by use of Artificial Synesthesia to improve the system’s performance at steering and directing the attention of the user. We describe techniques for an enhanced immersive VR that displays associations between a variety of senses: between colors and characters, also between colors and sounds, and between sounds and the position of tactile sensations. The sense association provided by Artificial Synesthesia allows the system to better capture the user’s attention and better direct that attention. A major application of our work in VR-induced Artificial Synesthesia is to provide an enhanced methodology for controlling the attention of the subject, and to improve the direction of attention of subjects undergoing guided imagery therapies for pain relief. Other potential high-impact applications include improved immersive VR, more programmable human/computer interfaces and other medical therapies.

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully-supervised, requiring extensive precise manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—Segment Anything Model (SAM) into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPoly-SAM, a novel weakly-supervised approach for colonoscopy polyp segmentation. WSPoly-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotations data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPoly-SAM outperforms current fully-supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly-supervised and fully-supervised experiments, it is found that weakly-supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully-supervised fine-tuning. This study provides a new perspective on the combination of weakly-supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

1,3,5-Tris-(α-naphthyl)benzene is an organic non-electrolyte with notable stability of an amorphous phase. Its glassy and supercooled liquid states were previously studied by spectroscopic and calorimetric methods. However, the thermodynamic parameters of phase transitions available from the literature are inconsistent. In this work, the heat capacities of crystalline and liquid phases, the temperature dependence of the saturated vapor pressures, fusion and vaporization enthalpies were determined using differential and fast scanning calorimetry and verified using the estimates based on solution calorimetry. The structural features of 1,3,5-tris-(α-naphthyl)benzene are discussed based on the computations performed and the data on the molecular refractivity. The consistency between the values obtained by independent techniques was demonstrated. The deviations in the previously published data were attributed to possible polymorphism.

Additive manufactured interlocking structures often face challenges in achieving suitable joinability due to thermal deformation. This issue becomes particularly interesting when fabricating structures that require high density but not fully connected layers, such as soft-magnetic materials. This study focuses on systematical investigation of the deformation as a function of finger thickness and building direction in model interlocking structure. In the perpendicular direction to the build plate, the distortions of joint part were significantly reduced due to lower thermal stress. In addition, the effect of laser power and scan speed on interlocking structure are systematically discussed. Additionally, through stress and thermal simulations of additive manufacturing process, it was confirmed that the compensated model can enhance the joinability of interlocking structures. These findings contribute to the development of optimal design for additive manufactured parts of soft magnetic materials such as stators in electric motor components, which needs insulations and density.

In this paper, the tensile behavior of unidirectional carbon/epoxy prepreg is experimentally analyzed at varying loads and temperatures, focusing on the considerable nonlinearity at the beginning of the stress-strain curve. The high viscosity of this material presented difficulties in securely holding specimens during tensile testing. As a result, modifications were made to the conventional gripping method to enable the acquisition of reliable test data. Additionally, a longer gauge length was chosen to minimize the impact of slippage on the elastic modulus measurement. To support the experiment, a micromechanical model of a prepreg tow with fiber waviness is proposed. An RVE model of periodically distributed unidirectional waved cylindrical fibers embedded within the matrix is developed to predict the effective material stiffness parameters. Numerical results are presented for different amplitude-to-wavelength ratios which indicate the fiber waviness reduces the tensile modulus of the composite. The simulation results are in good agreement with the uniaxial tensile test of the prepreg tow.

We consider the role information energy can play as a source of dark energy. Firstly, we note that, if stars and structure had not formed in the universe, elemental bits of information describing the attributes of particles would have exhibited properties similar to the cosmological constant. The Landauer equivalent energy of such elemental bits would be defined identical in form and value to the characteristic energy of the cosmological constant. But, with the formation of stars and structure, stellar heated gas and dust now provides the dominant contribution to information energy with the characteristics of a dynamic, transitional, dark energy. At low redshift, z<~1.35, this dark energy emulates the cosmological constant with a near constant energy density, w=−1.03±0.05, and an energy total similar to the mc² of the universe's ∼10⁵³ kg of baryons. At earlier times, z>~1.35, information energy was phantom, differing from the cosmological constant, Λ, by a CPL parameter difference of ∆w_o=−0.03±0.05 and ∆w_a=−0.79±0.08, values sufficient to account for the H₀ Tension. Information dark energy agrees with most phenomena as well as Λ, while exhibiting characteristics that resolve many tensions and problems of ΛCDM: the cosmological constant problem; the cosmological coincidence problem; the H₀ and σ₈ tensions. As this proposed dark energy source is not usually considered, we identify the expected signature in H(a) that will enable the role of information dark energy to be falsified by experimental observation.

Laminate structures composed of stiff plates and thin soft interlayers are widely used in aerospace, automotive and civil engineering encouraging the development of reliable non-destructive strategies for their condition assessment. In the paper, elastodynamic behaviour of such laminate structures is investigated with emphasis on its application in ultrasonic based NDT and SHM for the identification of interlayer mechanical and interfacial contact properties. A particular attention is given to the practically important frequency range, in which the wavelength considerably exceeds the thickness of the film. Three layer model with spring-type boundary conditions employed for imperfect contact simulation is used for numerical investigation. Novel effective boundary conditions are derived via asymptotic expansion technique and used for analysis of the peculiar properties of elastic guided waves in considered laminates. It is revealed that the thin and soft film influences the behaviour of the laminate mainly via the effective stiffnesses being a combination of the elastic moduli of the film, its thickness and interface stiffnesses. To evaluate each of these parameters separately (or to figure out that the available experimental data are insufficient), a step-wise procedure employing the effective boundary conditions is proposed and tested versus the laser Doppler vibrometry data for Lamb waves in Aluminium/Polymer film/Alumunium structure. The possibility of using film-related thickness resonance frequencies to estimate the film properties and contact quality is also demonstrated. Additionally, the rich family of edge waves is also investigated, and the splitting of fundamental edge waves into pairs is revealed.

This study was performed to synthesize multimodal radiopharmaceutical designed for the diagnosis and treatment of prostate cancer. To achieve this goal, Super Paramagnetic Iron Oxide (SPIO) nanoparticles were used as a platform for targeting molecule (PSMA-617) and for complexation of two scandium radionuclides, 44Sc for PET imaging and 47Sc for radionuclide therapy. TEM and XPS images showed that the Fe3O4 NPs have a uniform cubic shape and a diameter from 38 to 50 nm. The Fe3O4 core are surrounded by SiO2 and an organic layer. The saturation magnetization of the SPION core was 60 emu/g. However, coating the SPIONs with silica and polyglycerol reduces the magnetization significantly. The obtained bioconjugates were labeled with 44Sc and 47Sc, with a yield higher than 97%. The radiobioconjugate exhibited high affinity and cytotoxicity towards the human prostate cancer LNCaP (PSMA+) cell line, much higher than for PC-3 (PSMA-) cells. High cytotoxicity of the radiobioconjugate was confirmed by radiotoxicity studies on LNCaP 3D-spheroids. In addition, the magnetic properties of the radiobioconjugate should allow for its use in guide drug delivery driven by magnetic field gradient.

The redshifted 21 cm line signal is a powerful probe of the cosmic dawn and the epoch of reionisation. The global spectrum can potentially be detected with a single antenna and spectrometer. However, this measurement requires an extremely accurate calibration of the instrument to facilitate the separation of the 21 cm signal from the much brighter foregrounds and possible variations in the instrument response. Understanding how the measurement errors propagate in a realistic instrument system and affect system calibration is the focus of this work. We simulate a 21 cm global spectrum observation based on the noise wave calibration scheme. We focus on how measurement errors in reflection coefficients affect the noise temperature, and how typical errors impact on the recovery of the 21 cm signal, especially in the frequency domain. Results show that for our example set up, a typical VNA measurement error in the magnitude of the reflection coefficients of the antenna, receiver, open cable which are 0.001, 0.001, 0.002 (linear) respectively would result in a 200 mK deviation on the detected signal, and a typical measurement error of 0.48∘, 0.78∘, 0.15∘ in the respective phases would cause a 40 mK deviation. The VNA measurement error can greatly affect the result of a 21 cm global spectrum experiment using this calibration technique, and such a feature could be mistaken for or be combined with the 21 cm signal.

With new discoveries and insights in atomic and optical physics, the field of spectroscopy is advancing to a new level with applications ranging from material science to astronomy. We here propose a theoretical description of a potential new phenomenon resulting from the extension of Compton's experiment on the scattering of high energy photons through atomic electrons. How the proposed phenomenon can be tested experimentally is discussed in the paper as well.

In this work, we introduce the TriFusion Network, an innovative deep learning framework designed for the simultaneous analysis of auditory, visual, and textual data to accurately assess emotional states. The architecture of the TriFusion Network is uniquely structured, featuring both independent processing pathways for each modality and integrated layers that harness the combined strengths of these modalities to enhance emotion recognition capabilities. Our approach addresses the complexities inherent in multimodal data integration, with a focus on optimizing the interplay between modality-specific features and their joint representation. Extensive experimental evaluations on the challenging AVEC Sentiment Analysis in the Wild dataset highlight the TriFusion Network's robust performance. It significantly outperforms traditional models that rely on simple feature-level concatenation or complex score-level fusion techniques. Notably, the TriFusion Network achieves Concordance Correlation Coefficients (CCC) of 0.606, 0.534, and 0.170 for the arousal, valence, and liking dimensions respectively, demonstrating substantial improvements over existing methods. These results not only confirm the effectiveness of the TriFusion Network in capturing and interpreting complex emotional cues but also underscore its potential as a versatile tool in real-world applications where accurate emotion recognition is critical.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

With the advent of modern technologies, the healthcare industry is moving towards a more Personalised smart care model. The enablers of such care models are the Internet of Things (IoT) and Artificial Intelligence. These technologies collect and analyse data from persons in care to alert relevant parties if any anomaly is detected in a patient’s regular pattern. However, such reliance on IoT devices to capture continuous data extends the attack surfaces and demands high-security measures. Both patients and devices need to be authenticated to mitigate a large number of attack vectors. The biometric authentication method has been seen as a promising technique in these scenarios. To this end, this paper proposes an AI-based multimodal biometric authentication model for single and group-based users’ device-level authentication that increases protection against the traditional single modal approach. To test the efficacy of the proposed model, a series of AI models are trained and tested using physiological biometric features such as ECG (Electrocardiogram) and PPG (Photoplethysmography) signals from five publicly available datasets from Physionet and Mendeley data repositories. The multimodal fusion authentication model shows promising results with 99.8% accuracy and an Equal Error Rate (EER) of 0.16.

Metabolomic analysis of biological fluids and tissues has become an increasingly routine tool in the biological toolbox. However, challenges remain to be overcome, including developing strategies to maximise coverage of the metabolome without requiring large sample volumes. Here we describe a multimodal strategy that combines data using both LC-MS and GC-MS from a unique vial with a sample of plasma (20µl) or a sample of brain tissue (3mg). Using a split phase extraction the non-aqueous phase was analyzed by reversed phase (RP) LC-MS, whilst the aqueous phase was analyzed using hydrophilic liquid interaction chromatography (HILIC)LC-MS, with both phases also analysed using GC-MS after derivatization of the extract. Analytical performance was assessed in 7 rat cerebellum samples and a pilot study of 40 plasma samples (20 vs. 20: AD vs. healthy controls). The method, which uses four hours of instrument time, measured 20,707 metabolite features in brain samples and 17,266 in plasma samples, from those 44.1% features displayed CV’s below 15% and 75.2% below 30%. The method has potential to resolve subtle biological differences and to correlate metabolite composition directly to clinical outcomes including MMSE, age and ADCS-ADL. This method can acquire in the order of 20K metabolic features when low volumes are available.

The paper presents the results of experimental studies and mathematical modeling of the effect of stress accumulation in thermosetting epoxy polymer "hot" curing on anhydride hardener. Stress accumulation occurs under cyclic thermomechanical action in a locked rod, similar effects are observed, for example, in thermoplastic elements subjected to the combined effect of mechanical loads and variable temperatures. Experimental results have shown that under cyclic thermomechanical loading during exploitation it is possible to accumulate residual stresses in the thermosetting polymer. A multi-element structural mathematical model with memory for thermomechanical load, which allows to consider the accumulation of residual thermal stresses, has been proposed. The results of modeling and experiment are compared. Based on the results, corrections are made in the approach to the application of this model to thermosetting polymers such as the epoxy resin under study. Considering the corrections, a good agreement (the difference is from 1 to 6%) with the results of experimental determination of stresses under complex cyclic thermomechanical load was obtained.

The steel grid structure with bolted ball joints is gaining popularity in offshore platforms and aquaculture cages, but the corrosion resistance of these joints is a critical safety concern. This article introduces an innovative method to enhance the sealing performance of bolted ball joints, preventing seawater ingress and corrosion. The approach involves creating a sealed surface within the contact gap between the sleeve and connecting components. Circular grooves and sealing washers are added to both ends of the sleeve. A two-dimensional finite element analysis model of the bolted ball joint with the sealing structure was created using SOLIDWORKS and ANSYS. The study analyzes the sealing gasket's contact pressure at various compression levels and evaluates its performance with bubble tests for air tightness. Research results show a linear relationship between contact pressure and compression rate, with a sealing pressure of 5.95MPa achieved at a 14% compression rate. This simple, cost-effective sealing method effectively prevents corrosion from seawater, making it ideal for marine environments.

It is known that ammonium has a higher permeability through anion-exchange and bipolar membranes compared to K+ cation that has the same mobility in water. However, the mechanism of this high permeability is not clear enough. We develop a mathematical model based of the Nernst-Planck and Poisson equations for diffusion of ammonium chloride through an anion-exchange membrane; proton exchange reactions between ammonium, water and ammonia are taken into account. It is assumed that ammonium, chloride and OH− ions can only pass through membrane hydrophilic pores, while ammonia can also dissolve in membrane matrix fragments not containing water and diffuse through these fragments. It is found that due to the Donnan exclusion of H+ ions as coions, the pH in the membrane internal solution increases when approaching the membrane side facing distilled water. Consequently, there is a change in the principal nitrogen-atom carrier in the membrane: in the part close to the side facing the feed NH4Cl solution (pH&lt;8.8), it is the NH4+ cation, and in the part close to distilled water, NH3 molecules. The concentration of NH4+ reaches almost zero at a point close to the middle of the membrane cross-section, which approximately halves the effective thickness of the diffusion layer for the transport of this ion. When NH3 takes over the nitrogen transport, it only needs to pass through the other half of the membrane. Leaving the membrane, it captures an H+ ion from water, and the released OH− goes towards the membrane side facing the feed solution to meet the NH4+ ions. The comparison of the simulation with experiment shows a satisfactory agreement.

Empirically based modeling is an essential aspect of design for a wave energy converter. These models are used in structural, mechanical and control design processes, as well as for performance prediction. The design of experiments and methods used to produce models from collected data have a strong impact on the quality of the model. This study considers the system identification and model validation process based on data collected from a wave tank test of a model-scale wave energy converter. Experimental design and data processing techniques based on general system identification procedures are discussed and compared with the practices often followed for wave tank testing. The general system identification processes are shown to have a number of advantages. The experimental data is then used to produce multiple models for the dynamics of the device. These models are validated and their performance is compared against one and other. While most models of wave energy converters use a formulation with wave elevation as an input, this study shows that a model using a hull pressure sensor to incorporate the wave excitation phenomenon has better accuracy.

Gold nanoclusters (AuNCs) with fluorescence in the Near Infrared (NIR) by both one- and two-photon electronic excitation were incorporated in mesoporous silica nanoparticles (MSNs) using a novel one-pot synthesis procedure where the condensation polymerization of alkoxysilane monomers in the presence of the AuNCs and a surfactant produce hybrid MSNs of 49 nm diameter. This method was further developed to prepare 30 nm diameter nanocomposite particles with simultaneous NIR fluorescence and superparamagnetic properties, with a core composed of superparamagnetic manganese ferrite nanoparticles (MnFe2O4) coated with a thin silica layer, and a shell of mesoporous silica decorated with AuNCs. The nanocomposite particles feature NIR-photoluminescence with 0.6% quantum yield and large Stokes shift (290 nm), and superparamagnetic response at 300 K, with a saturation magnetization of 13.4 emu g-1. The conjugation of NIR photoluminescence and superparamagnetic properties in the biocompatible nanocomposite has high potential for application in multimodal bioimaging.

Acute low back pain (LBP) stands as a leading cause of activity limitation and work absenteeism, and its associated healthcare expenditures are expected to become substantial when acute LBP develops into a chronic and even refractory condition. Therefore, early intervention is crucial to prevent progression to chronic pain whose management is particularly challenging and for which the most effective pharmacological therapy is still controversial. Current guideline treatment recommendations vary and are mostly driven by expertise with opinion differing across different interventions. Thus, it is difficult to formulate evidence-based guidance when relatively few randomized clinical trials did explore the diagnosis and management of LBP while employing different selection criteria, statistical analyses, and outcome measurements. This narrative review aims to provide a critical appraisal of current acute LBP management by discussing the unmet needs and areas of improvement from bench-to-bedside and proposes multimodal analgesia as the way forward to attain an effective and prolonged pain relief and functional recovery in patients with acute LBP.

The increasing complexity of the space flight program and the increase in the duration of missions require improvement of psychological monitoring tools for astronauts in orbit. The article summarizes the experience of using quantitative content analysis of communication between the crews and the Mission control center (MCC). This method allows to assess dynamics of astronaut’s psycho-emotional state, to identify the communicative style, and to detect the communication phenomena of board-MCC communication. The method is based on a combination of coping strategies approach by Lazarus and Folkman as well as B.F. Lomov’s concept about the three functions of communication. We found influence of workload on the structure and volume of communication, defined the main stable communication styles of crewmembers, and confirmed presence of the emotional transfer phenomenon. We detected that astronauts successfully solve problems that arise in orbit using the capabilities of their communication style. An ineffective MCC communication style the leads to the psycho-emotional ill-being manifesting in emotional transfer phenomenon. The presence of “third quarter” phenomenon was not confirmed by materials from six-month space flights.

The well-known coupling between the magnetic and electric fields in electromagnetic radiation is revisited in light of the recent introduction of a microscopic theory for the Ørsted magnetic field induction. I argue that, if the Ørsted magnetic field induction does indeed have a microscopic origin rather than the continuum solution offered by the Maxwell-Ampere equation, the "electromagnetic wave"' propagating in vacuum will not have a magnetic component.

Background: Recently some photon models of a Wigner's friend experiment have led investigators to suggest objective reality does not exist, and to publish non-academic articles with such claims. The public is not equipped to evaluate the severe limitations of these experiments. The separation of Wigner from the experiment and use of only reversible coherent processes for the friend allow operations that are not possible in ordinary reality according to the latest quantum research. Methods: We suggest directly testing the implied claim that objective reality, including incoherent objects with irreversible non-destructive memory, can be held in superposition. We suspect it will fail, but provide for a graduated approach that may discover something about the conditions for superposition collapse. To this end we design a thought experiment to model the objective world, investigating under what conditions experimenters in the same world (ensemble member) will be able to record a result and find it does not appear to change. An observer has a viewing apparatus and a memory apparatus. A second uncorrelated viewer of the same recorded result is employed to obtain objectivity. By hypothesis the uncorrelated second viewer obtains the same view of the measurement record as the first observer. There are not two measurements. This is not an investigation of hidden variables. Results: To model the objective world, incoherent and irreversible processes must be included. To test for superposition, coherence has to be established. These seem to present a contradiction. Conclusions: The thought experiment has suggested new places to look other than size for the origin of objective reality from the quantum world, casts doubt on the Many-Worlds interpretation, and provides a method of testing it.

The realization of a perfect absorber A = 1 with transmittance and reflectance T=R=0 by a thin metasurface is one of the hot topics in recent nanophotonics prompted by energy harvesting and sensor applications (A + R + T =1 is the energy conservation). Here we tested optical properties of over 400 structures of metal-insulator-metal (MIM) metasurfaces for a range of variation in thickness of insulator, the diameter of a disc and intra-disc distance experimentally and numerically. Conditions of a near-perfect absorption A > 95% with simultaneously occurring anti-reflection property (R < 5%) were experimentally determined. Differences between the bulk vs. nano-thin film properties at mid-IR of the used materials can be of interest for plasmonic multi-metal alloys and high entropy metals.

We introduce and analyse a simple formal thought experiment designed to reflect a qualitative decision dilemma humanity might currently face in view of climate change. In it, each generation can choose between just two options, either setting humanity on a pathway to certain high wellbeing after one generation of suffering, or leaving the next generation in the same state as this one with the same options, but facing a continuous risk of permanent collapse. We analyse this abstract setup regarding the question of what the right choice would be both in a rationality-based framework including optimal control, welfare economics and game theory, and by means of other approaches based on the notions of responsibility, safe operating spaces, and sustainability paradigms. Despite the simplicity of the setup, we find a large diversity and disagreement of assessments both between and within these different approaches.

Large aluminum alloy ring forgings are the core components of heavy-duty rocket fuel storage tanks, and the large residual stress inside the rings leads to poor shape accuracy of large thin-walled parts. The initial stress of the 2219 aluminum alloy ring blank was tested using the drilling method, and the creep constitutive coefficient of the 2219 aluminum alloy was determined through stress relaxation tests. The numerical simulation processes of thermal stress relief (TSR), vibration stress relief (VSR), and thermal-vibration stress relief (TVSR) were compared and established. Through the correlation analysis between the actual measurement results of residual stress and the simulation results, it can be seen that the strong correlation in three directions at each measurement point accounts for over 37.5%, and the moderate correlation accounts for over 62.5%. This indicates that the numerical simulation model of 2219 aluminum alloy ring containing initial residual stress can accurately reflect the size and distribution of residual stress inside the actual ring. The simulation results show that the derived constitutive model can describe the stress relaxation process of TVSR by combining a single thermal time effect stress relaxation constitutive theory with a VSR plastic deformation material model. The simulation models established above were used to calculate the residual stress homogenization ability of three types of aging. The results showed that VSR, TSR, and TVSR can homogenize and reduce the residual stress field inside the ring, improve the distribution of residual stress inside the ring, and have a better overall homogenization ability of TVSR. The VSR control has a certain effect on reducing and homogenizing residual stress, but compared with TSR and TVSR, the reduction and homogenization ability of residual stress control is limited. The homogenization control effect TVSR>TSR>VSR, and the maximum equivalent stress homogenization rates of VSR, TSR, and TVSR are 52.8%, 80.6%, and 82.2%, respectively. Then, numerical simulation technology is used to study how the initial residual stress in the blank will cause the deformation of the ring during the thin-walled machining process. The roundness error theory of the minimum containment area method is applied to evaluate the deformation degree during the thin-walled numerical machining process, and the TVSR method is used for stress regulation. The deformation law of the thin-walled machining of the ring under different aging parameters is studied.

In this note, I analyze the data generated by M. Fodje's (2013) simulation programs "epr-simple" and "epr-clocked". They were written in Python and published on Github. Inspection of the program descriptions shows that they make use of the detection-loophole and the coincidence-loophole respectively. I evaluate them with appropriate modified Bell-CHSH type inequalities: the Larsson detection-loophole adjusted CHSH, and the Larsson-Gill coincidence-loophole adjusted CHSH (NB: its correctness is conjecture, we do not have proof). The experimental efficiencies turn out to be approximately eta = 81% (close to optimal) and gamma = 55% (far from optimal). The observed values of CHSH are, as they should be, within the appropriately adjusted bounds. Fodjes' detection-loophole model turns out to be very, very close to Pearle's famous 1970 model, so the efficiency is close to optimal. The model has the same defect as Pearle's: the joint detection rates exhibit signaling. Fodje's coincidence-loophole model is actually a clever modification of his detection-loophole model. Because of this, however, it cannot lead to optimal efficiency.

As the use of AI in medical imaging has increased, so has the need to explain a model’s results. Segmentation models are one technique used to produce explainable results. Due to larger size and sophistication, segmentation models which operate on 2D data can often produce better results than models operating on 3D data. In the real world, imaging is combined with clinical factors for diagnosis. To replicate this, multimodal models are used which combine image and text modalities. I propose a multimodal arrangement that converts 3D scans to 2D and uses a 2D segmentation model (DeepLabV3) to analyze the images. This is combined with clinical biomarkers to achieve a complete confidence score. Using the Medical Segmentation Decathlon Lung (MSDL) dataset and the LUng CAncer Screening dataset (LUCAS), I achieved a testing Dice coefficient of 0.91 on segmentation with a receiver operating characteristic (ROC), average precision (AP), and F-Score of 0.89, 0.91, and 0.85 respectively on the final multimodal results. This approach raises the F-score from the previously achieved value of 0.508 to 0.85, creating a new baseline of what is achievable with multimodal lung cancer diagnostics and possible methods to achieve these accuracies.

(1) Background: With the global population aging, the demand for effective rehabilitation products for the elderly is increasing. Traditional products often fail to meet the comprehensive needs of elderly users, who require solutions addressing physical, psychological, and social aspects; (2) Methods: Using the Analytic Hierarchy Process, Quality Function Deployment, Axiomatic Design, and the System Usability Scale to identify and prioritize user needs, market research and user interviews were conducted to understand the preferences of the elderly and obtain design specifications. The focus was on multimodal sensory feedback, which was validated through the study; (3) Results: Elderly users have a strong preference for rehabilitation products that are durable, easy to use and have comprehensive sensory feedback. Intelligent rehabilitation bed as the carrier, strengthened structure, high strength material, ergonomic adjustment, integrated health monitoring system. Using digital technology for real-time health monitoring and personalized feedback to provide a comprehensive recovery experience, high user satisfaction was reported in the evaluation; (4) Conclusion: It is important to emphasize user-centered design and integrate multi-modal sensory feedback to meet the comprehensive rehabilitation needs of elderly users. Future studies should expand user samples and expert opinions to refine and validate the design and improve its effectiveness and usability.

The incessant evolution of online platforms has ushered in a multitude of shopping modalities. Within the food industry, however, assessing the delectability of meals can only be tentatively determined based on consumer feedback encompassing aspects such as taste, pricing, packaging, service quality, delivery timeliness, hygiene standards, and environmental considerations. Traditional text data mining techniques primarily focus on consumers' emotional traits, disregarding pertinent information pertaining to the online products themselves. In light of these aforementioned issues in current research methodologies, this paper introduces the Bert BiGRU Softmax model combined with multimodal features to enhance the efficacy of sentiment classification in data analysis. Comparative experiments conducted using existing data demonstrate that the accuracy rate of the model employed in this study reaches 90.9%. In comparison to single models or combinations of three models with the highest accuracy rate of 7.7%, the proposed model exhibits superior accuracy and proves highly applicable to online reviews.

Previous studies to recognize negative emotions (e.g. disgust, fear, sadness) for mental health care have used heavy equipment directly attaching electroencephalogram (EEG) electrodes to the head, making it difficult to use in daily life, and they have proposed binary classification methods to determine whether negative emotion or not. To tackle this problem, we propose a negative emotion recognition system to collect multimodal biosignal data such as five EEG signals in an EEG headset and heart rate, galvanic skin response, and skin temperature in a smart band for classifying multiple negative emotions. It consists of android Internet of Things (IoT) application, an oneM2M-compliant IoT server, and a machine learning server. The android IoT application upload the biosignal data to the IoT server. By using the biosignal data stored in the IoT server, the machine learning server recognizes the negative emotions of disgust, fear, and sadness using a multi-class support vector machine (SVM) model with a radial basis function kernel (RBF). The experimental results showed that the multi-class SVM model achieved 93% accuracy when considering all the multimodal biosignal data. Moreover, when considering only data in the smart band, it could achieve 98% accuracy by optimizing the hyper-parameter of the RBF kernel.

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from camera. For image feature extraction, the ResNet50+FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and regional voxel fusion methods. After information fusion, the Coordinate attention mechanism and SimAM attention mechanism extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm, the proposed algorithm improves the mAP value by 7.9% in BEV view and 7.8% in 3D view at IOU=0.5 (cars) and IOU=0.25 (pedestrians and cyclist). At IOU=0.7 (cars) and IOU=0.5 (pedestrians and cyclist), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms.

Autonomous driving vehicles rely on sensors for the robust perception of surroundings. Such vehicles are equipped with multiple perceptive sensors with a high level of redundancy to ensure safety and reliability in any driving condition. However, multi-sensor, such as camera, LiDAR and radar, systems bring up the requirements related to sensor calibration and synchronization, which are the fundamental blocks of any autonomous system. On the other hand, sensor fusion and integration have become important aspects of autonomous driving research and directly determine the efficiency and accuracy of advanced functions such as object detection and path planning. Classical model-based estimation and data-driven models are two mainstream approaches to achieving such integration. Most recent research is shifting to the latter, showing high robustness in real-world applications but requiring large quantities of data to be collected, synchronized, and properly categorized. To generalize the implementation of the multi-sensor perceptive system, we introduce an end-to-end generic sensor dataset collection framework that includes both hardware deploying solutions and sensor fusion algorithms. The framework prototype integrates a diverse set of sensors, such as cameras, LiDAR, and radar. Furthermore, we present a universal toolbox to calibrate and synchronize three types of sensors based on their characteristics. The framework also includes the fusion algorithms, which utilize the merits of three sensors , namely, camera, LiDAR and radar, and fuse their sensory information in a manner that is helpful for object detection and tracking research. The generality of this framework makes it applicable in any robotic or autonomous applications, also suitable for quick and large-scale practical deployment.

Improved oil recovery from tight carbonate formations may provide the world with a major source of lower-rate power over several decades. Here we provide an overview of the Arab D formation in the largest oil field on earth, the Ghawar. We investigate the occurrence of microporosity of different origins and sizes using scanning electron microscopy (SEM) and pore casting techniques. Then, we present a robust calculation of the probability of invasion and oil saturation distribution in the nested micropores using mercury injection capillary pressure data available in the literature. We show that large portions of the micropores in Arab D formation would have been bypassed during primary drainage unless the invading crude oil ganglia were sufficiently long. Considering the asphaltenic nature of oil in the Ghawar, we expect the invaded portions of the pores to turn mixed-wet, thus becoming inaccessible to waterflooding until further measures are taken to modify the system’s chemistry.

Many engineered approaches have been proposed over the years for solving the hard problem of performing indoor localisation using smartphone sensors. However, specialising these solutions for difficult edge cases remains challenging. Here we propose an end-to-end hybrid multimodal deep neural network localisation system, MM-Loc, relying on zero hand-engineered features, learning them automatically from data instead. This is achieved by using modality-specific neural networks to extract preliminary features from each sensing modality, which are then combined by cross-modality neural structures. We show that our choice of modality-specific neural architectures is capable of estimating the location with good accuracy independently. But for better accuracy, a multimodal neural network fusing the features of early modality-specific representations is a better proposition. Our proposed MM-Loc solution is tested on cross-modality samples characterised by different sampling rates and data representation (inertial sensors, magnetic and WiFi signals), outperforming traditional approaches for location estimation. MM-Loc elegantly trains directly from data unlike conventional indoor positioning systems, which rely on human intuition.

Automatic ice charting can not be achieved using only SAR modalities. It is fundamental to combine information from other remote sensors with different characteristics for more reliable sea ice characterization. In this paper, we employ principal feature analysis (PFA) to select significant information from multimodal remote sensing data. PFA is a simple yet very effective approach that can be applied to several types of data without loss of physical interpretability. Considering that different homogeneous regions require different types of information, we perform the selection patch-wise. Accordingly, by exploiting the spatial information, we increase the robustness and accuracy of PFA.

Multimodal traveling is expected to enhance mobility for users, reduce inequalities of car ownership and reduce emissions. In the same context, ride-sharing aims to minimize negative impacts related to emissions, reduce travelling costs and congestion, and increase passenger vehicle occupancy, and public transit ridership when planned for first/last mile trips. The goal of this study is to present the planning of a multimodal pilot demonstration and the challenges that emerged during and after its implementation in Athens, Greece. The demo aims to enhance the connection of low-density Attica Region areas to public transport (PT) modes, and specifically to the metro, through the provision of demand responsive ride-sharing services. During the demo period two different applications were utilized: the “Travel Companion” app and the “Driver Companion” app, which refer to passengers and drivers of the ride-sharing service. Identification of demo participants is performed through a Stated Preference (SP) experiment. Results of the demo implementation, as well as challenges that were faced show that although participants are willing to try new mobility solutions, the readiness and reliability of the new service are essential attributes towards maintaining existing users and engaging new ones.