Network Science and Graph Analytics

Intelligent visual question answering in TCM education: An innovative application of IoT and multimodal fusion This paper proposes an innovative Traditional Chinese Medicine Ancient Text Education Intelligent Visual Question Answering System ( TCM-VQA IoTNet ), which integrates Internet of Things (IoT) technology with multimodal learning to achieve a deep understanding and intelligent question answering of both the images and textual content of traditional Chinese medicine ancient texts. The system utilizes the VisualBERT model for multimodal feature extraction, combined with Gated Recurrent Units (GRU) to process time-series data from IoT sensors, and employs an attention mechanism to optimize feature fusion, dynamically adjusting the question answering strategy. Experimental evaluations on standard datasets such as VQA v2.0, CMRC 2018, and the Chinese Traditional Medicine Dataset demonstrate that TCM-VQA IoTNet achieves accuracy rates of 72.7%, 69.%, and 75.4% respectively, with F1-...

Optimizing the effect of battery relaxation on electrochemical impedance spectroscopy measurement for real-time SOC estimation using transfer learning Conventional Electrochemical Impedance Spectroscopy (EIS) measurements require extended battery rest periods, restricting real-time use in battery management systems (BMS) and limiting generalization across chemistries. This work introduces transfer learning to significantly shorten rest time and improve model adaptability, enabling more practical and scalable EIS integration for real-world state of charge (SOC) estimations. EIS experiments were performed on 52 Ah Lithium Iron Phosphate (LFP) and 3.6 Ah Nickel Cobalt Manganese (NCM) cells at varying SOCs, with and without rest periods. The transfer learning-based Deep Neural Network (DNN-TL) model achieved high SOC estimation accuracy for LFP cells with mean squared error (MSE) of 0.0063 and mean absolute error (MAE) of 0.0664, improving MSE by 77.58% and MAE by 50.92% compared to stan...

Exclusive: Intel Reveals Plan To Spin Off Networking Business In Memo In a memo to customers, Intel says it will spin off the Network and Edge Group into a stand-alone business that is ‘focused exclusively on delivering leading silicon solutions for critical communications, enterprise networking and ethernet connectivity infrastructure. Intel Thursday revealed its plan to spin off its Network and Edge Group in a memo addressed to customers and said it will seek outside investment for the business unit. The memo, seen by CRN, was authored by Sachin Katti, who has led the Network and Edge Group, shortened as NEX, since early 2023. He was given the extra role of chief technology and AI officer by Intel CEO Lip-Bu Tan in April to lead the chipmaker’s AI strategy. An Intel spokesperson confirmed the contents of the memo to CRN. “We plan to establish key elements of our Networking and Communications business as a stand-alone company and we have begun the process of identifying strat...

2025 global network outage report and internet health check ThousandEyes tracks internet and cloud traffic and provides Network World with weekly updates on the performance of ISPs, cloud service providers, and UCaaS providers. The reliability of services delivered by ISPs, cloud providers and conferencing services is critical for enterprise organizations. ThousandEyes, a Cisco company, monitors how providers are handling any performance challenges and provides Network World with a weekly roundup of events that impact service delivery. Read on to see the latest analysis, and stop back next week for another update on the performance of cloud providers and ISPs. Internet Report for July 14-20 ThousandEyes reported 216 global network outage events across ISPs, cloud service provider networks, collaboration app networks and edge networks (including DNS, content delivery networks, and security as a service) during the week of July 14-20. That’s an increase of 44% in outages from the wee...

MultiFeature fusion graph attention network for aspect-based sentiment analysis Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which aims to predict the sentiment polarity of a given aspect in a sentence. Most of the approaches rely on syntactic and semantic parsing to derive textual insights, often overlooking how aspectual and contextual factors impact model performance. Alternatively, they focus on an in-depth study of the information in the dependency tree, thereby ignoring the importance of the constituent trees. In this work, we introduce a multifeature fusion graph attention network ( MFF-GAT ) model. The model constructs syntactic, semantic and contextual channels, fusing dependent syntactic information and constituent syntactic information through a gating mechanism. The semantic graph is constructed based on self-attention, and the contextual graph is constructed based on point interaction information. In addition, this study uses the multi-...

Network analysis with quantum dynamics clarifies why photosystem II exploits both chlorophyll a and b In green plants, chlorophyll a and chlorophyll b are the predominant pigments bound to light-harvesting proteins. While the individual characteristics of these chlorophylls are well understood, the advantages of their coexistence remain unclear. In this study, we establish a method to simulate excitation energy transfer within the entire photosystem II supercomplex by using network analysis integrated with quantum dynamic calculations. We then investigate the effects of the coexistence of chlorophyll a and chlorophyll b by comparing various chlorophyll compositions. Our results reveal that the natural chlorophyll composition allows the excited energy to preferentially flow through specific domains that act as safety valves, preventing downstream overflow. Our findings suggest that the light-harvesting proteins in a photosystem II supercomplex achieve evolutionary advantages with the na...

The silent backbone of 5G & beyond: How network APIs are powering the future of connectivity 5G has become a technological backbone as the world speeds toward a hyper-connected future, driving advancements in Healthcare, Industrial Manufacturing, Immersive Entertainment, Smart Cities, Connected Cars, Finance & Banking, Public Safety and Emergency Services. However, network APIs-the real facilitator of this change-frequently go unnoticed. Network APIs are fueling significant changes across the telecom industry and beyond by enabling new business models, enhancing service innovation, and transforming how networks and applications interact.  Key changes driven by Network APIs include: Unlocking New Revenue Streams for Telecom Operators Accelerating Innovation and Enterprise Product Development Enhancing Customer and Enterprise On Demand Experiences Enabling Programmable, Flexible, and Cost-Efficient Networks Driving Industry Collaboration and Ecosystem Development Addressing C...

Intrusion detection in IoT and wireless networks using image-based neural network classification Telecommunication networks play more and more important role in our modern times, and there are significant security risks associated with both wireless and wired networks. These risks stem from various malicious actions and security threats that have emerged with the development of Fourth Generation (4G), Fifth Generation (5G), and Internet of Things (IoT) networks. Machine learning (ML) algorithms have been applied to Intrusion Detection Systems (IDSs) due to their capacity to their ability to detect complex network traffic patterns. Deep learning (DL) networks are highly effective in processing images and videos and they have potential to solve other types of data.   Given the characteristics of network traffic records used for intrusion detection in wireless and wired networks, we propose a simple data preprocessing method to convert the data into a grid-structured format, making i...

Microsoft server hack likely single actor, thousands of firms now vulnerable, researchers say Unclear who is behind attacks LONDON, July 21 (Reuters) - A global attack on Microsoft server software used by thousands of government agencies and businesses to share documents within organisations is likely the work of a single actor, a cybersecurity researcher said on Monday. Microsoft on Saturday issued an alert about "active attacks" on SharePoint servers used within organisations. It said that SharePoint Online in Microsoft 365, which is in the cloud, was not hit by the exploit, also known as a "zero day" because it was previously unknown to cybersecurity researchers. "Based on the consistency of the tradecraft seen across observed attacks, the campaign launched on Friday appears to be a single actor. However, it's possible that this will quickly change," Rafe Pilling, Director of Threat Intelligence at Sophos, a British cybersecurity firm. That tradecra...

Deep Learning-Based Method for Operation Dispatch Strategy Generation of Virtual Power Plants Centralized and distributed optimization methods used by traditional virtual power plants (VPPs) in power system dispatching face issues such as high computational complexity, difficulties in privacy protection, and slow iterative convergence. There is an urgent need to propose an accurate and efficient acceleration method for generating VPP operational dispatching strategies. This paper proposes a deep learning-based acceleration method for generating VPP operational dispatching strategies. By using the equivalent projection method to solve the operation feasible region of the VPP, the objective function and constraints of the VPP are transformed into constraints of coordination variables and submitted to the system dispatching center for optimization, thereby avoiding the slow convergence problem of iterative computation methods. The Kolmogorov–Arnold Network (KAN) is employed to predict the...

An introduction to satellite network architecture Satellite networking is a digital revolution that connects people from across the world instantly -- from enabling real-time communications to making the world a safer place. A satellite is an artificial object put into the Earth's orbit to gather and distribute crucial data. Since the late 1950s, satellites have only transmitted and received data, as bent pipe satellites weren't able to perform other functions. In modern times, a group of satellites in the same orbit forms a satellite network. Satellite networks process data and provide accurate visual and textual information. Unlike terrestrial network infrastructure, satellite network scalability isn't limited by geography and cost. According to a March 2025 report from Goldman Sachs, the global satellite market is expected to hit $108 billion by 2035, growing sevenfold from its current valuation. Satellite networks consist of the following: The ground equipment. The sa...

Applying Network Science to Networking at IceLab Days The annual IceLab Days meeting, organized by the Integrated Science Lab (IceLab), took place on November 13–14 at Skeppsvik Herrgård. The event fostered collaboration among IceLab members and affiliated researchers while strengthening the social and interdisciplinary work culture. This year, IceLab members turned their tools inward, applying network science to visualize current and potential research overlaps. Bridging Disciplines and Building Connections IceLab’s mission is to connect researchers across disciplines for the love of launching and landing new ideas. Through initiatives like the IceLab Lunch Pitches, the lab has built a reputation for facilitating spontaneous collaborations. However, what about researchers who aren’t actively seeking collaborations? Rubén Bernardo Madrid, a postdoctoral fellow at IceLab and one of the event organizers, tackled this challenge head-on while designing the program for IceLab Days. “Man...