Artificial Intelligence

Multimodal large language models (MLLMs) have shown remarkable progress in high-level semantic tasks such as visual question answering, image captioning, and emotion recognition. However, despite advancements, there remains a lack of standardized benchmarks for evaluating MLLMs performance in multi-object sentiment analysis, a key task in semantic understanding. To address this gap, we introduce MOSABench, a novel evaluation dataset designed specifically for multi-object sentiment analysis.

Channel estimation is crucial in cognitive communications, as it enables intelligent spectrum sensing and adaptive transmission by providing accurate information about the channel state information. Current channel estimation neural networks are frequently tested by training and testing on one example channel or similar channels. However, data-driven methods often degrade on new data which they are not trained on, because they cannot extrapolate their training knowledge.

In this paper, a lightweight optimization method for complex analog integrated circuits (ICs) is proposed based on convolution neural network (CNN)-multilayer perceptron (MLP) and particle swarm optimization (PSO) algorithm. According to the circuit structure and the proposed design specifications, the circuit is divided into several sub-module circuits. Then, the sub-module and overall dataset are constructed.

kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kitti kit

These datasets originate from two separate power transformers, identified as Transformer 1 and Transformer 2. Each dataset is further categorized into two distinct time intervals for data collection. The first time interval, labeled as "m," represents a short-term sampling period with data recorded every 15 minutes, capturing detailed temporal fluctuations over shorter durations. The second time interval, labeled as "h," signifies a longer-term sampling period with data recorded at hourly intervals, providing an overview of broader trends and patterns.

The Human voice Natural Language from On-demand media (HENLO) dataset is a high-quality emotional speech dataset created to address the need for representative and realistic data in speech emotion recognition research. Unlike many existing datasets, which rely on simulated emotions performed by untrained speakers or directed participants, HENLO sources its data from professionally produced films and podcasts available on Media On-Demand (MOD).

In this paper we use Natural Language Processing techniques to improve different machine learning approaches (Support Vector Machines (SVM), Local SVM, Random Forests) to the problem of automatic keyphrases extraction from scientific papers. For the evaluation we propose a large and high-quality dataset: 2000 ACM papers from the Computer Science domain. We evaluate by comparison with expert-assigned keyphrases.

This dataset contains survey responses collected from Agile practitioners across various roles, including Scrum Masters, Developers, Product Owners, and Agile Coaches, from organizations with diverse Agile practices. The survey aimed to identify the common challenges in backlog refinement, such as time constraints, prioritization issues, and ambiguous user stories. It also explored perceptions of Generative AI's role in streamlining Agile workflows, enhancing productivity, and reducing cognitive load.

Hyperspectral images are represented by numerous
narrow wavelength bands in the visible and near-infrared parts
of the electromagnetic spectrum. As hyperspectral imagery gains
traction for general computer vision tasks, there is an increased
need for large and comprehensive datasets for use as training
data.
Recent advancements in sensor technology allow us to capture
hyperspectral data cubes at higher spatial and temporal reso-
lution. However, there are few publicly available multi-purpose
hyperspectral datasets captured in outdoor terrestrial conditions.

The necessity for strong security measures to fend off cyberattacks has increased due to the growing use of Industrial Internet of Things (IIoT) technologies. This research introduces IoTForge Pro, a comprehensive security testbed designed to generate a diverse and extensive intrusion dataset for IIoT environments. The testbed simulates various IIoT scenarios, incorporating network topologies and communication protocols to create realistic attack vectors and normal traffic patterns.