IoT

Indoor plant watering is not always effective - people often overwater or underwater plants, wasting water and harming plant health. In view of this, a smart watering system using artificial intelligence that runs on a tiny microcontroller chip has been developed. The proposed system predicts when plants need water and waters them automatically. Testing on 12 plants for 3 months has showed 27% water savings versus manual watering and 15% savings versus simple automated systems. The AI model is only 8.7 KB and runs for months on battery power without Internet.

This paper presents a cryptographic user authentication protocol based on AES in Galois/Counter Mode (GCM) and key derivation using PBKDF2-HMAC-SHA256. The proposed scheme follows a challenge–response model and ensures confidentiality, integrity, and authenticity of transmitted data without disclosing or storing the password in plaintext. A client-server architecture was implemented, with the backend developed in Flask (Python) and the frontend in JavaScript. The protocol incorporates nonce usage, authentication tag verification, and protection against replay and brute-force attacks.

Assessment of the volume and quality of a rower's efforts during training plays an important role in preparing for competitions and improving his results. The article reviews existing commercial solutions, such as rowing simulators and individual sensor devices. It was determined that such proposals allow recording the frequency or trajectory of movement, but do not measure force. They also have limited functionality in real water conditions or high cost.

This paper presents the development and inves- tigation of a speech-to-text conversion and speaker identi- fication system based on a Raspberry Pi microcomputer, designed for local audio data processing in environments with limited network connectivity. The system integrates Silero and WebRTC models for voice activity detection, SpeechBrain for speaker identification, and the Whisper family of models for speech recognition.

The article focuses on innovative measurement and control methods in electrical power engineering, specifically addressing challenges of power quality, signal diagnostics, and automation within smart grids. Emphasis is placed on wavelet analysis, smart metering, IoT integration, and automated control systems. These technologies are examined in the context of enhancing the adaptability and efficiency of modern electrical systems in line with Industry 4.0 requirements.

The rapid expansion of the Internet of Things (IoT) has resulted in a substantial increase of diverse data from distributed devices. This extensive data stream makes it increasingly important to implement robust and efficient real-time anomaly detection techniques that can promptly alert about issues before they could escalate into critical system failures.

The article is devoted to the development of an automated care system for indoor plants based on the use of an Arduino microcontroller and IoT technologies. The system contains soil moisture, temperature, and light sensors that monitor the main environmental parameters for effective plant care. The structural and schematic diagrams and algorithm of the system were developed. A prototype of the system was implemented. The prototype of the system was tested in real conditions, which confirmed the correctness of the decisions made, as well as the efficiency and usability of the system.

The article presents a method for optimizing the algorithm flow graph of a deep neural network to reduce the number of processor elements (PE) required for executing the algorithm on single-board computers. The proposed approach is based on the use of a structural matrix to optimize the neural network architecture without loss of performance. The research demonstrated that by reducing the width of the graph, the number of processor elements was reduced from 3 to 2, while maintaining network performance at 75% efficiency.