High-level Recognition Research Articles

Does culture moderate the encoding and recognition of negative cues? Evidence from an eye-tracking study.

Cross-cultural research has elucidated many important differences between people from Western European and East Asian cultural backgrounds regarding how each group encodes and consolidates the contents of complex visual stimuli. While Western European groups typically demonstrate a perceptual bias towards centralised information, East Asian groups favour a perceptual bias towards background information. However, this research has largely focused on the perception of neutral cues and thus questions remain regarding cultural group differences in both the perception and recognition of negative, emotionally significant cues. The present study therefore compared Western European (n = 42) and East Asian (n = 40) participants on a free-viewing task and a subsequent memory task utilising negative and neutral social cues. Attentional deployment to the centralised versus background components of negative and neutral social cues was indexed via eye-tracking, and memory was assessed with a cued-recognition task two days later. While both groups demonstrated an attentional bias towards the centralised components of the neutral cues, only the Western European group demonstrated this bias in the case of the negative cues. There were no significant differences observed between Western European and East Asian groups in terms of memory accuracy, although the Western European group was unexpectedly less sensitive to the centralised components of the negative cues. These findings suggest that culture modulates low-level attentional deployment to negative information, however not higher-level recognition after a temporal interval. This paper is, to our knowledge, the first to concurrently consider the effect of culture on both attentional outcomes and memory for both negative and neutral cues.

Transfer Learning Based Traffic Light Detection and Recognition Using CNN Inception-V3 Model

Due to the lack of vehicle-to-infrastructure (V2I) communication in the existing transportation systems, traffic light detection and recognition is essential for advanced driver assistant systems (ADAS) and road infrastructure surveys. Additionally, autonomous vehicles have the potential to change urban transportation by making it safe, economical, sustainable, congestion-free, and transportable in other ways. Because of their limitations, traditional traffic light detection and recognition algorithms are not able to recognize traffic lights as effectively as deep learning-based techniques, which take a lot of time and effort to develop. The main aim of this research is to propose a traffic light detection and recognition model based on a transfer learning-based model that uses the Inception-V3 network model to significantly reduce the amount of training data and computing costs. The proposed model was trained and tested in the laboratory for the intelligent and safe automobiles (LISA) traffic light dataset, which has been augmented by several pre-processing methods. Then, using different convolution and pooling techniques, the retrieved layer-wise features were compared and analyzed. Lastly, great reliability and repeatability are seen based on statistical analysis when the transfer learning-based model is frequently retrained utilizing precise tuning parameters. The results demonstrate that a transfer learning-based model is capable of high-level recognition performance in the proposed model, with an accuracy rate of 98.6%.

Radial bias in face identification

Human vision in the periphery is most accurate for stimuli that point towards the fovea. This so-called radial bias has been linked with the organization and spatial selectivity of neurons at the lowest levels of the visual system, from retinal ganglion cells onwards. Despite evidence that the human visual system is radially biased, it is not yet known whether this bias persists at higher levels of processing, or whether high-level representations are invariant to this low-level orientation bias. We used the case of face identity recognition to address this question. The specialized high-level mechanisms that support efficient face recognition are highly dependent on horizontally oriented information, which convey the most useful identity cues in the fovea. We show that face selective mechanisms are more sensitive on the horizontal meridian (to the left and right of fixation) compared to the vertical meridian (above and below fixation), suggesting that the horizontal cues in the face are better extracted on the horizontal meridian, where they align with the radial bias. The results demonstrate that the radial bias is maintained at high-level recognition stages and emphasize the importance of accounting for the radial bias in future investigation of visual recognition processes in peripheral vision.

Optically transparent graphene-based cognitive metasurface for adaptive frequency manipulation

Optically transparent microwave absorbing metasurfaces have shown great potential and are needed in multiple applications environments containing optical windows owing to their ability to reduce backscattering electromagnetic (EM) signals while keeping continuous optical observation. Meanwhile, they are also required to have adaptive EM manipulation capability to cope with complex and capricious EM environments. As a general approach, distributed circuit components, including positive-intrinsic-negative diodes and varactors and sensing components, are integrated with passive absorbing metasurfaces to realize adaptive control of microwave absorption. However, these circuit elements generally require bulky electrical wires and complex control circuits to regulate the operating state, resulting in the absorbing structures being optically opaque. Hence, it is a great challenge to realize self-operating absorbers while maintaining optical transparency. Here, we report an optically transparent cognitive metasurface made of patterned graphene sandwich structures and a radio frequency detector, which can achieve adaptive frequency manipulation to match incident EM waves. As a proof-of-principle application example, we realize a closed-loop automatic absorber system prototype of the proposed graphene metasurface with self-adaptive frequency variation, without any human intervention. The approach may facilitate other adaptive metadevices in microwave regime with high-level recognition and manipulation and, more generally, promote the development of intelligent stealth technologies.

Comparative Analysis of Bacillariophyceae Chloroplast Genomes Uncovers Extensive Genome Rearrangements Associated with Speciation.

The Bacillariophyceae is a species-rich, ecologically significant class of Bacillariophyta. Despite their critical importance in marine ecosystems as primary producers and in the development of harmful algal blooms (HABs), taxonomic research on Bacillariophyceae species has been hindered because of their limited morphological features, plasticity of morphologies, and the low resolution of common molecular markers. Hence molecular markers with improved resolution are urgently needed. Organelle genomes, which can be constructed efficiently with the recent development of high throughput DNA sequencing technologies and the advancement of bioinformatics tools, have been proposed as super barcodes for their higher resolution for distinguishing different species and intra-species genomic variations. In this study, we tested the value of full-length chloroplast genomes (cpDNAs) as super barcodes for distinguishing diatom species, by constructing cpDNAs of 11 strains of the class Bacillariophyceae, including Nitzschia ovalis, Nitzschia traheaformis, Cylindrotheca spp., Psammodictyon constrictum, Bacillaria paxillifer, two strains of Haslea tsukamotoi, Haslea avium, Navicula arenaria, and Pleurosigma sp. Comparative analysis of cpDNAs revealed that cpDNAs were not only adequate for resolving different species, but also for enabling recognition of high levels of genome rearrangements between cpDNAs of different species, especially for species of the genera Nitzschia, Cylindrotheca, Navicula and Haslea. Additionally, comparative analysis suggested that the positioning of species in the genus Haslea should be transferred to the genus Navicula. Chloroplast genome-based evolutionary analysis suggested that the Bacillariophyceae species first appeared during the Cretaceous period and the diversity of species rose after the mass extinction about 65 Mya. This study highlighted the value of cpDNAs in research on the biodiversity and evolution of Bacillariophyceae species, and, with the construction of more cpDNAs representing additional genera, deeper insight into the biodiversity and evolutionary relationships of Bacillariophyceae species will be gained.

Jarvis: AI Virtual Assistant

"Jarvis" was the protagonist of Tony's Stark starring in the movie Iron Man. Unlike the first jokes when Jarvis was Stark's servant, Jarvis' movie version is a smart computer that communicates critical issues, monitors his family, and helps build and organize his hero's suit. In this project, Jarvis is a Digital Health Assistant who uses social media i.e., voice that creates two-way communication between people and his personnel Computer, performing various tasks such as calling and chatting on WhatsApp, taking notes, locating, etc. In our project, we use the word just as communication means that Jarvis is a Speech recognition program. The concept of speech technology combines two technologies: Synthesizer and vision. Speech synthesizer captures input and generates audio streams as output this is achieved using the pyttsx3 library accompanied by Speech function. Speech recognition. On the other hand, he did the opposite. It treats audio streaming as input and thus converts it into text writing and this output uses the Speech Recognition library accompanied by the TakeCommand function. The word is a symbol of endless knowledge. Direct analysis and integration of complex voice signal is due to the vast amount of information contained in the signal. Therefore, digital signal processes such as Feature Visibility and Feature Matching are introduced to represent the voice signal. For this project, we are directly using a speech engine that uses an output element such as Mel scaled frequency cepstral. The mel scale frequency cepstral coefficients (MFCCs) obtained from the fourier transform and filter bank analysis are probably the most widely used in high-level speech recognition systems. We aim to create more jobs that can help people in their daily lives and reduce their efforts as in this project we have introduced Chrome and Youtube Automation. In our test, we checked that all of this functionality works well. We test this on 2 speakers (1 female and 1 male) to find the exact motive for the speculation.

Competing voices: Indigenous rights in the shadow of conventional fisheries management in the tropical rock lobster fishery in Torres Strait, Australia

Much progress has been made in recent decades in achieving high-level recognition of indigenous fishing rights. Despite these advances, actualization of indigenous rights to own and control marine resources has proven challenging. Insufficient attention to the centrality of power and its workings in fisheries are often the subject of critiques and of calls for more empirical research. This paper draws on interviews, participant observation, cognitive mapping, scenario workshops, and policy document review to examine power configurations and dynamics in the tropical rock lobster (TRL) fishery in Torres Strait (TS), Australia. Despite recognition of indigenous commercial fishing rights by the High Court in 2013, there have been only limited changes in how fisheries governance operates in the region. The current TRL management plan also risks entrenching non-indigenous interests in the fishery, thereby preventing Islanders from achieving their aspiration to fully own and control TS fisheries. Through an analysis drawing from Foucault’s theory of governmentality and Blaser’s political ontology framework, we show (1) how current fisheries management structures, processes and discourses are at odds with Islanders’ conceptions of the fisheries; and (2) how the existing regime excludes and renders silent Islander priorities. Our findings extend to indigenous-state relations in other state-managed fisheries. We believe our proposed conceptual framework can be useful in unveiling power relations that constrain indigenous rights and in identifying transformation options. We conclude that a sea change in conventional fisheries governance arrangements is needed to respond to new imperatives and expectations around indigenous fishing rights and interests.

How Networks of Citizen Observatories Can Increase the Quality and Quantity of Citizen-Science-Generated Data Used to Monitor SDG Indicators

There is a growing acknowledgement that citizen observatories, and other forms of citizen-generated data, have a significant role in tracking progress towards the Sustainable Development Goals. This is evident in the increasing number of Sustainable Development Goals’ indicators for which such data are already being used and in the high-level recognition of the potential role that citizen science can play. In this article, we argue that networks of citizen observatories will help realise this potential. Drawing on the Cos4Cloud project as an example, we highlight how such networks can make citizen-generated data more interoperable and accessible (among other qualities), increasing their impact and usefulness. Furthermore, we highlight other, perhaps overlooked, advantages of citizen observatories and citizen-generated data: educating and informing citizen scientists about the Sustainable Development Goals and co-creating solutions to the global challenges they address.

Video Content Analysis of Human Sports under Engineering Management Incorporating High-Level Semantic Recognition Models.

In this paper, a high-level semantic recognition model is used to parse the video content of human sports under engineering management, and the stream shape of the previous layer is embedded in the convolutional operation of the next layer, so that each layer of the convolutional neural network can effectively maintain the stream structure of the previous layer, thus obtaining a video image feature representation that can reflect the image nearest neighbor relationship and association features. The method is applied to image classification, and the experimental results show that the method can extract image features more effectively, thus improving the accuracy of feature classification. Since fine-grained actions usually share a very high similarity in phenotypes and motion patterns, with only minor differences in local regions, inspired by the human visual system, this paper proposes integrating visual attention mechanisms into the fine-grained action feature extraction process to extract features for cues. Taking the problem as the guide, we formulate the athlete's tacit knowledge management strategy and select the distinctive freestyle aerial skills national team as the object of empirical analysis, compose a more scientific and organization-specific tacit knowledge management program, exert influence on the members in the implementation, and revise to form a tacit knowledge management implementation program with certain promotion value. Group behavior can be identified by analyzing the behavior of individuals and the interaction information between individuals. Individual interactions in a group can be represented by individual representations, and the relationship between individual behaviors can be analyzed by modeling the relationship between individual representations. The performance improvement of the method on mismatched datasets is comparable between the long-short time network based on temporal information and the language recognition method with high-level semantic embedding vectors, with the two methods improving about 12.6% and 23.0%, respectively, compared with the method using the original model and with the i-vector baseline system based on the support vector machine classification method with radial basis functions, with performance improvements about 10.10% and 10.88%, respectively.

Prospects for Valuation in Marine Decision Making in Europe

There is now high-level recognition that the UN Sustainable Development Goals can only be achieved if the decline of ecosystems and biodiversity can be halted and reversed. This will require effective control of ongoing pressures, meaningful protection and enforcement of protected areas, and significant investments in ecosystem restoration. This paper explores the possible use of economic valuation and appraisal in achieving these goals in marine systems and discusses the European marine policy instruments where they should have an important role The paper first briefly reviews the tools of economic valuation and appraisal for marine ecosystem management. A critique of the use of economic valuation and appraisal in marine conservation and restoration is then presented. The paper argues that while progress has been made there remains a pressing need for better integration of marine environmental values in policy processes. It also highlights the fact that the focus on natural capital accounting, and more generally on green/blue growth and market instruments, could create a reliance on exchange values at the expense of welfare values required for policy appraisal.

Research and Practice of Telecommunication User Rating Method Based on Machine Learning

The machine learning model has advantages in multi-category credit rating classification. It can replace discriminant analysis based on statistical methods, greatly helping credit rating reduce human interference and improve rating efficiency. Therefore, we use a variety of machine learning algorithms to study the credit rating of telecom users. This paper conducts data understanding and preprocessing on Operator Telecom user data, and matches the user’s characteristics and tags based on the time sliding window method. In order to deal with the deviation caused by the imbalance of multi-category data, the SMOTE oversampling method is used to balance the data. Using the Removing features with low variance method and packaging method for feature selection, then the basic models are established. The empirical results of the model show that the Random Forest and XGBOOST ensemble models are better than the single models such as Bayes, SVM, KNN, and Decision Tree. The performance of Decision Tree in single models is better. Therefore, Random Forest, XGBOOST and Decision Tree models were selected to debug the hyper parameters to achieve model optimization. Based on the optimized model, the accuracy, recall, precision, confusion matrix and other indicators are evaluated, and it is concluded that low-level recognition is more accurate than high-level recognition and fewer misjudgments. Comparing the evaluation indicators of each level of different models, it is found that the integrated model performs better, indicating that Random Forest and XGBOOST are more suitable for solving the problem of telecommunications user rating. For this reason, this article proposes an implementation plan based on Random Forest and XGBOOST algorithm and model for the problem of telecommunications user rating.

Making Room for Everyone’s Talent

See RECORDING. Current societal challenges demand more cooperation and a multidisciplinary approach from scientists. Putting into practice the shared ambition in Dutch academia requires a modernisation of the system of Recognition & Rewards. The modernisation should improve the quality of each of the key areas in academia: education, research, impact, leadership and (for university medical centres) patient care. Why do we think a change in recognition and rewards is needed? We see a mismatch between what we deem important in academic work and what we reward academic staff for. Careers depend heavily on research performance, which is measured by a limited number of criteria. We need a better balance in how we recognize and reward academics to help us achieve excellent education, research, impact, and leadership, as well as the highest level of patient care in our university medical centres. We want to make Room for everyone’s talent! In the Dutch Recognition & Rewards programme we work in cooperation with all Dutch research universities, university medical centres, reputable research institutes, the Royal Academy, and research funders. We aim for a healthy and inspiring environment for all our staff, where all talents are valued. In this presentation I will explain what we want to change in academic career assessment in the Netherlands, and how we hope to initiate the desired cultural change. This change is a fundamental change of beliefs, not just a change in the rules of the game. To achieve this, a broad dialogue in academia is needed. We think that sharing best practices and experimenting will initiate the desired movement. Every university and research organisation in the Netherlands has set up a high-level Recognition & Rewards committee. The various committees are working enthusiastically to stimulate the intended culture change at an institutional level. There is a great and inspiring diversity of approaches. Experimenting, inspiring, co-creating, sharing best practices, and learning from each other are central in the joint programme. At a national level, we also monitor the commonality and ensure connections between the developments at the universities, university medical centres, research institutes, and research funders. We are aware that the Netherlands is only a very small country. We cannot change academic career assessment on our own. We need to work together all over the world to change the recognition and rewards of academics. We hope you are curious, critical, and open about your concerns and become involved!

To Grasp the World at a Glance: The Role of Attention in Visual and Semantic Associative Processing.

Associative relations among words, concepts and percepts are the core building blocks of high-level cognition. When viewing the world ‘at a glance’, the associative relations between objects in a scene, or between an object and its visual background, are extracted rapidly. The extent to which such relational processing requires attentional capacity, however, has been heavily disputed over the years. In the present manuscript, I review studies investigating scene–object and object–object associative processing. I then present a series of studies in which I assessed the necessity of spatial attention to various types of visual–semantic relations within a scene. Importantly, in all studies, the spatial and temporal aspects of visual attention were tightly controlled in an attempt to minimize unintentional attention shifts from ‘attended’ to ‘unattended’ regions. Pairs of stimuli—either objects, scenes or a scene and an object—were briefly presented on each trial, while participants were asked to detect a pre-defined target category (e.g., an animal, a nonsense shape). Response times (RTs) to the target detection task were registered when visual attention spanned both stimuli in a pair vs. when attention was focused on only one of two stimuli. Among non-prioritized stimuli that were not defined as to-be-detected targets, findings consistently demonstrated rapid associative processing when stimuli were fully attended, i.e., shorter RTs to associated than unassociated pairs. Focusing attention on a single stimulus only, however, largely impaired this relational processing. Notably, prioritized targets continued to affect performance even when positioned at an unattended location, and their associative relations with the attended items were well processed and analyzed. Our findings portray an important dissociation between unattended task-irrelevant and task-relevant items: while the former require spatial attentional resources in order to be linked to stimuli positioned inside the attentional focus, the latter may influence high-level recognition and associative processes via feature-based attentional mechanisms that are largely independent of spatial attention.

Human Action recognition using STIP Evaluation techniques

Human action recognition plays a big role in human-to-human interaction and interpersonal relations. As a result, it provides information regarding the identity of someone, their temperament, and condition, it’s tough to extract. Recognition of actions within the video isn’t a matter for human sensory system. The identification of the actions of the person by the system wants someone special mechanisms. The identification of the actions by the systems are going to be useful in computer vision method. This method is divided into low level action recognition process and high level recognition process. Recognizing the actions victimization the one feature values extracted goes under low level action recognition method. These method is simple to implement and that they don’t seem to be reliable all the time. The high level action recognition method needs some special hardware’s to discover the actions within the video. The experimental results proved that the proposed methodology achieved better performance in terms of accuracy, sensitivity and specificity.

Continuous flash suppression: Known and unknowns.

Studies utilizing continuous flash suppression (CFS) provide valuable information regarding conscious and nonconscious perception. There are, however, crucial unanswered questions regarding the mechanisms of suppression and the level of visual processing in the absence of consciousness with CFS. Research suggests that the answers to these questions depend on the experimental configuration and how we assess consciousness in these studies. The aim of this review is to evaluate the impact of different experimental configurations and the assessment of consciousness on the results of the previous CFS studies. We review studies that evaluated the influence of different experimental configuration on the depth of suppression with CFS and discuss how different assessments of consciousness may impact the results of CFS studies. Finally, we review behavioral and brain recording studies of CFS. In conclusion, previous studies provide evidence for survival of low-level visual information and complete impairment of high-level visual information under the influence of CFS. That is, studies suggest that nonconscious perception of lower-level visual information happens with CFS, but there is no evidence for nonconscious high-level recognition with CFS.

Effects of Caffeine on Event-Related Potentials and Neuropsychological Indices After Sleep Deprivation.

Objective: Caffeine is a central nervous system stimulant that can effectively alleviate brain fatigue and low cognitive efficiency induced by total sleep deprivation (TSD). Recent studies have demonstrated that caffeine can improve subjective attention and objective behavioral metrics, such as arousal level, reaction time, and memory efficiency. However, only a few studies have examined the electrophysiological changes caused by the caffeine in humans following sleep disturbance. In this study, an event-related potential (ERP) technique was employed to measure the behavioral, cognitive, and electrophysiological changes produced by caffeine administration after TSD.Methods: Sixteen healthy subjects within-subject design performed a visual Go/No-Go task with simultaneous electroencephalogram recording. Behavioral and ERP data were evaluated after 36 h of TSD, and the effects of ingestion of either 400 mg of caffeine or placebo were compared in a double-blind randomized design.Results: Compared with placebo administration, the Go hit rates were significantly enhanced in the caffeine condition. A simple effect analysis revealed that, compared with baseline, the Go-P2 amplitude was significantly enhanced after TSD in the caffeine consumption condition. A significant main effect of the drug was found on No-Go-P2, No-Go-N2 amplitude, and Go-P2 latency before and after TSD.Conclusion: Our findings indicate that caffeine administration has acute effects on improving the efficiency of individual automatic reactions and early cognitive processes. Caffeine was related to the preservation of an individual’s arousal level and accelerated response-related decisions, while subjects’ higher-level recognition had limited improvement with prolonged awareness.

Smart sensing metasurface with self-defined functions in dual polarizations

Abstract For the intelligence of metamaterials, the -sensing mechanism and programmable reaction units are two important components for self-recognition and -determination. However, their realization still face great challenges. Here, we propose a smart sensing metasurface to achieve self-defined functions in the framework of digital coding metamaterials. A sensing unit that can simultaneously process the sensing channel and realize phase-programmable capability is designed by integrating radio frequency (RF) power detector and PIN diodes. Four sensing units distributed on the metasurface aperture can detect the microwave incidences in the x- and y-polarizations, while the other elements can modulate the reflected phase patterns under the control of a field programmable gate array (FPGA). To validate the performance, three schemes containing six coding patterns are presented and simulated, after which two of them are measured, showing good agreements with designs. We envision that this work may motivate studies on smart metamaterials with high-level recognition and manipulation.

Reading into the mind’s eye: Boosting automatic visual recognition with EEG signals

Classifying visual information is an apparently simple and effortless task in our everyday routine, but can we automatically predict what we see from signals emitted by the brain?While other researchers have already attempted to answer this question, we are the first to show that a commercially available BCI could be effectively used for visual image classification in real-world scenarios – when testing takes place at a completely different time than training data collection. The task is difficult, as it requires relating the noisy and low-level EEG signals to complex and highly semantic visual categories. In this paper, we propose different learning approaches and show that simpler classifiers such as Ridge Regression with Gabor filtering of the input EEG signal could be more effective than the powerful Long Short Term Memory Networks and Convolutional Neural Networks in this case of limited and noisy training data. We analyzed the importance of each electrode for the visual classification task and noticed that the sensors with the highest accuracy were the ones that recorded brain activity from regions known to be correlated more with higher level recognition and cognitive processes and less to lower-level visual signal processing. The result is also in accordance with research in computer vision with deep neural networks, which shows that semantic visual features are learned only at higher levels of neural depth.While EEG signals are weaker by themselves for the task of visual classification, we demonstrate that they could be powerful when combined with deep visual features extracted from the image, improving performance from 91% to over 97% in a multi-class recognition setting. Our tests show that EEG input brings additional information that is not learned by artificial deep networks on the given image training set. Thus, a commercially available BCI could be effectively used in conjunction with a deep learning based vision system to form together a stronger visual recognition system that is suitable for real-world applications.

Ultra-coarse, single-glance human face detection in a dynamic visual stream

Effective human interaction depends on our ability to rapidly detect faces in dynamic visual environments. Here we asked how basic units of visual information (spatial frequencies, or SF) contribute to this fundamental brain function. Human observers viewed initially blurry, unrecognizable natural object images presented at a fast 12 Hz rate and parametrically increasing in SF content over the course of one minute. By inserting highly variable natural face images as every 8th stimulus we captured an objective neural index of face detection in participants’ electroencephalogram (EEG) at exactly 1.5 Hz. This face-selective signal emerged over the right occipito-temporal cortex at <5 cycles/image, suggesting that the brain can – at a single glance – discriminate vastly different faces from multiple unsegmented object categories using only very coarse visual information. Local features (e.g., eyes) are not yet discernable at this threshold, indicating that fast face detection critically relies on global facial configuration. Interestingly, the face-selective neural response continued to increase with additional higher SF content until saturation around >50 cycles/image, potentially supporting higher-level recognition functions (e.g., facial identity recognition).

Evaluation of Smartphone Diabetes Tracking Applications for Use in Pregnancy Using the APPLICATIONS Scoring System [10K

INTRODUCTION: To systematically evaluate the quality and functionality of smartphone diabetes tracking applications for use in pregnancies complicated by diabetes. METHODS: We adapted the previously described APPLICATIONS scoring system (score 0-16) with the definition of comprehensiveness as the incorporation of: ability to record blood glucose, medication use, carbohydrates, and weight gain; provide reminders for checks and/or medication; identify abnormal glucose levels; and export the collected data in reports. The Apple App Store (iPhone/iPad) and the Google Play Store (Android phones/tablets) were both searched systematically with pertinent key words to identify smartphone applications for review by three independent reviewers. RESULTS: Initial searches revealed 408 smartphone applications. Non-English applications and those without diabetes tracking abilities were excluded as well as applications that were not available on both operating systems, all paid applications, and those requiring institutional affiliation or proprietary equipment--leaving eight pairs of applications for evaluation. No application received a perfect APPLICATIONS score. The mean score for each was 11.3 (SD 2.1). Only one application was found to have all seven functions on both operating systems. The desired functions were available in the following percentages: blood glucose tracking (100%); medication tracking (94%); carbohydrate tracking (81%); weight tracking (75%); data exporting (75%), ability to set reminders (56%); in-app recognition of high and low glucose levels (69%). CONCLUSION: This systematic review using the adapted APPLICATIONS scoring system identified many diabetes tracking smartphone applications most suitable for in pregnancies complicated by diabetes. There are many excellent apps but only one app that contained all desired functions.