Time series event detection methods are evaluated mainly by standard classification metrics that focus solely on detection accuracy. However, inaccuracy in detecting an event can often result from its preceding or delayed effects reflected in neighboring detections. These detections are valuable to trigger necessary actions or help mitigate unwelcome consequences. In this context, current metrics are insufficient and inadequate for the context of event detection. There is a demand for metrics that incorporate both the concept of time and temporal tolerance for neighboring detections. This paper introduces SoftED metrics, a new set of metrics designed for soft evaluating event detection methods. They enable the evaluation of both detection accuracy and the degree to which their detections represent events. They improved event detection evaluation by associating events and their representative detections, incorporating temporal tolerance in over 36\% of experiments compared to the usual classification metrics. SoftED metrics were validated by domain specialists that indicated their contribution to detection evaluation and method selection.

Stroke is the second leading cause of death worldwide. Machine learning classification algorithms have been widely adopted for stroke prediction. However, these algorithms were evaluated using different datasets and evaluation metrics. Moreover, there is no comprehensive framework for stroke data analytics. This paper proposes an intelligent stroke prediction framework based on a critical examination of machine learning prediction algorithms in the literature. The five most used machine learning algorithms for stroke prediction are evaluated using a unified setup for objective comparison. Comparative analysis and numerical results reveal that the Random Forest algorithm is best suited for stroke prediction.

Although large language models (LLMs) have shown exceptional performance in various natural language processing tasks, they are prone to hallucinations. State-of-the-art chatbots, such as the new Bing, attempt to mitigate this issue by gathering information directly from the internet to ground their answers. In this setting, the capacity to distinguish trustworthy sources is critical for providing appropriate accuracy contexts to users. Here we assess whether ChatGPT, a prominent LLM, can evaluate the credibility of news outlets. With appropriate instructions, ChatGPT can provide ratings for a diverse set of news outlets, including those in non-English languages and satirical sources, along with contextual explanations. Our results show that these ratings correlate with those from human experts (Spearmam's $\rho=0.54, p<0.001$). These findings suggest that LLMs could be an affordable reference for credibility ratings in fact-checking applications. Future LLMs should enhance their alignment with human expert judgments of source credibility to improve information accuracy.

Quantum kernels are considered as potential resources to illustrate benefits of quantum computing in machine learning. Considering the impact of hyperparameters on the performance of a classical machine learning model, it is imperative to identify promising hyperparameters using quantum kernel methods in order to achieve quantum advantages. In this work, we analyse and classify sentiments of textual data using a new quantum kernel based on linear and full entangled circuits as hyperparameters for controlling the correlation among words. We also find that the use of linear and full entanglement further controls the expressivity of the Quantum Support Vector Machine (QSVM). In addition, we also compare the efficiency of the proposed circuit with other quantum circuits and classical machine learning algorithms. Our results show that the proposed fully entangled circuit outperforms all other fully or linearly entangled circuits in addition to classical algorithms for most of the features. In fact, as the feature increases the efficiency of our proposed fully entangled model also increases significantly.

As machine learning systems have been increasingly applied in social fields, it is imperative that machine learning models do not reflect real-world discrimination. However, machine learning models have shown biased predictions against disadvantaged groups on several real-world tasks (Larson et al., 2016; Dressel and Farid, 2018; Mehrabi et al., 2021a). In order to improve fairness and reduce discrimination of machine learning systems, a variety of work has been proposed to quantify and rectify bias (Hardt et al., 2016; Kleinberg et al., 2016; Mitchell et al., 2018). Despite the emerging interest in fairness, the topic of adversarial fairness attack and robustness against such attack have not yet been properly discussed. Most of current literature on adversarial training has been focusing on improving robustness against accuracy attack (Chakraborty et al., 2018), while the problem of adversarial attack and adversarial training w.r.t.

In many real-world settings, the critical class is rare and a missed detection carries a disproportionately high cost. For example, tumors are rare and a false negative diagnosis could have severe consequences on treatment outcomes; fraudulent banking transactions are rare and an undetected occurrence could result in significant losses or legal penalties. In such contexts, systems are often operated at a high true positive rate, which may require tolerating high false positives. In this paper, we present a novel approach to address the challenge of minimizing false positives for systems that need to operate at a high true positive rate. We propose a ranking-based regularization (RankReg) approach that is easy to implement, and show empirically that it not only effectively reduces false positives, but also complements conventional imbalanced learning losses. With this novel technique in hand, we conduct a series of experiments on three broadly explored datasets (CIFAR-10&100 and Melanoma) and show that our approach lifts the previous state-of-the-art performance by notable margins.

Due to the increasing number of graduates, many applicants experience the situation about finding a job, and employers experience difficulty filtering job applicants, which might negatively impact their effectiveness. However, most job-hunting websites lack job recommendation and CV filtering or ranking functionality, which are not integrated into the system. Thus, a smart job hunter combined with the above functionality will be conducted in this project, which contains job recommendations, CV ranking and even a job dashboard for skills and job applicant functionality. Job recommendation and CV ranking starts from the automatic keyword extraction and end with the Job/CV ranking algorithm. Automatic keyword extraction is implemented by Job2Skill and the CV2Skill model based on Bert. Job2Skill consists of two components, text encoder and Gru-based layers, while CV2Skill is mainly based on Bert and fine-tunes the pre-trained model by the Resume- Entity dataset. Besides, to match skills from CV and job description and rank lists of jobs and candidates, job/CV ranking algorithms have been provided to compute the occurrence ratio of skill words based on TFIDF score and match ratio of the total skill numbers. Besides, some advanced features have been integrated into the website to improve user experiences, such as the calendar and sweetalert2 plugin. And some basic features to go through job application processes, such as job application tracking and interview arrangement.

Background: Alzheimer's disease (AD) is the most common type of age-related dementia, affecting 6.2 million people aged 65 or older according to CDC data. It is commonly agreed that discovering an effective AD diagnosis biomarker could have enormous public health benefits, potentially preventing or delaying up to 40% of dementia cases. Tau neurofibrillary tangles are the primary driver of downstream neurodegeneration and subsequent cognitive impairment in AD, resulting in structural deformations such as hippocampal atrophy that can be observed in magnetic resonance imaging (MRI) scans. Objective: To build a surface-based model to 1) detect differences between APOE subgroups in patterns of tau deposition and hippocampal atrophy, and 2) use the extracted surface-based features to predict cognitive decline. Methods: Using data obtained from different institutions, we develop a surface-based federated Chow test model to study the synergistic effects of APOE, a previously reported significant risk factor of AD, and tau on hippocampal surface morphometry. Results: We illustrate that the APOE-specific morphometry features correlate with AD progression and better predict future AD conversion than other MRI biomarkers. For example, a strong association between atrophy and abnormal tau was identified in hippocampal subregion cornu ammonis 1 (CA1 subfield) and subiculum in e4 homozygote cohort. Conclusion: Our model allows for identifying MRI biomarkers for AD and cognitive decline prediction and may uncover a corner of the neural mechanism of the influence of APOE and tau deposition on hippocampal morphology.

To advance automated detection of extreme weather events, which are increasing in frequency and intensity with climate change, we explore modifications to a novel light-weight Context Guided convolutional neural network architecture trained for semantic segmentation of tropical cyclones and atmospheric rivers in climate data. Our primary focus is on tropical cyclones, the most destructive weather events, for which current models show limited performance. We investigate feature engineering, data augmentation, learning rate modifications, alternative loss functions, and architectural changes. In contrast to previous approaches optimizing for intersection over union, we specifically seek to improve recall to penalize under-counting and prioritize identification of tropical cyclones. We report success through the use of weighted loss functions to counter class imbalance for these rare events. We conclude with directions for future research on extreme weather events detection, a crucial task for prediction, mitigation, and equitable adaptation to the impacts of climate change.

Endoscopic video recordings are widely used in minimally invasive robot-assisted surgery, but when the endoscope is outside the patient's body, it can capture irrelevant segments that may contain sensitive information. To address this, we propose a framework that accurately detects out-of-body frames in surgical videos by leveraging self-supervision with minimal data labels. We use a massive amount of unlabeled endoscopic images to learn meaningful representations in a self-supervised manner. Our approach, which involves pre-training on an auxiliary task and fine-tuning with limited supervision, outperforms previous methods for detecting out-of-body frames in surgical videos captured from da Vinci X and Xi surgical systems. The average F1 scores range from 96.00 to 98.02. Remarkably, using only 5% of the training labels, our approach still maintains an average F1 score performance above 97, outperforming fully-supervised methods with 95% fewer labels. These results demonstrate the potential of our framework to facilitate the safe handling of surgical video recordings and enhance data privacy protection in minimally invasive surgery.