MAROKO133 Hot ai: New sensor uses microneedles to confirm fish freshness in just two minut

📌 MAROKO133 Eksklusif ai: New sensor uses microneedles to confirm fish freshness i

Checking whether fish is fresh has traditionally meant relying on appearance and smell.

Clear eyes, bright gills, and a clean scent usually signal freshness, while cloudy eyes or a foul odor are seen as warnings. But these visible and sensory signs often appear late in the spoilage process.

Chemical changes begin long before the fish looks or smells bad. Now, researchers have developed a portable device that can measure freshness in under two minutes by detecting those early changes.

The prototype sensor could eventually make seafood evaluation faster, easier, and far more accurate.

Detecting freshness at the molecular level

Fish begin decomposing almost immediately after death. One of the earliest chemical markers of this process is hypoxanthine (HX).

It forms as nucleic acids and other molecules start breaking down. Because HX levels rise quickly, scientists recognize it as a reliable freshness indicator. It works for both whole fish and packaged fillets.

However, testing for HX currently requires skilled technicians, laboratory equipment, and long analysis times. These factors make routine testing unrealistic in markets, cold storage, or kitchens.

The research team, including Nicolas Voelcker, Azadeh Nilghaz, and Muamer Dervisevic, set out to design a tool that could be used almost anywhere without complicated preparation or machines.

Simple Test With Microneedles

The device uses a small four-by-four microneedle array coated with gold nanoparticles and an enzyme that reacts specifically to HX.

Microneedles are often found in skincare and medical patches, but here they play a different role.

They help the device make contact with chemical activity below the surface of the fish, where spoilage starts.

To perform a measurement, the sensor is gently pressed against the fish. The tiny needles anchor it in place. As the enzyme reacts with hypoxanthine, electrical signals shift inside the flesh.

The sensor reads those shifts and interprets them to determine freshness.

The researchers tested the prototype on fresh salmon cut into pieces and left out at room temperature for up to 48 hours.

The sensor detected hypoxanthine levels as low as 500 parts per billion, which corresponds to what experts classify as very fresh fish.

Results appeared in roughly 100 seconds. The accuracy and sensitivity matched those of an existing lab-based testing kit.

Although more work is needed before it becomes widely available, the demonstration shows strong potential. The researchers say the device could be used for real-time food quality monitoring.

If developed commercially, the tool could benefit seafood distributors, grocery stores, restaurants, and home cooks.

Consumers often rely on trust and guesswork when buying fish.

A sensor that quickly and objectively confirms freshness could reduce waste, cut the risk of foodborne illness, and increase confidence in seafood products.

The study suggests that in the future, testing fish for freshness might become as simple as pressing a small device onto its surface and waiting a minute.

Instead of judging by smell or guessing based on appearance, users could get a measurable answer backed by chemistry.

The study is published in the journal ACS Sensors.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Hot ai: ByteDance Introduces Astra: A Dual-Model Architecture for Auto

The increasing integration of robots across various sectors, from industrial manufacturing to daily life, highlights a growing need for advanced navigation systems. However, contemporary robot navigation systems face significant challenges in diverse and complex indoor environments, exposing the limitations of traditional approaches. Addressing the fundamental questions of “Where am I?”, “Where am I going?”, and “How do I get there?”, ByteDance has developed Astra, an innovative dual-model architecture designed to overcome these traditional navigation bottlenecks and enable general-purpose mobile robots.

Traditional navigation systems typically consist of multiple, smaller, and often rule-based modules to handle the core challenges of target localization, self-localization, and path planning. Target localization involves understanding natural language or image cues to pinpoint a destination on a map. Self-localization requires a robot to determine its precise position within a map, especially challenging in repetitive environments like warehouses where traditional methods often rely on artificial landmarks (e.g., QR codes). Path planning further divides into global planning for rough route generation and local planning for real-time obstacle avoidance and reaching intermediate waypoints.

While foundation models have shown promise in integrating smaller models to tackle broader tasks, the optimal number of models and their effective integration for comprehensive navigation remained an open question.

ByteDance’s Astra, detailed in their paper “Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning” (website: https://astra-mobility.github.io/), addresses these limitations. Following the System 1/System 2 paradigm, Astra features two primary sub-models: Astra-Global and Astra-Local. Astra-Global handles low-frequency tasks like target and self-localization, while Astra-Local manages high-frequency tasks such as local path planning and odometry estimation. This architecture promises to revolutionize how robots navigate complex indoor spaces.

Astra-Global: The Intelligent Brain for Global Localization

Astra-Global serves as the intelligent core of the Astra architecture, responsible for critical low-frequency tasks: self-localization and target localization. It functions as a Multimodal Large Language Model (MLLM), adept at processing both visual and linguistic inputs to achieve precise global positioning within a map. Its strength lies in utilizing a hybrid topological-semantic graph as contextual input, allowing the model to accurately locate positions based on query images or text prompts.

The construction of this robust localization system begins with offline mapping. The research team developed an offline method to build a hybrid topological-semantic graph G=(V,E,L):

• V (Nodes): Keyframes, obtained by temporal downsampling of input video and SfM-estimated 6-Degrees-of-Freedom (DoF) camera poses, act as nodes encoding camera poses and landmark references.
• E (Edges): Undirected edges establish connectivity based on relative node poses, crucial for global path planning.
• L (Landmarks): Semantic landmark information is extracted by Astra-Global from visual data at each node, enriching the map’s semantic understanding. These landmarks store semantic attributes and are connected to multiple nodes via co-visibility relationships.

In practical localization, Astra-Global’s self-localization and target localization capabilities leverage a coarse-to-fine two-stage process for visual-language localization. The coarse stage analyzes input images and localization prompts, detects landmarks, establishes correspondence with a pre-built landmark map, and filters candidates based on visual consistency. The fine stage then uses the query image and coarse output to sample reference map nodes from the offline map, comparing their visual and positional information to directly output the predicted pose.

For language-based target localization, the model interprets natural language instructions, identifies relevant landmarks using their functional descriptions within the map, and then leverages landmark-to-node association mechanisms to locate relevant nodes, retrieving target images and 6-DoF poses.

To empower Astra-Global with robust localization abilities, the team employed a meticulous training methodology. Using Qwen2.5-VL as the backbone, they combined Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). SFT involved diverse datasets for various tasks, including coarse and fine localization, co-visibility detection, and motion trend estimation. In the GRPO phase, a rule-based reward function (including format, landmark extraction, map matching, and extra landmark rewards) was used to train for visual-language localization. Experiments showed GRPO significantly improved Astra-Global’s zero-shot generalization, achieving 99.9% localization accuracy in unseen home environments, surpassing SFT-only methods.

Astra-Local: The Intelligent Assistant for Local Planning

Astra-Local acts as the intelligent assistant for Astra’s high-frequency tasks, a multi-task network capable of efficiently generating local paths and accurately estimating odometry from sensor data. Its architecture comprises three core components: a 4D spatio-temporal encoder, a planning head, and an odometry head.

The 4D spatio-temporal encoder replaces traditional mobile stack perception and prediction modules. It begins with a 3D spatial encoder that processes N omnidirectional images through a Vision Transformer (ViT) and Lift-Splat-Shoot to convert 2D image features into 3D voxel features. This 3D encoder is trained using self-supervised learning via 3D volumetric differentiable neural rendering. The 4D spatio-temporal encoder then builds upon the 3D encoder, taking past voxel features and future timestamps as input to predict future voxel features through ResNet and DiT modules, providing current and future environmental representations for planning and odometry.

The planning head, based on pre-trained 4D features, robot speed, and task information, generates executable trajectories using Transformer-based flow matching. To prevent collisions, the planning head incorporates a masked ESDF loss (Euclidean Signed Distance Field). This loss calculates the ESDF of a 3D occupancy map and applies a 2D ground truth trajectory mask, significantly reducing collision rates. Experiments demonstrate its superior performance in collision rate and overall score on out-of-distribution (OOD) datasets compared to other methods.

The odometry head predicts the robot’s relative pose using current and past 4D features and additional sensor data (e.g., IMU, wheel data). It trains a Transformer model to fuse information from different sensors. Each sensor modality is processed by a specific tokenizer, combined with modality embeddings and temporal positional embeddi…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com