Baseline System Research Articles

Coupling of Advanced Guidance and Robust Control for the Descent and Precise Landing of Reusable Launchers

This paper investigates the coupling of successive convex optimization guidance with robust structured H∞ control for the descent and precise landing of Reusable Launch Vehicles (RLVs). More particularly, this Guidance and Control (G&C) system is foreseen to be integrated into a nonlinear six-degree-of-freedom RLV controlled dynamics simulator which covers the aerodynamic and powered descent phase until vertical landing of a first-stage rocket equipped with a thrust vector control system and steerable planar fins. A cost function strategy analysis is performed to find out the most efficient one to be implemented in closed-loop with the robust control system and the vehicle flight mechanics involved. In addition, the controller synthesis via structured H∞ is thoroughly described. The latter are built at different points of the descent trajectory using Proportional-Integral-Derivative (PID)-like structures with feedback on the attitude angles, rates, and lateral body velocities. The architecture is verified through linear analyses as well as nonlinear cases with the aforementioned simulator, and the G&C approach is validated by comparing the performance and robustness with a baseline system in nominal conditions as well as in the presence of perturbations. The overall results show that the proposed G&C system represents a relevant candidate for realistic descent flight and precise landing phase for reusable launchers.

Data Augmentation Method Using Room Transfer Function for Monitoring of Domestic Activities

Monitoring domestic activities helps us to understand user behaviors in indoor environments, which has garnered interest as it aids in understanding human activities in context-aware computing. In the field of acoustics, this goal has been achieved through studies employing machine learning techniques, which are widely used for classification tasks involving sound recognition and other objectives. Machine learning typically achieves better performance with large amounts of high-quality training data. Given the high cost of data collection, development datasets often suffer from imbalanced data or lack high-quality samples, leading to performance degradations in machine learning models. The present study aims to address this data issue through data augmentation techniques. Specifically, since the proposed method targets indoor activities in domestic activity detection, room transfer functions were used for data augmentation. The results show that the proposed method achieves a 0.59% improvement in the F1-Score (micro) from that of the baseline system for the development dataset. Additionally, test data including microphones that were not used during training achieved an F1-Score improvement of 0.78% over that of the baseline system. This demonstrates the enhanced model generalization performance of the proposed method on samples having different room transfer functions to those of the trained dataset.

A benchmark for Portuguese zero-shot stance detection

Stance detection is the task of inferring for/against attitudes towards a particular target from text. As targets are in principle unlimited, however, research in the field has moved from so-called in-domain classification (which assume the availability of a sufficient number of stances towards the intended target for training purposes) to more realistic zero-shot scenarios. However, regardless of which - or how much - training data is taken into account, most existing zero-shot approaches are devoted to the English language, in stark opposition to alternatives devoted to Portuguese. As a means to overcome some of these difficulties, this article presents a benchmark (hereby understood as the combination of a dataset, baseline systems and their results) for zero-shot Portuguese stance detection that is, to the best of our knowledge, the first of it kind. More specifically, we adapt a number of existing models available for the English language to Portuguese, and introduce novel approaches to the task based on more recent prompt engineering methods and off-task labelling, achieving SOTA results that are, in some cases, even superior to in-domain classification.

Carrier Phase-Based Underwater Source Localization for Ultrashort Baseline

In this paper, we propose a phase-based pseudorange estimation and source localization algorithm to improve the localization performances of ultrashort baseline (USBL) systems. The conventional USBL system estimates pseudorange through cross-correlation of received chirps. However, due to the limited sampling rate, precise pseudorange cannot be estimated, resulting in low localization performance. The proposed method calculates the number of wavelengths between the transducer and receiver and detects the initial phase to estimate the pseudorange more accurately than the conventional method. It also improves localization performance by estimating and compensating for phase variations by underwater channels. The source localization performances of the proposed method and the conventional methods were compared and analyzed through computer simulations and ocean experiments, and the proposed method had better localization performances than the conventional methods.

Designing a Technique-Oriented Sport Training Game for Motivating a Change in Running Technique

Athletes often learn suboptimal techniques that place a ceiling on their performance or put them at risk of injury. Adopting a new technique can lead to a short-term dip in performance while learning it, which can be demotivating and cause an athlete to revert to their previous, suboptimal technique. To address the challenge of demotivation in adopting new techniques, we explore technique-oriented sport training games, which aim to improve sport skills by capturing behaviour and providing feedback that motivates adopting a new technique. As of yet, previous work has provided little information on how to design sports training games, and some early research suggests that immersive games may distract players, preventing them from being able to learn a new technique effectively. We designed a study comparing a baseline non-game training system with three versions of a running game, ranging from a simplistic text-based game to a 3D audiovisual game with motion feedback. We find that the games with more immersive elements were as effective as the baseline system for adopting a new technique but were preferred by players and improved their intrinsic motivation. We propose design considerations from these findings and provide new directions for researching effective sport training games.

Enhancing bilingual lexicon induction via harnessing polysemous words

Bilingual Lexicon Induction (BLI) aims to induce word translation pairs across different languages. We find there is a large proportion of polysemous words in the dataset used by BLI, which impacts the quality of the induced translation pairs. In particular, the mainstream BLI models map two monolingual word embeddings (WEs) into a shared space and regard the closest cross-lingual words as translation pairs. However, when a word has multiple translations, it becomes challenging to ensure that the polysemous word is the closest neighbor to all its translations. Based on the analysis of polysemy, we propose a simple yet effective method by harnessing polysemous words to enhance BLI. We first detect polysemous words in the seed lexicons and filter their multiple translations by comparing their semantic similarities. Therefore, a refined seed lexicon mitigates the confusion caused by translations with divergent semantics for the BLI model. Moreover, in scenarios where only single translations are available in the seed lexicon, we propose to employ a Large Language Model (LLM) to acquire monolingual synonyms, thereby refining the structure of the seed lexicon more effectively. On benchmark BLI datasets, our method demonstrates superior performance compared to five state-of-the-art (SOTA) baseline systems across almost all experimental language pairs, encompassing both sides of three similar language pairs and three distant language pairs.

GraNDe: Efficient Near-Data Processing Architecture for Graph Neural Networks

Graph Neural Network (GNN) models have attracted attention, given their high accuracy in interpreting graph data. One of the primary building blocks of a GNN model is aggregation, which gathers and averages the feature vectors corresponding to the nodes adjacent to each node. Aggregation works by multiplying the adjacency and feature matrices. The size of both matrices exceeds the on-chip cache capacity for many realistic datasets, and the adjacency matrix is highly sparse. These characteristics lead to little data reuse, causing intensive main-memory accesses during the aggregation process. Thus, aggregation exhibits memory-intensive characteristics and dominates most of the total execution time. In this paper, we propose GraNDe, an NDP architecture that accelerates memory-intensive aggregation operations by locating NDP modules near DRAM datapath to exploit rank-level parallelism. GraNDe maximizes bandwidth utilization by separating the memory channel path with the buffer chip in between so that pre-/post-processing in the host processor and reduction in NDP modules operate simultaneously. By exploring the preferred data mappings of the operand matrices to DRAM ranks, we architect GraNDe to support adaptive matrix mapping that applies the optimal mapping for each layer depending on the dimension of the layer and the configuration of a memory system. We also propose adj-bundle broadcasting and re-tiling optimizations to reduce the transfer time for adjacency matrix data and to improve feature vector data reusability by exploiting tiling with consideration of adjacency between nodes. GraNDe achieves 3.01× and 1.69× on average, and up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4.00\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1.98\times$</tex-math></inline-formula> speedups of GCN aggregation over the baseline system and the state-of-the-art NDP architecture for GCN, respectively.

Multi-objective optimization and comprehensive Thermodynamic, economic, and environmental analysis of an innovative solar-geothermal integrated system for synergistic power generation and water desalination

ABSTRACT This paper presents a novel multi-objective optimization and sustainability analysis framework for an innovative solar-geothermal integrated system for power generation and water desalination. Harnessing renewable solar and geothermal energy, the system offers a sustainable solution for energy, water, and environmental challenges. Advanced thermodynamic modeling techniques, validated by industry simulations, accurately characterize system performance. Departing from conventional analyses, the research incorporates exergy-based economic and environmental assessments and the emergy concept to quantify the total available energy required, enabling a comprehensive sustainability evaluation. Through multi-objective optimization using genetic algorithms, the system’s design and operational parameters are optimized to enhance exergy efficiency, economic emergy performance, and environmental emergy performance simultaneously. The optimization framework considers turbine inlet conditions, pressures, and desalination configurations to identify optimal operating points balancing energy efficiency, economic feasibility, and environmental impact. Results demonstrate significant improvements of up to 23.49% in exergy efficiency, 25.97% in economic emergy performance, and 16.04% in environmental emergy performance compared to the baseline system. This study focuses on the multi-objective optimization of a novel solar-geothermal integrated system for synergistic power generation and water desalination. The methodology combines thermodynamic, economic, and environmental analyses to evaluate system performance. Key findings include a significant improvement in overall efficiency and sustainability compared to conventional systems, highlighting the potential for large-scale implementation.

Knowledge Graph-Based Integration of Conversational Advisors and Faceted Filtering

Abstract Modern e-commerce websites often provide users with a variety of components, such as faceted filters and conversational recommender systems, that act as product advisors to help them find relevant products. However, these components are often treated separately and presented as independent components, leading to increased cognitive load and disruption in the search process. Also, the reasoning behind the resulting product recommendations is often not transparent. To address these limitations, we propose a novel approach that relies on a knowledge graph structure to seamlessly integrate faceted filtering and conversational advisors based on graphical user interfaces (GUI). Concretely, the knowledge graph is used to suggest filter values and products based on the user’s answers in the advisor, and, conversely, to determine follow-up questions based on the user’s selected filter values. The user interface also visualizes and explains the underlying relationships between answers given to the advisor and relevant product features in the filter component in order to increase the transparency of the search process. We conducted two user studies with a total of 448 participants to compare a system that integrates the different components according to our approach with a baseline system in which the mechanisms operate separately. Sequence analysis of the logged interaction data provided insights into participants’ behavior as they interacted with both systems. The results indicate that displaying recommended products and related explanations directly in the filter component increases acceptance and trust in the system. Also, the combination of a conversational advisor with values displayed in a filter interface, along with explanations of the underlying relationships, significantly contributes to the knowledge and understanding of those product features that are important in terms of the current search goal.

Experimental investigation of enhanced CO2 refrigeration systems at varying operating condi-tions

The efficiency of a CO2 refrigeration system depends mainly on the operating conditions and the system design. To increase the energy efficiency, advanced system designs include additional components and their combinations such as parallel compression, ejectors, and expansion machines. For a direct comparison of different system designs, measurements were performed on an advanced CO2 laboratory refrigeration system at different operating conditions. The system behaviour was investigated at different gas cooler outlet temperatures, varying cooling loads, different evaporation temperatures and amounts of superheating. The results of the measurements performed on a baseline system configuration and advanced system designs are presented. It was observed that the influence of operating conditions is less important for certain measures in terms of efficiency improvement than for others. For each system design, operating conditions were identified under which a particularly advantageous behaviour of the respective measures was found. In the future, this will allow the judgment of the efficiency enhancement of each of different respective features for each individual application.

Transfer Learning and Deep Neural Networks for Robust Intersubject Hand Movement Detection from EEG Signals

In this research, five systems were developed to classify four distinct motor functions—forward hand movement (FW), grasp (GP), release (RL), and reverse hand movement (RV)—from EEG signals, using the WAY-EEG-GAL dataset where participants performed a sequence of hand movements. During preprocessing, band-pass filtering was applied to remove artifacts and focus on the mu and beta frequency bands. The initial system, a preliminary study model, explored the overall framework of EEG signal processing and classification, utilizing time-domain features such as variance and frequency-domain features such as alpha and beta power, with a KNN model for classification. Insights from this study informed the development of a baseline system, which innovatively combined the common spatial patterns (CSP) method with continuous wavelet transform (CWT) for feature extraction and employed a GoogLeNet classifier with transfer learning. This system classified six unique pairs of events derived from the four motor functions, achieving remarkable accuracy, with the highest being 99.73% for the GP–RV pair and the lowest 80.87% for the FW–GP pair in intersubject classification. Building on this success, three additional systems were developed for four-way classification. The final model, ML-CSP-OVR, demonstrated the highest intersubject classification accuracy of 78.08% using all combined data and 76.39% for leave-one-out intersubject classification. This proposed model, featuring a novel combination of CSP-OVR, CWT, and GoogLeNet, represents a significant advancement in the field, showcasing strong potential as a general system for motor imagery (MI) tasks that is not dependent on the subject. This work highlights the prominence of the research contribution by demonstrating the effectiveness and robustness of the proposed approach in achieving high classification accuracy across different motor functions and subjects.

Application of Proximal Policy Optimization for Resource Orchestration in Serverless Edge Computing

Serverless computing is a new cloud computing model suitable for providing services in both large cloud and edge clusters. In edge clusters, the autoscaling functions play a key role on serverless platforms as the dynamic scaling of function instances can lead to reduced latency and efficient resource usage, both typical requirements of edge-hosted services. However, a badly configured scaling function can introduce unexpected latency due to so-called “cold start” events or service request losses. In this work, we focus on the optimization of resource-based autoscaling on OpenFaaS, the most-adopted open-source Kubernetes-based serverless platform, leveraging real-world serverless traffic traces. We resort to the reinforcement learning algorithm named Proximal Policy Optimization to dynamically configure the value of the Kubernetes Horizontal Pod Autoscaler, trained on real traffic. This was accomplished via a state space model able to take into account resource consumption, performance values, and time of day. In addition, the reward function definition promotes Service-Level Agreement (SLA) compliance. We evaluate the proposed agent, comparing its performance in terms of average latency, CPU usage, memory usage, and loss percentage with respect to the baseline system. The experimental results show the benefits provided by the proposed agent, obtaining a service time within the SLA while limiting resource consumption and service loss.

Design optimization of finned multi-tube PCM heat exchanger for enhancing EV energy performance

This study presents an optimized design of a finned multi-tube phase change material-based thermal energy storage system for electric vehicle thermal management, addressing the challenge of low battery efficiency in cold climates. While finned multi-tube designs are recognized for their thermal advantages, their application in electric vehicles has been underexplored. Previous research often overlooks the full operational cycle of electric vehicles, including charging (melting), discharging (solidification), and driving conditions. This work bridges the gap by optimizing the thermal energy storage design using a multi-objective genetic algorithm to enhance both thermal efficiency and energy density. The optimized design reduces melting and solidification times by 68.6% and 60.3%, respectively, and increases energy density by 4.9% compared to the initial design. The study further integrates the optimized thermal energy storage system into an electric vehicle thermal management strategy, analyzing its performance under real-life driving cycles in various ambient temperatures. This integration reduces total energy consumption by 20.6% compared to a baseline system. These findings offer a novel approach to improving the driving range of electric vehicles in cold climates by minimizing power demand on electric batteries for cabin heating.

Long-range LBL underwater acoustic navigation considering Earth curvature and Doppler effect

The accuracy of underwater acoustic navigation is significantly influenced by geometry configuration and systematic errors coming from geophysical environment. Long baseline (LBL) systems exhibit superior positioning precision than other acoustic navigation systems, primarily attributable to the better Geometric Dilution of Precision (GDOP). However, the geometry configuration tends to degrade when the underwater vehicle is far away from the seafloor beacons. Factors such as acoustic ray bending error, Doppler effect and Earth curvature may seriously affect the navigation accuracy. To address these issues, we present a robust Kalman filter with systematic error compensation for long-range LBL systems. Firstly, a reversed acoustic ray tracking method is proposed for a unique phenomenon in acoustic wave propagation. Following that, we construct an acoustic positioning model with a time bias parameter, to weaken the impact of Doppler effect on acoustic ranging. This additional parameter was estimated with the state of the user vehicle in real time. At last, an observation equation of pressure gauge considering Earth curvature is presented for depth constraint. Long-range LBL experiments conducted in the South China Sea is employed to validate the performance of the proposed methods, taking the positioning results of inverted ultra-short baseline (iUSBL) system as reference. The results show that the proposed method outperform traditional method with a decrease of about 60 % in the three-dimensional root mean square (3DRMS) of navigation errors. With mentioned three improvements, the 3DRMS of the long-range LBL system with the longest distance of 20 km from the beacon center is less than 14 m. These findings can provide theoretical basis for other long-range LBL systems.

Large Language Models Improve the Identification of Emergency Department Visits for Symptomatic Kidney Stones.

Recent advancements of large language models (LLMs) like Generative Pre-trained Transformer 4 (GPT-4) have generated significant interest among the scientific community. Yet, the potential of these models to be utilized in clinical settings remains largely unexplored. This study investigated the abilities of multiple LLMs and traditional machine learning models to analyze emergency department (ED) reports and determine if the corresponding visits were caused by symptomatic kidney stones. Leveraging a dataset of manually annotated ED reports, we developed strategies to enhance the performance of GPT-4, GPT-3.5, and Llama-2 including prompt optimization, zero- and few-shot prompting, fine-tuning, and prompt augmentation. Further, we implemented fairness assessment and bias mitigation methods to investigate the potential disparities by these LLMs with respect to race and gender. A clinical expert manually assessed the explanations generated by GPT-4 for its predictions to determine if they were sound, factually correct, unrelated to the input prompt, or potentially harmful. The evaluation includes a comparison between LLMs, traditional machine learning models (logistic regression, extreme gradient boosting, and light gradient boosting machine), and a baseline system utilizing International Classification of Diseases (ICD) codes for kidney stones. The best results were achieved by GPT-4 (macro-F1=0.833, 95% confidence interval [CI]=0.826-0.841) and GPT-3.5 (macro-F1=0.796, 95% CI=0.796-0.796), both being statistically significantly better than the ICD-based baseline result (macro-F1=0.71). Ablation studies revealed that the initial pre-trained GPT-3.5 model benefits from fine-tuning when using the same parameter configuration. Adding demographic information and prior disease history to the prompts allows LLMs to make more accurate decisions. The evaluation of bias found that GPT-4 exhibited no racial or gender disparities, in contrast to GPT-3.5, which failed to effectively model racial diversity. The analysis of explanations provided by GPT-4 demonstrates advanced capabilities of this model in understanding clinical text and reasoning with medical knowledge.

Bio-inspired machine-learning aided geo-magnetic field based AUV navigation system

The navigational accuracy of sea animals and trans-ocean birds provides inspiration in using geo-magnetic field (GMF) for realizing strategic truly autonomous underwater vehicles (AUV) capable of determining their absolute position on earth, without the aid of ship-referenced acoustic baseline systems. Supervised Machine Learning algorithms are applied on the GMF intensity data obtained from NOAA World Magnetic Model for a 900 km2 within the Indian mineral exploratory area in the Central Indian Ocean, with a resolution of 50 m, considering the sensitivity of commercially available magnetometers. It is identified that, for AUVs equipped with magnetometers with a detection sensitivity of 0.1 nT, the supervisory random forest regression and decision tree algorithm trained with priori GMF data, could provide trajectory guidance to AUVs with an absolute mean position accuracy in 2D plane, with reference to the last known position from Integrated Navigation system aided initially with GPS and with acoustic positioning in underwater. Circular Error Probable (CEP 50) of 53 m and 56 m, respectively. The scalar GMF anomaly navigation demonstrated to be a viable GPS-alternative navigation system could be extended to larger areas with inclination and declination vectors, as unique identifiers.

Machine anomalous sound detection based on audio synthesis generative adversarial network

Abstract In the pursuit of implementing safety monitoring within Industry 4.0 smart production, deep learning methodologies are employed to harness the audio signals emanating from the operation of machinery and equipment, facilitating anomaly detection. Aiming to address the challenge of the few-shot samples for anomalous sound detection in an unsupervised setting, this paper introduces a machine anomalous sound detection method using an Audio Synthesis Adversarial Generative Network (ASGAN). The augmentation of classifiers within the network’s discriminator is proposed to execute a multi-classification task, thereby transforming the unsupervised training milieu into a semi-supervised one and enhancing the discriminator’s accuracy. To address the oversight of audio frequency domain features by conventional generative adversarial networks, the squeeze-and-excitation network is applied to concentrate on crucial frequency bands within the frequency domain. Experimental validation is conducted by using the DCASE Challenge Task2 dataset, revealing that the performance of the anomaly detection method leveraging audio synthesis generative adversarial networks surpasses that of the baseline system.

Improving biomedical entity linking for complex entity mentions with LLM-based text simplification.

Large amounts of important medical information are captured in free-text documents in biomedical research and within healthcare systems, which can be made accessible through natural language processing (NLP). A key component in most biomedical NLP pipelines is entity linking, i.e. grounding textual mentions of named entities to a reference of medical concepts, usually derived from a terminology system, such as the Systematized Nomenclature of Medicine Clinical Terms. However, complex entity mentions, spanning multiple tokens, are notoriously hard to normalize due to the difficulty of finding appropriate candidate concepts. In this work, we propose an approach to preprocess such mentions for candidate generation, building upon recent advances in text simplification with generative large language models. We evaluate the feasibility of our method in the context of the entity linking track of the BioCreative VIII SympTEMIST shared task. We find that instructing the latest Generative Pre-trained Transformer model with a few-shot prompt for text simplification results in mention spans that are easier to normalize. Thus, we can improve recall during candidate generation by 2.9percentage points compared to our baseline system, which achieved the best score in the original shared task evaluation. Furthermore, we show that this improvement in recall can be fully translated into top-1 accuracy through careful initialization of a subsequent reranking model. Our best system achieves an accuracy of 63.6% on the SympTEMIST test set. The proposed approach has been integrated into the open-source xMEN toolkit, which is available online via https://github.com/hpi-dhc/xmen.

Topic-Centric Explanations for News Recommendation

News recommender systems (NRS) have been widely applied for online news websites to help users find relevant articles based on their interests. Recent methods have demonstrated considerable success in terms of recommendation performance. However, the lack of explanation for these recommendations can lead to mistrust among users and lack of acceptance of recommendations. To address this issue, we propose a new explainable news model to construct a topic-aware explainable recommendation approach that can both accurately identify relevant articles and explain why they have been recommended, using information from associated topics. Additionally, our model incorporates two coherence metrics applied to assess topic quality, providing a measure of the interpretability of these explanations. The results of our experiments on the MIND dataset indicate that the proposed explainable NRS outperforms several other baseline systems, while it is also capable of producing interpretable topics measured by coherence metrics. Furthermore, we present a case study through real-world examples showcasing the usefulness of our NRS for generating explanations.

Unmasking Acne: Azithromycin Edges Out Doxycycline in Randomized Trial at Tertiary Care Centre

Background: Acne vulgaris, a prevalent global condition, often necessitates antibiotic therapy. Doxycycline has been a mainstay treatment; however, recent research suggests azithromycin might be superior. Conflicting data and a lack of local studies regarding their comparative efficacy warrant further investigation. Objectives: This study aimed to compare the efficacy of oral azithromycin with oral doxycycline in treating acne vulgaris at a tertiary care hospital in Islamabad. Methods: A randomized controlled trial was conducted. Patients aged 14-30 years (n=190) were enrolled and randomly assigned to either azithromycin or doxycycline treatment groups. Baseline and post-treatment (12 weeks) Global Acne Grading System (GAGS) scores were assessed. Percent reductions in GAGS score were categorized into four groups (&lt;25%, 25-50%, 51-75%, and &gt;75%) for intergroup comparison. Written informed consent was obtained from all participants. Results: The mean patient age was 21.30±4.93 years, with a female predominance (male:female ratio 1:1.2). Most patients had Fitz-Patrick Skin Type-V (64.7%) compared to Type-IV (35.3%). Baseline GAGS scores were comparable between groups (p=0.612). Notably, post-treatment GAGS scores were significantly lower in the azithromycin group (p&lt;0.001), demonstrated by a greater mean change (19.33±3.03 vs. 17.70±2.99; p&lt;0.001) and percent reduction (81.87±8.74 vs. 75.97±11.12%; p&lt;0.001) compared to doxycycline. Additionally, 75.3% of patients achieved an excellent reduction in GAGS score, with a significantly higher proportion observed in the azithromycin group (87.4% vs. 63.2%; p&lt;0.001). Similar significant differences were observed across subgroups based on age, gender, and skin type. Conclusion: This study suggests that azithromycin demonstrates superior efficacy to doxycycline for acne vulgaris management, regardless of patient demographics or skin type. Its established better safety profile further supports its potential as a preferred therapeutic option in future dermatological practice. Keywords: Acne Vulgaris, Azithromycin, Doxycycline, Percent Reduction in GAGS Score