In this work, we investigate the challenging problem of on-demand federated learning (FL) over heterogeneous edge devices with diverse resource constraints. We propose a cost-adjustable FL framework, named AnycostFL, that enables diverse edge devices to efficiently perform local updates under a wide range of efficiency constraints. To this end, we design the model shrinking to support local model training with elastic computation cost, and the gradient compression to allow parameter transmission with dynamic communication overhead. An enhanced parameter aggregation is conducted in an element-wise manner to improve the model performance. Focusing on AnycostFL, we further propose an optimization design to minimize the global training loss with personalized latency and energy constraints. By revealing the theoretical insights of the convergence analysis, personalized training strategies are deduced for different devices to match their locally available resources. Experiment results indicate that, when compared to the state-of-the-art efficient FL algorithms, our learning framework can reduce up to 1.9 times of the training latency and energy consumption for realizing a reasonable global testing accuracy. Moreover, the results also demonstrate that, our approach significantly improves the converged global accuracy.

Atmospheric mass-loss is known to play a leading role in sculpting the demographics of small, close-in exoplanets. Knowledge of how such planets evolve allows one to ``rewind the clock'' to infer the conditions in which they formed. Here, we explore the relationship between a planet's core mass and their atmospheric mass after protoplanetary disc dispersal by exploiting XUV photoevaporation as an evolutionary process. Historically, this style of inference problem would be computationally infeasible due to the large number of planet models required; however, we make use of a novel atmospheric evolution emulator which utilises neural networks to provide three orders of magnitude in speedup. First, we provide proof-of-concept for this emulator on a real problem, by inferring the initial atmospheric conditions to the TOI-270 multi-planet system. Using the emulator we find near-indistinguishable results when compared to original model. We then apply the emulator to the more complex inference problem, which aims to find the initial conditions for a sample of \textit{Kepler}, \textit{K2} and \textit{TESS} planets with well-constrained masses and radii. We demonstrate there is a relationship between core masses and the atmospheric mass that they retain after disc dispersal, and this trend is consistent with the `boil-off' scenario, in which close-in planets undergo dramatic atmospheric escape during disc dispersal. Thus, it appears the exoplanet population is consistent with the idea that close-in exoplanets initially acquired large massive atmospheres, the majority of which is lost during disc dispersal; before the final population is sculpted by atmospheric loss over 100~Myr to Gyr timescales.

The current research work is being developed as a training and evaluation object. the performance of a predictive model to apply it to the imports of vegetable products into Peru using artificial intelligence algorithms, specifying for this study the Machine Learning models: LSTM and PROPHET. The forecast is made with data from the monthly record of imports of vegetable products(in kilograms) from Peru, collected from the years 2021 to 2022. As part of applying the training methodology for automatic learning algorithms, the exploration and construction of an appropriate dataset according to the parameters of a Time Series. Subsequently, the model with better performance will be selected, evaluating the precision of the predicted values so that they account for sufficient reliability to consider it a useful resource in the forecast of imports in Peru.

Deep learning (DL) relies heavily on data, and the quality of data influences its performance significantly. However, obtaining high-quality, well-annotated datasets can be challenging or even impossible in many real-world applications, such as structural risk estimation and medical diagnosis. This presents a significant barrier to the practical implementation of DL in these fields. Physics-guided deep learning (PGDL) is a novel type of DL that can integrate physics laws to train neural networks. This can be applied to any systems that are controlled or governed by physics laws, such as mechanics, finance and medical applications. It has been demonstrated that, with the additional information provided by physics laws, PGDL achieves great accuracy and generalisation in the presence of data scarcity. This review provides a detailed examination of PGDL and offers a structured overview of its use in addressing data scarcity across various fields, including physics, engineering and medical applications. Moreover, the review identifies the current limitations and opportunities for PGDL in relation to data scarcity and offers a thorough discussion on the future prospects of PGDL.

Nature provides several examples of organisms that utilize shape change as a means of operating in challenging, dynamic environments. For example, the spider Araneus Rechenbergi [1, 2] and the caterpillar of the Mother-of-Pearl Moth (Pleurotya ruralis) [3] transition from walking gaits to rolling in an attempt to escape predation. Across larger time scales, caterpillar-tobutterfly metamorphosis enables land to air transitions, while mobile to sessile metamorphosis, as observed in sea squirts, is accompanied by radical morphological change. Inspired by such change, engineers have created caterpillar-like rolling [4], modular [5, 6, 7], tensegrity [8, 9], plant-like growing [10], and origami [11, 12] robots that are capable of some degree of shape change. However, progress toward robots which dynamically adapt their resting shape to attain different modes of locomotion is still limited. Further, design of such robots and their controllers is still a manually intensive process. Despite the growing recognition of the importance of morphology and embodiment on enabling intelligent behavior in robots [13], most previous studies have approached the challenge of operating in multiple environments primarily through the design of appropriate control strategies.

Non-intrusive load monitoring (NILM) or energy disaggregation is an inverse problem whereby the goal is to extract the load profiles of individual appliances, given an aggregate load profile of the mains of a home. NILM could help identify the power usage patterns of individual appliances in a home, and thus, could help realize novel energy conservation schemes for smart homes. In this backdrop, this work proposes a novel deep-learning approach to solve the NILM problem and a few related problems as follows. 1) We build upon the reputed seq2-point convolutional neural network (CNN) model to come up with the proposed seq2-[3]-point CNN model to solve the (home) NILM problem and site-NILM problem (basically, NILM at a smaller scale). 2) We solve the related problem of appliance identification by building upon the state-of-the-art (pre-trained) 2D-CNN models, i.e., AlexNet, ResNet-18, and DenseNet-121, which are trained upon two custom datasets that consist of Wavelets and short-time Fourier transform (STFT)-based 2D electrical signatures of the appliances. 3) Finally, we do some basic qualitative inference about an individual appliance's health by comparing the power consumption of the same appliance across multiple homes. Low-frequency REDD dataset is used to train and test the proposed deep learning models for all problems, except site-NILM where REFIT dataset has been used. As for the results, we achieve a maximum accuracy of 94.6\% for home-NILM, 81\% for site-NILM, and 88.9\% for appliance identification (with Resnet-based model).

Artificial Intelligence (AI) is at a crucial point in its development: stable enough to be used in production systems, and increasingly pervasive in our lives. What does that mean for its safety? In his book Normal Accidents, the sociologist Charles Perrow proposed a framework to analyze new technologies and the risks they entail. He showed that major accidents are nearly unavoidable in complex systems with tightly coupled components if they are run long enough. In this essay, we apply and extend Perrow’s framework to AI to assess its potential risks. Today’s AI systems are already highly complex, and their complexity is steadily increasing. As they become more ubiquitous, different algorithms will interact directly, leading to tightly coupled systems whose capacity to cause harm we will be unable to predict. We argue that under the current paradigm, Perrow’s normal accidents apply to AI systems and it is only a matter of time before one occurs. This article appears in the AI & Society track.

Samsung Electronics has added to its SmartThings features, introducing the SmartThings station, which gives users a wider room to remotely control home-use Samsung appliances, placing homeowners as the operators over home-based devices from any distance. The company has announced its new partnership and vision to reduce carbon emissions for home-use appliances by 2050. Samsung is also part of the founders of the Home Connectivity Alliance (HCA). HCA is a fifteen-membership organization dedicated to promoting the safe and secure use of appliances through interoperability and proper energy consumption. SmartThings station is a centralized and integrated control device that supports multiple device connections concurrently; the device is designed with up to 15W wireless charging capacity for compatible devices.

Answer selection (AS) is a critical subtask of the open-domain question answering (QA) problem. The present paper proposes a method called RLAS-BIABC for AS, which is established on attention mechanism-based long short-term memory (LSTM) and the bidirectional encoder representations from transformers (BERT) word embedding, enriched by an improved artificial bee colony (ABC) algorithm for pretraining and a reinforcement learning-based algorithm for training backpropagation (BP) algorithm. BERT can be comprised in downstream work and fine-tuned as a united task-specific architecture, and the pretrained BERT model can grab different linguistic effects. Existing algorithms typically train the AS model with positive-negative pairs for a two-class classifier. A positive pair contains a question and a genuine answer, while a negative one includes a question and a fake answer. The output should be one for positive and zero for negative pairs. Typically, negative pairs are more than positive, leading to an imbalanced classification that drastically reduces system performance. To deal with it, we define classification as a sequential decision-making process in which the agent takes a sample at each step and classifies it. For each classification operation, the agent receives a reward, in which the prize of the majority class is less than the reward of the minority class. Ultimately, the agent finds the optimal value for the policy weights. We initialize the policy weights with the improved ABC algorithm. The initial value technique can prevent problems such as getting stuck in the local optimum. Although ABC serves well in most tasks, there is still a weakness in the ABC algorithm that disregards the fitness of related pairs of individuals in discovering a neighboring food source position.

Project Canary is a SaaS-based data analytics company focused on environmental performance or the E in ESG for energy and additional business sectors. We are the leaders in assessing and scoring responsible operations and provide independent, measured emission profiles, including methane, via high fidelity continuous monitoring technology that helps companies take ESG action. Formed as a Public Benefit Corporation (B-Corp rating score 107), Project Canary's Denver-based team of technologists, engineers, and seasoned industry operators have earned recognition for their uncompromising standards and high-fidelity data. Project Canary's mission is to fight climate change and put actionable insights starting with the energy sector. We ingest data from various sources, including our own proprietary environmental sensors/hardware, to calculate carbon emissions from different facilities in real-time via SaaS.