SIH 2026

← Back to hardware Themes

Smart Vehicles

2 Problem Statements

#26005

Solar-Powered Smart Mini Cold Storage System for Fresh Vegetables in North Eastern Region (NER)

Background

The North Eastern Region (NER) produces a substantial quantity of fresh vegetables and horticultural crops. However, due to inadequate cold storage infrastructure, unreliable electricity supply, difficult terrain, and transportation delays, farmers often face heavy post-harvest losses. Most remote farming areas lack access to affordable small-scale cold storage facilities near production clusters and local markets. As a result, fresh vegetables deteriorate rapidly before reaching consumers, reducing farmer income and affecting supply chain efficiency. There is a need for a low-cost, energy-efficient, and decentralized cold storage solution suitable for rural and remote regions of NER.

Description

This problem statement seeks the development of a Solar-Powered Smart Mini Cold Storage System for farmers and vegetable producers in the North Eastern Region (NER) to reduce postharvest losses of perishable vegetables. Due to poor cold-chain infrastructure, difficult transportation routes, frequent power cuts, and long travel durations from remote villages to markets, fresh vegetables often spoil within a short time after harvest. Farmers are forced to sell produce at low prices or suffer financial losses due to lack of nearby storage facilities. The proposed system should function as a decentralized mini cold storage unit that can be installed at village-level collection centres, local markets, farmer cooperatives, and farm-gate aggregation points. The system should

Preserve fresh vegetables such as tomatoes, cabbage, beans, leafy vegetables, chilli, and other horticultural produce under suitable storage conditions
Operate using solar energy with battery backup support for off-grid and low-electricity areas
Maintain controlled temperature and humidity levels for extending shelf life of vegetables
Include smart monitoring features for Temperature fluctuation Humidity variation Power failure alerts Storage condition status
Be compact, modular, and suitable for deployment in remote hilly terrain and rural agricultural clusters
Be energy-efficient, weather-resistant, and capable of operating under varying climatic conditions of NER
Support easy operation and low maintenance for farmer groups, cooperatives, and local vendors
Help reduce spoilage during temporary storage before transportation to larger markets The solution should strengthen local agricultural supply chains, reduce vegetable wastage, improve market accessibility, and enhance income opportunities for farmers in the North Eastern Region.

Expected Solution

A functional hardware-based smart mini cold storage system suitable for rural and remote agricultural areas of the North Eastern Region. The proposed solution should include

Solar-powered cooling system with energy-efficient operation
Insulated cold storage chamber for preserving fresh vegetables and horticultural produce
Battery backup support for uninterrupted operation during power outages or low sunlight conditions
Temperature and humidity monitoring mechanism for maintaining suitable storage conditions
Smart alert/indicator system for: Temperature fluctuations Power failure Unsafe storage conditions
Compact and modular design suitable for village-level deployment and difficult terrain
Weather-resistant and durable structure for varying climatic conditions in NER
Low-maintenance and cost-effective system suitable for farmer cooperatives, local markets, and collection centres
Basic digital monitoring/display interface for storage status and system performance The solution should help reduce post-harvest vegetable spoilage, improve shelf life of produce, strengthen local cold-chain infrastructure, and enhance income opportunities for farmers in the North Eastern Region.
Department
Ministry of Development of North Eastern Region (MDoNER)
PS Number
SIH26005
#26052

To develop an AI/ML-enabled adaptive noise cancellation (ANC) system that effectively suppresses stationary, non-stationary, and impulsive defence noises while maintaining high speech intelligibility and real-time performance on embedded hardware.

Background

In defence and mission-critical communication systems, reliable speech transmission is severely affected by diverse acoustic disturbances such as gunshots, artillery fire, helicopter rotor noise, armored vehicle sound and emergency sirens. Traditional signal processing techniques—like spectral subtraction, Wiener filtering, and classical LMS-based ANC—are limited in handling highly dynamic and non-linear noise environments. These methods assume stationary noise characteristics and often introduce artifacts or speech distortion under rapidly changing conditions. Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) have transformed the field of speech enhancement and ANC. Deep learning models and time-domain architectures are capable of learning complex spectral-temporal patterns directly from data. These models significantly outperform conventional approaches in terms of perceptual quality (PESQ), intelligibility (STOI), and noise suppression (SNR). Additionally, the rise of edge AI platforms enables deployment of such models on embedded systems for real-time applications.

Description

The proposed system integrates AI/ML-driven noise suppression with adaptive filtering to create a robust ANC pipeline. The development begins with dataset generation, where clean speech data is combined with curated defence noise datasets (gunshots, drones, artillery, vehicle engines, wind, etc.) at varying SNR levels. This synthetic data generation ensures coverage of both stationary and impulsive noise scenarios. The training pipeline involves transforming audio into time-frequency representations (e.g., STFT spectrograms) or directly using raw waveform inputs. Models process both full-band and sub-band features to capture global and local dependencies. while its also operates in the complex domain to preserve phase information. Training is performed using loss functions such as SI-SNR, L1/L2 loss, and perceptual loss, with evaluation metrics including SNR, STOI, and PESQ. Data augmentation techniques (random noise mixing, reverberation, clipping) are applied to improve generalization. During inference, the trained model processes incoming noisy audio in real time, estimating a mask or directly reconstructing enhanced speech. The system can optionally include a lightweight adaptive filter (e.g., LMS) for residual noise suppression. For prototype demonstration, the trained model is deployed on embedded/edge hardware such as DSPs or AI-enabled SoCs (e.g., NVIDIA Jetson AGX Orin 64GB Developer Kit or similar platforms). Optimization techniques like quantization, pruning, and ONNX / TensorRT conversion are applied to meet latency and power constraints. The system is integrated with microphones (primary + reference) and headphones/communication units to validate real-time ANC performance in practical environments

Expected Solution

The final solution is a hybrid AI-driven ANC system capable of operating in real-time and handling diverse noise environments, including impulsive and highly dynamic defence scenarios. It should include A scalable dataset pipeline for generating realistic noisy-clean speech pairs A state-of-the-art AI/ML model trained for robust noise suppression A training framework with optimized hyper-parameters and perceptual loss functions A real-time inference engine deployable on edge hardware A prototype system demonstrating live noise cancellation using microphones / headset integration The system is expected to achieve significant performance improvements, targeting SNR > 15 dB, STOI > 0. 85, and PESQ > 2. 5, while maintaining low latency suitable for real-time communication. This solution will enable reliable and intelligible communication in defence, aerospace, and high-noise industrial environments.

Department
Department of Defence Production /IDEX
PS Number
SIH26052