Artificial Intelligence (AI) technologies have become increasingly central to software development, enhancing efficiency with tools such as intelligent code assistants and driving innovations in products like chatbots, recommendation engines, and predictive analytics. Despite these advancements, the inherent complexity of AI-integrated software projects often leads to the accumulation of technical debt (TD), which can compromise the reliability and sustainability of systems in the long term. Managing TD effectively in these projects can be achieved by adapting international standards. Although these standards are not designed for TD management, they can be systematically applied to detect and address TD by aligning with AI system lifecycle processes. The aim of this study is to demonstrate how AI-related TD correlates with various AI lifecycle processes, thereby enabling systematic detection and management of TD in AI-integrated software projects. To achieve this, we studied 73 unique cases of TD, each reflecting either an instance or a root cause of data-related TD. These cases were subsequently mapped to the processes and activities outlined in the ISO/IEC 5338 AI Systems Lifecycle Processes standard. Subsequently, the accuracy of these mappings was validated bidirectionally by a large language model and two domain experts. Our findings revealed that data-related TD categories are associated with a diverse range of processes such as design definition, quality management and human resource management and tend to accumulate more significantly in certain areas within the AI lifecycle. This study not only serves as a proof of concept for developing a management approach for AI-related TD, but also enhances the body of knowledge on managing TD in AI projects by detailing how TD interacts with and impacts various AI lifecycle processes.

Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related conditions. In this article, we propose a hybrid personalised model involving a kernel density estimation model and a generalised linear mixed model to model office workers’ available moments for rest breaks during working hours. We adopt the experience-based sampling method through which we collected office workers’ responses regarding their availability through a mobile application with contextual information extracted by means of the mobile phone sensors. The experiment lasted 10 workdays and involved 19 office workers with a total of 528 responses. Our results show that time, location, ringer mode, and activity are effective features for predicting office workers’ availability. Our method can address sparse sample issues for building individual predictive behavioural models based on limited and unbalanced data. In particular, the proposed method can be considered as a potential solution to the “cold-start problem,” i.e., the negative impact of the lack of individual data when a new application is installed.

Temporal or spatio-temporal sequential pattern discovery is a well-recognized important problem in many domains like seismology, criminology, and finance. The majority of the current approaches are based on candidate generation which necessitates parameter tuning, namely, definition of a neighborhood, an interest measure, and a threshold value to evaluate candidates. However, their performance is limited as the success of these methods relies heavily on parameter settings. In this paper, we propose an algorithm which uses a nonparametric stochastic de-clustering procedure and a multivariate Hawkes model to define triggering relations within and among the event types and employs the estimated model to extract significant triggering patterns of event types. We tested the proposed method with real and synthetic data sets exhibiting different characteristics. The method gives good results that are comparable with the methods based on candidate generation in the literature.

Coherent nature of crowd movement allows representing the crowd motion using sparse features. However, surveillance videos recorded at different periods of time are likely to have different crowd densities and motion characteristics. These varying scene properties necessitate use of different models for an effective representation of behaviour at different periods. In this study, a density aware approach is proposed to detect motion‐based anomalies for scenes having varying crowd densities. In the training, the sparse features are modelled using separate hidden Markov models, each of which becomes an expert for specific scene characteristics. These models are then used for anomaly detection. The proposed method automatically adapts to the changing scene dynamics by switching to the most representative model at each frame. The authors demonstrate the effectiveness and real‐time performance of the proposed method on real‐life datasets as well as on simulated crowd videos that they generated and made publicly available to download.

The incorporation of pharmacogenomics information into the drug dosing estimation formulations has been shown to increase the accuracy in drug dosing and decrease the frequency of adverse drug effects in many studies in the literature. In this paper, an estimation framework based on the Bayesian structural equation modeling, which is driven by pharmacogenomics, is proposed. The results show that the model compares favorably with the linear models in terms of prediction and explaining the variations in warfarin dosing.

With the increasing focus on safety and security in public areas, anomaly detection in video surveillance systems has become increasingly more important. In this paper, we describe a method that models the temporal behavior and detects behavioral anomalies in the scene using probabilistic graphical models. The Coupled Hidden Markov Model (CHMM) method that we use shows that sparse features obtained via feature detection and description algorithms are suitable for modeling the temporal behavior patterns and performing global anomaly detection. We model the scene using these features, perform perspective independent velocity analysis for anomaly detection purposes and demonstrate the results obtained on UCSD pedestrian walkway dataset. The training is unsupervised and does not require any data having anomaly. This eliminates the need to obtain anomaly data and to define anomalies in advance.

Surveillance of crowded public spaces and detection of anomalies from the video is important for public safety and security. While anomaly detection is possible by detection and tracking of individuals in low-density areas, such methods are not reliable in high-density crowded scenes. In this work we propose a holistic unsupervised approach to cluster different behaviors in high density crowds and detect the local anomalies using these clusters. Finite-Time Lyapunov Exponents (FTLE) is used for analyzing the crowd flow and this flow data is clustered by agglomerative hierarchical clustering. To detect if there is any anomaly in the video, mean of maximum values for pixels in each cluster is used and skewness value of the clusters are calculated. An adaptive threshold is calculated using equal width thresholding which is subsequently used to determine abnormal clusters which are not coherent with the general flow. The method does not require any user defined thresholds or preset rules. Publicly available datasets and our own dataset (which is also made publicly available) are used for testing and demonstrating the effectiveness of the proposed method.

Road traffic congestions are one of the major problems in highly populated cities. In the recent years, GPS based solutions have become popular since people are able to see the traffic flow on streets instantaneously. However such systems are lack of intelligent reasoning regarding the traffic problems. As a result, one cannot anticipate the traffic slowdown duration and overall impact. This study proposes a social network based solution using web services where people will be able to share latest traffic incidents such as accidents and roadwork. The proposed solution aims to help people to make the right decisions between alternative routes. The prototype developed was evaluated in a survey among 182 smart phone users and the results show that the most of the participants (72%) reveal a very positive attitude towards the solution and accept it as a desirable tool as a remedy for daily traffic problems.

Hybrid methods comprising autoregressive integrated moving average (ARIMA) and neural network models are generally favored against single neural network and single ARIMA models in the literature. The benefits of such methods appear to be substantial especially when dealing with non-stationary series: nonstationary linear component can be modeled using ARIMA and nonlinear component using neural networks. Our studies suggest that the use of a nonlinear component may degenerate the performance of such hybrids and that a simpler hybrid comprising linear AR model with a TDNN outperforms the more complex hybrid in tests on benchmark economic and financial time series.