Search

Low‐power localisation systems are crucial for machine‐to‐machine communication technologies. This article investigates LoRa technology for localisation using multiple features of the received signal, such as Received Signal Strength Indicator (RSSI), Spreading Factors (SF), and Signal to Noise Ratio (SNR). A novel range‐based technique to estimate the distance of a target node from a LoRa gateway using machine‐learning models that incorporates SF, SNR, and RSSI to train the models is proposed. A modified trilateration approach is then used to localise the target node from three gateways. Our experiment used three LoRaWAN gateways and two sensor nodes, on a sports oval with an approximate area coverage of 30,000 square metres. The authors also used a public LoRaWAN dataset to build a model test the proposed method and compare both range‐based distance mapping with trilateration and fingerprint‐based direct location estimation techniques. Our method achieved an average distance error of 43.97 m on our experimental dataset. The results show that the combination of RSSI, SNR, and SF‐based distance mapping provides ∼10% improvement on ranging accuracy and 26.58% higher accuracy for trilateration‐based localisation when compared with just using RSSI. Our method also achieved 50% superior localisation accuracy with fingerprint‐based direct location estimation approaches. Collection of a Global Positioning System‐independent low‐cost LoRa‐based localisation dataset. Machine learning‐based estimation of distance from multiple received signal features. Thorough performance analysis of LoRa localisation approaches.

The COVID-19 patient data for composite outcome prediction often comes with class imbalance issues, i.e., only a small group of patients develop severe composite events after hospital admission, while the rest do not. An ideal COVID-19 composite outcome prediction model should possess strong imbalanced learning capability. The model also should have fewer tuning hyperparameters to ensure good usability and exhibit potential for fast incremental learning. Towards this goal, this study proposes a novel imbalanced learning approach called Imbalanced maximizing-Area Under the Curve (AUC) Proximal Support Vector Machine (ImAUC-PSVM) by the means of classical PSVM to predict the composite outcomes of hospitalized COVID-19 patients within 30 days of hospitalization. ImAUC-PSVM offers the following merits: (1) it incorporates straightforward AUC maximization into the objective function, resulting in fewer parameters to tune. This makes it suitable for handling imbalanced COVID-19 data with a simplified training process. (2) Theoretical derivations reveal that ImAUC-PSVM has the same analytical solution form as PSVM, thus inheriting the advantages of PSVM for handling incremental COVID-19 cases through fast incremental updating. We built and internally and externally validated our proposed classifier using real COVID-19 patient data obtained from three separate sites of Mayo Clinic in the United States. Additionally, we validated it on public datasets using various performance metrics. Experimental results demonstrate that ImAUC-PSVM outperforms other methods in most cases, showcasing its potential to assist clinicians in triaging COVID-19 patients at an early stage in hospital settings, as well as in other prediction applications.

Context Insects are a major threat to crop production. They can infect, damage, and reduce agricultural yields. Accurate and fast detection of insects will help insect control. From a computer algorithm point of view, insect detection from imagery is a tiny object detection problem. Handling detection of tiny objects in large datasets is challenging due to small resolution of the insects in an image, and other nuisances such as occlusion, noise, and lack of features. Aims Our aim was to achieve a high-performance agricultural insect detector using an enhanced artificial intelligence machine learning technique. Methods We used a YOLOv3 network-based framework, which is a high performing and computationally fast object detector. We further improved the original feature pyramidal network of YOLOv3 by integrating an adaptive feature fusion module. For training the network, we first applied data augmentation techniques to regularise the dataset. Then, we trained the network using the adaptive features and optimised the hyper-parameters. Finally, we tested the proposed network on a subset dataset of the multi-class insect pest dataset Pest24, which contains 25878 images. Key results We achieved an accuracy of 72.10%, which is superior to existing techniques, while achieving a fast detection rate of 63.8 images per second. Conclusions We compared the results with several object detection models regarding detection accuracy and processing speed. The proposed method achieved superior performance both in terms of accuracy and computational speed. Implications The proposed method demonstrates that machine learning networks can provide a foundation for developing real-time systems that can help better pest control to reduce crop damage.

Context Most weed species can adversely impact agricultural productivity by competing for nutrients required by high-value crops. Manual weeding is not practical for large cropping areas. Many studies have been undertaken to develop automatic weed management systems for agricultural crops. In this process, one of the major tasks is to recognise the weeds from images. However, weed recognition is a challenging task. It is because weed and crop plants can be similar in colour, texture and shape which can be exacerbated further by the imaging conditions, geographic or weather conditions when the images are recorded. Advanced machine learning techniques can be used to recognise weeds from imagery. Aims In this paper, we have investigated five state-of-the-art deep neural networks, namely VGG16, ResNet-50, Inception-V3, Inception-ResNet-v2 and MobileNetV2, and evaluated their performance for weed recognition. Methods We have used several experimental settings and multiple dataset combinations. In particular, we constructed a large weed-crop dataset by combining several smaller datasets, mitigating class imbalance by data augmentation, and using this dataset in benchmarking the deep neural networks. We investigated the use of transfer learning techniques by preserving the pre-trained weights for extracting the features and fine-tuning them using the images of crop and weed datasets. Key results We found that VGG16 performed better than others on small-scale datasets, while ResNet-50 performed better than other deep networks on the large combined dataset. Conclusions This research shows that data augmentation and fine tuning techniques improve the performance of deep learning models for classifying crop and weed images. Implications This research evaluates the performance of several deep learning models and offers directions for using the most appropriate models as well as highlights the need for a large scale benchmark weed dataset.

The purpose of sentiment analysis is to detect an opinion or polarity in text data. We can apply such an analysis to detect negative sentiment, which represents the anomalous activities in operating system (OS) logs. Existing methods involve manual searching, predefined rules, or traditional machine learning techniques to detect such suspicious events. In this article, we propose a novel deep learning-based sentiment analysis technique to check whether there are anomalous activities in OS logs. Log messages are modeled as sentences and we identify the sentiments using the gated recurrent unit (GRU) networks. OS log datasets inherently have a class imbalance in the sense that the number of negative sentiment is much lower than that of the number of positive ones. In order to address the class imbalance, we build a GRU layer on top of a class imbalance solver using the Tomek link method. Experimental results demonstrate that the proposed method can detect anomalous events in OS logs with an overall F1 and accuracy of 99.84 and 99.93 percent, respectively.

This paper proposes a long-range (LoRa)-based outdoor localization and tracking method. Our method presents an unsupervised localization approach that utilizes symbolized LoRa received signal features, such as RSSI, SNR, and path loss, where each symbol represents a system state. To identify the partitioning boundaries between the symbols in time series, we employ maximum entropy partitioning. The D-Markov machine is used to construct nondeterministic finite-state automata for extracting temporal patterns. We incorporate the Chinese restaurant process for online estimation, especially in scenarios with an unbounded number of probable areas around each LoRa gateway. An adaptive trilateration approach is then used to localize the target node from the estimated ranged radii of areas. The point-wise localization data was used for time-series continuous tracking. We collected a dataset using three LoRaWAN gateways, sensor nodes powered by single-use batteries, and a Chirpstack server on a sports oval. We thoroughly evaluated the proposed method from the perspectives of localization accuracy and tracking capability. Our method outperformed state-of-the-art machine learning-driven range-based and fingerprint-based localization techniques.

In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks (CNNs) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects (using a CAD model) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.

Sound event detection (SED) has been widely applied in real world applications. Convolutional recurrent neural network based SED approaches have achieved state-of-the-art performance. However, the convolution process is typically performed by using a fixed sized kernel, which adversely affects the detection accuracy especially when the acoustic features of different event classes are characterized by high variations. To deal with this, this article proposes a sound event detection technique using a convolutional recurrent neural network framework with multiple convolutional kernels of different sizes. The top performing kernels are selected from a kernel pool based on the unsupervised clustering errors and the accuracies of the temporarily trained models. Afterwards, the selected kernels are fed to multiple convolution layers to deal with the acoustic feature variations. Experimental results on different subsets of AudioSet, namely the DCASE Challenge 2017 Task 4 and DCASE Challenge 2018 Task 4, demonstrate the performance of the proposed approach compared to state-of-the-art systems.

In this paper, we present an approach for acoustic scene classification, which aggregates spectral and temporal features. We do this by proposing the first use of the variable-Q transform (VQT) to generate the time-frequency representation for acoustic scene classification. The VQT provides finer control over the resolution compared to the constant-Q transform (CQT) or short time fourier transform and can be tuned to better capture acoustic scene information. We then adopt a variant of the local binary pattern (LBP), the adjacent evaluation completed LBP (AECLBP), which is better suited to extracting features from acoustic time-frequency images. Our results yield a 5.2% improvement on the DCASE 2016 dataset compared to the application of standard CQT with LBP. Fusing our proposed AECLBP with HOG features, we achieve a classification accuracy of 85.5%, which outperforms one of the top performing systems.

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes are abundant, making them an overrepresented majority, and data of other classes are scarce, making them an underrepresented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this paper, we propose a cost-sensitive (CoSen) deep neural network, which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class-dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multiclass problems without any modification. Moreover, as opposed to data-level approaches, we do not alter the original data distribution, which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification data sets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and CoSen classifiers demonstrate the superior performance of our proposed method.

Introduction:Machine learning models (MLM) hold promise for improved risk stratification and to guide personalized care.Hypothesis:MLM would outperform conventional statistical (CS) methods and existing iScore for predicting composite of recurrent stroke or death at 90 days and 3 years after ischemic stroke (IS)Methods:We built 3 MLM (random forest [RF], support vector machine [SVM], and extreme gradient boosting decision trees [XGBoost]) and two CS models (logistic regression [LR] and least absolute shrinkage and selection operator [LASSO]) to predict composite outcome at 90 days or 3 years after AIS in a retrospective cohort of 721 adults. The performance of these models was evaluated against the existing iScore to predict outcomes after AIS.Results:Composite outcome occurred in11% at 90 days and in 34% at 3 years after AIS. Performance metrics for predicting 90-day and 3-year composite outcome were comparable across all study models except SM LR. Measurements for the area under the receiver operating characteristic curve for each model in validation set was as follow. 1) 90-day prediction: 0.779 for RF, 0.771 for SVM, 0.772 for EXBOOST, 0.613 for LR, 0.811 for LASSO, and 0.720 for iScore; 2) 3-year prediction: 0.743 for RF, 0.777 for SVM, and 0.773 for EXBOOST, 0.724 for LR, 0.790 for LASSO, and 0.710 for iScore.Conclusions:ML-based algorithms did not improve prediction of composite outcome at 90 days or 3 years after AIS compared with CS-based LASSO. iScore was successfully validated and compared broadening its generalizability and applicability.