Search

Driving under drowsy conditions significantly escalates the risk of vehicular accidents. Although recent efforts have focused on using electroencephalography to detect drowsiness, helping prevent accidents caused by driving in such states, seamless human-machine interaction in driving scenarios requires a more versatile EEG-based system. This system should be capable of understanding a driver's intention while demonstrating resilience to artifacts induced by sudden movements. This paper pioneers a novel research direction in BCI-assisted driving, studying the neural patterns related to driving intentions and presenting a novel method for driving intention prediction. In particular, our preliminary analysis of the EEG signal using independent component analysis suggests a close relation between the intention of driving maneuvers and the neural activities in central-frontal and parietal areas. Power spectral density analysis at a group level also reveals a notable distinction among various driving intentions in the frequency domain. To exploit these brain dynamics, we propose a novel Masked EEG Modeling framework for predicting human driving intentions, including the intention for left turning, right turning, and straight proceeding. Extensive experiments, encompassing comprehensive quantitative and qualitative assessments on public dataset, demonstrate the proposed method is proficient in predicting driving intentions across various vigilance states. Specifically, our model attains an accuracy of 85.19% when predicting driving intentions for drowsy subjects, which shows its promising potential for mitigating traffic accidents related to drowsy driving. Notably, our method maintains over 75% accuracy when more than half of the channels are missing or corrupted, underscoring its adaptability in real-life driving.

Decoding linguistic information from non-invasive brain signals using EEG has gained increasing research attention due to its vast applicational potential. Recently, a number of works have adopted a generative-based framework to decode electroencephalogram (EEG) signals into sentences by utilizing the power generative capacity of pretrained large language models (LLMs). However, this approach has several drawbacks that hinder the further development of linguistic applications for brain-computer interfaces (BCIs). Specifically, the ability of the EEG encoder to learn semantic information from EEG data remains questionable, and the LLM decoder's tendency to generate sentences based on its training memory can be hard to avoid. These issues necessitate a novel approach for converting EEG signals into sentences. In this paper, we propose a novel two-step pipeline that addresses these limitations and enhances the validity of linguistic EEG decoding research. We first confirm that word-level semantic information can be learned from EEG data recorded during natural reading by training a Conformer encoder via a masked contrastive objective for word-level classification. To achieve sentence decoding results, we employ a training-free retrieval method to retrieve sentences based on the predictions from the EEG encoder. Extensive experiments and ablation studies were conducted in this paper for a comprehensive evaluation of the proposed approach. Visualization of the top prediction candidates reveals that our model effectively groups EEG segments into semantic categories with similar meanings, thereby validating its ability to learn patterns from unspoken EEG recordings. Despite the exploratory nature of this work, these results suggest that our method holds promise for providing more reliable solutions for converting EEG signals into text.

Proteins govern most biological functions essential for life, but achieving controllable protein discovery and optimization remains challenging. Recently, machine learning-assisted protein editing (MLPE) has shown promise in accelerating optimization cycles and reducing experimental workloads. However, current methods struggle with the vast combinatorial space of potential protein edits and cannot explicitly conduct protein editing using biotext instructions, limiting their interactivity with human feedback. To fill these gaps, we propose a novel method called ProtET for efficient CLIP-informed protein editing through multi-modality learning. Our approach comprises two stages: in the pretraining stage, contrastive learning aligns protein-biotext representations encoded by two large language models (LLMs), respectively. Subsequently, during the protein editing stage, the fused features from editing instruction texts and original protein sequences serve as the final editing condition for generating target protein sequences. Comprehensive experiments demonstrated the superiority of ProtET in editing proteins to enhance human-expected functionality across multiple attribute domains, including enzyme catalytic activity, protein stability and antibody specific binding ability. And ProtET improves the state-of-the-art results by a large margin, leading to significant stability improvements of 16.67% and 16.90%. This capability positions ProtET to advance real-world artificial protein editing, potentially addressing unmet academic, industrial, and clinical needs., Comment: 13 pages, 7 figures, 5 tables

We propose AMP-Designer, an LLM-based foundation model approach for the rapid design of novel antimicrobial peptides (AMPs) with multiple desired properties. Within 11 days, AMP-Designer enables de novo design of 18 novel candidates with broad-spectrum potency against Gram-negative bacteria. Subsequent in vitro validation experiments demonstrate that almost all in silico recommended candidates exhibit notable antibacterial activity, yielding a 94.4% positive rate. Two of these candidates exhibit exceptional activity, minimal hemotoxicity, substantial stability in human plasma, and a low propensity of inducing antibiotic resistance as observed in murine lung infection experiments, showcasing their significant efficacy in reducing bacterial load by approximately one hundredfold. The entire process, from in silico design to in vitro and in vivo validation, is completed within a timeframe of 48 days. Moreover, AMP-Designer demonstrates its remarkable capability in designing specific AMPs to target strains with extremely limited labeled datasets. The most outstanding candidate against Propionibacterium acnes suggested by AMP-Designer exhibits an in vitro minimum inhibitory concentration value of 2.0 $\mu$g/ml. Through the integration of advanced machine learning methodologies such as contrastive prompt tuning, knowledge distillation, and reinforcement learning within the AMP-Designer framework, the process of designing AMPs demonstrates exceptional efficiency. This efficiency remains conspicuous even in the face of challenges posed by constraints arising from a scarcity of labeled data. These findings highlight the tremendous potential of AMP-Designer as a promising approach in combating the global health threat of antibiotic resistance., Comment: 43 pages, 6 figures, 5 tables. Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract appearing here is slightly shorter than that in the PDF file

Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm. Token-Mol is built on the transformer decoder architecture and trained using random causal masking techniques. Additionally, we proposed the Gaussian cross-entropy (GCE) loss function to overcome the challenges in regression tasks, significantly enhancing the capacity of LLMs to learn continuous numerical values. Through a combination of fine-tuning and reinforcement learning (RL), Token-Mol achieves performance comparable to or surpassing existing task-specific methods across various downstream tasks, including pocket-based molecular generation, conformation generation, and molecular property prediction. Compared to existing molecular pre-trained models, Token-Mol exhibits superior proficiency in handling a wider range of downstream tasks essential for drug design. Notably, our approach improves regression task accuracy by approximately 30% compared to similar token-only methods. Token-Mol overcomes the precision limitations of token-only models and has the potential to integrate seamlessly with general models such as ChatGPT, paving the way for the development of a universal artificial intelligence drug design model that facilitates rapid and high-quality drug design by experts.

Ensembling multiple models has always been an effective approach to push the limits of existing performance and is widely used in classification tasks by simply averaging the classification probability vectors from multiple classifiers to achieve better accuracy. However, in the thriving open-source Large Language Model (LLM) community, ensembling methods are rare and typically limited to ensembling the full-text outputs of LLMs, such as selecting the best output using a ranker, which leads to underutilization of token-level probability information. In this paper, we treat the Generation of each token by LLMs as a Classification (GaC) for ensembling. This approach fully exploits the probability information at each generation step and better prevents LLMs from producing early incorrect tokens that lead to snowballing errors. In experiments, we ensemble state-of-the-art LLMs on several benchmarks, including exams, mathematics and reasoning, and observe that our method breaks the existing community performance ceiling. Furthermore, we observed that most of the tokens in the answer are simple and do not affect the correctness of the final answer. Therefore, we also experimented with ensembling only key tokens, and the results showed better performance with lower latency across benchmarks.

De novo molecule generation allows the search for more drug-like hits across a vast chemical space. However, lead optimization is still required, and the process of optimizing molecular structures faces the challenge of balancing structural novelty with pharmacological properties. This study introduces the Deep Genetic Molecular Modification Algorithm (DGMM), which brings structure modification to the level of medicinal chemists. A discrete variational autoencoder (D-VAE) is used in DGMM to encode molecules as quantization code, mol-gene, which incorporates deep learning into genetic algorithms for flexible structural optimization. The mol-gene allows for the discovery of pharmacologically similar but structurally distinct compounds, and reveals the trade-offs of structural optimization in drug discovery. We demonstrate the effectiveness of the DGMM in several applications.

Jersey number recognition (JNR) has always been an important task in sports analytics. Improving recognition accuracy remains an ongoing challenge because images are subject to blurring, occlusion, deformity, and low resolution. Recent research has addressed these problems using number localization and optical character recognition. Some approaches apply player identification schemes to image sequences, ignoring the impact of human body rotation angles on jersey digit identification. Accurately predicting the number of jersey digits by using a multi-task scheme to recognize each individual digit enables more robust results. Based on the above considerations, this paper proposes a multi-task learning method called the angle-digit refine scheme (ADRS), which combines human body orientation angles and digit number clues to recognize athletic jersey numbers. Based on our experimental results, our approach increases inference information, significantly improving prediction accuracy. Compared to state-of-the-art methods, which can only handle a single type of sport, the proposed method produces a more diverse and practical JNR application. The incorporation of diverse types of team sports such as soccer, football, basketball, volleyball, and baseball into our dataset contributes greatly to generalized JNR in sports analytics. Our accuracy achieves 64.07% on Top-1 and 89.97% on Top-2, with corresponding F1 scores of 67.46% and 90.64%, respectively., Comment: 10 pages, 6 figures, 5 tables

Utilizing large language models (LLMs) for transforming natural language questions into SQL queries (text-to-SQL) is a promising yet challenging approach, particularly when applied to real-world databases with complex and extensive schemas. In particular, effectively incorporating data catalogs and database values for SQL generation remains an obstacle, leading to suboptimal solutions. We address this problem by proposing a new pipeline that effectively retrieves relevant data and context, selects an efficient schema, and synthesizes correct and efficient SQL queries. To increase retrieval precision, our pipeline introduces a hierarchical retrieval method leveraging model-generated keywords, locality-sensitive hashing indexing, and vector databases. Additionally, we have developed an adaptive schema pruning technique that adjusts based on the complexity of the problem and the model's context size. Our approach generalizes to both frontier proprietary models like GPT-4 and open-source models such as Llama-3-70B. Through a series of ablation studies, we demonstrate the effectiveness of each component of our pipeline and its impact on the end-to-end performance. Our method achieves new state-of-the-art performance on the cross-domain challenging BIRD dataset.

We explore the influence of radio-mode feedback on the properties of the cool circumgalactic medium (CGM). To this end, we assemble a statistical sample of approximately 30,000 radio galaxies with background quasars by combining optical spectroscopic measurements of luminous red galaxies (LRGs) and quasars from the year 1 dataset of Dark Energy Spectroscopic Instrument (DESI) and radio sources from the LOw-Frequency ARray Two-metre Sky Survey (LoTSS) DR2 catalog and the Very Large Array Sky Survey (VLASS) quick look catalog. Galaxies with similar optical properties but with no radio counterparts in LoTSS and VLASS are selected as the control group. We measure the cool CGM properties of radio galaxies and their control samples traced by MgII absorption lines, including covering fraction, rest equivalent width, and gas kinematics. Our results show no significant difference in the properties of gas around radio galaxies and their control sample, indicating that the operating radio-mode feedback of massive galaxies does not produce detectable effects on the properties of the cool CGM. Finally, we show that the CGM of radio galaxies contain a non-negligible amount of cool gas with approximately 10^10 solar masses. This abundance can place a stringent constraint on the radio-mode feedback models., Comment: 20 pages, 12 figures

The idea of using deep-learning-based molecular generation to accelerate discovery of drug candidates has attracted extraordinary attention, and many deep generative models have been developed for automated drug design, termed molecular generation. In general, molecular generation encompasses two main strategies: de novo design, which generates novel molecular structures from scratch, and lead optimization, which refines existing molecules into drug candidates. Among them, lead optimization plays an important role in real-world drug design. For example, it can enable the development of me-better drugs that are chemically distinct yet more effective than the original drugs. It can also facilitate fragment-based drug design, transforming virtual-screened small ligands with low affinity into first-in-class medicines. Despite its importance, automated lead optimization remains underexplored compared to the well-established de novo generative models, due to its reliance on complex biological and chemical knowledge. To bridge this gap, we conduct a systematic review of traditional computational methods for lead optimization, organizing these strategies into four principal sub-tasks with defined inputs and outputs. This review delves into the basic concepts, goals, conventional CADD techniques, and recent advancements in AIDD. Additionally, we introduce a unified perspective based on constrained subgraph generation to harmonize the methodologies of de novo design and lead optimization. Through this lens, de novo design can incorporate strategies from lead optimization to address the challenge of generating hard-to-synthesize molecules; inversely, lead optimization can benefit from the innovations in de novo design by approaching it as a task of generating molecules conditioned on certain substructures.

In a recent work [Ann. Inst. H. Poincar\'e C Anal. Non Lin\'eaire 2024], Gastel and Neff introduced an interesting system from a geometrically nonlinear flat cosserat micropolar model and established interior regularity in the critical dimension. Motived by this work, in this article, we establish both interior regularity and sharp $L^p$ regularity for their system in supercritical dimensions., Comment: 21 pages

Recombinant adeno-associated virus (rAAV) vectors have revolutionized gene therapy, but their broad tropism and suboptimal transduction efficiency limit their clinical applications. To overcome these limitations, researchers have focused on designing and screening capsid libraries to identify improved vectors. However, the large sequence space and limited resources present challenges in identifying viable capsid variants. In this study, we propose an end-to-end diffusion model to generate capsid sequences with enhanced viability. Using publicly available AAV2 data, we generated 38,000 diverse AAV2 viral protein (VP) sequences, and evaluated 8,000 for viral selection. The results attested the superiority of our model compared to traditional methods. Additionally, in the absence of AAV9 capsid data, apart from one wild-type sequence, we used the same model to directly generate a number of viable sequences with up to 9 mutations. we transferred the remaining 30,000 samples to the AAV9 domain. Furthermore, we conducted mutagenesis on AAV9 VP hypervariable regions VI and V, contributing to the continuous improvement of the AAV9 VP sequence. This research represents a significant advancement in the design and functional validation of rAAV vectors, offering innovative solutions to enhance specificity and transduction efficiency in gene therapy applications.

Grain boundaries (GBs) in polycrystalline materials are powerful sinks for irradiation defects. While standard theories assume that the sink efficiency of a grain boundary is defined solely by its character before irradiation, recent evidence conclusively shows that the irradiation sink efficiency is a highly dynamic property controlled by the intrinsic metastability of GBs under far-from-equilibrium irradiation conditions. In this paper, we reveal that the denuded (i.e., defect-free) zone, typically the signature of a strong sink, can collapse as irradiation damage accumulates. We propose a radiation damage evolution model that captures this behavior based on the emergence of a series of irradiation defect-enabled metastable GB microstate changes that dynamically alter the ability of the GB to absorb further damage. We show that these microstate changes control further defect absorption and give rise to the formation of a defect network that manifests itself as a net Nye-tensor signal detectable via lattice curvature experiments.

Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets. These methods, while effective in designing tightly bound ligands, often overlook other essential properties such as synthesizability. The fragment-wise generation paradigm offers a promising solution. However, a common challenge across both atom-wise and fragment-wise methods lies in their limited ability to co-design plausible chemical and geometrical structures, resulting in distorted conformations. In response to this challenge, we introduce the Deep Geometry Handling protocol, a more abstract design that extends the design focus beyond the model architecture. Through a comprehensive review of existing geometry-related models and their protocols, we propose a novel hybrid strategy, culminating in the development of FragGen - a geometry-reliable, fragment-wise molecular generation method. FragGen marks a significant leap forward in the quality of generated geometry and the synthesis accessibility of molecules. The efficacy of FragGen is further validated by its successful application in designing type II kinase inhibitors at the nanomolar level.

Deep learning (DL) models encompass millions or even billions of parameters and learn complex patterns from big data. However, not all data are initially stored in a suitable formation to effectively train a DL model, e.g., gas chromatography-mass spectrometry (GC-MS) spectra and DNA sequence. These datasets commonly contain many zero values, and the sparse data formation causes difficulties in optimizing DL models. A DL module called the basis-projected layer (BPL) was proposed to mitigate the issue by transforming the sparse data into a dense representation. The transformed data is expected to facilitate the gradient calculation and finetuned process in a DL training process. The dataset, example of a sparse dataset, contained 362 specialty coffee odorant spectra detected from GC-MS. The BPL layer was placed at the beginning of the DL model. The tunable parameters in the layer were learnable projected axes that were the bases of a new representation space. The layer rotated these bases when its parameters were updated. When the number of the bases was the same as the original dimension, the increasing percentage of the F1 scores was 8.56%. Furthermore, when the number was set as 768 (the original dimension was 490), the increasing percentage of the F1 score was 11.49%. The layer not only maintained the model performance and even constructed a better representation space in analyzing sparse datasets., Comment: 5 pages, 2 figures, 2 tables, conference

We propose the class of galled tree-child networks which is obtained as intersection of the classes of galled networks and tree-child networks. For the latter two classes, (asymptotic) counting results and stochastic results have been proved with very different methods. We show that a counting result for the class of galled tree-child networks follows with similar tools as used for galled networks, however, the result has a similar pattern as the one for tree-child networks. In addition, we also consider the (suitably scaled) numbers of reticulation nodes of random galled tree-child networks and show that they are asymptotically normal distributed. This is in contrast to the limit laws of the corresponding quantities for galled networks and tree-child networks which have been both shown to be discrete., Comment: Submitted to AofA2024

Two-dimensional hybrid organic-inorganic perovskites (HOIPs) have emerged as promising materials for light-emitting diode applications. In this study, by using time-of-flight neutron spectroscopy we identified and quantitatively separated the lattice vibrational and molecular rotational dynamics of two perovskites, butylammonium lead iodide $(\text{BA})_{2}\text{PbI}_{4}$ and phenethyl-ammonium lead iodide $\text{(PEA)}_{2}\text{PbI}_{4}$. By examining the corresponding temperature dependence, we found that the lattice vibrations, as evidenced by neutron spectra, are consistent with the lattice dynamics obtained from Raman scattering. We revealed that the rotational dynamics of organic molecules in these materials tend to suppress their photoluminescence quantum yield while the vibrational dynamics did not show predominant correlations with their optoelectronic properties. This study proposes that the rotational motions of the polarized molecules could significantly interrupt the exciton binding energy potential, cause the exciton dissociations, enhance the non-radiative recombination rates, and hence reduce the photoluminescence yield. These findings provide a deeper understanding of the fundamental interactions in 2D HOIPs and may guide the design of more efficient light-emitting materials for advanced technological applications.

The design of novel protein sequences with targeted functionalities underpins a central theme in protein engineering, impacting diverse fields such as drug discovery and enzymatic engineering. However, navigating this vast combinatorial search space remains a severe challenge due to time and financial constraints. This scenario is rapidly evolving as the transformative advancements in AI, particularly in the realm of generative models and optimization algorithms, have been propelling the protein design field towards an unprecedented revolution. In this survey, we systematically review recent advances in generative AI for controllable protein sequence design. To set the stage, we first outline the foundational tasks in protein sequence design in terms of the constraints involved and present key generative models and optimization algorithms. We then offer in-depth reviews of each design task and discuss the pertinent applications. Finally, we identify the unresolved challenges and highlight research opportunities that merit deeper exploration., Comment: 9 pages

Variational quantum algorithms (VQAs), as one of the most promising routes in the noisy intermediate-scale quantum (NISQ) era, offer various potential applications while also confront severe challenges due to near-term quantum hardware restrictions. In this work, we propose a framework to enhance the expressiveness of variational quantum ansatz by incorporating variational post-selection techniques. These techniques apply variational modules and neural network post-processing on ancilla qubits, which are compatible with the current generation of quantum devices. Equipped with variational post-selection, we demonstrate that the accuracy of the variational ground state and thermal state preparation for both quantum spin and molecule systems is substantially improved. Notably, in the case of estimating the local properties of a thermalized quantum system, we present a scalable approach that outperforms previous methods through the combination of neural post-selection and a new optimization objective., Comment: 6 pages, 8 figures + supplemental materials

With the improvements in generative models, the issues of producing hallucinations in various domains (e.g., law, writing) have been brought to people's attention due to concerns about misinformation. In this paper, we focus on neural fake news, which refers to content generated by neural networks aiming to mimic the style of real news to deceive people. To prevent harmful disinformation spreading fallaciously from malicious social media (e.g., content farms), we propose a novel verification framework, Style-News, using publisher metadata to imply a publisher's template with the corresponding text types, political stance, and credibility. Based on threat modeling aspects, a style-aware neural news generator is introduced as an adversary for generating news content conditioning for a specific publisher, and style and source discriminators are trained to defend against this attack by identifying which publisher the style corresponds with, and discriminating whether the source of the given news is human-written or machine-generated. To evaluate the quality of the generated content, we integrate various dimensional metrics (language fluency, content preservation, and style adherence) and demonstrate that Style-News significantly outperforms the previous approaches by a margin of 0.35 for fluency, 15.24 for content, and 0.38 for style at most. Moreover, our discriminative model outperforms state-of-the-art baselines in terms of publisher prediction (up to 4.64%) and neural fake news detection (+6.94% $\sim$ 31.72%)., Comment: EACL 2024 Main Track

Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio, video), the inherent heterogeneity between these modalities and the dynamic cross-modal interactions influenced by an individual's unique behavioral patterns make the task of emotion recognition very challenging. This difficulty is compounded in group settings, where the emotion and its temporal evolution are not only influenced by the individual but also by external contexts like audience reaction and context of the ongoing conversation. To meet this challenge, we propose a Multimodal Attention Network that captures cross-modal interactions at various levels of spatial abstraction by jointly learning its interactive bunch of mode-specific Peripheral and Central networks. The proposed MAN injects cross-modal attention via its Peripheral key-value pairs within each layer of a mode-specific Central query network. The resulting cross-attended mode-specific descriptors are then combined using an Adaptive Fusion technique that enables the model to integrate the discriminative and complementary mode-specific data patterns within an instance-specific multimodal descriptor. Given a dialogue represented by a sequence of utterances, the proposed AMuSE model condenses both spatial and temporal features into two dense descriptors: speaker-level and utterance-level. This helps not only in delivering better classification performance (3-5% improvement in Weighted-F1 and 5-7% improvement in Accuracy) in large-scale public datasets but also helps the users in understanding the reasoning behind each emotion prediction made by the model via its Multimodal Explainability Visualization module.

This little note is devoted to refining the almost optimal regularity results of Breiner and Lamm \cite{Breiner-Lamm-2015} on minimizing and stationary biharmonic maps via the powerful quantitative stratification method introduced by Cheeger and Naber \cite{Cheeger-Naber-2013} and further developed by Naber and Valtorta \cite{Naber-V-2017,Naber-V-2018} for harmonic maps. In particular, we obtain an optimal regularity results for minimizing biharmonic maps.

We give exact and asymptotic counting results for the number of galled networks and reticulation-visible networks with few reticulation vertices. Our results are obtained with the component graph method, which was introduced by L. Zhang and his coauthors, and generating function techniques. For galled networks, we in addition use analytic combinatorics. Moreover, in an appendix, we consider maximally reticulated reticulation-visible networks and derive their number, too., Comment: Revised version; accepted for publication in Bull. Math. Biol

Multi-agent systems often require agents to collaborate with or compete against other agents with diverse goals, behaviors, or strategies. Agent modeling is essential when designing adaptive policies for intelligent machine agents in multiagent systems, as this is the means by which the ego agent understands other agents' behavior and extracts their meaningful policy representations. These representations can be used to enhance the ego agent's adaptive policy which is trained by reinforcement learning. However, existing agent modeling approaches typically assume the availability of local observations from other agents (modeled agents) during training or a long observation trajectory for policy adaption. To remove these constrictive assumptions and improve agent modeling performance, we devised a Contrastive Learning-based Agent Modeling (CLAM) method that relies only on the local observations from the ego agent during training and execution. With these observations, CLAM is capable of generating consistent high-quality policy representations in real-time right from the beginning of each episode. We evaluated the efficacy of our approach in both cooperative and competitive multi-agent environments. Our experiments demonstrate that our approach achieves state-of-the-art on both cooperative and competitive tasks, highlighting the potential of contrastive learning-based agent modeling for enhancing reinforcement learning., Comment: 8 pages, 6 figures