Applied Sciences最新文献

{"title":"IW-NeRF: Using Implicit Watermarks to Protect the Copyright of Neural Radiation Fields","authors":"Lifeng Chen, Chaoyue Song, Jia Liu, Wenquan Sun, Weina Dong, Fuqiang Di","doi":"10.3390/app14146184","DOIUrl":"https://doi.org/10.3390/app14146184","url":null,"abstract":"The neural radiance field (NeRF) has demonstrated significant advancements in computer vision. However, the training process for NeRF models necessitates extensive computational resources and ample training data. In the event of unauthorized usage or theft of the model, substantial losses can be incurred by the copyright holder. To address this concern, we present a novel algorithm that leverages the implicit neural representation (INR) watermarking technique to safeguard NeRF model copyrights. By encoding the watermark information implicitly, we integrate its parameters into the NeRF model’s network using a unique key. Through this key, the copyright owner can extract the embedded watermarks from the NeRF model for ownership verification. To the best of our knowledge, this is the pioneering implementation of INR watermarking for the protection of NeRF model copyrights. Our experimental results substantiate that our approach not only offers robustness and preserves high-quality 3D reconstructions but also ensures the flawless (100%) extraction of watermark content, thereby effectively securing the copyright of the NeRF model.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"4 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MicroBERT: Distilling MoE-Based Knowledge from BERT into a Lighter Model","authors":"Dashun Zheng, Jiaxuan Li, Yunchu Yang, Yapeng Wang, P. Pang","doi":"10.3390/app14146171","DOIUrl":"https://doi.org/10.3390/app14146171","url":null,"abstract":"Natural language-processing tasks have been improved greatly by large language models (LLMs). However, numerous parameters make their execution computationally expensive and difficult on resource-constrained devices. For this problem, as well as maintaining accuracy, some techniques such as distillation and quantization have been proposed. Unfortunately, current methods fail to integrate model pruning with downstream tasks and overlook sentence-level semantic modeling, resulting in reduced efficiency of distillation. To alleviate these limitations, we propose a novel distilled lightweight model for BERT named MicroBERT. This method can transfer the knowledge contained in the “teacher” BERT model to a “student” BERT model. The sentence-level feature alignment loss (FAL) distillation mechanism, guided by Mixture-of-Experts (MoE), captures comprehensive contextual semantic knowledge from the “teacher” model to enhance the “student” model’s performance while reducing its parameters. To make the outputs of “teacher” and “student” models comparable, we introduce the idea of a generative adversarial network (GAN) to train a discriminator. Our experimental results based on four datasets show that all steps of our distillation mechanism are effective, and the MicroBERT (101.14%) model outperforms TinyBERT (99%) by 2.24% in terms of average distillation reductions in various tasks on the GLUE dataset.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"4 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141642546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Surveillance of Airport Apron: Detection and Location of Abnormal Behavior in Typical Non-Cooperative Human Objects","authors":"Jun Li, Xiangqing Dong","doi":"10.3390/app14146182","DOIUrl":"https://doi.org/10.3390/app14146182","url":null,"abstract":"Most airport surface surveillance systems focus on monitoring and commanding cooperative objects (vehicles) while neglecting the location and detection of non-cooperative objects (humans). Abnormal behavior by non-cooperative objects poses a potential threat to airport security. This study collects surveillance video data from civil aviation airports in several regions of China, and a non-cooperative abnormal behavior localization and detection framework (NC-ABLD) is established. As the focus of this paper, the proposed framework seamlessly integrates a multi-scale non-cooperative object localization module, a human keypoint detection module, and a behavioral classification module. The framework uses a serial structure, with multiple modules working in concert to achieve precise position, human keypoints, and behavioral classification of non-cooperative objects in the airport field. In addition, since there is no publicly available rich dataset of airport aprons, we propose a dataset called IIAR-30, which consists of 1736 images of airport surfaces and 506 video clips in six frequently occurring behavioral categories. The results of experiments conducted on the IIAR-30 dataset show that the framework performs well compared to mainstream behavior recognition methods and achieves fine-grained localization and refined class detection of typical non-cooperative human abnormal behavior on airport apron surfaces.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"11 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-Time Analysis of Facial Expressions for Mood Estimation","authors":"Juan Sebastián Filippini, Javier Varona, Cristina Manresa-Yee","doi":"10.3390/app14146173","DOIUrl":"https://doi.org/10.3390/app14146173","url":null,"abstract":"This paper proposes a model-based method for real-time automatic mood estimation in video sequences. The approach is customized by learning the person’s specific facial parameters, which are transformed into facial Action Units (AUs). A model mapping for mood representation is used to describe moods in terms of the PAD space: Pleasure, Arousal, and Dominance. From the intersection of these dimensions, eight octants represent fundamental mood categories. In the experimental evaluation, a stimulus video randomly selected from a set prepared to elicit different moods was played to participants, while the participant’s facial expressions were recorded. From the experiment, Dominance is the dimension least impacted by facial expression, and this dimension could be eliminated from mood categorization. Then, four categories corresponding to the quadrants of the Pleasure–Arousal (PA) plane, “Exalted”, “Calm”, “Anxious” and “Bored”, were defined, with two more categories for the “Positive” and “Negative” signs of the Pleasure (P) dimension. Results showed a 73% of coincidence in the PA categorization and a 94% in the P dimension, demonstrating that facial expressions can be used to estimate moods, within these defined categories, and provide cues for assessing users’ subjective states in real-world applications.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"2 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141642261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tilt-X: Development of a Pitch-Axis Tiltrotor Quadcopter for Maximizing Horizontal Pulling Force and Yaw Moment","authors":"Xiaodi Tao, Seong Young Ko","doi":"10.3390/app14146181","DOIUrl":"https://doi.org/10.3390/app14146181","url":null,"abstract":"In recent years, there has been a significant amount of research on tiltrotor multicopter unmanned aerial vehicles (TM-UAVs) in aerial robotics. Despite the varying frame types of TM-UAVs, they all still aim to decouple the propeller from the body, which means that the propeller’s attitude control is independent of the body’s attitude control. On the one hand, this solves the issue of multicopter unmanned aerial vehicles (M-UAVs) being limited by small roll and pitch angles, thereby improving flight performance. On the other hand, it addresses the drawbacks of M-UAVs as typical underactuated systems. However, the fact still remains that it cannot significantly change thrust direction, thus providing the necessary wrench direction for aerial manipulation. This paper presents a pitch-axis tiltrotor quadcopter unmanned aerial vehicle (UAV) design named Tilt-X, which can maximize horizontal pulling force and yaw moment when used as an aerial manipulator. This design contributes to tasks such as pushing, pulling, and twisting. The reliability of the design has been demonstrated through dynamic modeling and experimental validation.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"5 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141641972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Treatment of Orthognathic Surgical Class III Patient with Coffin–Siris Syndrome: A Case Report","authors":"M. Macrì, Chiara Rotelli, Claudia Di Pace, Mario Festa, Gabriella Galluccio, Felice Festa","doi":"10.3390/app14146179","DOIUrl":"https://doi.org/10.3390/app14146179","url":null,"abstract":"We present a case report of a 26-year-old female suffering from Coffin–Siris Syndrome, who underwent orthodontic treatment and surgery to solve her malocclusion and to improve her aesthetics and functional occlusion. Methods: The presurgical phase involved multibracket self-ligating attachments, namely a Damon prescription. The patient underwent maxillofacial surgery to correct the severe skeletal malocclusion and to relocate the bone bases to the right position. Post-surgical orthodontic treatment was performed to complete the alignment. Results: The patient’s aesthetics and functional abilities improved. Conclusions: Syndromic patients can undergo orthodontic treatment if comorbidities and collaboration allow it. The support and collaboration of families and psychotherapists must be considered, but clinical cases of syndromic patients can be faced and solved. Obviously, each syndromic patient is considered unique, and the risk–benefit ratio must be correctly assessed for each one.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"23 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141641434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18","authors":"Longxin Yao, Yun Lu, Yukun Qian, Changjun He, Mingjiang Wang","doi":"10.3390/app14146175","DOIUrl":"https://doi.org/10.3390/app14146175","url":null,"abstract":"The high-accuracy detection of multiple distinct human emotions is crucial for advancing affective computing, mental health diagnostics, and human–computer interaction. The integration of deep learning networks with entropy measures holds significant potential in neuroscience and medicine, especially for analyzing EEG-based emotion states. This study proposes a method combining ResNet18 with differential entropy to identify five types of human emotions (happiness, sadness, fear, disgust, and neutral) from EEG signals. Our approach first calculates the differential entropy of EEG signals to capture the complexity and variability of the emotional states. Then, the ResNet18 network is employed to learn feature representations from the differential entropy measures, which effectively captures the intricate spatiotemporal dynamics inherent in emotional EEG patterns using residual connections. To validate the efficacy of our method, we conducted experiments on the SEED-V dataset, achieving an average accuracy of 95.61%. Our findings demonstrate that the combination of ResNet18 with differential entropy is highly effective in classifying multiple distinct human emotions from EEG signals. This method shows robust generalization and broad applicability, indicating its potential for extension to various pattern recognition tasks across different domains.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"83 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141643302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CO2 Emissions Resulting from Large-Scale Integration of Electric Vehicles Using a Macro Perspective","authors":"Fátima Monteiro, Armando Sousa","doi":"10.3390/app14146177","DOIUrl":"https://doi.org/10.3390/app14146177","url":null,"abstract":"Smart grids with EVs have been proposed as a great contribution to sustainability. Considering environmental sustainability is of great importance to humanity, it is essential to assess whether electrical vehicles (EVs) actually contribute to improving it. The objectives of the present study are, from a macro (broad-scope) perspective, to identify the sources of emissions and to create a framework for the calculation of CO2 emissions resulting from large-scale EV use. The results show that V2G mode increases emissions and therefore reduces the benefits of using EVs. The results also show that in the best scenario (NC mode), an EV will have 32.7% less emissions, and in the worst case (V2G mode), it will have 25.6% more emissions than an internal combustion vehicle (ICV), meaning that sustainability improvement is not always ensured. The present study shows that considering a macro perspective is essential to estimate a more comprehensive value of emissions. The main contributions of this work are the creation of a framework for identifying the main contributions to CO2 emissions resulting from large-scale EV integration, and the calculation of estimated CO2 emissions from a macro perspective. These are important contributions to future studies in the area of smart grids and large-scale EV integration, for decision-makers as well as common citizens.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"3 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141642298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multicriteria Decision Model for Port Evaluation and Ranking: An Analysis of Container Terminals in Latin America and the Caribbean Using PCA-TOPSIS Methodologies","authors":"Adriana Pabón-Noguera, M. G. Carrasco-García, J. J. Ruíz-Aguilar, M. I. Rodríguez-García, María Cerbán-Jimenez, Ignacio José Turias Domínguez","doi":"10.3390/app14146174","DOIUrl":"https://doi.org/10.3390/app14146174","url":null,"abstract":"In recent years, despite a decline in international trade and disruptions in the supply chain caused by COVID-19, the main container terminals in Latin America and the Caribbean (LAC) have increased their container volumes. This growth has necessitated significant adaptations by seaports and their authorities to meet new demands. Consequently, there has been a focused analysis on the performance, efficiency, and competitiveness, particularly their most relevant logistical aspects. In this paper, a multi-objective hybrid approach was employed. The Principal Component Analysis (PCA) technique was combined with the Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) to rank LAC container terminals and identify operational criteria affecting efficiency. The analysis considered all input variables (berth/quay length, quay draught, yard area, number of quay cranes (portainer), number of yard cranes (trastainer), reachstacker, multicranes, daily montainer movement capacity, number of station reefer container type, number of terminals, and distance to the Panama Canal) and output variable (port performance expressed in TEUs from 2014 to 2023). The results revealed noteworthy findings for several terminals, particularly Colón, Santos, or Cartagena, which stands out as the main container port in LAC not only in annual TEUs throughput, but also in resource utilization.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"11 44","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141640528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Efficacy of Transcranial Magnetic Stimulation in Symptom Relief and Cognitive Function in Obsessive–Compulsive Disorder, Substance Use Disorder, and Depression: An Insight from a Naturalistic Observational Study","authors":"A. Moro, Daniele Saccenti, A. Vergallito, Regina Gregori Grgič, Silvia Grazioli, Novella Pretti, Sofia Crespi, Antonio Malgaroli, Simona Scaini, G. Ruggiero, S. Sassaroli, Mattia Ferro, J. Lamanna","doi":"10.3390/app14146178","DOIUrl":"https://doi.org/10.3390/app14146178","url":null,"abstract":"The utilization of non-invasive neurostimulation techniques, such as transcranial magnetic stimulation (TMS), is increasingly prevalent in psychiatry due to their efficacy and safety. Although the precise therapeutic mechanisms remain partially unclear, repetitive TMS, particularly high-frequency stimulation, may enhance cognitive functions, contributing to therapeutic benefits. This within-subjects study examined the impact of TMS on cognitive and symptomatic outcomes in patients with obsessive–compulsive disorder (OCD), substance use disorder (SUD), and major depressive disorder (MDD). A total of 44 patients underwent cognitive tests and symptom assessments before and after an intensive four-week TMS treatment phase, followed by a four-week maintenance phase. Cognitive assessments included Raven’s matrices, verbal fluency, and digit span tests, while symptom severity was measured using the Italian version of the SCL-90-R. Decision-making performance was also evaluated by administering a delay discounting (DD) test. Principal component analysis was used to generate a dimensional characterization of subjects along cognitive and symptom-related axes before and after treatment. The results indicated that TMS significantly improved symptom scores, but no significant cognitive enhancement was observed. Statistical analysis based on linear mixed-effects models confirmed these findings, showing a significant fixed effect of TMS treatment on symptoms but not on cognitive performance. DD metrics remained unchanged. These findings suggest that while TMS effectively alleviates clinical symptoms, it does not produce consistent or appreciable enhancement of cognitive functions in these protocols. This study highlights the need for more personalized and combined therapeutic approaches to maximize the benefits of TMS, potentially incorporating cognitive enhancement strategies. Future studies will be useful to explore whether the results we obtained are valid for other pathologies, cognitive tests, and stimulation protocols.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"27 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141641388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}