Journal Articles
Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915
Browse
Search Results
Item Static Hand Gesture Recognition Using Capacitive Sensing and Machine Learning(MDPI AG, 24/03/2023) Noble F; Xu M; Alam FAutomated hand gesture recognition is a key enabler of Human-to-Machine Interfaces (HMIs) and smart living. This paper reports the development and testing of a static hand gesture recognition system using capacitive sensing. Our system consists of a 6×18 array of capacitive sensors that captured five gestures-Palm, Fist, Middle, OK, and Index-of five participants to create a dataset of gesture images. The dataset was used to train Decision Tree, Naïve Bayes, Multi-Layer Perceptron (MLP) neural network, and Convolutional Neural Network (CNN) classifiers. Each classifier was trained five times; each time, the classifier was trained using four different participants' gestures and tested with one different participant's gestures. The MLP classifier performed the best, achieving an average accuracy of 96.87% and an average F1 score of 92.16%. This demonstrates that the proposed system can accurately recognize hand gestures and that capacitive sensing is a viable method for implementing a non-contact, static hand gesture recognition system.Item Weed Detection by Faster RCNN Model: An Enhanced Anchor Box Approach(MDPI AG, 29/06/2022) Saleem MH; Potgieter J; Arif KMTo apply weed control treatments effectively, the weeds must be accurately detected. Deep learning (DL) has been quite successful in performing the weed identification task. However, various aspects of the DL have not been explored in previous studies. This research aimed to achieve a high average precision (AP) of eight classes of weeds and a negative (non-weed) class, using the DeepWeeds dataset. In this regard, a DL-based two-step methodology has been proposed. This article is the second stage of the research, while the first stage has already been published. The former phase presented a weed detection pipeline and consisted of the evaluation of various neural networks, image resizers, and weight optimization techniques. Although a significant improvement in the mean average precision (mAP) was attained. However, the Chinee apple weed did not reach a high average precision. This result provided a solid ground for the next stage of the study. Hence, this paper presents an in-depth analysis of the Faster Region-based Convolutional Neural Network (RCNN) with ResNet-101, the best-obtained model in the past step. The architectural details of the Faster RCNN model have been thoroughly studied to investigate each class of weeds. It was empirically found that the generation of anchor boxes affects the training and testing performance of the Faster RCNN model. An enhancement to the anchor box scales and aspect ratios has been attempted by various combinations. The final results, with the addition of 64 × 64 scale size, and aspect ratio of 1:3 and 3:1, produced the best classification and localization of all classes of weeds and a negative class. An enhancement of 24.95% AP was obtained in Chinee apple weed. Furthermore, the mAP was improved by 2.58%. The robustness of the approach has been shown by the stratified k-fold cross-validation technique and testing on an external dataset.Item The potential reduction of carbon dioxide (CO2) emissions from gas flaring in Nigeria’s oil and gas industry through alternative productive use(MDPI, 23/11/2016) Otene IJJ; Murray PE; Enongene KE; Levy, JK; Yu, PGlobally, climate change and its adverse effects on the human population and the environment has necessitated significant research on the sustainable use of natural resources. Gas flaring in Nigeria’s oil and gas industry causes environmental and health hazards and to a large extent, culminates in yearly loss of the Nation’s revenue. The aim of the study is to highlight the potentials of converting flared gas from the Nigerian oil and gas industry to compressed natural gas (CNG) which could be an alternative fuel for the 220 Lagos Bus Rapid Transit (BRT-Lite) while reducing CO2 emissions. In addition, the study provided an overview of gas flaring in the oil and gas industry and energy utilisation in some selected sectors in the country. The Long-range Energy Alternative Planning System (LEAP) software was employed to model the energy demand and carbon dioxide emissions from the BRT-Lite by creating a current scenario and projections to the year 2030. The use of CNG as an alternative fuel for Lagos BRT-Lite will significantly reduce CO2 emissions in Nigeria’s oil and gas industry. Other utilization options for flared gas from this industry includes: Liquefied Natural Gas (LNG), Liquefied Petroleum Gas (LPG), and power generationItem Changes in the welfare of an injured working farm dog assessed using the Five Domains Model(21/09/2016) Littlewood KE; Mellor DJ© 2016 by the authors; licensee MDPI, Basel, Switzerland.The present structured, systematic and comprehensive welfare evaluation of an injured working farm dog using the Five Domains Model is of interest in its own right. It is also an example for others wanting to apply the Model to welfare evaluations in different species and contexts. Six stages of a fictitious scenario involving the dog are considered: (1) its on-farm circumstances before one hind leg is injured; (2) its entanglement in barbed wire, cutting it free and transporting it to a veterinary clinic; (3) the initial veterinary examination and overnight stay; (4) amputation of the limb and immediate post-operative recovery; (5) its first four weeks after rehoming to a lifestyle block; and (6) its subsequent life as an amputee and pet. Not all features of the scenario represent average-to-good practice; indeed, some have been selected to indicate poor practice. It is shown how the Model can draw attention to areas of animal welfare concern and, importantly, to how welfare enhancement may be impeded or facilitated. Also illustrated is how the welfare implications of a sequence of events can be traced and evaluated, and, in relation to specific situations, how the degrees of welfare compromise and enhancement may be graded. In addition, the choice of a companion animal, contrasting its welfare status as a working dog and pet, and considering its treatment in a veterinary clinical setting, help to highlight various welfare impacts of some practices. By focussing attention on welfare problems, the Model can guide the implementation of remedies, including ways of promoting positive welfare states. Finally, wider applications of the Five Domains Model are noted: by enabling both negative and positive welfare-relevant experiences to be graded, the Model can be applied to quality of life assessments and end-of-life decisions and, with particular regard to negativeexperiences, the Model can also help to strengthen expert witness testimony during prosecutions for serious ill treatment of animals.Item Low-Cost Sensor for Continuous Measurement of Brix in Liquids(MDPI AG, 25/11/2022) Jaywant SA; Singh H; Arif KThis 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.Item Growth and Body Composition of Artificially-Reared Lambs Exposed to Three Different Rearing Regimens.(24/11/2021) Herath HMGP; Pain SJ; Kenyon PR; Blair HT; Morel PCHThis study was designed to investigate the influence of pellet fibre level, milk replacer composition and age at weaning on growth and body composition of lambs reared artificially. Romney ram lambs were randomly allocated to one of three rearing treatments; HFP57: commercial milk replacer to 57 days of age, and high fibre concentrate pellets; HFP42: commercial milk replacer with early weaning at 42 days of age, and high fibre concentrate pellets; LFP42: high protein milk replacer from 2-16 days of age followed by commercial milk replacer with early weaning at 42 days of age, and low fibre concentrate pellets. Lambs were slaughtered at 57 days of age. Overall average daily liveweight gain of lambs did not differ (p > 0.05) between treatments. Dressing out percentage, carcass weight, empty small intestine and omental fat were higher (p < 0.05) in HFP57 than in both HFP42 and LFP42 lambs. HFP42 and LFP42 lambs had heavier (p < 0.05) empty rumen weights. Whole body protein content was higher (p < 0.05) in HFP42 lambs compared to both HFP57 and LFP42 lambs. Fat content and daily fat deposition were greater (p < 0.05) in HFP57 lambs than HFP42 and LFP42 lambs. Weaning lambs at 42 days of age with provision of either low or high fibre concentrate pellets, resulted in similar growth rates, reduced whole body fat deposition and was a more cost-effective rearing regimen.Item Identity and Gender Recognition Using a Capacitive Sensing Floor and Neural Networks(MDPI AG, 23/09/2022) Konings D; Alam F; Faulkner N; de Jong CIn recent publications, capacitive sensing floors have been shown to be able to localize individuals in an unobtrusive manner. This paper demonstrates that it might be possible to utilize the walking characteristics extracted from a capacitive floor to recognize subject and gender. Several neural network-based machine learning techniques are developed for recognizing the gender and identity of a target. These algorithms were trained and validated using a dataset constructed from the information captured from 23 subjects while walking, alone, on the sensing floor. A deep neural network comprising a Bi-directional Long Short-Term Memory (BLSTM) provided the most accurate identity performance, classifying individuals with an accuracy of 98.12% on the test data. On the other hand, a Convolutional Neural Network (CNN) was the most accurate for gender recognition, attaining an accuracy of 93.3%. The neural network-based algorithms are benchmarked against Support Vector Machine (SVM), which is a classifier used in many reported works for floor-based recognition tasks. The majority of the neural networks outperform SVM across all accuracy metrics.Item Analysis of Failure to Finish a Race in a Cohort of Thoroughbred Racehorses in New Zealand.(25/05/2016) Tanner J; Rogers C; Bolwell C; Cogger N; Gee E; Mcllwraith WThe objective was to describe the incidence of failure to finish a race in flat-racing Thoroughbreds in New Zealand as these are summary indicators of falls, injuries and poor performance. Retrospective data on six complete flat racing seasons (n = 188,615 race starts) of all Thoroughbred flat race starts from 1 August 2005 to 31 July 2011 were obtained. The incidence of failure to finish events and binomial exact 95% confidence intervals were calculated per 1000 horse starts. The association between horse-, rider- and race-level variables with the outcomes failure to finish, pulled-up/fell and lost rider were examined with a mixed effects Poisson regression model. A total of 544 horses failed to finish in 188,615 race starts with an overall incidence of 2.88 per 1000 horse starts (95% CI 2.64-3.12). The incidence of failure to finish horses across each race year showed little variability. In the univariable analysis race distance, larger field size, season, and ratings bands showed association with failing to finish a race. The overall failure to finish outcome was associated with season, race distance and ratings bands (horse experience and success ranking criteria). In the multivariable analysis, race distance and ratings bands were associated with horses that pulled-up/fell; season, apprentice allowances and ratings bands were associated with the outcome lost rider. The failure to finish rate was lower than international figures for race day catastrophic injury. Racing and environmental variables were associated with failure to finish a race highlighting the multifactorial nature of race-day events. Further investigation of risk factors for failure to finish is required to better understand the reasons for a low failure to finish rate in Thoroughbred flat races in New Zealand.Item A Novel Weighted Clustering Algorithm Supported by a Distributed Architecture for D2D Enabled Content-Centric Networks(MDPI (Basel, Switzerland), 25/09/2020) Aslam S; Alam F; Hasan S; Rashid MNext generation cellular systems need efficient content-distribution schemes. Content-sharing via Device-to-Device (D2D) clustered networks has emerged as a popular approach for alleviating the burden on the cellular network. In this article, we utilize Content-Centric Networking and Network Virtualization to propose a distributed architecture, that supports efficient content delivery. We propose to use clustering at the user level for content-distribution. A weighted multifactor clustering algorithm is proposed for grouping the D2D User Equipment (DUEs) sharing a common interest. The proposed algorithm is evaluated in terms of energy efficiency, area spectral efficiency, and throughput. The effect of the number of clusters on these performance parameters is also discussed. The proposed algorithm has been further modified to allow for a tradeoff between fairness and other performance parameters. A comprehensive simulation study demonstrates that the proposed clustering algorithm is more flexible and outperforms several classical and state-of-the-art algorithms.Item Characterization of the Volatile Profiles of Six Industrial Hemp (Cannabis sativa L.) Cultivars(American Society of Agronomy, 27/10/2022) Sofkova-Bobcheva SVolatile organic compounds (VOCs) play an important role in plant ecology and can be useful in pest management. This work characterises, for the first time, the VOC emissions of six industrial hemp (Cannabis sativa L.) cultivars grown in New Zealand: CFX-2, CRS-1, Ferimon 12, Katani, Futura 75, and Finola. Volatiles emitted from flowers and foliage of eight-week-old plants were collected using a dynamic headspace sampling method and analysed using gas chromatography coupled to mass spectrometry. We assessed the effect of cultivar, sex (monoecious, male, and female), and site (i.e., two sites differing in soil types, maintained under irrigation and rain-fed conditions) on VOC emissions. Thirty-five volatile compounds were tentatively identified from the headspace samples of hemp plants, but none of the cultivars emitted all 35 compounds. β-Myrcene was the most abundant compound in most cultivars. Overall, there was a significant effect of sex, and the interaction of sex and cultivar on the volatile profiles, but no effect of site. Female plants typically emitted more volatiles than their male counterparts and monoecious cultivars. The main compounds driving the difference between cultivars and sexes were (Z)- and (E)-β-ocimene. We hypothesize that differences in emission emerged as a defence strategy to protect costly female flowers from herbivores (since C. sativa is wind pollinated), but this hypothesis needs further testing. We recommend additional studies exploring how biotic and abiotic factors influence hemp VOC emissions, changes in VOCs throughout the crop cycle, the role of VOCs in plant-insect interactions and their use in pest management.
