Processing Algorithms Research Articles

PFedBASC: Personalized Federated Learning with Blockchain-Assisted Semi-Centralized Framework

As network technology advances, there is an increasing need for a trusted new-generation information management system. Blockchain technology provides a decentralized, transparent, and tamper-proof foundation. Meanwhile, data islands have become a significant obstacle for machine learning applications. Although federated learning (FL) ensures data privacy protection, server-side security concerns persist. Traditional methods have employed a blockchain system in FL frameworks to maintain a tamper-proof global model database. In this context, we propose a novel personalized federated learning (pFL) with blockchain-assisted semi-centralized framework, pFedBASC. This approach, tailored for the Internet of Things (IoT) scenarios, constructs a semi-centralized IoT structure and utilizes trusted network connections to support FL. We concentrate on designing the aggregation process and FL algorithm, as well as the block structure. To address data heterogeneity and communication costs, we propose a pFL method called FedHype. In this method, each client is assigned a compact hypernetwork (HN) alongside a normal target network (TN) whose parameters are generated by the HN. Clients pull together other clients’ HNs for local aggregation to personalize their TNs, reducing communication costs. Furthermore, FedHype can be integrated with other existing algorithms, enhancing its functionality. Experimental results reveal that pFedBASC effectively tackles data heterogeneity issues while maintaining positive accuracy, communication efficiency, and robustness.

Modelling and Prediction of Process Parameters with Low Energy Consumption in Wire Arc Additive Manufacturing Based on Machine Learning

Modelling and Prediction of Process Parameters with Low Energy Consumption in Wire Arc Additive Manufacturing Based on Machine Learning

Application of network data security based on wireless sensor technology in the development of digital sharing economy

Nowadays, when the existing algorithms are fused in the feature function network feature, they do not consider the different effects of different features on the saliency detection task. In order to solve this problem, this paper proposes a saliency feature fusion network based on multi-focus mechanism to complete the saliency detection task. While recognizing the important role of the network, it must also be realized that because most network users do not understand the details of network composition and network system analysis, the security of computer network data is relatively low. Unscrupulous hackers use their network technology and software to invade unauthorized networks and hosts without authorization. Therefore, network data security is very important. The competition and monopoly of the digital sharing economy platform has always been a hot topic of increasing attention from domestic and foreign economists. The platform economy is based on an efficient data collection and transmission system, a digital platform supported by continuously developing computing power and powerful data processing algorithms, which greatly promotes the development of social productivity. The core trend of the development of China's digital economy is the ecologicalization of the digital sharing economy. Small industrial platforms rely on massive user resources collected by a large platform to quickly connect the upper and lower channels of the industry to transform and form a new industry ecosystem.

A roadmap to artificial intelligence (AI): Methods for designing and building AI ready data to promote fairness

ObjectivesWe evaluated methods for preparing electronic health record data to reduce bias before applying artificial intelligence (AI). MethodsWe created methods for transforming raw data into a data framework for applying machine learning and natural language processing techniques for predicting falls and fractures. Strategies such as inclusion and reporting for multiple races, mixed data sources such as outpatient, inpatient, structured codes, and unstructured notes, and addressing missingness were applied to raw data to promote a reduction in bias. The raw data was carefully curated using validated definitions to create data variables such as age, race, gender, and healthcare utilization. For the formation of these variables, clinical, statistical, and data expertise were used. The research team included a variety of experts with diverse professional and demographic backgrounds to include diverse perspectives. ResultsFor the prediction of falls, information extracted from radiology reports was converted to a matrix for applying machine learning. The processing of the data resulted in an input of 5,377,673 reports to the machine learning algorithm, out of which 45,304 were flagged as positive and 5,332,369 as negative for falls. Processed data resulted in lower missingness and a better representation of race and diagnosis codes. For fractures, specialized algorithms extracted snippets of text around keywork “femoral” from dual x-ray absorptiometry (DXA) scans to identify femoral neck T-scores that are important for predicting fracture risk. The natural language processing algorithms yielded 98% accuracy and 2% error rate The methods to prepare data for input to artificial intelligence processes are reproducible and can be applied to other studies. ConclusionThe life cycle of data from raw to analytic form includes data governance, cleaning, management, and analysis. When applying artificial intelligence methods, input data must be prepared optimally to reduce algorithmic bias, as biased output is harmful. Building AI-ready data frameworks that improve efficiency can contribute to transparency and reproducibility. The roadmap for the application of AI involves applying specialized techniques to input data, some of which are suggested here. This study highlights data curation aspects to be considered when preparing data for the application of artificial intelligence to reduce bias.

MmSign: mmWave-based Few-Shot Online Handwritten Signature Verification

Handwritten signature verification has become one of the most important document authentication methods that are widely used in the financial, legal, and administrative sectors. Compared with offline methods based on static signature images, online handwritten signature verification methods are more reliable because of the temporary dynamic information (e.g., signing velocity, writing force, stroke order) that alleviates the risk of being forged. However, most existing online handwritten signature verification solutions are reliant on specific signing devices (e.g., customized pens or writing pads) and require extensive data collection during the registration phase, resulting in poor adaptability and applicability for new users. In this article, we propose mmSign, a millimeter wave (mmWave)–based online handwritten signature verification system, which enables accurate sensing of the user’s hand movements when signing through the superior sensing capability of mmWave. mmSign extracts the time-velocity feature maps from the captured mmWave signals by the carefully designed signal processing algorithms and then exploits a transformer-based verification model for signature verification. In addition, a novel meta-learning strategy with proposed task generation and data augmentation methods is introduced in mmSign to teach the verification model to learn effectively with limited samples, allowing our model to quickly adapt to new users. Extensive experiments show that mmSign is a robust, efficient, and secure handwritten signature verification system, achieving 84.07%, 87.31%, 91.12%, and 96.54% verification accuracy when 1, 3, 5, and 10 labeled signatures are available, respectively, while being resistant to common forgery attacks.

Anomalous trends in global ocean carbon concentrations following the 2022 eruptions of Hunga Tonga-Hunga Ha’apai

We report on observed trend anomalies in climate-relevant global ocean biogeochemical properties, as derived from satellite ocean color measurements, that show a substantial decline in phytoplankton carbon concentrations following eruptions of the submarine volcano Hunga Tonga-Hunga Ha’apai in January 2022. The anomalies are seen in remotely-sensed ocean color data sets from multiple satellite missions, but not in situ observations, thus suggesting that the observed anomalies are a result of ocean color retrieval errors rather than indicators of a major shift in phytoplankton carbon concentrations. The enhanced concentration of aerosols in the stratosphere following the eruptions results in a violation of some fundamental assumptions in the processing algorithms used to obtain marine biogeochemical properties from satellite radiometric observations, and it is demonstrated through radiative transfer simulations that this is the likely cause of the anomalous trends. We note that any future stratospheric aerosol disturbances, either natural or geoengineered, may lead to similar artifacts in satellite ocean color and other remote-sensing measurements of the marine environment, thus confounding our ability to track the impact of such events on ocean ecosystems.

Elite Multi-Criteria Decision Making—Pareto Front Optimization in Multi-Objective Optimization

Optimization is a process of minimizing or maximizing a given objective function under specified constraints. In multi-objective optimization (MOO), multiple conflicting functions are optimized within defined criteria. Numerous MOO techniques have been developed utilizing various meta-heuristic methods such as Evolutionary Algorithms (EAs), Genetic Algorithms (GAs), and other biologically inspired processes. In a cooperative environment, a Pareto front is generated, and an MOO technique is applied to solve for the solution set. On other hand, Multi-Criteria Decision Making (MCDM) is often used to select a single best solution from a set of provided solution candidates. The Multi-Criteria Decision Making–Pareto Front (M-PF) optimizer combines both of these techniques to find a quality set of heuristic solutions. This paper provides an improved version of the M-PF optimizer, which is called the elite Multi-Criteria Decision Making–Pareto Front (eMPF) optimizer. The eMPF method uses an evolutionary algorithm for the meta-heuristic process and then generates a Pareto front and applies MCDM to the Pareto front to rank the solutions in the set. The main objective of the new optimizer is to exploit the Pareto front while also exploring the solution area. The performance of the developed method is tested against M-PF, Non-Dominated Sorting Genetic Algorithm-II (NSGA-II), and Non-Dominated Sorting Genetic Algorithm-III (NSGA-III). The test results demonstrate the performance of the new eMPF optimizer over M-PF, NSGA-II, and NSGA-III. eMPF was not only able to exploit the search domain but also was able to find better heuristic solutions for most of the test functions used.

Multi-sensor signal fusion method for rolling bearing based on the standard relative mean–variance value and random weighting algorithm

In the study, an optimization fusion method based on the standard relative mean–variance value and a random weighting algorithm is proposed to effectively utilize multisensory-acquired signals for realizing accurate monitoring of rolling bearing faults. First, a novel feature-standard relative mean variance value is developed to adjust the balance parameter in the random weighting algorithm to adaptively obtain the best estimate value. Second, upper and lower thresholds of the balance parameter are provided to improve the noise reduction and feature retention abilities of the algorithm in the fusion process. Finally, the weight of each sensor signal is determined based on the overall variance of each sensor. The parameters in the optimization fusion method can be adaptively adjusted based on the collected signal, which has practical value. Simulations and laboratory experiments demonstrate the effectiveness of the method.

360-Degree Tri-Modal Scanning: Engineering a Modular Multi-Sensor Platform for Semantic Enrichment of BIM Models

Abstract. Point clouds, image data, and corresponding processing algorithms are intensively investigated to create and enrich Building Information Models (BIM) with as-is information and maintain their value across the building lifecycle. Point clouds can be captured using LiDAR and enriched with color information from images. Complementary to such dual-sensor systems, thermography captures the infrared light spectrum, giving insight into the temperature distribution on an object’s surface and allowing a diagnosis of the as-is energetic health of buildings beyond what humans can see. Although the three sensor modes are commonly used in pair-wise combinations, only a few systems leveraging the power of tri-modal sensor fusion have been proposed. This paper introduces a sensor system comprising LiDAR, RGB, and a radiometric thermal infrared sensor that can capture a 360-degree range through bi-axial rotation. The resulting tri-modal data is fused to a thermo-color point cloud from which temperature values are derived for a standard indoor building setting. Qualitative data analysis shows the potential for unlocking further object semantics in a state-of-the-art Scan-to-BIM pipeline. Furthermore, an outlook is provided on the cross-modal usage of semantic segmentation for automatic, accurate temperature calculations.

Automatic classification of smart sensor data for evaluating machine tool efficiency

The assessment of production plant efficiency is crucial for optimizing the operational performance of manufacturing systems. In traditional facilities, automated data collection is limited and information primarily relies on operators declarations, which are prone to inaccuracy. There is therefore a need for readily accessible digital alternatives. This paper introduces a cost-effective method for classifying the status of machine tools using smart sensors to monitor their primary doors with minimal integration, and a streamlined algorithm for efficient data processing. The innovative algorithm was conceived using data collected in over 3 months in a manufacturing plant comprising 50 diverse machine tools engaged in batch production for the automotive industry, and is based on non-dimensional thresholds, making it suitable for generic applications requiring classification of repetitive patterns. Also, a realistic simulator was developed to provide reliable data for algorithm accuracy evaluation. The classification performance was fully tested using synthetic data, showing very good accuracy. In addition, the performance of the algorithm was compared to basic machine learning approaches further proving the validity of the proposed method. Ultimately, the classification algorithm was employed to assess the Overall Equipment Effectiveness (OEE) of the real plant machines, which were closely aligned with the estimates provided by the enterprise management.

Comparing natural language processing representations of coded disease sequences for prediction in electronic health records.

Natural language processing (NLP) algorithms are increasingly being applied to obtain unsupervised representations of electronic health record (EHR) data, but their comparative performance at predicting clinical endpoints remains unclear. Our objective was to compare the performance of unsupervised representations of sequences of disease codes generated by bag-of-words versus sequence-based NLP algorithms at predicting clinically relevant outcomes. This cohort study used primary care EHRs from 6286233 people with Multiple Long-Term Conditions in England. For each patient, an unsupervised vector representation of their time-ordered sequences of diseases was generated using 2 input strategies (212 disease categories versus 9462 diagnostic codes) and different NLP algorithms (Latent Dirichlet Allocation, doc2vec, and 2 transformer models designed for EHRs). We also developed a transformer architecture, named EHR-BERT, incorporating sociodemographic information. We compared the performance of each of these representations (without fine-tuning) as inputs into a logistic classifier to predict 1-year mortality, healthcare use, and new disease diagnosis. Patient representations generated by sequence-based algorithms performed consistently better than bag-of-words methods in predicting clinical endpoints, with the highest performance for EHR-BERT across all tasks, although the absolute improvement was small. Representations generated using disease categories perform similarly to those using diagnostic codes as inputs, suggesting models can equally manage smaller or larger vocabularies for prediction of these outcomes. Patient representations produced by sequence-based NLP algorithms from sequences of disease codes demonstrate improved predictive content for patient outcomes compared with representations generated by co-occurrence-based algorithms. This suggests transformer models may be useful for generating multi-purpose representations, even without fine-tuning.

Integrated LSPR Biosensing Signal Processing Strategy and Visualization Implementation.

The LSPR biosensor chip is a groundbreaking tool popular in laboratory settings for identifying disease markers. However, its use in clinical environments is not as widespread. One notable gap is the lack of a universal signal processing tool for LSPR biosensing. To escalate its precision, there is an emerging need for software that not only optimizes signal processing but also incorporates self-verification functionalities within LSPR biochemical sensors. Enter the visual LSPR sensor software-an innovative platform that processes real-time transmission or reflection spectra. This advanced software adeptly captures the nuanced structural changes at the nanostructure interface prompted by environmental fluctuations. It diligently records and computes a suite of parameters, including the resonance wavelength shift, full width at half maximum, sensitivity, and quality factor. These features empower users to tailor processing algorithms for each data capture session. Transcending traditional instruments, this method accommodates a multitude of parameters and ensures robust result validation while tactfully navigating nanostructure morphology complexities. Forsaking third-party tool dependencies, the software tackles challenges of precision and cost-effectiveness head-on, heralding a significant leap forward in nanophotonics, especially for high-throughput LSPR biosensing applications. This user-centric innovation marks substantial progress in biochemical detection. It is designed to serve both researchers and practitioners in the field of nanophotonic sensing technology, simplifying complexity while enhancing reliability and efficiency.

Detection and Counting of Fake Currency & Genuine Currency Using Image Processing

In today's digital age, the proliferation of counterfeit currency poses a significant challenge to financial institutions and businesses worldwide. The detection and prevention of counterfeit currency transactions require advanced technological solutions to safeguard the integrity of financial systems. In our research, we present a novel approach to tackle this problem by leveraging image processing techniques. The proposed system utilizes state-of-the-art image processing algorithms to distinguish between fake and genuine currency notes accurately. By analyzing various features such as texture, color, and watermark patterns, our system can effectively identify counterfeit currency notes with high precision. Additionally, the system is capable of counting and validating genuine currency notes, providing a comprehensive solution for currency authentication and management. The integration of image processing technology into currency verification systems offers numerous benefits, including enhanced accuracy, speed, and reliability. Our research aims to contribute to the development of robust and efficient solutions for combating counterfeit currency fraud, thereby safeguarding the integrity of financial transactions and promoting trust in monetary systems.

A Hybrid Optimization Model for Efficient Detection and Classification of Malware in the Internet of Things

The proliferation of Internet of Things (IoT) devices and their integration into critical infrastructure and business operations has rendered them susceptible to malware and cyber-attacks. Such malware presents a threat to the availability and reliability of IoT devices, and a failure to address it can have far-reaching impacts. Due to the limited resources of IoT devices, traditional rule-based detection systems are often ineffective against sophisticated attackers. This paper addressed these issues by designing a new framework that uses a machine learning (ML) algorithm for the detection of malware. Additionally, it also employed sequential detection architecture and evaluated eight malware datasets. The design framework is lightweight and effective in data processing and feature selection algorithms. Moreover, this work proposed a classification model that utilizes one support vector machine (SVM) algorithm and is individually tuned with three different optimization algorithms. The employed optimization algorithms are Nuclear Reactor Optimization (NRO), Artificial Rabbits Optimization (ARO), and Particle Swarm Optimization (PSO). These algorithms are used to explore a diverse search space and ensure robustness in optimizing the SVM for malware detection. After extensive simulations, our proposed framework achieved the desired accuracy among eleven existing ML algorithms and three proposed ensemblers (i.e., NRO_SVM, ARO_SVM, and PSO_SVM). Among all algorithms, NRO_SVM outperforms the others with an accuracy rate of 97.8%, an F1 score of 97%, and a recall of 99%, and has fewer false positives and false negatives. In addition, our model successfully identified and prevented malware-induced attacks with a high probability of recognizing new evolving threats.

Braille-Vox Pro Empowering Inclusive Communication

Braille-Vox Pro is an innovative project with the objective of creating a voice-to-Braille conversion system for individuals with vision impairments. The project intends to overcome the reading and writing difficulties encountered by visually impaired individuals, which can have a substantial impact on their ability to access information and communicate effectively. By turning spoken words into Braille text in real-time, the technology will give a practical answer to these issues, allowing visually impaired people to be more autonomous and productive. The research employs advanced natural language processing algorithms capable of effectively recognizing and interpreting spoken words and translating them to Braille text. Also, the system will include a Braille display device that will allow visually impaired individuals to read the transformed text. The development of this technology will give visually impaired individuals with a new degree of accessibility and inclusion, providing them more effective communication and information access. The Braille-Vox Pro project is a huge advancement in assistive technology, providing visually impaired folks with a much-needed answer to their difficulties. By allowing individuals to read and write Braille with their voice, the technology will enhance their capacity to communicate, gain access to information, and participate more fully in society. This project has the potential to aid millions of visually impaired individuals worldwide, which is a tremendous impact. The Braille-Vox Pro project is an innovative and vital Endeavor that will have a significant influence on the lives of individuals with vision impairments. [1] Keywords— Sub-images, Fuzzy logic, Image enhancement, Histogram, HSV, Image processing.

Management, Utilization, and Outcomes of Preterm Labor in an Integrated Health Care System.

Fetal fibronectin (fFN) testing and transvaginal ultrasound (TVUS) are diagnostic tools used to predict impending spontaneous preterm birth (sPTB) among women presenting with preterm labor (PTL). We evaluated the association between fFN testing or TVUS cervical length (CL) measurement in predicting sPTB, respiratory distress syndrome (RDS), neonatal intensive care unit (NICU) admission, and sPTB-related costs. We conducted a retrospective cohort study using data from the Kaiser Permanente Southern California electronic health system (January 1, 2009-December 31, 2020) using diagnostic and procedure codes, along with a natural language processing algorithm to identify pregnancies with PTL evaluations. PTL evaluation was defined as having fFN and/or TVUS assessment. Outcomes were ascertained using diagnostic, procedural, and diagnosis-related group codes. Multivariable logistic regression assessed the association between fFN and/or TVUS results and perinatal outcomes. Compared with those without PTL evaluations, those with positive fFN tests had higher adjusted odds ratio (adj.OR) for sPTB (2.95, 95% confidence interval [CI]: 2.64, 3.29), RDS (2.34, 95% CI: 2.03, 2.69), and NICU admission (2.24, 95% CI: 2.01, 2.50). In contrast, those who tested negative had lower odds for sPTB (adj.OR: 0.75, 95% CI: 0.70, 0.79), RDS (adj.OR: 0.67, 95% CI: 0.61, 0.73), and NICU admission (adj.OR: 0.74, 95% CI: 0.70, 0.79). Among those with positive fFN results, the odds of sPTB was inversely associated with CL. Health care costs for mothers and neonates were lowest for those with fFN testing only. This study demonstrates that positive fFN results were associated with an increased odds of sPTB, RDS, and NICU admission and the association with sPTB was inversely proportional to CL. Additionally, negative fFN results were associated with decreased odds of sPTB, RDS, and NICU admissions. fFN testing may predict these and other sPTB-related adverse outcomes hence its utility should be explored further. Moreover, fFN testing has some cost savings over TVUS. · Patients with positive fFN tests had higher odds of sPTB, RDS, and NICU admission.. · Inverse relationship between sPTB and CL among those with positive fFN tests was observed.. · Health care costs for mothers and neonates were lowest for those with fFN testing only..

HEALPAL: YOUR PERSONAL HEALTH COMAPANION

In an era where rapid technological advancements intersect with healthcare needs, the development of an intelligent healthcare chatbot has emerged as a promising solution. This study presents a comprehensive exploration into the conceptualization, design, and implementation of an AI-powered chatbot tailored to provide accurate and personalized healthcare information. Integrating Natural Language Processing (NLP) algorithms and Artificial Intelligence Markup Language (AIML), the chatbot aims to bridge the gap between individuals and reliable medical knowledge. Keywords—Chatbot, NLP, Markup Language

Alamouti-coded DSP algorithm with a simplified PTBC decoder for next-generation optical access networks

The use of Alamouti-coded polarization-time block code (A-PTBC) in combination with a simple single polarization coherent receiver enables phase-diverse coherent detection without any optical polarization tracking. However, applying this technique to high-speed single-carrier systems is not straightforward, as it requires specialized digital signal processing (DSP) algorithms for data recovery, which increases DSP complexity. In this paper, we propose a novel Alamouti-coded coherent algorithm designed to significantly reduce the complexity of the receiver DSP for data recovery. The proposed algorithm achieves the comparable performance to the conventional algorithm but requires only half the number of necessary equalizers for data recovery. We validate its performance through simulations and also experimentally demonstrate a 100 Gb/s 16-quadrature amplitude modulation (QAM) single-carrier coherent system employed the single-polarization coherent receiver over 20 km of standard single-mode fiber (SMF). Through the performance verification, the coherent system with the proposed algorithm exhibits performance comparable to that of the conventional Alamouti-coded coherent system and achieves a power budget of 34 dB when the transmit launch power is set to 7 dBm at a Bit Error Rate (BER) of 1 × 10−2 for 0-20 km fiber transmission.

Identification of sleep phenotypes in COPD using machine learning-based cluster analysis

BackgroundDisturbed sleep in patients with COPD impact quality of life and predict adverse outcomes. Research questionTo identify distinct phenotypic clusters of patients with COPD using objective sleep parameters and evaluate the associations between clusters and all-cause mortality to inform risk stratification. Study design and methodsA longitudinal observational cohort study using nationwide Veterans Health Administration data of patients with COPD investigated for sleep disorders. Sleep parameters were extracted from polysomnography physician interpretation using a validated natural language processing algorithm. We performed cluster analysis using an unsupervised machine learning algorithm (K-means) and examined the association between clusters and mortality using Cox regression analysis, adjusted for potential confounders, and visualized with Kaplan-Meier estimates. ResultsAmong 9992 patients with COPD and a clinically indicated baseline polysomnogram, we identified five distinct clusters based on age, comorbidity burden and sleep parameters. Overall mortality increased from 9.4 % to 42 % and short-term mortality (<5.3 years) ranged from 3.4 % to 24.3 % in Cluster 1 to 5. In Cluster 1 younger age, in 5 high comorbidity burden and in the other three clusters, total sleep time and sleep efficiency had significant associations with mortality. InterpretationWe identified five distinct clinical clusters and highlighted the significant association between total sleep time and sleep efficiency on mortality. The identified clusters highlight the importance of objective sleep parameters in determining mortality risk and phenotypic characterization in this population.

A transdiagnostic prodrome for severe mental disorders: an electronic health record study.

Effective prevention of severe mental disorders (SMD), including non-psychotic unipolar mood disorders (UMD), non-psychotic bipolar mood disorders (BMD), and psychotic disorders (PSY), rely on accurate knowledge of the duration, first presentation, time course and transdiagnosticity of their prodromal stages. Here we present a retrospective, real-world, cohort study using electronic health records, adhering to RECORD guidelines. Natural language processing algorithms were used to extract monthly occurrences of 65 prodromal features (symptoms and substance use), grouped into eight prodromal clusters. The duration, first presentation, and transdiagnosticity of the prodrome were compared between SMD groups with one-way ANOVA, Cohen's f and d. The time course (mean occurrences) of prodromal clusters was compared between SMD groups with linear mixed-effects models. 26,975 individuals diagnosed with ICD-10 SMD were followed up for up to 12 years (UMD = 13,422; BMD = 2506; PSY = 11,047; median[IQR] age 39.8[23.7] years; 55% female; 52% white). The duration of the UMD prodrome (18[36] months) was shorter than BMD (26[35], d = 0.21) and PSY (24[38], d = 0.18). Most individuals presented with multiple first prodromal clusters, with the most common being non-specific ('other'; 88% UMD, 85% BMD, 78% PSY). The only first prodromal cluster that showed a medium-sized difference between the three SMD groups was positive symptoms (f = 0.30). Time course analysis showed an increase in prodromal cluster occurrences approaching SMD onset. Feature occurrence across the prodromal period showed small/negligible differences between SMD groups, suggesting that most features are transdiagnostic, except for positive symptoms (e.g. paranoia, f = 0.40). Taken together, our findings show minimal differences in the duration and first presentation of the SMD prodromes as recorded in secondary mental health care. All the prodromal clusters intensified as individuals approached SMD onset, and all the prodromal features other than positive symptoms are transdiagnostic. These results support proposals to develop transdiagnostic preventive services for affective and psychotic disorders detected in secondary mental healthcare.