PON systems are primarily deployed in fiber-to-thehome (FTTH) networks to deliver a wide range of communication and multimedia services [1]. Due to the omission of active electronic components, OPEX is reduced, and this also makes them less failure-prone in the outside plant. Implementing and deploying effective monitoring schemes in these systems can result in significant additional OPEX savings. Optical time domain reflectometry (OTDR), a technique based on Rayleigh backscattering, has primarily been used to monitor individual optical fiber spans. However, applying OTDR to monitor PON systems can be challenging because the backscattered signals from each branch are added together, making it difficult to distinguish between the backward signals of the individual branches [2]. In the case of (almost) equidistant branch terminations, event analysis becomes most difficult as the reflected signals from the branches with the same length overlap and add up.

Current trends in networking propose the use of Machine Learning (ML) for a wide variety of network optimization tasks. As such, many efforts have been made to produce ML-based solutions for Traffic Engineering (TE), which is a fundamental problem in ISP networks. Nowadays, state-of-the-art TE optimizers rely on traditional optimization techniques, such as Local search, Constraint Programming, or Linear programming. In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization. MAGNNETO deploys a set of agents across the network that learn and communicate in a distributed fashion via message exchanges between neighboring agents. Particularly, we apply this framework to optimize link weights in OSPF, with the goal of minimizing network congestion. In our evaluation, we compare MAGNNETO against several state-of-the-art TE optimizers in more than 75 topologies (up to 153 nodes and 354 links), including realistic traffic loads. Our experimental results show that, thanks to its distributed nature, MAGNNETO achieves comparable performance to state-of-the-art TE optimizers with significantly lower execution times. Moreover, our ML-based solution demonstrates a strong generalization capability to successfully operate in new networks unseen during training.

In recent years, the use of WiFi fingerprints for indoor positioning has grown in popularity, largely due to the widespread availability of WiFi and the proliferation of mobile communication devices. However, many existing methods for constructing fingerprint datasets rely on labor-intensive and time-consuming processes of collecting large amounts of data. Additionally, these methods often focus on ideal laboratory environments, rather than considering the practical challenges of large multi-floor buildings. To address these issues, we present a novel WiDAGCN model that can be trained using a small number of labeled site survey data and large amounts of unlabeled crowdsensed WiFi fingerprints. By constructing heterogeneous graphs based on received signal strength indicators (RSSIs) between waypoints and WiFi access points (APs), our model is able to effectively capture the topological structure of the data. We also incorporate graph convolutional networks (GCNs) to extract graph-level embeddings, a feature that has been largely overlooked in previous WiFi indoor localization studies. To deal with the challenges of large amounts of unlabeled data and multiple data domains, we employ a semi-supervised domain adversarial training scheme to effectively utilize unlabeled data and align the data distributions across domains. Our system is evaluated using a public indoor localization dataset that includes multiple buildings, and the results show that it performs competitively in terms of localization accuracy in large buildings.

Stop me if you've heard this one before: ChatGPT is huge right now. After exploding in popularity in late 2022, the AI chatbot has been on an enormous rise, with no sign of slowing down. One of the ways we've seen ChatGPT expand is its continued integration into smartphone apps. Whether it's Bing Chat coming to mobile or a ChatGPT iPhone keyboard, it's all been fascinating to watch unfold. One of the latest ChatGPT mobile apps to hit the scene is one called "Perplexity AI," which is an iPhone app that brings ChatGPT directly to your smartphone.

TileDB, the database for any complex data and compute, announced the launch of TileDB-SOMA, the first collection of software libraries that implement the open-source SOMA API specification. SOMA and TileDB-SOMA are the result of a collaboration between the Chan Zuckerberg Initiative and TileDB to accelerate single-cell research by eliminating data silos and enable large-scale computations that are otherwise too challenging to execute on commodity hardware. "By streamlining access to enormous datasets, powerful new tools like TileDB-SOMA will accelerate the research efforts of single-cell biologists" New technologies and analysis tools have led to the exponential growth of single-cell RNA sequencing (scRNA-seq) data, requiring new solutions that can accommodate datasets at scale. Advancements in genomics technologies have also enabled researchers to combine multiple modalities of data collected from the same cell samples, increasing the complexity and impact of single-cell analysis. "The unsaid assumption in single-cell research is that dataset size is bound by RAM, but instead of asking researchers to change their computational tools, we're rethinking how the data model itself could do more heavy lifting for scientists," said Stavros Papadopoulos, Founder & CEO, TileDB, Inc. "With TileDB-SOMA for R and Python, computational biologists can work across programming languages and combine data that was previously formatted specifically for Seurat, Anndata/Scanpy or Bioconductor. This breaks down data silos, and allows scientists to collaborate without the hassle of converting or duplicating data. Everyone can access the dataset, stored locally or in the cloud, at any scale."

Telecommunication companies are generating billions of dollars in revenue annually by leveraging the power of Artificial Intelligence, Data Science, and IoT integrations. In 2020, a potential American telecom company/operator, AT&T, generated €161.5 billion in revenue, but there is a decline in annual revenues compared to 2021 and 2022. The reason behind the revenue decline can be the abandonment of Artificial intelligence technologies. So, what should these companies have to do? To achieve success over the competitors and increase revenue streams in 2023.

Relational events are a type of social interactions, that sometimes are referred to as dynamic networks. Its dynamics typically depends on emerging patterns, so-called endogenous variables, or external forces, referred to as exogenous variables. Comprehensive information on the actors in the network, especially for huge networks, is rare, however. A latent space approach in network analysis has been a popular way to account for unmeasured covariates that are driving network configurations. Bayesian and EM-type algorithms have been proposed for inferring the latent space, but both the sheer size many social network applications as well as the dynamic nature of the process, and therefore the latent space, make computations prohibitively expensive. In this work we propose a likelihood-based algorithm that can deal with huge relational event networks. We propose a hierarchical strategy for inferring network community dynamics embedded into an interpretable latent space. Node dynamics are described by smooth spline processes. To make the framework feasible for large networks we borrow from machine learning optimization methodology. Model-based clustering is carried out via a convex clustering penalization, encouraging shared trajectories for ease of interpretation. We propose a model-based approach for separating macro-microstructures and perform a hierarchical analysis within successive hierarchies. The method can fit millions of nodes on a public Colab GPU in a few minutes. The code and a tutorial are available in a Github repository.

Along with the rapid evolution of mobile communication technologies, such as 5G, there has been a drastically increase in telecom fraud, which significantly dissipates individual fortune and social wealth. In recent years, graph mining techniques are gradually becoming a mainstream solution for detecting telecom fraud. However, the graph imbalance problem, caused by the Pareto principle, brings severe challenges to graph data mining. This is a new and challenging problem, but little previous work has been noticed. In this paper, we propose a Graph ATtention network with COst-sensitive BOosting (GAT-COBO) for the graph imbalance problem. First, we design a GAT-based base classifier to learn the embeddings of all nodes in the graph. Then, we feed the embeddings into a well-designed cost-sensitive learner for imbalanced learning. Next, we update the weights according to the misclassification cost to make the model focus more on the minority class. Finally, we sum the node embeddings obtained by multiple cost-sensitive learners to obtain a comprehensive node representation, which is used for the downstream anomaly detection task. Extensive experiments on two real-world telecom fraud detection datasets demonstrate that our proposed method is effective for the graph imbalance problem, outperforming the state-of-the-art GNNs and GNN-based fraud detectors. In addition, our model is also helpful for solving the widespread over-smoothing problem in GNNs. The GAT-COBO code and datasets are available at https://github.com/xxhu94/GAT-COBO.

San Diego, California, March 28, 2023 (GLOBE NEWSWIRE) -- HUMBL, Inc. (OTCQB: HMBL) HUMBL announced today the launch of its Artificial Intelligence (AI) and Automated Machine Learning initiatives across its consumer, commercial and Latin America business units. On the commercial side, HUMBL kicked off its AI / Automated Machine Learning initiatives with the announcement of its first commercial sales contract in its HUMBL Latin America subsidiary, with the sale of AI / Automated Machine Learning services for a leading IT / Telecommunications provider in the Latin America region in the form of a $60,000 (USD) contract for initial deliverables and a total contract value of $195,000 (USD) over three years, pending the achievement of milestones by HUMBL Latin America. "Artificial Intelligence is an accelerant to the principles of web3," said Brian Foote, CEO of HUMBL. "The use of public data sets to create more autonomous, intelligent outcomes for consumers, as well as the corporations and governments that serve them, is an excellent use of automated machine learning technologies," continued Foote. "The use of AI can help our clients model for more predictive outcomes around things like credit scoring, default rates, churn rates, healthcare patterns and more; driving more tailored experiences for consumers, while driving revenues and improved efficiencies for corporations and governments."

Detecting malicious activity within an enterprise computer network can be framed as a temporal link prediction task: given a sequence of graphs representing communications between hosts over time, the goal is to predict which edges should--or should not--occur in the future. However, standard temporal link prediction algorithms are ill-suited for computer network monitoring as they do not take account of the peculiar short-term dynamics of computer network activity, which exhibits sharp seasonal variations. In order to build a better model, we propose a source separation-inspired description of computer network activity: at each time step, the observed graph is a mixture of subgraphs representing various sources of activity, and short-term dynamics result from changes in the mixing coefficients. Both qualitative and quantitative experiments demonstrate the validity of our approach.