AI, Volume 4, Issue 1 (March 2023) – 17 articles

In this study, a basic insect detection system consisting of a manual-focus camera, a Jetson Nano—a low-cost, low-power single-board computer, and a trained deep learning model was developed. The model was validated through a live visual feed. Detecting, classifying, and monitoring insect pests in a grain storage or food facility in real time is vital to making insect control decisions. The camera captures the image of the insect and passes it to a Jetson Nano for processing. The Jetson Nano runs a trained deep-learning model to detect the presence and species of insects. With three different lighting situations: white LED light, yellow LED light, and no lighting condition, the detection results are displayed on a monitor. Validating using F1 scores and comparing the accuracy based on light sources, the system was tested with a variety of stored grain insect pests and was able to detect and classify adult cigarette beetles and warehouse beetles with acceptable accuracy. The results demonstrate that the system is an effective and affordable automated solution to insect detection. Such an automated insect detection system can help reduce pest control costs and save producers time and energy while safeguarding the quality of stored products. Full article

Understanding different aspects of public concerns and sentiments during large health emergencies, such as the COVID-19 pandemic, is essential for public health agencies to develop effective communication strategies, deliver up-to-date and accurate health information, and mitigate potential impacts of emerging misinformation. Current infoveillance systems generally focus on discussion intensity (i.e., number of relevant posts) as an approximation of public awareness, while largely ignoring the rich and diverse information in texts with granular information of varying public concerns and sentiments. In this study, we address this grand challenge by developing a novel natural language processing (NLP) infoveillance workflow based on bidirectional encoder representation from transformers (BERT). We first used a smaller COVID-19 tweet sample to develop a content classification and sentiment analysis model using COVID-Twitter-BERT. The classification accuracy was between 0.77 and 0.88 across the five identified topics. In the sentiment analysis with a three-class classification task (positive/negative/neutral), BERT achieved decent accuracy, 0.7. We then applied the content topic and sentiment classifiers to a much larger dataset with more than 4 million tweets in a 15-month period. We specifically analyzed non-pharmaceutical intervention (NPI) and social issue content topics. There were significant differences in terms of public awareness and sentiment towards the overall COVID-19, NPI, and social issue content topics across time and space. In addition, key events were also identified to associate with abrupt sentiment changes towards NPIs and social issues. This novel NLP-based AI workflow can be readily adopted for real-time granular content topic and sentiment infoveillance beyond the health context. Full article

Context: In cancer centres and hospitals particularly during the pandemic, there was a great demand for information, which could hardly be handled by the limited manpower available. This necessitated the development of an educational chatbot to disseminate topics in radiotherapy customized for various user groups, such as patients and their families, the general public and radiation staff. Objective: In response to the clinical demands, the objective of this work is to explore how to design a chatbot for educational purposes in radiotherapy using artificial intelligence. Methods: The chatbot is designed using the dialogue tree and layered structure, incorporated with artificial intelligence features such as natural language processing (NLP). This chatbot can be created in most platforms such as the IBM Watson Assistant and deposited in a website or various social media. Results: Based on the question-and-answer approach, the chatbot can provide humanlike communication to users requesting information on radiotherapy. At times, the user, often worried, may not be able to pinpoint the question exactly. Thus, the chatbot will be user friendly and reassuring, offering a list of questions for the user to select. The NLP system helps the chatbot to predict the intent of the user so as to provide the most accurate and precise response to him or her. It is found that the preferred educational features in a chatbot are functional features such as mathematical operations, which should be updated and modified routinely to provide new contents and features. Conclusions: It is concluded that an educational chatbot can be created using artificial intelligence to provide information transfer to users with different backgrounds in radiotherapy. In addition, testing and evaluating the performance of the chatbot is important, in response to user’s feedback to further upgrade and fine-tune the chatbot. Full article

In this paper, a computational framework is proposed that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models that are currently stored in public databases in SBML. With the proposed framework, existing SBML models may be redesigned into hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and uploaded in model databases, where they may be further analyzed as regular SBML models. This approach is illustrated with three well-known case studies: the Escherichia coli threonine synthesis model, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications. Full article

Computer vision is a branch of computer science that studies how computers can ‘see’. It is a field that provides significant value for advancements in academia and artificial intelligence by processing images captured with a camera. In other words, the purpose of computer vision is to impart computers with the functions of human eyes and realise ‘vision’ among computers. Deep learning is a method of realising computer vision using image recognition and object detection technologies. Since its emergence, computer vision has evolved rapidly with the development of deep learning and has significantly improved image recognition accuracy. Moreover, an expert system can imitate and reproduce the flow of reasoning and decision making executed in human experts’ brains to derive optimal solutions. Machine learning, including deep learning, has made it possible to ‘acquire the tacit knowledge of experts’, which was not previously achievable with conventional expert systems. Machine learning ‘systematises tacit knowledge’ based on big data and measures phenomena from multiple angles and in large quantities. In this review, we discuss some knowledge-based computer vision techniques that employ deep learning. Full article

This manuscript compares deterministic artificial intelligence to a model-following control applied to DC motor control, including an evaluation of the threshold computation rate to let unmanned underwater vehicles correctly follow the challenging discontinuous square wave command signal. The approaches presented in the main text are validated by simulations in MATLAB^®, where the motor process is discretized at multiple step sizes, which is inversely proportional to the computation rate. Performance is compared to canonical benchmarks that are evaluated by the error mean and standard deviation. With a large step size, discrete deterministic artificial intelligence shows a larger error mean than the model-following self-turning regulator approach (the selected benchmark). However, the performance improves with a decreasing step size. The error mean is close to the continuous deterministic artificial intelligence when the step size is reduced to 0.2 s, which means that the computation rate and the sampling period restrict discrete deterministic artificial intelligence. In that case, continuous deterministic artificial intelligence is the most feasible and reliable selection for future applications on unmanned underwater vehicles, since it is superior to all the approaches investigated at multiple computation rates. Full article

Over the years, detecting stable communities in a complex network has been a major challenge in network science. The global and local structures help to detect communities from different perspectives. However, previous methods based on them suffer from high complexity and fall into local optimum, respectively. The Four-Stage Algorithm (FSA) is proposed to reduce these issues and to allocate nodes to stable communities. Balancing global and local information, as well as accuracy and time complexity, while ensuring the allocation of nodes to stable communities, are the fundamental goals of this research. The Four-Stage Algorithm (FSA) is described and demonstrated using four real-world data with ground truth and three real networks without ground truth. In addition, it is evaluated with the results of seven community detection methods: Three-stage algorithm (TS), Louvain, Infomap, Fastgreedy, Walktrap, Eigenvector, and Label propagation (LPA). Experimental results on seven real network data sets show the effectiveness of our proposed approach and confirm that it is sufficiently capable of identifying those communities that are more desirable. The experimental results confirm that the proposed method can detect more stable and assured communities. For future work, deep learning methods can also be used to extract semantic content features that are more beneficial to investigating networks. Full article

In many manufacturing systems, anomaly detection is critical to identifying process errors and ensuring product quality. This paper proposes three semi-supervised solutions to detect anomalies in Direct Current (DC) Nut Runner engine assembly processes. The nut runner process is a challenging anomaly detection problem due to the manual nature of the process inducing high variability and ambiguity of the anomalous class. These characteristics lead to a scenario where anomalies are not outliers, and the normal operating conditions are difficult to define. To address these challenges, a Gaussian Mixture Model (GMM) was trained using a semi-supervised approach. Three dimensionality reduction methods were compared in pre-processing: PCA, t-SNE, and UMAP. These approaches are demonstrated to outperform the current approaches used by a major automotive company on two real-world datasets. Furthermore, a novel approach to labelling real-world data is proposed, including the concept of an ‘Anomaly No Concern’ class, in addition to the traditional labels of ‘Anomaly’ and ‘Normal’. Introducing this new term helped address knowledge gaps between data scientists and domain experts, as well as providing new insights during model development and testing. This represents a major advancement in identifying anomalies in manual production processes that use handheld tools. Full article

Besides the many advances made in the facial detection and recognition fields, face recognition applied to visual images (VIS-FR) has received increasing interest in recent years, especially in the field of communication, identity authentication, public safety and to address the risk of terrorism and crime. These systems however encounter important problems in the presence of variations in pose, expression, age, occlusion, disguise, and lighting as these factors significantly reduce the recognition accuracy. To prevent problems in the visible spectrum, several researchers have recommended the use of infrared images. This paper provides an updated overview of deep infrared (IR) approaches in face recognition (FR) and analysis. First, we present the most widely used databases, both public and private, and the various metrics and loss functions that have been proposed and used in deep infrared techniques. We then review deep face analysis and recognition/identification methods proposed in recent years. In this review, we show that infrared techniques have given interesting results for face recognition, solving some of the problems encountered with visible spectrum techniques. We finally identify some weaknesses of current infrared FR approaches as well as many future research directions to address the IR FR limitations. Full article

In many industrialized and developing nations, credit cards are one of the most widely used methods of payment for online transactions. Credit card invention has streamlined, facilitated, and enhanced internet transactions. It has, however, also given criminals more opportunities to commit fraud, which has raised the rate of fraud. Credit card fraud has a concerning global impact; many businesses and ordinary users have lost millions of US dollars as a result. Since there is a large number of transactions, many businesses and organizations rely heavily on applying machine learning techniques to automatically classify or identify fraudulent transactions. As the performance of machine learning techniques greatly depends on the quality of the training data, the imbalance in the data is not a trivial issue. In general, only a small percentage of fraudulent transactions are presented in the data. This greatly affects the performance of machine learning classifiers. In order to deal with the rarity of fraudulent occurrences, this paper investigates a variety of data augmentation techniques to address the imbalanced data problem and introduces a new data augmentation model, K-CGAN, for credit card fraud detection. A number of the main classification techniques are then used to evaluate the performance of the augmentation techniques. These results show that B-SMOTE, K-CGAN, and SMOTE have the highest Precision and Recall compared with other augmentation methods. Among those, K-CGAN has the highest F1 Score and Accuracy. Full article

Annotation tools are an essential component in the creation of datasets for machine learning purposes. Annotation tools have evolved greatly since the turn of the century, and now commonly include collaborative features to divide labor efficiently, as well as automation employed to amplify human efforts. Recent developments in machine learning models, such as Transformers, allow for training upon very large and sophisticated multimodal datasets and enable generalization across domains of knowledge. These models also herald an increasing emphasis on prompt engineering to provide qualitative fine-tuning upon the model itself, adding a novel emerging layer of direct machine learning annotation. These capabilities enable machine intelligence to recognize, predict, and emulate human behavior with much greater accuracy and nuance, a noted shortfall of which have contributed to algorithmic injustice in previous techniques. However, the scale and complexity of training data required for multimodal models presents engineering challenges. Best practices for conducting annotation for large multimodal models in the most safe and ethical, yet efficient, manner have not been established. This paper presents a systematic literature review of crowd and machine learning augmented behavioral annotation methods to distill practices that may have value in multimodal implementations, cross-correlated across disciplines. Research questions were defined to provide an overview of the evolution of augmented behavioral annotation tools in the past, in relation to the present state of the art. (Contains five figures and four tables). Full article

Numerous publications showing that robust prediction models for microorganisms based on Raman micro-spectroscopy in combination with chemometric methods are feasible, often with very precise predictions. Advances in machine learning and easier accessibility to software make it increasingly easy for users to generate predictive models from complex data. However, the question regarding why those predictions are so accurate receives much less attention. In our work, we use Raman spectroscopic data of fungal spores and carotenoid-containing microorganisms to show that it is often not the position of the peaks or the subtle differences in the band ratios of the spectra, due to small differences in the chemical composition of the organisms, that allow accurate classification. Rather, it can be characteristic effects on the baselines of Raman spectra in biochemically similar microorganisms that can be enhanced by certain data pretreatment methods or even neutral-looking spectral regions can be of great importance for a convolutional neural network. Using a method called Gradient-weighted Class Activation Mapping, we attempt to peer into the black box of convolutional neural networks in microbiological applications and show which Raman spectral regions are responsible for accurate classification. Full article

Transformer architectures are highly expressive because they use self-attention mechanisms to encode long-range dependencies in the input sequences. In this paper, we present a literature review on Transformer-based (TB) models, providing a detailed overview of each model in comparison to the Transformer’s standard architecture. This survey focuses on TB models used in the field of Natural Language Processing (NLP) for textual-based tasks. We begin with an overview of the fundamental concepts at the heart of the success of these models. Then, we classify them based on their architecture and training mode. We compare the advantages and disadvantages of popular techniques in terms of architectural design and experimental value. Finally, we discuss open research, directions, and potential future work to help solve current TB application challenges in NLP. Full article

In modern life, the application of artificial intelligence (AI) has promoted the implementation of data-driven algorithms in high-stakes domains, such as healthcare. However, it is becoming increasingly challenging for humans to understand the working and reasoning of these complex and opaque algorithms. For AI to support essential decisions in these domains, specific ethical issues need to be addressed to prevent the misinterpretation of AI, which may have severe consequences for humans. However, little research has been published on guidelines that systematically addresses ethical issues when AI techniques are applied in healthcare. In this systematic literature review, we aimed to provide an overview of ethical concerns and related strategies that are currently identified when applying AI in healthcare. The review, which followed the PRISMA guidelines, revealed 12 main ethical issues: justice and fairness, freedom and autonomy, privacy, transparency, patient safety and cyber security, trust, beneficence, responsibility, solidarity, sustainability, dignity, and conflicts. In addition to these 12 main ethical issues, we derived 19 ethical sub-issues and associated strategies from the literature. Full article

In this paper we propose a procedure to enable the training of several independent Multilayer Perceptron Neural Networks with a different number of neurons and activation functions in parallel (ParallelMLPs) by exploring the principle of locality and parallelization capabilities of modern CPUs and GPUs. The core idea of this technique is to represent several sub-networks as a single large network and use a Modified Matrix Multiplication that replaces an ordinal matrix multiplication with two simple matrix operations that allow separate and independent paths for gradient flowing. We have assessed our algorithm in simulated datasets varying the number of samples, features and batches using 10,000 different models as well as in the MNIST dataset. We achieved a training speedup from 1 to 4 orders of magnitude if compared to the sequential approach. The code is available online. Full article

Alfalfa is critical to global food security, and its data is abundant in the U.S. nationally, but often scarce locally, limiting the potential performance of machine learning (ML) models in predicting alfalfa biomass yields. Training ML models on local-only data results in very low estimation accuracy when the datasets are very small. Therefore, we explore synthesizing non-local data to estimate biomass yields labeled as high, medium, or low. One option to remedy scarce local data is to train models using non-local data; however, this only works about as well as using local data. Therefore, we propose a novel pipeline that trains models using data synthesized from non-local data to estimate local crop yields. Our pipeline, synthesized non-local training (SNLT pronounced like sunlight), achieves a gain of 42.9% accuracy over the best results from regular non-local and local training on our very small target dataset. This pipeline produced the highest accuracy of 85.7% with a decision tree classifier. From these results, we conclude that SNLT can be a useful tool in helping to estimate crop yields with ML. Furthermore, we propose a software application called Predict Your CropS (PYCS pronounced like Pisces) designed to help farmers and researchers estimate and predict crop yields based on pretrained models. Full article