This paper introduces an innovative mobile-assisted language-learning (MALL) system that harnesses deep learning technology to analyze pronunciation patterns and deliver real-time, personalized feedback. Drawing inspiration from how the human brain processes speech through neural pathways, our system analyzes multiple speech features using spectrograms, mel-frequency cepstral coefficients (MFCCs), and formant frequencies in a manner that mirrors the auditory cortex’s interpretation of sound. The core of our approach utilizes a convolutional neural network (CNN) to classify pronunciation patterns from user-recorded speech. To enhance the assessment accuracy and provide nuanced feedback, we integrated a fuzzy inference system (FIS) that helps learners identify and correct specific pronunciation errors. The experimental results demonstrate that our multi-feature model achieved 82.41% to 90.52% accuracies in accent classification across diverse linguistic contexts. The user testing revealed statistically significant improvements in pronunciation skills, where learners showed a 5–20% enhancement in accuracy after using the system. The proposed MALL system offers a portable, accessible solution for language learners while establishing a foundation for future research in multilingual functionality and mobile platform optimization. By combining advanced speech analysis with intuitive feedback mechanisms, this system addresses a critical challenge in language acquisition and promotes more effective self-directed learning.

Indoor vertical hydroponics is one of the most recent agricultural technologies to be introduced as it is a method of growing plants in vertically stacked layers using water and nutrient solution instead of soil. When cultivating such a system, the technique used to utilize and maintain the quality of water and nutrients is critical for plant growth. Additionally, the use of LED growth lights has a significant effect on plants. Despite developments in LED lighting and IoT-based smart agriculture systems, there is a lack of information on the use of LED lighting for hydroponically grown crops in vertical culture, due to the fact that vertical agriculture is a relatively new field of study. Thus, the aim of this research was to develop an IoT-based agricultural system to automated control LED-based artificial lighting on crop cultivation, as well as to explore the effects of different LED light on plant growth. In terms of the IoT-based system, numerous sensors were installed and monitored to measure the pH, EC, and other parameters. Using the Blynk application, those who can remotely control the LEDs and monitor the entire sensor and actuator. As for the effects of LED light, particularly the red and blue light, we utilize a case study of three LED grow light models from the manufacturer as light treatments for cultivating green leaf lettuce (Lactuca sativa). The result showed that increased R light (R/B = 2:1) resulted in an increase in plant height, leaf width, and leaf length on both harvesting days (10 and 20 DAT). The lettuce plant shape and size signify that the lettuces in each tier are of good standard and comparable in size.

As global population growth and decreasing arable land create a demand for increased food production, hydroponic farming is gaining popularity due to its numerous advantages over traditional agriculture. However, high costs and limited accessibility of commercial hydroponic systems remain a challenge for small-scale farmers, especially in developing countries. This research paper presents a novel hydroponic system that leverages the Internet of Things (IoT) technology to enhance small-scale agriculture through the monitoring of crucial parameters such as electrical conductivity (EC), pH levels, temperature, and humidity. The system integrates wireless sensor nodes that send data to a central control unit for real-time monitoring and adjustments. A comparative analysis between a semi-automatic control system and a conventional control system demonstrated that the semi-automatic system resulted in enhanced plant growth, especially in Red Cos lettuce, leading to increased yields. The research emphasises the significant potential of intelligent hydroponic systems in revolutionising conventional farming techniques and providing valuable support to small-scale farmers.

The milk quantity of dairy cows is the most important piece of data in farm management. However, it is difficult to measure and record the milk quantity for small-scale dairy farms. Therefore, the automatic milk quantity recording system for small-scale dairy farms is studied. It consists of a weight scale mechanism and an embedded system installed on a wheelbarrow for measuring and recording milk quantity. For the process of the system, the milk quantity of each cow is measured based on the load cell in kilogram units. The data such as real-time clock, cow ID, and individual and total milk quantity are recorded on a microSD memory card and sent based on the Internet of Things (IoT) for recording in a Google sheet. Furthermore, the system can alert the farmers to remove the teat cups when the cow milk comes to the end by detecting the derivative of milk quantity with respect to time. The experimental results show that the proposed system can correctly measure and record milk quantity. This system can help the farmers in improving and managing dairy farms effectively.

Drip irrigation is?a?highly efficient method for watering crops, as? it?delivers water directly to?the roots and minimises wastage due to?evaporation or?runoff. This paper presents the development and implementation of? a?low-cost drip irrigat...

This paper presents a compact and accurate readout circuit for remote two-wire resistive sensors, based on an inverting operational amplifier with a fixed bias voltage, diode steering, and unidirectional square-wave excitation generated by a microcontroller. The proposed method determines the sensor resistance by directly sampling two steady-state voltage plateaus at the op-amp output during alternating excitation phases. This approach enables fast, lead-wire-insensitive measurements without the need for analog filtering or precise PWM duty-cycle control. The architecture supports sensor array multiplexing via analog switches, allowing scalable, low-power implementation. Experimental results demonstrate a maximum relative error of 0.23% across a wide resistance range (0.5–3.5 kΩ), confirming the method’s suitability for low-cost, embedded, and remote sensing applications.