Qian Huang

Background: Soybean is an important global crop in food security and agricultural economics. Accurate estimation of soybean pod counts is critical for yield prediction, breeding programs, precision farming, etc. Traditional methods, such as manual counting, are slow, labor-intensive, and prone to errors. With rapid advancements in artificial intelligence (AI), deep learning has enabled automatic pod number estimation in collaboration with unmanned aerial vehicles (UAVs). However, existing AI models are computationally demanding and require significant processing resources (e.g., memory). These resources are often not available in rural regions and small farms. Methods: To address these challenges, this study presents a set of lightweight, efficient AI models designed to overcome these limitations. By integrating model simplification, weight quantization, and squeeze-and-excitation (SE) self-attention blocks, we develop compact AI models capable of fast and accurate soybean pod count estimation. Results and Conclusions: Experimental results show a comparable estimation accuracy of 84–87%, while the AI model size is significantly reduced by a factor of 9–65, thus making them suitable for deployment in edge devices, such as Raspberry Pi. Compared to existing models such as YOLO POD and SoybeanNet, which rely on over 20 million parameters to achieve approximately 84% accuracy, our proposed lightweight models deliver a comparable or even higher accuracy (84.0–86.76%) while using fewer than 2 million parameters. In future work, we plan to expand the dataset by incorporating diverse soybean images to enhance model generalizability. Additionally, we aim to explore more advanced attention mechanisms—such as CBAM or ECA—to further improve feature extraction and model performance. Finally, we aim to implement the complete system in edge devices and conduct real-world testing in soybean fields.

Robot vacuum cleaners have gained widespread popularity as household appliances. One significant challenge in enhancing their functionality is to identify and classify small indoor objects suitable for safe suctioning and recycling during cleaning operations. However, the current state of research faces several difficulties, including the lack of a comprehensive dataset, size variation, limited visual features, occlusion and clutter, varying lighting conditions, the need for real-time processing, and edge computing. In this paper, I address these challenges by investigating a lightweight AI model specifically tailored for robot vacuum cleaners. First, I assembled a diverse dataset containing 23,042 ground-view perspective images captured by robot vacuum cleaners. Then, I examined state-of-the-art AI models from the existing literature and carefully selected three high-performance models (Xception, DenseNet121, and MobileNet) as potential model candidates. Subsequently, I simplified these three selected models to reduce their computational complexity and overall size. To further compress the model size, I employed post-training weight quantization on these simplified models. In this way, our proposed lightweight AI model strikes a balance between object classification accuracy and computational complexity, enabling real-time processing on resource-constrained robot vacuum cleaner platforms. I thoroughly evaluated the performance of the proposed AI model on a diverse dataset, demonstrating its feasibility and practical applicability. The experimental results show that, with a small memory size budget of 0.7 MB, the best AI model is L-w Xception 1, with a width factor of 0.25, whose resultant object classification accuracy is 84.37%. When compared with the most accurate state-of-the-art model in the literature, this proposed model accomplished a remarkable memory size reduction of 350 times, while incurring only a slight decrease in classification accuracy, i.e., approximately 4.54%.

Artificial intelligence (AI) plays a critical role in the operation of robot vacuum cleaners, enabling them to intelligently navigate to clean and avoid indoor obstacles. Due to limited computational resources, manufacturers must balance performance and cost. This necessitates the development of lightweight AI models that can achieve high performance. Traditional uniform weight quantization assigns the same number of levels to all weights, regardless of their distribution or importance. Consequently, this lack of adaptability may lead to sub-optimal quantization results, as the quantization levels do not align with the statistical properties of the weights. To address this challenge, in this work, we propose a new technique called low bitwidth strong non-uniform quantization, which largely reduces the memory footprint of AI models while maintaining high accuracy. Our proposed non-uniform quantization method, as opposed to traditional uniform quantization, aims to align with the actual weight distribution of well-trained neural network models. The proposed quantization scheme builds upon the observation of weight distribution characteristics in AI models and aims to leverage this knowledge to enhance the efficiency of neural network implementations. Additionally, we adjust the input image size to reduce the computational and memory demands of AI models. The goal is to identify an appropriate image size and its corresponding AI models that can be used in resource-constrained robot vacuum cleaners while still achieving acceptable accuracy on the object classification task. Experimental results indicate that when compared to the state-of-the-art AI models in the literature, the proposed AI model achieves a 2-fold decrease in memory usage from 15.51 MB down to 7.68 MB while maintaining the same accuracy of around 93%. In addition, the proposed non-uniform quantization model reduces memory usage by 20 times (from 15.51 MB down to 0.78 MB) with a slight accuracy drop of 3.11% (the classification accuracy is still above 90%). Thus, our proposed high-performance and lightweight AI model strikes an excellent balance between model complexity, classification accuracy, and computational resources for robot vacuum cleaners.

With the rapid development of artificial intelligence (AI) theory, particularly deep learning neural networks, robot vacuums equipped with AI power can automatically clean indoor floors by using intelligent programming and vacuuming services. To date, several deep AI models have been proposed to distinguish indoor objects between cleanable litter and noncleanable hazardous obstacles. Unfortunately, these existing deep AI models focus entirely on the accuracy enhancement of object classification, and little effort has been made to minimize the memory size and implementation cost of AI models. As a result, these existing deep AI models require far more memory space than a typical robot vacuum can provide. To address this shortcoming, this paper aims to study and find an efficient deep AI model that can achieve a good balance between classification accuracy and memory usage (i.e., implementation cost). In this work, we propose a weight-quantized SqueezeNet model for robot vacuums. This model can classify indoor cleanable litters from noncleanable hazardous obstacles based on the image or video captures from robot vacuums. Furthermore, we collect videos or pictures captured by built-in cameras of robot vacuums and use them to construct a diverse dataset. The dataset contains 20,000 images with a ground-view perspective of dining rooms, kitchens and living rooms for various houses under different lighting conditions. Experimental results show that the proposed deep AI model can achieve comparable object classification accuracy of around 93% while reducing memory usage by at least 22.5 times. More importantly, the memory footprint required by our AI model is only 0.8 MB, indicating that this model can run smoothly on resource-constrained robot vacuums, where low-end processors or microcontrollers are dedicated to running AI algorithms.

Artificial intelligence (AI) is fundamentally transforming smart buildings by increasing energy efficiency and operational productivity, improving life experience, and providing better healthcare services. Sudden Infant Death Syndrome (SIDS) is an unexpected and unexplained death of infants under one year old. Previous research reports that sleeping on the back can significantly reduce the risk of SIDS. Existing sensor-based wearable or touchable monitors have serious drawbacks such as inconvenience and false alarm, so they are not attractive in monitoring infant sleeping postures. Several recent studies use a camera, portable electronics, and AI algorithm to monitor the sleep postures of infants. However, there are two major bottlenecks that prevent AI from detecting potential baby sleeping hazards in smart buildings. In order to overcome these bottlenecks, in this work, we create a complete dataset containing 10,240 day and night vision samples, and use post-training weight quantization to solve the huge memory demand problem. Experimental results verify the effectiveness and benefits of our proposed idea. Compared with the state-of-the-art AI algorithms in the literature, the proposed method reduces memory footprint by at least 89%, while achieving a similar high detection accuracy of about 90%. Our proposed AI algorithm only requires 6.4 MB of memory space, while other existing AI algorithms for sleep posture detection require 58.2 MB to 275 MB of memory space. This comparison shows that the memory is reduced by at least 9 times without sacrificing the detection accuracy. Therefore, our proposed memory-efficient AI algorithm has great potential to be deployed and to run on edge devices, such as micro-controllers and Raspberry Pi, which have low memory footprint, limited power budget, and constrained computing resources.

Journal of Information Technology in Construction

A wireless sensor network (WSN) is typically composed of spatially distributed miniature sensors that help collect large amounts of real-time environmental data from buildings. These environmental data (e.g., temperature, humidity, CO₂ concentration) can assist a series of heating, ventilation, and air conditioning (HVAC) equipment to increase the building energy efficiency. From a system design perspective, heterogeneous wireless sensor networks need to address two challenges. First, sensor data acquisition, conversion, fusion, and packaging involve a series of software processing. Since each type of environmental sensor typically has unique processing requirements, it is difficult to develop an efficient software framework to combine the processing of multiple heterogeneous sensors. Second, during normal operation of a heterogeneous wireless sensor network, if users insert or remove some environmental sensors, the entire WSN system should operate normally. In this work, in order to solve the above two system design challenges, we have developed a low-power, low-cost, small form-factor WSN development platform, and its software framework can perform efficient data acquisition, conversion, fusion, and packaging for multiple heterogeneous sensors. Our proposed software framework enables easy and rapid WSN system deployment without affecting the overall functionality of each node. The proposed design differs from existing WSN platforms in that it emphasizes advanced high-level usability and reduces time to market without sacrificing low-level features. The proposed WSN system has been implemented and tested in an office building for indoor fire hazard detection. The experimental results show that our software framework can successfully complete data acquisition, conversion, fusion, and packaging tasks for three heterogeneous environmental sensors. In addition, we have verified that our software framework supports robust system operation when inserting or removing sensors from an existing heterogeneous WSN system.

According to the U.S. Department of Energy, a significant portion of energy used in buildings is wasted. If the occupancy quantity in a pre-determined thermal zone is aware, a building automation system (BAS) is able to intelligently adjust the building operation to provide “just-enough” heating, cooling, and ventilation capacities to building users. Therefore, an occupancy counting device that can be widely deployed at low prices with low failure rate, small form-factor, good usability, and conserved user privacy is highly desirable. Existing occupancy detection or recognition sensors (e.g., passive infrared, camera, acoustic, RFID, CO2) cannot meet all these above system requirements. In this work, we present an IoT (Internet of Things) prototype that collects room occupancy information to assist in the operation of energy-efficient buildings. The proposed IoT prototype consists of Lattice iCE40-HX1K stick FPGA boards and Raspberry Pi modules. Two pairs of our prototypes are installed at a door frame. When a person walks through this door frame, blocking of active infrared streams between both pairs of IoT prototypes is detected. The direction of human movement is obtained through comparing occurrence time instances of two obstructive events. Thus, the change in occupancy quantity of a thermal zone is calculated and updated. Besides, an open-source application user interface is developed to allow anonymous users or building automation systems to easily acquire room occupancy information. We carry out a three-month random test of human entry and exit of a thermal zone, and find that the occupancy counting accuracy is 97%. The proposed design is completely made of off-the-shelf electronic components and the estimated cost is less than $160. To investigate the impact on building energy savings, we conduct a building energy simulation using EnergyPlus and find the payback period is approximately 4 months. In summary, the proposed design is miniature, non-intrusive, ease of use, low failure rate, and cost-effective for smart buildings.

An Intelligent Internet of Things (IoT) Sensor System for Building Environmental Monitoring

Demand-driven HVAC (heating, ventilation, and air conditioning) operation is essential in occupant-oriented smart buildings, where the levels of heating, cooling, and ventilation are intelligently regulated to avoid energy waste. Despite the great potential of building energy efficiency, one of the remaining technical challenges is how to accurately estimate building occupancy information in real time. In this paper, this design challenge is addressed. An advanced audio-processing technique is adopted that minimizes the impacts of environmental sounds on the recorded voice sounds of humans. Adopted mathematical modeling and signal processing procedures are elaborated in this work. Experimental studies show that our proposed audio processing with background sound cancellation algorithm improves the estimation accuracy of room occupancy quantity by approximately 11–12%, which results in an averaged ventilation energy reduction of 3.54% compared to the case of not applying background sound cancellation. The proposed audio-processing technique is promising to achieve non-intrusive, cost-effective, robust, and accurate solutions for building occupancy estimation.