Search

Spatially constrained clustering is an important field of research, particularly when it involves changes over time. Partitioning a map is not simple since there is a vast number of possible partitions within the search space. In spatio-temporal clustering, this task becomes even more difficult, as we must consider sequences of partitions. Motivated by these challenges, we introduce a Bayesian model for time-dependent sequences of spatial random partitions by proposing a prior distribution based on product partition models that correlates partitions. Additionally, we employ random spanning trees to facilitate the exploration of the partition search space and to guarantee spatially constrained clustering. This work is motivated by a relevant applied problem: identifying spatial and temporal patterns of mosquito-borne diseases. Given the overdispersion present in this type of data, we introduce a spatio-temporal Poisson mixture model in which mean and dispersion parameters vary according to spatio-temporal covariates. The proposed model is applied to analyze the number of dengue cases reported weekly from 2018 to 2023 in the Southeast region of Brazil. We also evaluate model performance using simulated data. Overall, the proposed model has proven to be a competitive approach for analyzing the temporal evolution of spatial clustering.

Music source separation (MSS) is a task that involves isolating individual sound sources, or stems, from mixed audio signals. This paper presents an ensemble approach to MSS, combining several state-of-the-art architectures to achieve superior separation performance across traditional Vocal, Drum, and Bass (VDB) stems, as well as expanding into second-level hierarchical separation for sub-stems like kick, snare, lead vocals, and background vocals. Our method addresses the limitations of relying on a single model by utilising the complementary strengths of various models, leading to more balanced results across stems. For stem selection, we used the harmonic mean of Signal-to-Noise Ratio (SNR) and Signal-to-Distortion Ratio (SDR), ensuring that extreme values do not skew the results and that both metrics are weighted effectively. In addition to consistently high performance across the VDB stems, we also explored second-level hierarchical separation, revealing important insights into the complexities of MSS and how factors like genre and instrumentation can influence model performance. While the second-level separation results show room for improvement, the ability to isolate sub-stems marks a significant advancement. Our findings pave the way for further research in MSS, particularly in expanding model capabilities beyond VDB and improving niche stem separations such as guitar and piano.

We demonstrate mechanical threats classification including jackhammers and excavators, leveraging wavelet transform of MIMO-DFS output data across a 57-km operational network link. Our machine learning framework incorporates transfer learning and shows 93% classification accuracy from field data, with benefits for optical network supervision.

Lyrics play a crucial role in affecting and reinforcing emotional states by providing meaning and emotional connotations that interact with the acoustic properties of the music. Specific lyrical themes and emotions may intensify existing negative states in listeners and may lead to undesirable outcomes, especially in listeners with mood disorders such as depression. Hence, it is important for such individuals to be mindful of their listening strategies. In this study, we examine online music consumption of individuals at risk of depression in light of lyrical themes and emotions. Lyrics obtained from the listening histories of 541 Last.fm users, divided into At-Risk and No-Risk based on their mental well-being scores, were analyzed using natural language processing techniques. Statistical analyses of the results revealed that individuals at risk for depression prefer songs with lyrics associated with low valence and low arousal. Additionally, lyrics associated with themes of denial, self-reference, and ambivalence were preferred. In contrast, themes such as liberation, familiarity, and activity are not as favored. This study opens up the possibility of an approach to assessing depression risk from the digital footprint of individuals and potentially developing personalized recommendation systems., Comment: Accepted at the 25th International Society for Music Information Retrieval Conference (ISMIR) 2024, San Francisco, United States

As more distributed energy resources become part of the demand-side infrastructure, it is important to quantify the energy flexibility they provide on a community scale, particularly to understand the impact of geographic, climatic, and occupant behavioral differences on their effectiveness, as well as identify the best control strategies to accelerate their real-world adoption. CityLearn provides an environment for benchmarking simple and advanced distributed energy resource control algorithms including rule-based, model-predictive, and reinforcement learning control. CityLearn v2 presented here extends CityLearn v1 by providing a simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create virtual grid-interactive communities for resilient, multi-agent distributed energy resources and objective control with dynamic occupant feedback. This work details the v2 environment design and provides application examples that utilize reinforcement learning to manage battery energy storage system charging/discharging cycles, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

We detail several scientific and engineering innovations which enable the controlled spalling of 10 - 50 micron thick films of single crystal 4H silicon carbide (4H-SiC) from bulk substrates. 4H-SiC's properties, including high thermal conductivity and a wide bandgap, make it an ideal candidate for high-temperature, high-voltage power electronic devices. Moreover, 4H-SiC has been shown to be an excellent host of solid-state atomic defect qubits for quantum computing and quantum networking. Because 4H-SiC single crystal substrates are expensive (due to long growth times and limited yield), techniques for removal and transfer of bulk-quality films in the tens-of-microns thickness range are highly desirable to allow for substrate reuse and integration of the separated films. In this work we utilize novel approaches for stressor layer thickness control and spalling crack initiation to demonstrate controlled spalling of 4H-SiC, the highest fracture toughness material spalled to date. Additionally, we demonstrate substrate re-use, bonding of the spalled films to carrier substrates, and explore the spin coherence of the spalled films. In preliminary studies we are able to achieve coherent spin control of neutral divacancy ($VV^{0}$) qubit ensembles and measure a quasi-bulk spin $T_{2}$ of 79.7 $\mu$s in such spalled films., Comment: 16 pages, 6 figures

Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the best performing large language model for the translation task involving LLMs, which is based on LLaMA. Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as CHRF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using 2-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including for languages that are currently underrepresented in LLMs.

Building large AI fleets to support the rapidly growing DL workloads is an active research topic for modern cloud providers. Generating accurate benchmarks plays an essential role in designing the fast-paced software and hardware solutions in this space. Two fundamental challenges to make this scalable are (i) workload representativeness and (ii) the ability to quickly incorporate changes to the fleet into the benchmarks. To overcome these issues, we propose Mystique, an accurate and scalable framework for production AI benchmark generation. It leverages the PyTorch execution trace (ET), a new feature that captures the runtime information of AI models at the granularity of operators, in a graph format, together with their metadata. By sourcing fleet ETs, we can build AI benchmarks that are portable and representative. Mystique is scalable, due to its lightweight data collection, in terms of runtime overhead and instrumentation effort. It is also adaptive because ET composability allows flexible control on benchmark creation. We evaluate our methodology on several production AI models, and show that benchmarks generated with Mystique closely resemble original AI models, both in execution time and system-level metrics. We also showcase the portability of the generated benchmarks across platforms, and demonstrate several use cases enabled by the fine-grained composability of the execution trace., Comment: Accepted to ISCA 2023

The insertion of renewable sources in power systems may cause a decrease in the system's equivalent inertia, which result in the instability of the power system. On the other hand, energy storage systems have proven to be an effective tool to increase the flexibility in the operation of energy systems, which may favor integrating renewable energy sources. In this way, plug-in electric vehicle (PEVs) batteries can be used as storages when such vehicles are parked and connected to the grid. In this work, the contribution of PEVs to primary frequency response is analyzed in systems dominated by renewable sources. A day-ahead scheduling model is developed considering PEVs groups can actively participate in electricity markets, supporting day-ahead reserve capacity and providing primary frequency response. The proposed model is implemented in the distribution system of the Federal University of Amap\'a., Comment: In proceedings of the 11th Bulk Power Systems Dynamics and Control Symposium (IREP 2022), July 25-30, 2022, Banff, Canada

This article presents and describes a 229 bus test system that includes wind, hydro and fossil fuel power plants. It represents the Northeast subsystem of the Brazilian Interconnected Power System (BIPS). The test system supplies a load of 4.17 GW, being 13% powered by wind farms, which is the current wind power penetration level of the BIPS. The data comprehends different load levels based on the typical load behavior and typical capacity factors of wind, hydro and fossil fuel plants, as well as the capacity of transmission and sub-transmission lines, transformers, and the adopted structure for the test system. The data is compiled considering models and operating scenarios of the BIPS, and allow performing studies of static voltage stability, sensitivity of voltage stability margin considering the wind farms, and multi-objective optimization considering market constraints. The results of the simulations with the test system indicate the consistency of their data structure and its applicability to different studies of electric power systems., Comment: In proceedings of the 11th Bulk Power Systems Dynamics and Control Symposium (IREP 2022), July 25-30, 2022, Banff, Canada

The novel coronavirus disease (COVID-19) began in Wuhan, China, in late 2019 and to date has infected over 148M people worldwide, resulting in 3.12M deaths. On March 10, 2020, the World Health Organisation (WHO) declared it as a global pandemic. Many academicians and researchers started to publish papers describing the latest discoveries on covid-19. The large influx of publications made it hard for other researchers to go through a large amount of data and find the appropriate one that helps their research. So, the proposed model attempts to extract relavent titles from the large corpus of research publications which makes the job easy for the researchers. Allen Institute for AI released the CORD-19 dataset, which consists of 2,00,000 journal articles related to coronavirus-related research publications from PubMed's PMC, WHO (World Health Organization), bioRxiv, and medRxiv pre-prints. Along with this document corpus, they have also provided a topics dataset named topics-rnd3 consisting of a list of topics. Each topic has three types of representations like query, question, and narrative. These Datasets are made open for research, and also they released a TREC-COVID competition on Kaggle. Using these topics like queries, our goal is to find out the relevant documents in the CORD-19 dataset. In this research, relevant documents should be recognized for the posed topics in topics-rnd3 data set. The proposed model uses Natural Language Processing(NLP) techniques like Bag-of-Words, Average Word-2-Vec, Average BERT Base model and Tf-Idf weighted Word2Vec model to fabricate vectors for query, question, narrative, and combinations of them. Similarly, fabricate vectors for titles in the CORD-19 dataset. After fabricating vectors, cosine similarity is used for finding similarities between every two vectors. Cosine similarity helps us to find relevant documents for the given topic.

Human Activity Recognition (HAR) describes the machines ability to recognize human actions. Nowadays, most people on earth are health conscious, so people are more interested in tracking their daily activities using Smartphones or Smart Watches, which can help them manage their daily routines in a healthy way. With this objective, Kaggle has conducted a competition to classify 6 different human activities distinctly based on the inertial signals obtained from 30 volunteers smartphones. The main challenge in HAR is to overcome the difficulties of separating human activities based on the given data such that no two activities overlap. In this experimentation, first, Data visualization is done on expert generated features with the help of t distributed Stochastic Neighborhood Embedding followed by applying various Machine Learning techniques like Logistic Regression, Linear SVC, Kernel SVM, Decision trees to better classify the 6 distinct human activities. Moreover, Deep Learning techniques like Long Short-Term Memory (LSTM), Bi-Directional LSTM, Recurrent Neural Network (RNN), and Gated Recurrent Unit (GRU) are trained using raw time series data. Finally, metrics like Accuracy, Confusion matrix, precision and recall are used to evaluate the performance of the Machine Learning and Deep Learning models. Experiment results proved that the Linear Support Vector Classifier in machine learning and Gated Recurrent Unit in Deep Learning provided better accuracy for human activity recognition compared to other classifiers.