Leveraging Temporal Information to Improve Machine Learning-Based Calibration Techniques for Low-Cost Air Quality Sensors.

Low-cost ambient sensors have been identified as a promising technology for monitoring air pollution at a high spatio-temporal resolution. However, the pollutant data captured by these cost-effective sensors are less accurate than their conventional counterparts and require careful calibration to improve their accuracy and reliability. In this paper, we propose to leverage temporal information, such as the duration of time a sensor has been deployed and the time of day the reading was taken, in order to improve the calibration of low-cost sensors. This information is readily available and has so far not been utilized in the reported literature for the calibration of cost-effective ambient gas pollutant sensors. We make use of three data sets collected by research groups around the world, who gathered the data from field-deployed low-cost CO and NO2 sensors co-located with accurate reference sensors. Our investigation shows that using the temporal information as a co-variate can significantly improve the accuracy of common machine learning-based calibration techniques, such as Random Forest and Long Short-Term Memory.

Low-cost IoT based system for lake water quality monitoring.

Water quality monitoring is a critical process in maintaining the well-being of aquatic ecosystems and ensuring growth of the surrounding environment. Clean water supports and maintains the health, livelihoods, and ecological balance of the ecosystem as a whole. Regular assessment of water quality is essential to ensure clean and reliable water is available to everyone. This requires regular measurement of pollutants or contaminants in water that can be monitored in real-time. Hence, this research showcases a system that consists of low-cost sensors used to measure five basic parameters of water quality that are: turbidity, total dissolved solids, temperature, pH, and dissolved oxygen. The system incorporates electronics and IoT technology that are powered by a solar charged lead acid battery. The data gathered from the sensors was stored locally on a micro-SD card with live updates that could be viewed on a mobile device when in proximity to the system. Data was gathered from three different bodies of water over a span of three weeks, precisely during the seasonal transition from autumn to winter. We adopted a water sampling technique since our low-cost sensors were not designed for continuous submersion. The results show that the temperature drops gradually during this period and an inversely proportional relationship between pH and temperature could be observed. The concentration of total dissolved solids decreased during rainy periods with a variation in turbidity. The deployed system was robust and autonomous that effectively monitored the quality of water in real-time with scope of adding more sensors and employing Industry 4.0 paradigm to predict variations in water quality.

Electrochemical and Optical Sensors for Real-Time Detection of Nitrate in Water.

The health and integrity of our water sources are vital for the existence of all forms of life. However, with the growth in population and anthropogenic activities, the quality of water is being impacted globally, particularly due to a widespread problem of nitrate contamination that poses numerous health risks. To address this issue, investigations into various detection methods for the development of in situ real-time monitoring devices have attracted the attention of many researchers. Among the most prominent detection methods are chromatography, colorimetry, electrochemistry, and spectroscopy. While all these methods have their pros and cons, electrochemical and optical methods have emerged as robust and efficient techniques that offer cost-effective, accurate, sensitive, and reliable measurements. This review provides an overview of techniques that are ideal for field-deployable nitrate sensing applications, with an emphasis on electrochemical and optical detection methods. It discusses the underlying principles, recent advances, and various measurement techniques. Additionally, the review explores the current developments in real-time nitrate sensors and discusses the challenges of real-time implementation.

Low-Cost CO Sensor Calibration Using One Dimensional Convolutional Neural Network.

The advent of cost-effective sensors and the rise of the Internet of Things (IoT) presents the opportunity to monitor urban pollution at a high spatio-temporal resolution. However, these sensors suffer from poor accuracy that can be improved through calibration. In this paper, we propose to use One Dimensional Convolutional Neural Network (1DCNN) based calibration for low-cost carbon monoxide sensors and benchmark its performance against several Machine Learning (ML) based calibration techniques. We make use of three large data sets collected by research groups around the world from field-deployed low-cost sensors co-located with accurate reference sensors. Our investigation shows that 1DCNN performs consistently across all datasets. Gradient boosting regression, another ML technique that has not been widely explored for gas sensor calibration, also performs reasonably well. For all datasets, the introduction of temperature and relative humidity data improves the calibration accuracy. Cross-sensitivity to other pollutants can be exploited to improve the accuracy further. This suggests that low-cost sensors should be deployed as a suite or an array to measure covariate factors.

Low-Cost Sensor for Continuous Measurement of Brix in Liquids.

This paper presents a Brix sensor based on the differential pressure measurement principle. Two piezoresistive silicon pressure sensors were applied to measure the specific gravity of the liquid, which was used to calculate the Brix level. The pressure sensors were mounted inside custom-built water-tight housings connected together by fixed length metallic tubes containing the power and signal cables. Two designs of the sensor were prepared; one for the basic laboratory testing and validation of the proposed system and the other for a fermentation experiment. For lab tests, a sugar solution with different Brix levels was used and readings from the proposed sensor were compared with a commercially available hydrometer called Tilt. During the fermentation experiments, fermentation was carried out in a 1000 L tank over 7 days and data was recorded and analysed. In the lab experiments, a good linear relationship between the sugar content and the corresponding Brix levels was observed. In the fermentation experiment, the sensor performed as expected but some problems such as residue build up were encountered. Overall, the proposed sensing solution carries a great potential for continuous monitoring of the Brix level in liquids. Due to the usage of low-cost pressure sensors and the interface electronics, the cost of the system is considered suitable for large scale deployment at wineries or juice processing industries.

A weight optimization-based transfer learning approach for plant disease detection of New Zealand vegetables.

Deep learning (DL) is an effective approach to identifying plant diseases. Among several DL-based techniques, transfer learning (TL) produces significant results in terms of improved accuracy. However, the usefulness of TL has not yet been explored using weights optimized from agricultural datasets. Furthermore, the detection of plant diseases in different organs of various vegetables has not yet been performed using a trained/optimized DL model. Moreover, the presence/detection of multiple diseases in vegetable organs has not yet been investigated. To address these research gaps, a new dataset named NZDLPlantDisease-v2 has been collected for New Zealand vegetables. The dataset includes 28 healthy and defective organs of beans, broccoli, cabbage, cauliflower, kumara, peas, potato, and tomato. This paper presents a transfer learning method that optimizes weights obtained through agricultural datasets for better outcomes in plant disease identification. First, several DL architectures are compared to obtain the best-suited model, and then, data augmentation techniques are applied. The Faster Region-based Convolutional Neural Network (RCNN) Inception ResNet-v2 attained the highest mean average precision (mAP) compared to the other DL models including different versions of Faster RCNN, Single-Shot Multibox Detector (SSD), Region-based Fully Convolutional Networks (RFCN), RetinaNet, and EfficientDet. Next, weight optimization is performed on datasets including PlantVillage, NZDLPlantDisease-v1, and DeepWeeds using image resizers, interpolators, initializers, batch normalization, and DL optimizers. Updated/optimized weights are then used to retrain the Faster RCNN Inception ResNet-v2 model on the proposed dataset. Finally, the results are compared with the model trained/optimized using a large dataset, such as Common Objects in Context (COCO). The final mAP improves by 9.25% and is found to be 91.33%. Moreover, the robustness of the methodology is demonstrated by testing the final model on an external dataset and using the stratified k-fold cross-validation method.

All-Dielectric Transreflective Angle-Insensitive Near-Infrared (NIR) Filter.

This paper presents an all-dielectric, cascaded, multilayered, thin-film filter, allowing near-infrared filtration for spectral imaging applications. The proposed design is comprised of only eight layers of amorphous silicon (A-Si) and silicon nitride (Si3N4), successively deposited on a glass substrate. The finite difference time domain (FDTD) simulation results demonstrate a distinct peak in the near-infrared (NIR) region with transmission efficiency up to 70% and a full-width-at-half-maximum (FWHM) of 77 nm. The theoretical results are angle-insensitive up to 60∘ and show polarization insensitivity in the transverse magnetic (TM) and transverse electric (TE) modes. The theoretical response, obtained with the help of spectroscopic ellipsometry (SE), is in good agreement with the experimental result. Likewise, the experimental results for polarization insensitivity and angle invariance of the thin films are in unison with the theoretical results, having an angle invariance up to 50∘.

Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms.

The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.

Laser ablation assisted micropattern screen printed transduction electrodes for sensing applications.

In this work we present a facile method for the fabrication of several capacitive transduction electrodes for sensing applications. To prepare the electrodes, line widths up to 300 [Formula: see text]m were produced on polymethyl methacrylate (PMMA) substrate using a common workshop laser engraving machine. The geometries prepared with the laser ablation process were characterised by optical microscopy for consistency and accuracy. Later, the geometries were coated with functional polymer porous cellulose decorated sensing layer for humidity sensing. The resulting sensors were tested at various relative humidity (RH) levels. In general, good sensing response was produced by the sensors with sensitivities ranging from 0.13 to 2.37 pF/%RH. In ambient conditions the response time of 10 s was noticed for all the fabricated sensors. Moreover, experimental results show that the sensitivity of the fabricated sensors depends highly on the geometry and by changing the electrode geometry sensitivity increases up to 5 times can be achieved with the same sensing layer. The simplicity of the fabrication process and higher sensitivity resulting from the electrode designs is expected to enable the application of the proposed electrodes not only in air quality sensors but also in many other areas such as touch or tactile sensors.

Partial Biodegradable Blend for Fused Filament Fabrication: In-Process Thermal and Post-Printing Moisture Resistance.

Despite the extensive research, the moisture-based degradation of the 3D-printed polypropylene and polylactic acid blend is not yet reported. This research is a part of study reported on partial biodegradable blends proposed for large-scale additive manufacturing applications. However, the previous work does not provide information about the stability of the proposed blend system against moisture-based degradation. Therefore, this research presents a combination of excessive physical interlocking and minimum chemical grafting in a partial biodegradable blend to achieve stability against in-process thermal and moisture-based degradation. In this regard, a blend of polylactic acid and polypropylene compatibilized with polyethylene graft maleic anhydride is presented for fused filament fabrication. The research implements, for the first time, an ANOVA for combined thermal and moisture-based degradation. The results are explained using thermochemical and microscopic techniques. Scanning electron microscopy is used for analyzing the printed blend. Fourier transform infrared spectroscopy has allowed studying the intermolecular interactions due to the partial blending and degradation mechanism. Differential scanning calorimetry analyzes the blending (physical interlocking or chemical grafting) and thermochemical effects of the degradation mechanism. The thermogravimetric analysis further validates the physical interlocking and chemical grafting. The novel concept of partial blending with excessive interlocking reports high mechanical stability against moisture-based degradation.

Partial Biodegradable Blend with High Stability against Biodegradation for Fused Deposition Modeling.

This research presents a partial biodegradable polymeric blend aimed for large-scale fused deposition modeling (FDM). The literature reports partial biodegradable blends with high contents of fossil fuel-based polymers (>20%) that make them unfriendly to the ecosystem. Furthermore, the reported polymer systems neither present good mechanical strength nor have been investigated in vulnerable environments that results in biodegradation. This research, as a continuity of previous work, presents the stability against biodegradability of a partial biodegradable blend prepared with polylactic acid (PLA) and polypropylene (PP). The blend is designed with intended excess physical interlocking and sufficient chemical grafting, which has only been investigated for thermal and hydrolytic degradation before by the same authors. The research presents, for the first time, ANOVA analysis for the statistical evaluation of endurance against biodegradability. The statistical results are complemented with thermochemical and visual analysis. Fourier transform infrared spectroscopy (FTIR) determines the signs of intermolecular interactions that are further confirmed by differential scanning calorimetry (DSC). The thermochemical interactions observed in FTIR and DSC are validated with thermogravimetric analysis (TGA). Scanning electron microscopy (SEM) is also used as a visual technique to affirm the physical interlocking. It is concluded that the blend exhibits high stability against soil biodegradation in terms of high mechanical strength and high mass retention percentage.

Sensors and Instruments for Brix Measurement: A Review.

Quality assessment of fruits, vegetables, or beverages involves classifying the products according to the quality traits such as, appearance, texture, flavor, sugar content. The measurement of sugar content, or Brix, as it is commonly known, is an essential part of the quality analysis of the agricultural products and alcoholic beverages. The Brix monitoring of fruit and vegetables by destructive methods includes sensory assessment involving sensory panels, instruments such as refractometer, hydrometer, and liquid chromatography. However, these techniques are manual, time-consuming, and most importantly, the fruits or vegetables are damaged during testing. On the other hand, the traditional sample-based methods involve manual sample collection of the liquid from the tank in fruit/vegetable juice making and in wineries or breweries. Labour ineffectiveness can be a significant drawback of such methods. This review presents recent developments in different destructive and nondestructive Brix measurement techniques focused on fruits, vegetables, and beverages. It is concluded that while there exist a variety of methods and instruments for Brix measurement, traits such as promptness and low cost of analysis, minimal sample preparation, and environmental friendliness are still among the prime requirements of the industry.

Partial Polymer Blend for Fused Filament Fabrication with High Thermal Stability.

The materials for large scale fused filament fabrication (FFF) are not yet designed to resist thermal degradation. This research presents a novel polymer blend of polylactic acid with polypropylene for FFF, purposefully designed with minimum feasible chemical grafting and overwhelming physical interlocking to sustain thermal degradation. Multi-level general full factorial ANOVA is performed for the analysis of thermal effects. The statistical results are further investigated and validated using different thermo-chemical and visual techniques. For example, Fourier transform infrared spectroscopy (FTIR) analyzes the effects of blending and degradation on intermolecular interactions. Differential scanning calorimetry (DSC) investigates the nature of blending (grafting or interlocking) and effects of degradation on thermal properties. Thermogravimetric analysis (TGA) validates the extent of chemical grafting and physical interlocking detected in FTIR and DSC. Scanning electron microscopy (SEM) is used to analyze the morphology and phase separation. The novel approach of overwhelmed physical interlocking and minimum chemical grafting for manufacturing 3D printing blends results in high structural stability (mechanical and intermolecular) against thermal degradation as compared to neat PLA.

Study of Microchannels Fabricated Using Desktop Fused Deposition Modeling Systems.

Microfluidic devices are used to transfer small quantities of liquid through micro-scale channels. Conventionally, these devices are fabricated using techniques such as soft-lithography, paper microfluidics, micromachining, injection moulding, etc. The advancement in modern additive manufacturing methods is making three dimensional printing (3DP) a promising platform for the fabrication of microfluidic devices. Particularly, the availability of low-cost desktop 3D printers can produce inexpensive microfluidic devices in fast turnaround times. In this paper, we explore fused deposition modelling (FDM) to print non-transparent and closed internal micro features of in-plane microchannels (i.e., linear, curved and spiral channel profiles) and varying cross-section microchannels in the build direction (i.e., helical microchannel). The study provides a comparison of the minimum possible diameter size, the maximum possible fluid flow-rate without leakage, and absorption through the straight, curved, spiral and helical microchannels along with the printing accuracy of the FDM process for two low-cost desktop printers. Moreover, we highlight the geometry dependent printing issues of microchannels, pressure developed in the microchannels for complex geometry and establish that the profiles in which flowrate generates 4000 Pa are susceptible to leakages when no pre or post processing in the FDM printed parts is employed.

Image-Based Plant Disease Identification by Deep Learning Meta-Architectures.

The identification of plant disease is an imperative part of crop monitoring systems. Computer vision and deep learning (DL) techniques have been proven to be state-of-the-art to address various agricultural problems. This research performed the complex tasks of localization and classification of the disease in plant leaves. In this regard, three DL meta-architectures including the Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Networks (RFCN) were applied by using the TensorFlow object detection framework. All the DL models were trained/tested on a controlled environment dataset to recognize the disease in plant species. Moreover, an improvement in the mean average precision of the best-obtained deep learning architecture was attempted through different state-of-the-art deep learning optimizers. The SSD model trained with an Adam optimizer exhibited the highest mean average precision (mAP) of 73.07%. The successful identification of 26 different types of defected and 12 types of healthy leaves in a single framework proved the novelty of the work. In the future, the proposed detection methodology can also be adopted for other agricultural applications. Moreover, the generated weights can be reused for future real-time detection of plant disease in a controlled/uncontrolled environment.

Plant Disease Classification: A Comparative Evaluation of Convolutional Neural Networks and Deep Learning Optimizers.

Recently, plant disease classification has been done by various state-of-the-art deep learning (DL) architectures on the publicly available/author generated datasets. This research proposed the deep learning-based comparative evaluation for the classification of plant disease in two steps. Firstly, the best convolutional neural network (CNN) was obtained by conducting a comparative analysis among well-known CNN architectures along with modified and cascaded/hybrid versions of some of the DL models proposed in the recent researches. Secondly, the performance of the best-obtained model was attempted to improve by training through various deep learning optimizers. The comparison between various CNNs was based on performance metrics such as validation accuracy/loss, F1-score, and the required number of epochs. All the selected DL architectures were trained in the PlantVillage dataset which contains 26 different diseases belonging to 14 respective plant species. Keras with TensorFlow backend was used to train deep learning architectures. It is concluded that the Xception architecture trained with the Adam optimizer attained the highest validation accuracy and F1-score of 99.81% and 0.9978 respectively which is comparatively better than the previous approaches and it proves the novelty of the work. Therefore, the method proposed in this research can be applied to other agricultural applications for transparent detection and classification purposes.

Nanostructured Color Filters: A Review of Recent Developments.

Color plays an important role in human life: without it life would be dull and monochromatic. Printing color with distinct characteristics, like hue, brightness and saturation, and high resolution, are the main characteristic of image sensing devices. A flexible design of color filter is also desired for angle insensitivity and independence of direction of polarization of incident light. Furthermore, it is important that the designed filter be compatible with the image sensing devices in terms of technology and size. Therefore, color filter requires special care in its design, operation and integration. In this paper, we present a comprehensive review of nanostructured color filter designs described to date and evaluate them in terms of their performance.

Acrylonitrile Butadiene Styrene and Polypropylene Blend with Enhanced Thermal and Mechanical Properties for Fused Filament Fabrication.

Acrylonitrile butadiene styrene (ABS) is the oldest fused filament fabrication (FFF) material that shows low stability to thermal aging due to hydrogen abstraction of the butadiene monomer. A novel blend of ABS, polypropylene (PP), and polyethylene graft maleic anhydride (PE-g-MAH) is presented for FFF. ANOVA was used to analyze the effects of three variables (bed temperature, printing temperature, and aging interval) on tensile properties of the specimens made on a custom-built pellet printer. The compression and flexure properties were also investigated for the highest thermal combinations. The blend showed high thermal stability with enhanced strength despite three days of aging, as well as high bed and printing temperatures. Fourier-transform infrared spectroscopy (FTIR) provided significant chemical interactions. Differential scanning calorimetry (DSC) confirmed the thermal stability with enhanced enthalpy of glass transition and melting. Thermogravimetric analysis (TGA) also revealed high temperatures for onset and 50% mass degradation. Signs of chemical grafting and physical interlocking in scanning electron microscopy (SEM) also explained the thermo-mechanical stability of the blend.

A Comprehensive Review of Microfluidic Water Quality Monitoring Sensors.

Water crisis is a global issue due to water contamination and extremely restricted sources of fresh water. Water contamination induces severe diseases which put human lives at risk. Hence, water quality monitoring has become a prime activity worldwide. The available monitoring procedures are inadequate as most of them require expensive instrumentation, longer processing time, tedious processes, and skilled lab technicians. Therefore, a portable, sensitive, and selective sensor with in situ and continuous water quality monitoring is the current necessity. In this context, microfluidics is the promising technology to fulfill this need due to its advantages such as faster reaction times, better process control, reduced waste generation, system compactness and parallelization, reduced cost, and disposability. This paper presents a review on the latest enhancements of microfluidic-based electrochemical and optical sensors for water quality monitoring and discusses the relative merits and shortcomings of the methods.

Effect of Material and Process Specific Factors on the Strength of Printed Parts in Fused Filament Fabrication: A Review of Recent Developments.

Additive manufacturing (AM) is rapidly evolving as the most comprehensive tool to manufacture products ranging from prototypes to various end-user applications. Fused filament fabrication (FFF) is the most widely used AM technique due to its ability to manufacture complex and relatively high strength parts from many low-cost materials. Generally, the high strength of the printed parts in FFF is attributed to the research in materials and respective process factors (process variables, physical setup, and ambient temperature). However, these factors have not been rigorously reviewed for analyzing their effects on the strength and ductility of different classes of materials. This review systematically elaborates the relationship between materials and the corresponding process factors. The main focus is on the strength and ductility. A hierarchical approach is used to analyze the materials, process parameters, and void control before identifying existing research gaps and future research directions.