With the rapid advancement of Natural Language Processing in recent years, numerous studies have shown that generic summaries generated by Large Language Models (LLMs) can sometimes surpass those annotated by experts, such as journalists, according to human evaluations. However, there is limited research on whether these generic summaries meet the individual needs of ordinary people. The biggest obstacle is the lack of human-annotated datasets from the general public. Existing work on personalized summarization often relies on pseudo datasets created from generic summarization datasets or controllable tasks that focus on specific named entities or other aspects, such as the length and specificity of generated summaries, collected from hypothetical tasks without the annotators' initiative. To bridge this gap, we propose a high-quality, personalized, manually annotated summarization dataset called PersonalSum. This dataset is the first to investigate whether the focus of public readers differs from the generic summaries generated by LLMs. It includes user profiles, personalized summaries accompanied by source sentences from given articles, and machine-generated generic summaries along with their sources. We investigate several personal signals — entities/topics, plot, and structure of articles—that may affect the generation of personalized summaries using LLMs in a few-shot in-context learning scenario. Our preliminary results and analysis indicate that entities/topics are merely one of the key factors that impact the diverse preferences of users, and personalized summarization remains a significant challenge for existing LLMs.

Detecting anomalous events in time series data, ranging from manufacturing processes to health care monitoring, is important. The problem of uncertainty in real-world datasets and its anomalies makes it challenging to validate and compare results between algorithms. With this in mind, we present two benchmark suites to fill gaps in today’s landscape of datasets for anomaly detection in multivariate time series data. Here, one suite focuses only on fully synthetic sequences to provide a playground for testing algorithms with complete knowledge of the sequences. The second suite bridges between fully synthetic and real-world sequences. It provides a few extensive sequences with close-to-reality complexity but synthetic injected anomalies. The paper provides a detailed overview of the suites content and complexities. It further includes a concise overview and showcases the strengths and weaknesses of 34 algorithms in the evaluation. The benchmark suites highlight issues regarding algorithms and metrics and should support new research directions.

Abstract Single-person human pose estimation facilitates markerless movement analysis in sports, as well as in clinical applications. Still, state-of-the-art models for human pose estimation generally do not meet the requirements of real-life applications. The proliferation of deep learning techniques has resulted in the development of many advanced approaches. However, with the progresses in the field, more complex and inefficient models have also been introduced, which have caused tremendous increases in computational demands. To cope with these complexity and inefficiency challenges, we propose a novel convolutional neural network architecture, called EfficientPose, which exploits recently proposed EfficientNets in order to deliver efficient and scalable single-person pose estimation. EfficientPose is a family of models harnessing an effective multi-scale feature extractor and computationally efficient detection blocks using mobile inverted bottleneck convolutions, while at the same time ensuring that the precision of the pose configurations is still improved. Due to its low complexity and efficiency, EfficientPose enables real-world applications on edge devices by limiting the memory footprint and computational cost. The results from our experiments, using the challenging MPII single-person benchmark, show that the proposed EfficientPose models substantially outperform the widely-used OpenPose model both in terms of accuracy and computational efficiency. In particular, our top-performing model achieves state-of-the-art accuracy on single-person MPII, with low-complexity ConvNets.

Dense subregion (subgraph & subtensor) detection is a well-studied area, with a wide range of applications, and numerous efficient approaches and algorithms have been proposed. Approximation approaches are commonly used for detecting dense subregions due to the complexity of the exact methods. Existing algorithms are generally efficient for dense subtensor and subgraph detection, and can perform well in many applications. However, most of the existing works utilize the state-or-the-art greedy 2-approximation algorithm to capably provide solutions with a loose theoretical density guarantee. The main drawback of most of these algorithms is that they can estimate only one subtensor, or subgraph, at a time, with a low guarantee on its density. While some methods can, on the other hand, estimate multiple subtensors, they can give a guarantee on the density with respect to the input tensor for the first estimated subsensor only. We address these drawbacks by providing both theoretical and practical solution for estimating multiple dense subtensors in tensor data and giving a higher lower bound of the density. In particular, we guarantee and prove a higher bound of the lower-bound density of the estimated subgraph and subtensors. We also propose a novel approach to show that there are multiple dense subtensors with a guarantee on its density that is greater than the lower bound used in the state-of-the-art algorithms. We evaluate our approach with extensive experiments on several real-world datasets, which demonstrates its efficiency and feasibility.

Dense subtensor detection is a well-studied area, with a wide range of applications, and numerous efficient approaches and algorithms have been proposed. Existing algorithms are generally efficient for dense subtensor detection and could perform well in many applications. However, the main drawback of most of these algorithms is that they can estimate only one subtensor at a time, with a low guarantee on the subtensor's density. While some methods can, on the other hand, estimate multiple subtensors, they can give a guarantee on the density with respect to the input tensor for the first estimated subsensor only. We address these drawbacks by providing both theoretical and practical solution for estimating multiple dense subtensors in tensor data. In particular, we guarantee and prove a higher bound of the lower-bound density of the estimated subtensors. We also propose a novel approach to show that there are multiple dense subtensors with a guarantee on its density that is greater than the lower bound used in the state-of-the-art algorithms. We evaluate our approach with extensive experiments on several real- world datasets, which demonstrates its efficiency and feasibility.

Prediction intervals are a machine- and human-interpretable way to represent predictive uncertainty in a regression analysis. In this paper, we present a method for generating prediction intervals along with point estimates from an ensemble of neural networks. We propose a multi-objective loss function fusing quality measures related to prediction intervals and point estimates, and a penalty function, which enforces semantic integrity of the results and stabilizes the training process of the neural networks. The ensembled prediction intervals are aggregated as a split normal mixture accounting for possible multimodality and asymmetricity of the posterior predictive distribution, and resulting in prediction intervals that capture aleatoric and epistemic uncertainty. Our results show that both our quality-driven loss function and our aggregation method contribute to well-calibrated prediction intervals and point estimates.

This paper provides a short overview of space–time series clustering, which can be generally grouped into three main categories such as: hierarchical, partitioning-based, and overlapping clustering. The first hierarchical category is to identify hierarchies in space–time series data. The second partitioning-based category focuses on determining disjoint partitions among the space–time series data, whereas the third overlapping category explores fuzzy logic to determine the different correlations between the space–time series clusters. We also further describe solutions for each category in this paper. Furthermore, we show the applications of these solutions in an urban traffic data captured on two urban smart cities (e.g., Odense in Denmark and Beijing in China). The perspectives on open questions and research challenges are also mentioned and discussed that allow to obtain a better understanding of the intuition, limitations, and benefits for the various space–time series clustering methods. This work can thus provide the guidances to practitioners for selecting the most suitable methods for their used cases, domains, and applications.

Keeping the electricity production in balance with the actual demand is becoming a difficult and expensive task in spite of an involvement of experienced human operators. This is due to the increasing complexity of the electric power grid system with the intermittent renewable production as one of the contributors. A beforehand information about an occurring imbalance can help the transmission system operator to adjust the production plans, and thus ensure a high security of supply by reducing the use of costly balancing reserves, and consequently reduce undesirable fluctuations of the 50 Hz power system frequency. In this paper, we introduce the relatively new problem of an intra-hour imbalance forecasting for the transmission system operator (TSO). We focus on the use case of the Norwegian TSO, Statnett. We present a complementary imbalance forecasting tool that is able to support the TSO in determining the trend of future imbalances, and show the potential to proactively alleviate imbalances with a higher accuracy compared to the contemporary solution.

We propose a novel sketching approach for streaming data that, even with limited computing resources, enables processing high volume and high velocity data efficiently. Our approach accounts for the fact that a stream of data is generally dynamic, with the underlying distribution possibly changing all the time. Specifically, we propose a hashing (sketching) technique that is able to automatically estimate a histogram from a stream of data by using a model with adaptive coefficients. Such a model is necessary to enable the preservation of histogram similarities, following the varying weight/importance of the generated histograms. To address the dynamic properties of data streams, we develop a novel algorithm that can sketch the histograms from a data stream using multiple weighted factors. The results from our extensive experiments on both synthetic and real-world datasets show the effectiveness and the efficiency of the proposed method.

This paper introduces a highly efficient pattern mining technique called Clustering-Based Pattern Mining (CBPM). This technique discovers relevant patterns by studying the correlation between transactions in transaction databases using clustering techniques. The set of transactions are first clus-tered using the k-means algorithm, where highly correlated transactions are grouped together. Next, the relevant patterns are derived by applying a pattern mining algorithm to each cluster. We present two different pattern mining algorithms, one approximate and one exact. We demonstrate the efficiency and effectiveness of CBPM through a thorough experimental evaluation.

We propose a location prediction method for tweets based on the geographical probability distribution of their terms over a region. In our method, the probabilities are calculated using Kernel Density Estimation (KDE), where the bandwidth of the kernel function for each term is determined separately according to the location indicativeness of the term. Prediction for a new tweet is performed by combining the probability distributions of its terms weighted by their information gain ratio. The method we propose relies on statistical approaches without requiring any parameter tuning. Experiments conducted on three tweet sets from different regions of the world indicate significant improvement in prediction accuracy compared to the state-of-the-art methods.

Cumulative citation recommendation refers to the task of filtering a time-ordered corpus for documents that are highly relevant to a predefined set of entities. This task has been introduced at the TREC Knowledge Base Acceleration track in 2012, where two main families of approaches emerged: classification and ranking. In this paper we perform an experimental comparison of these two strategies using supervised learning with a rich feature set. Our main finding is that ranking outperforms classification on all evaluation settings and metrics. Our analysis also reveals that a ranking-based approach has more potential for future improvements.

The number of scientific publications is constantly increasing, and the results published on Empirical Software Engineering are growing even faster. Some software engineering publishers have began to collaborate with research groups to make available repositories of software engineering empirical da

Image clustering is a problem that has been treated extensively in both Content-based (CBIR) and Text-Based (TBIR) Image Retrieval Systems. In this paper, we propose a new image clustering approach that takes both annotation, time and geographical position into account. Our goal is to develop a clustering method that allows an image to be part of an event cluster. We extend a well-known clustering algorithm called Suffix Tree Clustering (STC), which was originally developed to cluster text documents using a document snippet. To be able to use this algorithm, we consider an image with annotation as a document. Then, we extend it to also include time and geographical position. This appears to be particularly useful on the images gathered from online photo-sharing applications such as Flickr. Here image tags are often subjective and incomplete. For this reason, clustering based on textual annotations alone is not enough to capture all context information related to an image. Our approach has been suggested to address this challenge. In addition, we propose a novel algorithm to extract event clusters. The algorithm is evaluated using an annotated dataset from Flickr, and a comparison between different granularity of time and space is provided.

The theme of this paper is on support of mobile applications using adaptable transactional framework. We specifically look at the case of the adaptable-transactional framework approach CAGISTrans. The paper discusses how such a framework can be used to address the challenges incurred by the collaborative and dynamic nature of mobile applications, as well as its inherited mobile nature. It is widely known that several approaches to this theme already exist. However, many of the solutions are at most proprietary, and do not take all aspects and challenges of mobile applications and mobile environments into consideration. With CAGISTrans, which was originally developed for cooperative work support, we have attempted allow the transactional support to be adaptable, thus covering most situations and needs as possible. Our hypothesis is that with extensions, CAGISTrans can be used to address mobile collaborative applications. In general, we believe our approach is useful, but we still recognise the fact that it still has rooms for improvements. There are issues that have still to be addressed such as full support for frequent disconnection, replication and recovery requirements

BACKGROUND: Modern biology has shifted from "one gene" approaches to methods for genomic-scale analysis like microarray technology, which allow simultaneous measurement of thousands of genes. This has created a need for tools facilitating interpretation of biological data in "batch" mode. However, such tools often leave the investigator with large volumes of apparently unorganized information. To meet this interpretation challenge, gene-set, or cluster testing has become a popular analytical tool. Many gene-set testing methods and software packages are now available, most of which use a variety of statistical tests to assess the genes in a set for biological information. However, the field is still evolving, and there is a great need for "integrated" solutions. RESULTS: GeneTools is a web-service providing access to a database that brings together information from a broad range of resources. The annotation data are updated weekly, guaranteeing that users get data most recently available. Data submitted by the user are stored in the database, where it can easily be updated, shared between users and exported in various formats. GeneTools provides three different tools: i) NMC Annotation Tool, which offers annotations from several databases like UniGene, Entrez Gene, SwissProt and GeneOntology, in both single- and batch search mode. ii) GO Annotator Tool, where users can add new gene ontology (GO) annotations to genes of interest. These user defined GO annotations can be used in further analysis or exported for public distribution. iii) eGOn, a tool for visualization and statistical hypothesis testing of GO category representation. As the first GO tool, eGOn supports hypothesis testing for three different situations (master-target situation, mutually exclusive target-target situation and intersecting target-target situation). An important additional function is an evidence-code filter that allows users, to select the GO annotations for the analysis. CONCLUSION: GeneTools is the first "all in one" annotation tool, providing users with a rapid extraction of highly relevant gene annotation data for e.g. thousands of genes or clones at once. It allows a user to define and archive new GO annotations and it supports hypothesis testing related to GO category representations. GeneTools is freely available through www.genetools.no