Incorrect Application of Yilmaz-Poli (2022) Initialisation Method in dePater-Mitici 2023 paper entitled "A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers".

In this letter to the editor we report on a methodological error made in the article entitled "A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers" by dePater and Mitici recently appeared in this journal. The error relates to the incorrect application of a weight initialisation method we derived, published last year in this same journal.

Enhancing performance with multisensory cues in a realistic target discrimination task.

Making decisions is an important aspect of people's lives. Decisions can be highly critical in nature, with mistakes possibly resulting in extremely adverse consequences. Yet, such decisions have often to be made within a very short period of time and with limited information. This can result in decreased accuracy and efficiency. In this paper, we explore the possibility of increasing speed and accuracy of users engaged in the discrimination of realistic targets presented for a very short time, in the presence of unimodal or bimodal cues. More specifically, we present results from an experiment where users were asked to discriminate between targets rapidly appearing in an indoor environment. Unimodal (auditory) or bimodal (audio-visual) cues could shortly precede the target stimulus, warning the users about its location. Our findings show that, when used to facilitate perceptual decision under time pressure, and in condition of limited information in real-world scenarios, spoken cues can be effective in boosting performance (accuracy, reaction times or both), and even more so when presented in bimodal form. However, we also found that cue timing plays a critical role and, if the cue-stimulus interval is too short, cues may offer no advantage. In a post-hoc analysis of our data, we also show that congruency between the response location and both the target location and the cues, can interfere with the speed and accuracy in the task. These effects should be taken in consideration, particularly when investigating performance in realistic tasks.

A meta-learning BCI for estimating decision confidence.

Objective.We investigated whether a recently introduced transfer-learning technique based on meta-learning could improve the performance of brain-computer interfaces (BCIs) for decision-confidence prediction with respect to more traditional machine learning methods.Approach.We adapted the meta-learning by biased regularisation algorithm to the problem of predicting decision confidence from electroencephalography (EEG) and electro-oculogram (EOG) data on a decision-by-decision basis in a difficult target discrimination task based on video feeds. The method exploits previous participants' data to produce a prediction algorithm that is then quickly tuned to new participants. We compared it with with the traditional single-subject training almost universally adopted in BCIs, a state-of-the-art transfer learning technique called domain adversarial neural networks, a transfer-learning adaptation of a zero-training method we used recently for a similar task, and with a simple baseline algorithm.Main results.The meta-learning approach was significantly better than other approaches in most conditions, and much better in situations where limited data from a new participant are available for training/tuning. Meta-learning by biased regularisation allowed our BCI to seamlessly integrate information from past participants with data from a specific user to produce high-performance predictors. Its robustness in the presence of small training sets is a real-plus in BCI applications, as new users need to train the BCI for a much shorter period.Significance.Due to the variability and noise of EEG/EOG data, BCIs need to be normally trained with data from a specific participant. This work shows that even better performance can be obtained using our version of meta-learning by biased regularisation.

The NEVERMIND e-health system in the treatment of depressive symptoms among patients with severe somatic conditions: A multicentre, pragmatic randomised controlled trial.

Background: This study assessed the effectiveness of the NEVERMIND e-health system, consisting of a smart shirt and a mobile application with lifestyle behavioural advice, mindfulness-based therapy, and cognitive behavioural therapy, in reducing depressive symptoms among patients diagnosed with severe somatic conditions. Our hypothesis was that the system would significantly decrease the level of depressive symptoms in the intervention group compared to the control group. Methods: This pragmatic, randomised controlled trial included 425 patients diagnosed with myocardial infarction, breast cancer, prostate cancer, kidney failure, or lower limb amputation. Participants were recruited from hospitals in Turin and Pisa (Italy), and Lisbon (Portugal), and were randomly assigned to either the NEVERMIND intervention or to the control group. Clinical interviews and structured questionnaires were administered at baseline, 12 weeks, and 24 weeks. The primary outcome was depressive symptoms at 12 weeks measured by the Beck Depression Inventory II (BDI-II). Intention-to-treat analyses included 425 participants, while the per-protocol analyses included 333 participants. This trial is registered in the German Clinical Trials Register, DRKS00013391. Findings: Patients were recruited between Dec 4, 2017, and Dec 31, 2019, with 213 assigned to the intervention and 212 to the control group. The sample had a mean age of 59·41 years (SD=10·70), with 44·24% women. Those who used the NEVERMIND system had statistically significant lower depressive symptoms at the 12-week follow-up (mean difference=-3·03, p<0·001; 95% CI -4·45 to -1·62) compared with controls, with a clinically relevant effect size (Cohen's d=0·39). Interpretation: The results of this study show that the NEVERMIND system is superior to standard care in reducing and preventing depressive symptoms among patients with the studied somatic conditions. Funding: The NEVERMIND project received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreement No. 689691.

Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean.

The vanishing gradient problem (i.e., gradients prematurely becoming extremely small during training, thereby effectively preventing a network from learning) is a long-standing obstacle to the training of deep neural networks using sigmoid activation functions when using the standard back-propagation algorithm. In this paper, we found that an important contributor to the problem is weight initialization. We started by developing a simple theoretical model showing how the expected value of gradients is affected by the mean of the initial weights. We then developed a second theoretical model that allowed us to identify a sufficient condition for the vanishing gradient problem to occur. Using these theories we found that initial back-propagation gradients do not vanish if the mean of the initial weights is negative and inversely proportional to the number of neurons in a layer. Numerous experiments with networks with 10 and 15 hidden layers corroborated the theoretical predictions: If we initialized weights as indicated by the theory, the standard back-propagation algorithm was both highly successful and efficient at training deep neural networks using sigmoid activation functions.

Effect of different types of adhesive systems on the bond strength and marginal integrity of composite restorations in cavities prepared with the erbium laser-a systematic review.

There are inconclusive results regarding etching and bonding protocol to achieve optimal bond strength and marginal integrity of adhesive composite resin restorations in erbium laser prepared cavities. This systematic review aimed to consider which adhesive system protocol may be optimal in achieving the bond strength and marginal integrity in erbium laser-prepared cavities, comparable to that obtained with conventional method of cavity preparation. This review was developed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement with literature search based on all publications during the period January1, 2000-October 10, 2020, in three databases: MEDLINE, Google Scholar and ScienceDirect. The necessary information was extracted by two independent authors. The search resulted in 139 articles from all databases, and a total of thirty-one articles met the inclusion criteria. The results indicated that the selection of adhesives depending on their pH and composition and the laser pulse duration and pulse energy used plays an important role in predicting the adhesion and marginal integrity. The 10-MDP containing moderate self-etch adhesives has demonstrated predictable outcomes. Longer pulse durations used for cavity preparations may indicate the use of etch-and-rinse (EnR) or moderate self-etch adhesives (SEA) to allow better resin infiltration in deep craters formed due to laser irradiation. However, further studies with more standardizations in relation to adhesives and laser parameters are needed.

Anytime collaborative brain-computer interfaces for enhancing perceptual group decision-making.

In this paper we present, and test in two realistic environments, collaborative Brain-Computer Interfaces (cBCIs) that can significantly increase both the speed and the accuracy of perceptual group decision-making. The key distinguishing features of this work are: (1) our cBCIs combine behavioural, physiological and neural data in such a way as to be able to provide a group decision at any time after the quickest team member casts their vote, but the quality of a cBCI-assisted decision improves monotonically the longer the group decision can wait; (2) we apply our cBCIs to two realistic scenarios of military relevance (patrolling a dark corridor and manning an outpost at night where users need to identify any unidentified characters that appear) in which decisions are based on information conveyed through video feeds; and (3) our cBCIs exploit Event-Related Potentials (ERPs) elicited in brain activity by the appearance of potential threats but, uniquely, the appearance time is estimated automatically by the system (rather than being unrealistically provided to it). As a result of these elements, in the two test environments, groups assisted by our cBCIs make both more accurate and faster decisions than when individual decisions are integrated in more traditional manners.

Subject- and task-independent neural correlates and prediction of decision confidence in perceptual decision making.

Objective.In many real-world decision tasks, the information available to the decision maker is incomplete. To account for this uncertainty, we associate a degree of confidence to every decision, representing the likelihood of that decision being correct. In this study, we analyse electroencephalography (EEG) data from 68 participants undertaking eight different perceptual decision-making experiments. Our goals are to investigate (1) whether subject- and task-independent neural correlates of decision confidence exist, and (2) to what degree it is possible to build brain computer interfaces that can estimate confidence on a trial-by-trial basis. The experiments cover a wide range of perceptual tasks, which allowed to separate the task-related, decision-making features from the task-independent ones.Approach.Our systems train artificial neural networks to predict the confidence in each decision from EEG data and response times. We compare the decoding performance with three training approaches: (1) single subject, where both training and testing data were acquired from the same person; (2) multi-subject, where all the data pertained to the same task, but the training and testing data came from different users; and (3) multi-task, where the training and testing data came from different tasks and subjects. Finally, we validated our multi-task approach using data from two additional experiments, in which confidence was not reported.Main results.We found significant differences in the EEG data for different confidence levels in both stimulus-locked and response-locked epochs. All our approaches were able to predict the confidence between 15% and 35% better than the corresponding reference baselines.Significance.Our results suggest that confidence in perceptual decision making tasks could be reconstructed from neural signals even when using transfer learning approaches. These confidence estimates are based on the decision-making process rather than just the confidence-reporting process.

Decoding of semantic categories of imagined concepts of animals and tools in fNIRS.

Objective.Semantic decoding refers to the identification of semantic concepts from recordings of an individual's brain activity. It has been previously reported in functional magnetic resonance imaging and electroencephalography. We investigate whether semantic decoding is possible with functional near-infrared spectroscopy (fNIRS). Specifically, we attempt to differentiate between the semantic categories of animals and tools. We also identify suitable mental tasks for potential brain-computer interface (BCI) applications.Approach.We explore the feasibility of a silent naming task, for the first time in fNIRS, and propose three novel intuitive mental tasks based on imagining concepts using three sensory modalities: visual, auditory, and tactile. Participants are asked to visualize an object in their minds, imagine the sounds made by the object, and imagine the feeling of touching the object. A general linear model is used to extract hemodynamic responses that are then classified via logistic regression in a univariate and multivariate manner.Main results.We successfully classify all tasks with mean accuracies of 76.2% for the silent naming task, 80.9% for the visual imagery task, 72.8% for the auditory imagery task, and 70.4% for the tactile imagery task. Furthermore, we show that consistent neural representations of semantic categories exist by applying classifiers across tasks.Significance.These findings show that semantic decoding is possible in fNIRS. The study is the first step toward the use of semantic decoding for intuitive BCI applications for communication.

Laser Analgesia Associated with Restorative Dental Care: A Systematic Review of the Rationale, Techniques, and Energy Dose Considerations.

It is a common experience amongst laser dentists and patients that mid-IR wavelength application in cavity preparation may be achieved without causing any associated pain. The erbium family of lasers (Er,Cr:YSGG 2780 nm and Er:YAG 2940 nm) are frequently used without employing injectable local anesthesia as an adjunct: the phenomenon arising from the application of these devices is known as laser analgesia. This review seeks to apply a systematic approach to the examination of appropriate published studies but also to highlight the need for much more structured clinical investigations that consolidate photonic dose and methodology. A search of published data using PRISMA criteria was carried out to examine clinical trials into laser analgesia in conjunction with restorative dentistry, applying inclusion and exclusion criteria. From this, 10 published articles were selected for analysis. Suitability assessment was carried out, using a modified Cochrane risk of bias methodology. In 8/10 of the included studies, laser-induced analgesia is claimed to be better and effective, while in 2/10 of the studies, no difference was exhibited compared to the control group. Statistical analysis of three split mouth studies concluded that only one of these investigations reviewed demonstrated a significant analgesic effect for laser treatment while the other two did not support this observation. From this data, it is inconclusive to assess the predictability of laser analgesia in cavity preparation. A possible rationale and laser operating parametry has been discussed. Successful implementation of this treatment modality remains technique sensitive and subject to further investigation.

Potential pitfalls of widely used implementations of common spatial patterns.

We have uncovered serious flaws in handling EEG signals with a decreased rank in implementations of the common spatial patterns (CSP). The CSP algorithm assumes covariance matrices of the signal to have full rank. However, preprocessing techniques, such as artifact removal using independent component analysis, may decrease the rank of the signal, leading to potential errors in the CSP decomposition. We inspect what could go wrong when CSP implementations do not take this into consideration on a binary motor imagery classification task. We review CSP implementations in open-source toolboxes for EEG signal analysis (FieldTrip, BBCI Toolbox, BioSig, EEGLAB, BCILAB, and MNE). We show that unprotected implementations decreased mean classification accuracy by up to 32%, with spatial filters resulting in complex numbers, for which corresponding spatial patterns do not have a clear interpretation. We encourage researchers to check their implementations and analysis pipelines.

A protocol for a multicentre, parallel-group, pragmatic randomised controlled trial to evaluate the NEVERMIND system in preventing and treating depression in patients with severe somatic conditions.

BACKGROUND: Depressive symptoms are common in individuals suffering from severe somatic conditions. There is a lack of interventions and evidence-based interventions aiming to reduce depressive symptoms in patients with severe somatic conditions. The aim of the NEVERMIND project is to address these issues and provide evidence by testing the NEVERMIND system, designed to reduce and prevent depressive symptoms in comparison to treatment as usual. METHODS: The NEVERMIND study is a parallel-groups, pragmatic randomised controlled trial to assess the effectiveness of the NEVERMIND system in reducing depressive symptoms among individuals with severe somatic conditions. The NEVERMIND system comprises a smart shirt and a user interface, in the form of a mobile application. The system is a real-time decision support system, aiming to predict the severity and onset of depressive symptoms by modelling the well-being condition of patients based on physiological data, body movement, and the recurrence of social interactions. The study includes 330 patients who have a diagnosis of myocardial infarction, breast cancer, prostate cancer, kidney failure, or lower limb amputation. Participants are randomised in blocks of ten to either the NEVERMIND intervention or treatment as usual as the control group. Clinical interviews and structured questionnaires are administered at baseline, at 12 weeks, and 24 weeks to assess whether the NEVERMIND system is superior to treatment as usual. The endpoint of primary interest is Beck Depression Inventory II (BDI-II) at 12 weeks defined as (i) the severity of depressive symptoms as measured by the BDI-II. Secondary outcomes include prevention of the onset of depressive symptoms, changes in quality of life, perceived stigma, and self-efficacy. DISCUSSION: There is a lack of evidence-based interventions aiming to reduce and prevent depressive symptoms in patients with severe somatic conditions. If the NEVERMIND system is effective, it will provide healthcare systems with a novel and innovative method to attend to depressive symptoms in patients with severe somatic conditions. TRIAL REGISTRATION: DRKS00013391. Registered 23 November 2017.

SEEDS, simultaneous recordings of high-density EMG and finger joint angles during multiple hand movements.

We present the SurfacE Electromyographic with hanD kinematicS (SEEDS) database. It contains electromyographic (EMG) signals and hand kinematics recorded from the forearm muscles of 25 non-disabled subjects while performing 13 different movements at normal and slow-paced speeds. EMG signals were recorded with a high-density 126-channel array centered on the extrinsic flexors of the fingers and 8 further electrodes placed on the extrinsic extensor muscles. A data-glove was used to record 18 angles from the joints of the wrist and fingers. The correct synchronisation of the data-glove and the EMG was ascertained and the resulting data were further validated by implementing a simple classification of the movements. These data can be used to test experimental hypotheses regarding EMG and hand kinematics. Our database allows for the extraction of the neural drive as well as performing electrode selection from the high-density EMG signals. Moreover, the hand kinematic signals allow the development of proportional methods of control of the hand in addition to the more traditional movement classification approaches.

Cyborg groups enhance face recognition in crowded environments.

Recognizing a person in a crowded environment is a challenging, yet critical, visual-search task for both humans and machine-vision algorithms. This paper explores the possibility of combining a residual neural network (ResNet), brain-computer interfaces (BCIs) and human participants to create "cyborgs" that improve decision making. Human participants and a ResNet undertook the same face-recognition experiment. BCIs were used to decode the decision confidence of humans from their EEG signals. Different types of cyborg groups were created, including either only humans (with or without the BCI) or groups of humans and the ResNet. Cyborg groups decisions were obtained weighing individual decisions by confidence estimates. Results show that groups of cyborgs are significantly more accurate (up to 35%) than the ResNet, the average participant, and equally-sized groups of humans not assisted by technology. These results suggest that melding humans, BCI, and machine-vision technology could significantly improve decision-making in realistic scenarios.

Correction: Cyborg groups enhance face recognition in crowded environments.

[This corrects the article DOI: 10.1371/journal.pone.0212935.].

Neurotechnologies for Human Cognitive Augmentation: Current State of the Art and Future Prospects.

Recent advances in neuroscience have paved the way to innovative applications that cognitively augment and enhance humans in a variety of contexts. This paper aims at providing a snapshot of the current state of the art and a motivated forecast of the most likely developments in the next two decades. Firstly, we survey the main neuroscience technologies for both observing and influencing brain activity, which are necessary ingredients for human cognitive augmentation. We also compare and contrast such technologies, as their individual characteristics (e.g., spatio-temporal resolution, invasiveness, portability, energy requirements, and cost) influence their current and future role in human cognitive augmentation. Secondly, we chart the state of the art on neurotechnologies for human cognitive augmentation, keeping an eye both on the applications that already exist and those that are emerging or are likely to emerge in the next two decades. Particularly, we consider applications in the areas of communication, cognitive enhancement, memory, attention monitoring/enhancement, situation awareness and complex problem solving, and we look at what fraction of the population might benefit from such technologies and at the demands they impose in terms of user training. Thirdly, we briefly review the ethical issues associated with current neuroscience technologies. These are important because they may differentially influence both present and future research on (and adoption of) neurotechnologies for human cognitive augmentation: an inferior technology with no significant ethical issues may thrive while a superior technology causing widespread ethical concerns may end up being outlawed. Finally, based on the lessons learned in our analysis, using past trends and considering other related forecasts, we attempt to forecast the most likely future developments of neuroscience technology for human cognitive augmentation and provide informed recommendations for promising future research and exploitation avenues.

Brain⁻Computer Interfaces for Human Augmentation.

The field of brain⁻computer interfaces (BCIs) has grown rapidly in the last few decades, allowing the development of ever faster and more reliable assistive technologies for converting brain activity into control signals for external devices for people with severe disabilities [...].

Collaborative Brain-Computer Interfaces to Enhance Group Decisions in an Outpost Surveillance Task.

We present a two-layered collaborative Brain-Computer Interface (cBCI) to aid groups making decisions under time constraints in a realistic video surveillance setting - the very first cBCI application of this type. The cBCI first uses response times (RTs) to estimate the decision confidence the user would report after each decision. Such an estimate is then used with neural features extracted from EEG to refine the decision confidence so that it better correlates with the correctness of the decision. The refined confidence is then used to weigh individual responses and obtain group decisions. Results obtained with 10 participants indicate that cBCI-assisted groups are significantly more accurate than groups using standard majority or weighing decisions using reported confidence values. This two-layer architecture allows the cBCI to not only further enhance group performance but also speed up the decision process, as the cBCI does not have to wait for all users to report their confidence after each decision.