Refine
Has Fulltext
- no (187)
Year of publication
Document Type
- Article (187) (remove)
Is part of the Bibliography
- yes (187) (remove)
Keywords
- machine learning (5)
- COVID-19 (4)
- Visualization (4)
- 3D point clouds (3)
- Security (3)
- data profiling (3)
- duplicate detection (3)
- heuristics (3)
- performance (3)
- run time analysis (3)
- similarity measures (3)
- theory (3)
- 3D city models (2)
- BPMN (2)
- Case management (2)
- Classification (2)
- Compliance checking (2)
- Data profiling (2)
- Event processing (2)
- Functional dependencies (2)
- JavaScript (2)
- Nested graph conditions (2)
- Point-based rendering (2)
- Process modeling (2)
- Runtime analysis (2)
- SQL (2)
- Virtualization (2)
- cartographic design (2)
- clinical (2)
- data integration (2)
- data matching (2)
- data quality (2)
- data wrangling (2)
- databases (2)
- dialysis (2)
- digital health (2)
- dynamic (2)
- dynamic programming (2)
- entity resolution (2)
- genetic programming (2)
- prediction (2)
- programming (2)
- real-time rendering (2)
- record linkage (2)
- risk aversion (2)
- scalability (2)
- self-healing (2)
- 3D (1)
- 3D Point clouds (1)
- 3D geovirtual environments (1)
- 3D geovisualization (1)
- 3D information visualization (1)
- 3D semiotic model (1)
- AKI (1)
- APX-hardness (1)
- Aaron Wildavsky (1)
- Accounting (1)
- Actor (1)
- Actor model (1)
- Address matching (1)
- Algorithms (1)
- Anomaly detection (1)
- Anti-patterns (1)
- Application (1)
- Approximation algorithms (1)
- Artificial neural networks (1)
- Attribute aggregation (1)
- Attributed graph transformation (1)
- Attributed graphs (1)
- Authentication (1)
- B2B process integration (1)
- BPMN-Q (1)
- Behavior equivalence (1)
- Behavioral querying (1)
- Behavioural Abstraction (1)
- Behavioural analysis (1)
- Benchmarking (1)
- Bidirectional order dependencies (1)
- Big Data (1)
- Billing (1)
- Biomedicine (1)
- Bitcoin (1)
- Blockchain (1)
- Blockchains (1)
- Body sensor networks (1)
- Business Process Modeling Notation (1)
- Business process diagram (1)
- Business process management (1)
- Business process model (1)
- Business process modeling (1)
- Business processes (1)
- CCS Concepts (1)
- Cake cutting (1)
- Causal Behavioural Profiles (1)
- Causality (1)
- Change propagation (1)
- Charging (1)
- Choreographies (1)
- Chronic heart failure (1)
- Climate change (1)
- CoExist (1)
- Communication systems (1)
- Commute pattern (1)
- Commute process (1)
- Competition (1)
- Complexity theory (1)
- Compliance measurement (1)
- Computational modeling (1)
- Computational photography (1)
- Computer (1)
- Computer crime (1)
- Concurrency (1)
- Consistency (1)
- Consistency perception (1)
- Context-oriented programming (1)
- ContextJS (1)
- Convolution (1)
- CorMID (1)
- Correlation (1)
- Critical pairs (1)
- Cryptography (1)
- Cultural theory (1)
- Currencies (1)
- Data (1)
- Data dependencies (1)
- Data exchange (1)
- Data integration (1)
- Data mining (1)
- Data modeling (1)
- Data models (1)
- Data-centric (1)
- Deep learning (1)
- Delphi study (1)
- Delta preservation (1)
- Dependency discovery (1)
- Design (1)
- Distributed (1)
- Distributed 3D geovisualization (1)
- Distributed computing (1)
- Distributed debugging (1)
- Distributed programming (1)
- DoS (1)
- Duration prediction (1)
- Dynamic Data Structures (1)
- Dynamic adaptation (1)
- Dynamic analysis (1)
- Dynamic pricing (1)
- Dynamic pricing and advertising (1)
- E-commerce (1)
- EHR (1)
- Ecosystems (1)
- Electrocardiography (1)
- Electronic prescription (1)
- Energy-aware (1)
- Entity resolution (1)
- Estimation-of-distribution algorithm (1)
- Event normalization (1)
- Events (1)
- Evolutionary algorithms (1)
- Evolutionary computation (1)
- Exception handling (1)
- Exclusiveness (1)
- Experimentation (1)
- Facial mimicry (1)
- Feature extraction (1)
- Federated learning (1)
- Feedback heuristics (1)
- Finite horizon (1)
- First hitting time (1)
- Fitness level method (1)
- Fitness-distance correlation (1)
- Flexible Resource Manager (1)
- Flexible processes; (1)
- Formal Methods (1)
- Gender Inequality (1)
- General Earth and Planetary Sciences (1)
- Geography, Planning and Development (1)
- Graph databases (1)
- Graph homomorphisms (1)
- Graph queries (1)
- Graph repair (1)
- Graph rewriting (1)
- Graph transformation (1)
- HITS (1)
- HMM (1)
- HiGHmed (1)
- Hidden Markov models (1)
- Hospitalisation (1)
- IDS (1)
- IDS management (1)
- IMD (1)
- IMU (1)
- IOPS (1)
- Identity management systems (1)
- Image (1)
- Image filtering (1)
- Image-based rendering (1)
- In-memory (1)
- Inclusion dependencies (1)
- Industries (1)
- Initial conflicts (1)
- Interaction (1)
- Interaction modeling (1)
- Interviews (1)
- Introspection (1)
- Intrusion detection (1)
- Inventory holding costs (1)
- Inventory systems (1)
- JIT compilers (1)
- Java (1)
- Knowledge-intensive processes (1)
- LIDAR (1)
- LSTM (1)
- Label analysis (1)
- Lakes (1)
- Languages (1)
- Languages Model-driven engineering (1)
- Level of abstraction (1)
- Licenses (1)
- Live forensics (1)
- Lively Kernel (1)
- Location-based services (1)
- Log conformance (1)
- M-adhesive categories (1)
- M-adhesive transformation systems (1)
- Machine (1)
- Machine learning (1)
- Markov decision process (1)
- Markov decision process; (1)
- Markov model (1)
- Mary Douglas (1)
- Matroids (1)
- Measurement (1)
- Metamaterials (1)
- Mixed workload (1)
- Mobile device (1)
- Model equivalence (1)
- Model generation (1)
- Model refinement (1)
- Model repair (1)
- Model synchronisation (1)
- Model transformation (1)
- Model verification (1)
- Model-Driven Engineering (1)
- Model-driven (1)
- Modular decomposition (1)
- Monitoring language (1)
- Multi-objective optimization (1)
- Multimedia retrieval (1)
- Multiscale modeling (1)
- Mutation operators (1)
- NP-completeness (1)
- Natural language (1)
- Natural language processing (1)
- Network graph (1)
- Network monitoring (1)
- Network topology (1)
- Neural Networks (1)
- Nigeria (1)
- O (1)
- OLTP (1)
- Object Versioning (1)
- Open implementations (1)
- Operational reporting (1)
- Optimal stochastic and deterministic (1)
- Optionality (1)
- Order Relations (1)
- Order dependencies (1)
- Out-of-core (1)
- Outlier detection (1)
- PPMI (parkinson's progression markers initiative) (1)
- Parallelization (1)
- Performance (1)
- Personal fabrication (1)
- Petri net unfolding (1)
- Plugs (1)
- Prediction (1)
- Price collusion (1)
- Privacy (1)
- Process Monitoring (1)
- Process choreographies (1)
- Process compliance (1)
- Process mining (1)
- Process model (1)
- Process model alignment (1)
- Process model consistency (1)
- Process model repositories (1)
- Process model search (1)
- Processing strategies (1)
- Programming (1)
- Programming Environments (1)
- Property paths (1)
- Protocols (1)
- QRS detection (1)
- Quality of service (1)
- Query execution (1)
- Query optimization (1)
- Question answering (1)
- R Shiny (1)
- R package (1)
- Racket (1)
- Random graphs (1)
- Record and refinement (1)
- Record and replay (1)
- Record linkage (1)
- Reinforcement learning (1)
- Relational data (1)
- Remote patient management (1)
- Resource description framework (1)
- Resource management (1)
- Risk control (1)
- Robust optimization (1)
- Root cause analysis (1)
- Run time analysis (1)
- Runtime WCET Analysis (1)
- SAP HANA (1)
- SPARQL (1)
- Safety Critical Systems (1)
- Satisfiability (1)
- Scientific Publication Indicators (1)
- Scope (1)
- Self-configuration (1)
- Semantics (1)
- Sequential anomaly (1)
- Service composition (1)
- Service detection (1)
- Service orchestration (1)
- Service-oriented computing (1)
- Sexism (1)
- Signal-to-noise ratio (1)
- Smalltalk (1)
- Software (1)
- Squeak (1)
- Stochastic Petri nets (1)
- Structural Decomposition (1)
- Structured modeling (1)
- Structuring (1)
- Submodular function (1)
- Submodular functions (1)
- Subset selection (1)
- System architecture (1)
- TRIPOD (1)
- Tableau method (1)
- Task analysis (1)
- Telemonitoring (1)
- Texturing (1)
- Theory (1)
- Three-dimensional displays (1)
- Time series (1)
- Tool survey (1)
- Trace inclusion (1)
- Transformation tool contest (1)
- Two dimensional displays (1)
- Ubiquitous computing (1)
- Unique column combination (1)
- Unique column combinations (1)
- Video OCR (1)
- Video classification (1)
- Video indexing (1)
- View navigation (1)
- Virtual 3D city model (1)
- Virtual 3D scenes (1)
- Virtual camera control (1)
- Visual modeling (1)
- Vocabulary (1)
- W[3]-completeness (1)
- Water Science and Technology (1)
- Web browsers (1)
- Web navigational language (1)
- Web safeness (1)
- Web-based rendering (1)
- abdominal imaging (1)
- abundance (1)
- accounting (1)
- action recognition (1)
- activity recognition (1)
- acute renal failure (1)
- adaptation rules (1)
- address normalization (1)
- address parsing (1)
- adolescent (1)
- affective interfaces (1)
- algorithm (EDA) (1)
- algorithmic (1)
- analysis (1)
- anniversary (1)
- application (1)
- approximation (1)
- architecture recovery (1)
- architecture-based adaptation (1)
- architectures (1)
- argumentation research (1)
- artificial intelligence (1)
- atmospheric pressure chemical ionization (1)
- attack graph (1)
- attacks (1)
- attention mechanism (1)
- attribute assurance (1)
- authentication (1)
- authentication protocol (1)
- back pain (1)
- battery (1)
- battery-depletion attack (1)
- behaviour compatibility (1)
- behaviour equivalence (1)
- behavioural models (1)
- benchmark testing (1)
- bibliometrics (1)
- bidirectional shortest path (1)
- big data (1)
- billing (1)
- biomarker detection (1)
- biomechanics (1)
- bloat control (1)
- bridge management systems (1)
- building information modeling (1)
- business process management (1)
- cancer therapy (1)
- cartography-oriented visualization (1)
- center dot Computing (1)
- charging (1)
- child (1)
- chronic dialysis (1)
- clinical nephrology (1)
- cloud security (1)
- cluster resource management (1)
- clustering (1)
- co-location (1)
- cognition (1)
- cognitive (1)
- cohort (1)
- collaboration (1)
- collaborative tagging (1)
- color palettes (1)
- communication network (1)
- complex emotions (1)
- complexity (1)
- complexity dichotomy (1)
- comprehension (1)
- computational design (1)
- computer vision (1)
- conceptualization (1)
- concurrent graph rewriting (1)
- conditional functional dependencies (1)
- conditions (1)
- confidentiality (1)
- conflicts and dependencies in (1)
- contract (1)
- contracts (1)
- control (1)
- coronavirus 2019 (1)
- corporate takeovers (1)
- cost-effectiveness (1)
- cost-utility analysis (1)
- creativity and innovation management (1)
- critical pairs (1)
- cryptocurrency exchanges (1)
- cyber (1)
- cyber humanistic (1)
- cyber threat intelligence (1)
- damage detection (1)
- data analysis (1)
- data cleaning (1)
- data cleansing (1)
- data migration (1)
- data preparation (1)
- data transformation (1)
- data-driven demand (1)
- database systems (1)
- datasets (1)
- deduplication (1)
- deep learning (1)
- denial-of-service attack (1)
- dependency (1)
- dependency discovery (1)
- design (1)
- design thinking (1)
- deterministic properties (1)
- deterministic random walk (1)
- diabetes (1)
- differential (1)
- digital health app (1)
- digital identity (1)
- digital startup (1)
- digital therapy (1)
- distributed computing (1)
- distributed data-parallel processing (1)
- distributed systems (1)
- dynamic pricing (1)
- eHealth (1)
- ePA (1)
- ecological momentary assessment (1)
- ecosystems (1)
- electronic health record (1)
- electronic health records (1)
- electronic mail (1)
- embedding (1)
- emotional (1)
- empathy (1)
- end-stage kidney disease (1)
- endogenous (1)
- engine (1)
- engineering (1)
- enrichment calculation (1)
- enumeration complexity (1)
- epistasis (1)
- estimation-of-distribution (1)
- estimation-of-distribution algorithm (1)
- ethics (1)
- evaluation (1)
- event log (1)
- exact exponential-time algorithms (1)
- experimental design (1)
- experiments (1)
- expertise (1)
- explainability (1)
- explainability-accuracy trade-off (1)
- explainable AI (1)
- exploratory programming (1)
- expression (1)
- external knowledge bases (1)
- fabrication (1)
- factual (1)
- failure model (1)
- failure profile model (1)
- fair division (1)
- feature selection (1)
- feedback loops (1)
- flux (1)
- focus plus context visualization (1)
- folksonomy (1)
- forensics (1)
- fully concurrent bisimulation (1)
- functional dependencies (1)
- functional dependency (1)
- functional languages (1)
- game theory (1)
- gene (1)
- gene selection (1)
- generative multi-discriminative networks (1)
- genetic algorithms (1)
- geocoding (1)
- geographic information systems (1)
- geospatial artificial intelligence (1)
- geospatial digital twins (1)
- grammar-based compression (1)
- graph languages (1)
- graph pattern matching (1)
- graph replacement categories (1)
- graph transformation (1)
- health apps (1)
- health information privacy concern (1)
- health personnel (1)
- healthcare (1)
- heuristic algorithms (1)
- history (1)
- home-based studies (1)
- hospital (1)
- human immunodeficiency virus (1)
- hyperbolic geometry (1)
- identity broker (1)
- image captioning (1)
- image-based representation (1)
- imbalanced learning (1)
- implantable medical device (1)
- implants (1)
- inclusion (1)
- informatics (1)
- information storage and (1)
- interactive editing (1)
- interpretable machine learning (1)
- job (1)
- knowledge building (1)
- knowledge management (1)
- label-free (1)
- languages (1)
- laser cutting (1)
- law (1)
- layered architecture (1)
- lazy transformation (1)
- lean startup approach (1)
- learning (1)
- local confluence (1)
- logic (1)
- low back pain (1)
- low-code development approaches (1)
- lower bound (1)
- mHealth (1)
- mass isotopologue distribution (1)
- matching dependencies (1)
- maximal structuring (1)
- mean-variance optimization (1)
- medical (1)
- medical identity theft (1)
- medical malpractice (1)
- memory-based clustering (1)
- memory-based correlation (1)
- memory-based databases (1)
- mental disorders (1)
- mental health (1)
- methodologie (1)
- metric learning (1)
- mixed-methods (1)
- mobile health (1)
- mobile phone (1)
- model interpreter (1)
- model transformation (1)
- model verification (1)
- modeling language (1)
- models at runtime (1)
- modular counting (1)
- modularity (1)
- molecular tumor board (1)
- mortality (1)
- motion analysis (1)
- motion capture (1)
- motivations (1)
- multi-core (1)
- multi-perspective visualization (1)
- multi-product pricing (1)
- multilevel systems (1)
- multimodal representations (1)
- multimodal sensing (1)
- multiview classification (1)
- mutation (1)
- mutli-task learning (1)
- nested application conditions (1)
- network creation games (1)
- networks (1)
- neural (1)
- non-repudiation (1)
- one-time password (1)
- organizations (1)
- orthopedic (1)
- orthopedic; (1)
- ownership (1)
- pain management (1)
- panorama (1)
- parameterized complexity (1)
- parkinson's disease (1)
- parsimonious reduction (1)
- personal electronic health records (1)
- personal satisfaction (1)
- personalized medicine (1)
- phishing (1)
- physical activity assessment (1)
- point clouds (1)
- power-law (1)
- prevention (1)
- price of anarchy (1)
- pricing (1)
- prior knowledge (1)
- privacy (1)
- probabilistic (1)
- process mining (1)
- process modeling (1)
- process scheduling (1)
- process-aware digital twin cockpit (1)
- process-awareness (1)
- processes (1)
- processing (1)
- program (1)
- programs (1)
- proportional division (1)
- proteomics (1)
- protocols (1)
- prototypes (1)
- public health medicine (1)
- query optimisation (1)
- query rewriting (1)
- random I (1)
- random forest (1)
- random graphs (1)
- ranking (1)
- recursive tuning (1)
- reinforcement learning (1)
- reliability (1)
- remodularization (1)
- remote monitoring (1)
- requirements (1)
- requirements engineering (1)
- research challenges (1)
- resilient architectures (1)
- restoration (1)
- restricted edges (1)
- retrieval (1)
- reward (1)
- robustness (1)
- rotor-router model (1)
- runtime analysis (1)
- scale-free networks (1)
- school (environment) (1)
- science mapping (1)
- search plan generation (1)
- security (1)
- security chaos engineering (1)
- security risk assessment (1)
- segmentation (1)
- self-adaptive software (1)
- self-driving (1)
- self-learning scheduler (1)
- self-sovereign identity (1)
- semantic (1)
- sensor (1)
- sensor data (1)
- separation of concerns (1)
- service-oriented architecture (1)
- severe acute respiratory (1)
- similarity learning (1)
- simulation (1)
- single vertex discrepancy (1)
- small files (1)
- smallest grammar problem (1)
- smart card (1)
- sociology (1)
- software (1)
- software engineering (1)
- software evolution (1)
- software reference architecture (1)
- software/instrumentation (1)
- spamming (1)
- spatial data infrastructure (1)
- stable matchings (1)
- standardization (1)
- statistics (1)
- statutes and laws (1)
- steganography (1)
- straight-line (1)
- structured process model (1)
- style description languages (1)
- substitution effects (1)
- supervised machine learning (1)
- surveillance (1)
- symbolic graph transformation (1)
- syndrome coronavirus 2 (1)
- systems (1)
- teamwork (1)
- technology adoption (1)
- technology pivot (1)
- tools (1)
- tort law (1)
- traceability (1)
- tracing (1)
- transfer learning (1)
- transversal hypergraph (1)
- tree conjecture (1)
- trust model (1)
- typography (1)
- unequal shares (1)
- use-cases (1)
- user interaction (1)
- utility (1)
- virtual groups (1)
- vulnerabilities (1)
- wearable movement sensor (1)
- weight (1)
- word clouds (1)
- workflow (1)
- workload prediction (1)
- zero-power defense (1)
Institute
- Hasso-Plattner-Institut für Digital Engineering gGmbH (187) (remove)
Evaluating creativity of verbal responses or texts is a challenging task due to psychometric issues associated with subjective ratings and the peculiarities of textual data. We explore an approach to objectively assess the creativity of responses in a sentence generation task to 1) better understand what language-related aspects are valued by human raters and 2) further advance the developments toward automating creativity evaluations. Over the course of two prior studies, participants generated 989 four-word sentences based on a four-letter prompt with the instruction to be creative. We developed an algorithm that scores each sentence on eight different metrics including 1) general word infrequency, 2) word combination infrequency, 3) context-specific word uniqueness, 4) syntax uniqueness, 5) rhyme, 6) phonetic similarity, and similarity of 7) sequence spelling and 8) semantic meaning to the cue. The text metrics were then used to explain the averaged creativity ratings of eight human raters. We found six metrics to be significantly correlated with the human ratings, explaining a total of 16% of their variance. We conclude that the creative impression of sentences is partly driven by different aspects of novelty in word choice and syntax, as well as rhythm and sound, which are amenable to objective assessment.
Technology pivots were designed to help digital startups make adjustments to the technology underpinning their products and services. While academia and the media make liberal use of the term "technology pivot," they rarely align themselves to Ries' foundational conceptualization. Recent research suggests that a more granulated conceptualization of technology pivots is required. To scientifically derive a comprehensive conceptualization, we conduct a Delphi study with a panel of 38 experts drawn from academia and practice to explore their understanding of "technology pivots." Our study thus makes an important contribution to advance the seminal work by Ries on technology pivots.
Wendepunkt für Gesundheit
(2019)
Applications with different characteristics in the cloud may have different resources preferences. However, traditional resource allocation and scheduling strategies rarely take into account the characteristics of applications. Considering that an I/O-intensive application is a typical type of application and that frequent I/O accesses, especially small files randomly accessing the disk, may lead to an inefficient use of resources and reduce the quality of service (QoS) of applications, a weight allocation strategy is proposed based on the available resources that a physical server can provide as well as the characteristics of the applications. Using the weight obtained, a resource allocation and scheduling strategy is presented based on the specific application characteristics in the data center. Extensive experiments show that the strategy is correct and can guarantee a high concurrency of I/O per second (IOPS) in a cloud data center with high QoS. Additionally, the strategy can efficiently improve the utilization of the disk and resources of the data center without affecting the service quality of applications.
With the growth of virtualization and cloud computing, more and more forensic investigations rely on being able to perform live forensics on a virtual machine using virtual machine introspection (VMI). Inspecting a virtual machine through its hypervisor enables investigation without risking contamination of the evidence, crashing the computer, etc. To further access to these techniques for the investigator/researcher we have developed a new VMI monitoring language. This language is based on a review of the most commonly used VMI-techniques to date, and it enables the user to monitor the virtual machine's memory, events and data streams. A prototype implementation of our monitoring system was implemented in KVM, though implementation on any hypervisor that uses the common x86 virtualization hardware assistance support should be straightforward. Our prototype outperforms the proprietary VMWare VProbes in many cases, with a maximum performance loss of 18% for a realistic test case, which we consider acceptable. Our implementation is freely available under a liberal software distribution license. (C) 2014 Digital Forensics Research Workshop. Published by Elsevier Ltd. All rights reserved.
A business process is a set of steps designed to be executed in a certain order to achieve a business value. Such processes are often driven by and documented using process models. Nowadays, process models are also applied to drive process execution. Thus, correctness of business process models is a must. Much of the work has been devoted to check general, domain-independent correctness criteria, such as soundness. However, business processes must also adhere to and show compliance with various regulations and constraints, the so-called compliance requirements. These are domain-dependent requirements.
In many situations, verifying compliance on a model level is of great value, since violations can be resolved in an early stage prior to execution. However, this calls for using formal verification techniques, e.g., model checking, that are too complex for business experts to apply. In this paper, we utilize a visual language. BPMN-Q to express compliance requirements visually in a way similar to that used by business experts to build process models. Still, using a pattern based approach, each BPMN-Qgraph has a formal temporal logic expression in computational tree logic (CTL). Moreover, the user is able to express constraints, i.e., compliance rules, regarding control flow and data flow aspects. In order to provide valuable feedback to a user in case of violations, we depend on temporal logic querying approaches as well as BPMN-Q to visually highlight paths in a process model whose execution causes violations.
Business processes are commonly modeled using a graphical modeling language. The most widespread notation for this purpose is business process diagrams in the Business Process Modeling Notation (BPMN). In this article, we use the visual query language BPMN-Q for expressing patterns that are related to possible problems in such business process diagrams. We discuss two classes of problems that can be found frequently in real-world models: sequence flow errors and model fragments that can make the model difficult to understand.
By using a query processor, a business process modeler is able to identify possible errors in business process diagrams. Moreover, the erroneous parts of the business process diagram can be highlighted when an instance of an error pattern is found. This way, the modeler gets an easy-to-understand feedback in the visual modeling language he or she is familiar with. This is an advantage over current validation methods, which usually lack this kind of intuitive feedback.
Using Hidden Markov Models for the accurate linguistic analysis of process model activity labels
(2019)
Many process model analysis techniques rely on the accurate analysis of the natural language contents captured in the models’ activity labels. Since these labels are typically short and diverse in terms of their grammatical style, standard natural language processing tools are not suitable to analyze them. While a dedicated technique for the analysis of process model activity labels was proposed in the past, it suffers from considerable limitations. First of all, its performance varies greatly among data sets with different characteristics and it cannot handle uncommon grammatical styles. What is more, adapting the technique requires in-depth domain knowledge. We use this paper to propose a machine learning-based technique for activity label analysis that overcomes the issues associated with this rule-based state of the art. Our technique conceptualizes activity label analysis as a tagging task based on a Hidden Markov Model. By doing so, the analysis of activity labels no longer requires the manual specification of rules. An evaluation using a collection of 15,000 activity labels demonstrates that our machine learning-based technique outperforms the state of the art in all aspects.
Background:
Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models.
Methods:
For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases.
Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning
can then be deployed to classify specific behaviour and mental health patterns.
Results:
We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through
rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project.
Conclusions:
This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns
of unknown effects.