Efficient Semantic Communication Through Transformer-Aided Compression

/in /by

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework for semantic communication, where different regions of the image are encoded and compressed based on their semantic content. By employing vision transformers, we interpret the attention mask as a measure of the semantic contents of the patches and dynamically categorize the patches to be compressed at various rates as a function of the instantaneous channel bandwidth. Our method enhances communication efficiency by adapting the encoding resolution to the content’s relevance, ensuring that even in highly constrained environments, critical information is preserved. We evaluate the proposed adaptive transmission framework using the TinyImageNet dataset, measuring both reconstruction quality and accuracy. The results demonstrate that our approach maintains high semantic fidelity while optimizing bandwidth, providing an effective solution for transmitting multiresolution data in limited bandwidth conditions.

Read more

Optical Flow Processing for Chirp-Pulse Coherent OTDR

/in /by

We propose a novel optical flow processing technique for distributed temperature and strain sensing with the chirped-pulse coherent OTDR. Unlike conventional 1-dimensional cross-correlation methods, the technique treats the 2-dimensional waterfall data as sequential video frames, estimating local shifts through optical flow. The weighted least square approach with adaptive window size enables pixel-level optical flow calculation, providing accurate local shifts via accumulative tracks with enhanced spatial resolution. Preliminary experimental results over 20km fiber demonstrate its effectiveness for dynamic temperature and strain sensing, addressing limitations of traditional methods and improving sensing capabilities.

Read more

Detection of Waves and Sea-Surface Vessels via Time Domain Only Analysis of Underwater DAS Data

/in /by

A 100-meter-long fiber optic cable was installed at the bottom of a water tank at the Davidson Laboratory, together with a hydrophone for reference. The water tank is approximately 2.5 meters deep and 95 meters long; the tank also employs a 6-paddle wavemaker which can generate programmable surface waves. A 155-cm-long model boat weighing 6.5 kilograms was automatically dragged on the surface of the tank via an electrical towing mechanism. The movement of the model boat along the fiber cable and over the hydrophone was recorded using a commercially available NEC Distributed Acoustic Sensing (DAS) system and simultaneously by a hydrophone. The experiments were repeated with and without the artificially generated surface waves. The data obtained from the hydrophone and the DAS system are presented and compared. The results show the compatibility between the DAS data and the hydrophone data. More importantly, ourresults show that it is possible to measure the surface waves and to detect a surface vessel approaching the sensor by only using the time domain analysis in terms of detected total energy over time.

Read more

Resilient DFOS Placement Strategy for Power Grid Monitoring: Integrating Fiber and Power Network Dependencies

/in /by

We propose a novel Distributed Fiber Optic Sensing (DFOS) placement strategy tailored to the evolving needs of modern power grids, where fiber cables serve dual purposes: communication and real-time sensing. Our approach integrates a heuristic algorithm, PURE (Power Source-aware Route Exploration), with Integer Linear Programming (ILP) to optimize DFOS placement while addressing power supply constraints. The strategy ensures resilient monitoring across diverse grid scenarios by prioritizing observability during outages and leveraging advancements in fiber infrastructure deployment. Case studies demonstrate the effectiveness of our methodology in maintaining power grid resilience while minimizing deployment costs.

Read more

NEC Labs America Joins CS3 Advisory Board to Advance Smart Streetscapes

/in /by

NEC Laboratories America has joined the Center for Smart Streetscapes (CS3) Advisory Board, a National Science Foundation–funded initiative advancing urban innovation through technology, data, and design. As a leader in AI, computer vision, and edge computing, NEC Labs America will collaborate with researchers, civic leaders, and industry partners to develop intelligent infrastructure that enhances safety, accessibility, and efficiency in public spaces.

Read more

Latency-driven Execution of LLM-generated Application Code on the Computing Continuum

/in /by

Latency-critical applications demand quick responses. Ideally, detailed insights are preferable for the best decision making and response actions. However, in situations when detailed insights cannot be provided quickly, even basic information goes a long way in tackling the situation effectively. For example, in marine security application, it is critical to immediately notify as soon as an unauthorized vessel is seen. Hence, timely response may be prioritized over the response based on entire details. To address such latency-critical situations, in this paper, we propose a novel system called DiCE-EC, which leverages LLM to generate distributed code with speculative execution on Edge (fast and simple response using resource constrained hardware) and Cloud (detailed response using powerful hardware, but may be fast or slow depending on network conditions). DiCE-EC breaks down application into smaller components and executes them asynchronously across the edge and cloud computing continuum. As network conditions vary, we show through real-world marine security application, that DiCE-EC is effective in dynamically choosing detailed insights from cloud when received within latency-constraint, or falling back to simple response from edge to guarantee timely alert delivery. Without such dynamic selection of response from edge or cloud, existing systems either always provide simple responses or drop alerts. We perform real network measurements in the Gulf of Pozzuoli in Naples, Italy along accessible areas (inland and in a Ferry) and generate 1 million realistic measurements across four inaccessible regions, and demonstrate that DiCE-EC never misses an alert, while baseline misses up to ?4% alerts with real data and up to ?1% (10,000 alerts) with generated data.

Read more

Multiple Sensor-head Phase-sensitive Optical Time-domain Laser Vibrometer

/in /by

We propose a hybrid remote and distributed vibration sensing system based on phase-sensitive optical time-domain reflectometry with collimator-based sensor heads. We demonstrate dual-laser vibrometers that detects nm-scale displacements of remote targets.

Read more

Evidence-Based Out-of-Distribution Detection on Multi-Label Graphs

/in /by

The Out-of-Distribution (OOD) problem in graph-structured data is becoming increasingly important in various areas of research and applications, including social network recommendation [36], protein function detection [9, 21], etc. Furthermore, owing to the inherent multi-label properties of nodes, multi-label OOD detection remains more challenging than in multi-class scenarios. A lack of uncertainty modeling in multi-label classification methods prevents the separation of OOD nodes from in-distribution (ID) nodes. Existing uncertainty-based OOD detection methods on graphs are not applicable for multi-label scenarios because they are designed for multi-class settings. Therefore, node-level OOD detection on multi-label graphs becomes desirable but rarely touched. In this paper, we pro-pose a novel Evidence-Based Out-of-Distribution Detection method on multi-label graphs. The evidence for multiple labels, which indicates the amount of support to suggest that a sample should be classified into a specific class, is predicted by Multi-Label Evidential Graph Neural Networks (ML-EGNNs). The joint belief is designed for multi-label opinions fusion by a comultiplication operator. Additionally, we intro-duce a Kernel-based Node Positive Evidence Estimation (KNPE) method to reduce errors in quantifying positive evidence. Experimental results prove both the effectiveness and efficiency of our model for multi-label OOD detection on 7 multi-label benchmarks.

Read more

Position Really Matters: Towards a Holistic Approach for Prompt Tuning

/in /by

Prompt tuning is highly effective in efficiently extracting knowledge from foundation models, encompassing both language, vision, and vision-language models. However, the efficacy of employing fixed soft prompts with a predetermined position for concatenation with inputs for all instances, irrespective of their inherent disparities, remains uncertain. Variables such as the position, length, and representations of prompts across diverse instances and tasks can substantially influence the performance of prompt tuning. We first provide a theoretical analysis, revealing that optimizing the position of the prompt to encompass the input can capture additional semantic information that traditional prefix or postfix prompt tuning methods fail to capture. Then, we present a holistic parametric prompt tuning strategy that dynamically determines different factors of prompts based on specific tasks or instances. Experimental results underscore the significant performance improvement achieved by dynamic prompt tuning across a wide range of tasks, including NLP, vision recognition, and vision-language tasks. Furthermore, we establish the universal applicability of our approach under full-data, few-shot, and multitask settings.

Read more

MixLLM: Dynamic Routing in Mixed Large Language Models

/in /by

Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response quality and minimize cost and latency. However, the challenges involve: (1) dynamic trade-offs among quality, cost, and latency; (2) enabling continual learning in deployed systems; and (3) navigating a varying (e.g., new LLM addition or old LLM removal) set of LLM candidates over time. To bridge these gaps, we develop MixLLM, a dynamic contextual-banditbased routing system for query-LLM assignment. Specifically, we first leverage query tags to enhance query embeddings for the routing task. Next, we design lightweight prediction models to estimate the response qualities and costs of queries over LLMs. We then devise a meta-decision maker to choose the query-LLM assignments to best tradeoff response quality, cost, and latency. Finally, the system benefits from continual training, allowing it to adapt to evolving queries and user feedback over time. Our extensive experiments show that MixLLM achieves the best trade-offs in response quality, cost, and latency (97.25% of GPT-4’s quality at 24.18% of the cost under the time constraint). 

Read more