Current User Research Articles

SCANet

Continuous authentication monitors the security of a system throughout the login session on mobile devices. In this article, we present SCANet, a two-stream convolutional neural network--based continuous authentication system that leverages the accelerometer and gyroscope on smartphones to monitor users’ behavioral patterns. We are among the first to use two streams of data—frequency domain data and temporal difference domain data—from the two sensors as the inputs of the convolutional neural network (CNN). SCANet utilizes the two-stream CNN to learn and extract representative features and then performs the principal component analysis to select the top 25 features with high discriminability. With the CNN-extracted features, SCANet exploits the one-class support vector machine to train the classifier in the enrollment phase. Based on the trained CNN and classifier, SCANet identifies the current user as a legitimate user or an impostor in the continuous authentication phase. We evaluate the effectiveness of the two-stream CNN and the performance of SCANet on our dataset and BrainRun dataset, and the experimental results demonstrate that CNN achieves 90.04% accuracy, and SCANet reaches an average of 5.14% equal error rate on two datasets and takes approximately 3 s for user authentication.

Fog-Based Delay-Sensitive Data Transmission Algorithm for Data Forwarding and Storage in Cloud Environment for Multimedia Applications.

Fog computing is playing a vital role in data transmission to distributed devices in the Internet of Things (IoT) and another network paradigm. The fundamental element of fog computing is an additional layer added between an IoT device/node and a cloud server. These fog nodes are used to speed up time-critical applications. Current research efforts and user trends are pushing for fog computing, and the path is far from being paved. Unless it can reap the benefits of applying software-defined networks and network function virtualization techniques, network monitoring will be an additional burden for fog. However, the seamless integration of these techniques in fog computing is not easy and will be a challenging task. To overcome the issues as already mentioned, the fog-based delay-sensitive data transmission algorithm develops a robust optimal technique to ensure the low and predictable delay in delay-sensitive applications such as traffic monitoring and vehicle tracking applications. The method reduces latency by storing and processing the data close to the source of information with optimal depth in the network. The deployment results show that the proposed algorithm reduces 15.67 ms round trip time and 2 seconds averaged delay on 10 KB, 100 KB, and 1 MB data set India, Singapore, and Japan Amazon Datacenter Regions compared with conventional methodologies.

A BBR-based congestion control for delay-sensitive real-time applications

The current User Datagram Protocol (UDP) causes unfairness and bufferbloats to delay sensitive applications due to the uncontrolled congestion and monopolization of available bandwidth.This causes call drops and frequent communication/connection loss in delay sensitive applications such as VoIP. We present a Responsive Control Protocol using Bottleneck Bandwidth and Round trip propagation time (RCP-BBR) as an alternate solution to UDP. RCP-BBR achieves low latency, high throughput, and low call drops ratio by efficiently customizing Transmission Control Protocol (TCP) Bottleneck Bandwidth and Round-trip propagation time (TCP-BBR) congestion control. We conducted comprehensive experiments, and the results show that proposed protocol achieves better throughput over UDP in stable networks. Moreover, in unstable and long-distanced networks, RCP-BBR achieved smaller queues in deep buffers and lower delays as compared to UDP, which performed poorly by keeping delays above the call drop threshold.

Exploring Associations between Susceptibility to the Use of Electronic Nicotine Delivery Systems and E-Cigarette Use among School-Going Adolescents in Rural Appalachia.

Electronic nicotine delivery systems (ENDS) use, including e-cigarettes, has surpassed the use of conventional tobacco products. Emerging research suggests that susceptibility to e-cigarette use is associated with actual use among adolescents. However, few studies exist involving adolescents in high-risk, rural, socioeconomically distressed environments. This study examines susceptibility to and subsequent usage in school-going adolescents in a rural distressed county in Appalachian Tennessee using data from an online survey (N = 399). Relying on bivariate analyses and logistic regression, this study finds that while 30.6% of adolescents are ever e-cigarette users, 15.5% are current users. Approximately one in three adolescents are susceptible to e-cigarettes use, and susceptibility is associated with lower odds of being a current e-cigarette user (OR = 0.03; CI: 0.01–0.12; p < 0.00). The age of tobacco use initiation was significantly associated with decreased current use of e-cigarettes (OR = 0.89; CI: 0.83–0.0.97; p < 0.01). Overall, the results of this exploratory study suggest the need for larger studies to identify unique and generalizable factors that predispose adolescents in this high-risk rural, socioeconomically disadvantaged region to ENDS use. Nevertheless, this study offers insight into e-cigarette usage among U.S adolescents in rural, socioeconomically disadvantaged environments and provides a foundation for a closer examination of this vulnerable population.

Evaluation of the Dormitories in the Physical and Psychological Requirements: The Case of Karabük Province

Purpose The aim of this paper is to investigate the problems of meeting students’ housing needs in many cities that could not adapt to this change with its infrastructure against the rapid increase in the number of Turkish universities and students, who are educated in these institutions, in recent years. In addition, it is to develop alternative suggestions concerned with design criteria for increasing qualifications of the dormitories as one of the primary housing alternatives for students. Design/Methodology/Approach Users’ preferences and their management are very important for especially multi-user design processes. Hence, through a survey, it was planned to determine the physical conditions and the spatial characteristics of the existing dormitories beside their conformities in terms of the users’ satisfaction. At the end of the extensive literature research, the evaluation criteria which included basic psychological (privacy, sense of crowded, belonging and socializing, etc.) and physical (dorm rooms, social and service areas in the dorms and the dorms’ environment, etc.) factors were prepared for the survey. Then their validity was tested via the survey questions and the SPSS software. The obtained findings in the study were discussed in the frame of previous literature researches and their results. Evaluations were made in terms of the development of architectural planning principles of dormitory buildings. Findings Some outstanding findings and evaluations were listed as increasing the more customized using areas in the rooms, rehabilitation of study areas, multiplying variations of study and socializing areas, organizing social areas as partial units instead of the only central space for different functions, avoiding large-scale dormitories for decreasing the perception of crowded sense, creating flexible environments according to the conditions, etc. Besides, although the spatial planning of the dormitories was commonly compatible with the standards, the organization disorders like overcapacity and change of functions have been found to cause dissatisfaction. Many of these are thought to be innovative inputs for the design stages of dormitory buildings even if design contexts are different. Research Limitations/Implications The survey is conducted in Karabuk with 250 students from different faculties in Karabuk University whose development process has significantly affected the city and the city life in the last decade. So, the conditions of dormitories in Karabuk are examined. Practical Implications it is necessary to consider the users’ opinions and expectations about these buildings in the frame of their changing lifestyles and thus to review the criteria and approaches in designs of such buildings. Social Implications The fast and immediate solutions which have been done without considering in detail are often not useful. So, on behalf of solving this rapidly growing problem which has encountered in many cities in similar ways, improving them in line with the current user needs and thus increasing qualities in the students’ education and life standards, it is important to examine the conditions of the dormitory buildings which have been constructed or will be constructed. Originality/Value In this study, unlike the other dormitory studies, the design problems and user interactions have been evaluated with a more holistic approach from interior organization to the decisions on an urban scale.

Recurrent convolutional networks for session-based recommendations

Traditional recommender systems help users find items of interest by modeling long-term user profiles, which consist of items the users interacted with in the past. In many real-life applications, however, informative user profiles are not available. Instead, the system recommends by relying on the current user activities within an ongoing session, leading to the emergence of session-based recommendation methods. Among techniques used in such situations, recurrent neural networks (RNNs) present a natural choice thanks to their ability to model the order of session events and capture long-term dependencies. Recently, methods based on convolutional neural networks (CNNs) have also shown their potential in modeling session data, especially in extracting complex local patterns that are predictive of the user target. In this work, we propose a recurrent convolutional architecture that takes the advantages of both complex local features extracted by CNNs and long-term dependencies learned by RNNs from session sequences. Our model has two main layers: the lower layer consists of convolutional filters applied over consecutive session event embeddings, and the upper layer is a gated recurrent unit (GRU) RNN that takes as input the CNN’s output. This hybrid approach provides a flexible and unified network architecture for modeling various important features of session sequences. Experiments conducted on three benchmark datasets demonstrate the superiority of the proposed model over pure RNNs and CNNs models as well as state-of-the-art session-based recommendation methods.

Can Crop Models Identify Critical Gaps in Genetics, Environment, and Management Interactions?

Increasing food demand under climate change constraints may challenge and strain agricultural systems. The use of crop models to assess genotypes performance across diverse target environments and management practices, i.e., the genetic × environment × management interaction (GEMI), can help understand suitability of genotype and agronomic practices, and possibly accelerate turnaround in plant breeding programs. However, the readiness of models to support these tasks can be debated. In this article, we point out modeling and data limitations and argue the need for evaluation and improvement of relevant process algorithms as well as model convergence. Under conditions suitable for plant growth, without meteorological extremes or soil limitation to root exploration, models can simulate resource capture, growth, and yield with relative ease. As stresses accumulate, the plant species‐ and genotype-specific attributes and their interactions with the soil and atmospheric environment generate a large range of responses, including conditions where resources become so limiting as to make yields very low. The space in between high and low yields is where most rainfed production occurs, and where the current model and user skill at representing GEMI varies. We also review studies comparing the performance of a large number of crop models and the lessons learned. The overall message is that improvement of models appears as a necessary condition for progress, and perhaps relevancy. Model ensembles help mitigate data input, model, and user-driven uncertainty for some but not all applications, sometimes at a very high cost. Successful model-based assessment of GEMI not only requires better crop models and knowledgeable users, but also a realistic representation of the environmental conditions of the landscape where crops are grown, which is not trivial given the 3D nature of water and nutrient transport. Models remain the best quantitative repository of our knowledge on crop functioning; they contain a narrative of plant, soil, and atmospheric functioning in computer language and train the mind to couple processes. But in our quest to tame GEMI, will they lead the way or just ride along history?

The ORCA quantum chemistry program package.

In this contribution to the special software-centered issue, the ORCA program package is described. We start with a short historical perspective of how the project began and go on to discuss its current feature set. ORCA has grown into a rather comprehensive general-purpose package for theoretical research in all areas of chemistry and many neighboring disciplines such as materials sciences and biochemistry. ORCA features density functional theory, a range of wavefunction based correlation methods, semi-empirical methods, and even force-field methods. A range of solvation and embedding models is featured as well as a complete intrinsic to ORCA quantum mechanics/molecular mechanics engine. A specialty of ORCA always has been a focus on transition metals and spectroscopy as well as a focus on applicability of the implemented methods to "real-life" chemical applications involving systems with a few hundred atoms. In addition to being efficient, user friendly, and, to the largest extent possible, platform independent, ORCA features a number of methods that are either unique to ORCA or have been first implemented in the course of the ORCA development. Next to a range of spectroscopic and magnetic properties, the linear- or low-order single- and multi-reference local correlation methods based on pair natural orbitals (domain based local pair natural orbital methods) should be mentioned here. Consequently, ORCA is a widely used program in various areas of chemistry and spectroscopy with a current user base of over 22 000 registered users in academic research and in industry.

Passphrase and keystroke dynamics authentication: Usable security

It was found that employees spend a total of 2.25 days within 60 days on password-related activities. The time consumed by this is unproductive and has a negative impact on usability. The problem is caused by current text-based user authentication policies in use. This study aims to address this research problem by assessing the effectiveness of a proposed two-tier user authentication solution involving passphrases and keystroke dynamics.A design science research approach was used to guide this study, the theoretical foundation of which included three theories: the Shannon Entropy theory which was used to calculate the strength of passwords, passphrases and keystroke dynamics; Chunking theory assisted in assessing password and passphrase memorisation issues; and the Keystroke Level model was used to assess password and passphrase typing issues.Two primary data collection methods were used to evaluate the findings and to ensure that gaps in the research were filled. Firstly, a login assessment experiment was used to collect data on user authentication and user–system interaction for passwords and passphrases and, secondly, an expert review was conducted to validate findings and assess the research artefact in the form of a model.The model was finalised after it had been updated based on the expert review feedback. The model indicates the components that should be considered to implement the user authentication solution successfully. If all the model components are considered, the proposed two-tier user authentication solution has the potential to improve security and usability in the user authentication process.

Applying Importance-Performance Analysis (IPA) to Interpret the Results of the User Experience Questionnaire (UEQ)

In recent years, user experience questionnaires have established themselves to measure various aspects of User Experience (UX). In addition to these questionnaires, an evaluation tool is usually offered so that the results of a study can be evaluated in the light of the questionnaire. As a rule, the evaluation consists of preparing the data and comparing it with a benchmark. Often this interpretation of the data is not sufficient as it only evaluates the current User Experience. However, it is desirable to determine exactly where there is a need for action. The User Experience Questionnaire (UEQ) is a common and valid questionnaire with an evaluation tool to measure and analyse the User Experience for a product or service. In our article we present an approach that evaluates the results from the User Experience Questionnaire using the importance-performance analysis (IPA). The aim is to create another possibility to interpret the results of the UEQ and to derive recommendations for action from them. In a study with 467 participants, we validated the approach presented with YouTube, WhatsApp, and Facebook. The results show that the IPA provides additional insights from which further recommendations for action can be derived.

Attitudes about cannabis mediate the relationship between cannabis knowledge and use in active adult athletes

BackgroundLittle is known about how cannabis knowledge and attitudes impact cannabis use behavior.ObjectiveTo test the knowledge-attitudes-behavior paradigm in active adult athletes.DesignThe Athlete Pain, Exercise, and Cannabis Experience (PEACE) Survey, a cross-sectional survey study, used social media and email blasts to recruit participants and SurveyGizmo to collect data.ParticipantsSelf-defined active adult athletes (n = 1161).Main measuresKnowledge about cannabis was evaluated with four questions. Attitudes toward cannabis was evaluated with 11 questions. The attitudes questions were used in a TwoStep Cluster analysis in SPSS to assign group membership by attitudes. Chi-square was used to determine if there were differences in cluster membership by demographic factors and if knowledge about cannabis differed by cluster membership. Regression analysis was performed to determine if cannabis attitudes mediated the relationship between cannabis knowledge and cannabis use.Key resultsA three-cluster solution was the best fit to the data. The clusters were named Conservative (n = 374, 32.2%), Unsure (n = 533, 45.9%), and Liberal (n = 254, 21.9). There was a significant difference among the clusters for all 11 attitudes items (all p < 0.001). Attitude cluster membership was significantly different by age (p < 0.001), primary sport (p < 0.05), and knowledge about cannabis (p < 0.001). Athletes in the liberal cluster answered the knowledge questions correctly most often. Attitudes mediated the relationship between cannabis knowledge and cannabis use [Never (32.4%), Past (41.6%), Current (26.0%)] with athletes in the liberal cluster showing more knowledge and greater likelihood to be a current cannabis user (p < 0.001). Among current cannabis users there were differential patterns of cannabis use depending on their attitudes and knowledge; liberal athletes tended to co-use THC and CBD and used cannabis longer. (p < 0.001).ConclusionsCannabis education needs to consider attitudes about cannabis, especially among those who might benefit from medical cannabis.

COMPARATIVE EXAMPLES IN HANDWRITING RESEARCH

The article is devoted to the consideration of working situations that may arise with comparative samples of signatures provided for research during the relevant examinations. Possible changes in regulatory legal acts that will optimize the work of an expert during judicial handwriting examinations are highlighted. The main goal of this article is to consider the practical situations that an expert has when studying and working with comparative samples received for research. An analysis of expert practice will help minimize expert errors, which in turn will affect the objectivity of an expert’s opinion. The article sets out the situations that arise at the stage of studying materials that can affect the objectivity and categorization of an expert’s opinion: -providing free samples of signatures in documents issued to another person; -providing free samples of signatures in documents with amendments, supplements, incorrect indication of the name, and signature of the current user of the subscriber book or the owner of the document (passport). The situations discussed will help interns, novice experts in the study of materials received for research. It should be noted that a superficial approach at the stage of their research might lead to the need for additional examinations. The article can be useful to judges, assistant judges, representatives of law enforcement agencies, lawyers when assigning a handwriting examination and can help to reduce the time for the examination.

Item Response Theory analyses of DSM-5 substance use disorder criteria in French outpatient addiction clinic participants. How much is craving special?

BackgroundTo evaluate the dimensionality and psychometric validity of the 11 DSM-5 criteria for 5 substance use disorders, with a focus on craving, and taking into account age, gender and psychiatric comorbidities in a French sample of subjects seeking addiction treatment. MethodsThis cross-sectional study, included participants with DSM-5 substance use disorders that sought treatment for at least one addiction from outpatient clinics. Diagnostic criteria were evaluated with the Mini international Neuropsychiatric Interview. In Current regular user (2 times per week), factor and 2-parameter IRT analysis was used to investigate the dimensionality and psychometric properties of the 11 DSM-5 SUD criteria. Differential Item and Test functioning (DIF and DTF) analysis were performed across sociodemographic characteristics and psychiatric disorders. Results1359 participants (alcohol n = 787, opiates n = 131, cocaine n = 141, tobacco n = 1014, cannabis n = 504), were included (68% male; mean age 38.7). One-factor dimensionality was confirmed, except for tobacco. Craving criterion had the strongest factor loadings, lower difficulty (range, −1.29 to −0.67) and higher discrimination (range, 2.11–3.05), and no DIF compared to other criteria. The tobacco criteria set functioned differently by mood and anxiety disorders. ConclusionsWe confirmed the unidimensionality of the 11 SUD DSM-5 criteria and furthermore that craving was the most selective criterion because of its psychometric properties and no DIF compared to other criteria, regardless of the substance in this adult clinical sample. Unidimensionality of tobacco criteria was not confirmed, suggesting DSM-IV abuse criteria limitations as indicators of the construct.

Multistroke Grouping of Online Freehand Axonometric Sketches for Mechanical Models

Multistroke drawing occurs frequently in conceptual design sketches; however, it is almost unsupported by the current sketch-based user interfaces. We proposed a sketch recognition system based on the multistroke primitive grouping method. Based on grouping the strokes that lie within the mutual boundaries between adjacent regions, we create line drawings from online freehand axonometric sketches of mechanical models. First, closed regions and their boundary bands of the sketch were extracted. Then, the strokes that cross the boundary bands of two or more closed regions are segmented, and the strokes that lie within the intersection of two adjacent boundary bands are grouped. Finally, grouped strokes are simplified into a new single stroke and then fitted as a geometric primitive; thus, the input sketches are recognized to the line drawings. We developed a prototype of the sketch recognition system to evaluate the proposed method. The results showed that the input sketches are simplified into the accurate line drawings efficiently. The proposed method can be applied to both multistroke overtracing and nonovertracing sketches.

The luxury of doing nothing: inferring luxury from idleness display in travel setting

ABSTRACT Extant studies on luxury have focused on exploring motivations and service attributes behind the consumption of luxury travel brands. However, the underlying psychological mechanism of how customers develop a luxury perception of hospitality and tourism brands has received scant attention. By identifying scarcity of time as a significant factor behind luxury perception development, the current study argues that observers are more likely to perceive travel experiences as luxurious when they observe idleness rather than busyness. This perception is mediated by high social status inference on the part of the current user.

Establishing Vibration-Based Tactile Line Profiles for Use in Multimodal Graphics

Vibration plays a significant role in the way users interact with touchscreens. For many users, vibration affords tactile alerts and other enhancements. For eyes-free users and users with visual impairments, vibration can also serve a more primary role in the user interface, such as indicating streets on maps, conveying information about graphs, or even specifying basic graphics. However, vibration is rarely used in current user interfaces beyond basic cuing. Furthermore, designers and developers who do actually use vibration more extensively are often unable to determine the exact properties of the vibration signals they are implementing, due to out-of-the-box software and hardware limitations. We make two contributions in this work. First, we investigate the contextual properties of touchscreen vibrations and how vibrations can be used to effectively convey traditional, embossed elements, such as dashes and dots. To do so, we developed an open source, Android-based library to generate vibrations that are perceptually salient and intuitive, improving upon existing vibration libraries. Second, we conducted a user study with 26 blind or visually impaired users to evaluate and categorize the effects with respect to traditional tactile line profiles. We have established a range of vibration effects that can be reliably generated by our haptic library and are perceptible and distinguishable by users.

A probabilistic approach for calibration time reduction in hybrid EEG\u2013fTCD brain\u2013computer interfaces

BackgroundGenerally, brain–computer interfaces (BCIs) require calibration before usage to ensure efficient performance. Therefore, each BCI user has to attend a certain number of calibration sessions to be able to use the system. However, such calibration requirements may be difficult to fulfill especially for patients with disabilities. In this paper, we introduce a probabilistic transfer learning approach to reduce the calibration requirements of our EEG–fTCD hybrid BCI designed using motor imagery (MI) and flickering mental rotation (MR)/word generation (WG) paradigms. The proposed approach identifies the top similar datasets from previous BCI users to a small training dataset collected from a current BCI user and uses these datasets to augment the training data of the current BCI user. To achieve such an aim, EEG and fTCD feature vectors of each trial were projected into scalar scores using support vector machines. EEG and fTCD class conditional distributions were learnt separately using the scores of each class. Bhattacharyya distance was used to identify similarities between class conditional distributions obtained using training trials of the current BCI user and those obtained using trials of previous users.ResultsExperimental results showed that the performance obtained using the proposed transfer learning approach outperforms the performance obtained without transfer learning for both MI and flickering MR/WG paradigms. In particular, it was found that the calibration requirements can be reduced by at least 60.43% for the MI paradigm, while at most a reduction of 17.31% can be achieved for the MR/WG paradigm.ConclusionsData collected using the MI paradigm show better generalization across subjects.

A partial mediation effect of father-child attachment and self-esteem between parental marital conflict and subsequent features of internet gaming disorder in children: a 12-month follow-up study

BackgroundThis study evaluated whether parent-child attachment and self-esteem may mediate the relationship between parental marital conflict and increases in features of internet gaming disorder (IGD) in children at 1 year.MethodsThe baseline and one-year follow-up data for 268 pre-teens aged between 9 and 10 from the Internet User Cohort for Unbiased Recognition of Gaming Disorder in Early Adolescence (iCURE) study were collected. The students were children at low risk for IGD in the initial self-reported assessment, anyone living with both parents, current game user at baseline, and those who completed a 12-month follow-up assessment. The Internet Game Use-Elicited Symptom Screen (IGUESS) was used to identify increases in IGD features at 12 months. To examine a potential mediation effect, structural equation modeling was performed.ResultsThe direct effect was statistically significant, and parental marital conflict at baseline significantly predicted the increases in IGD features in children at the 12-month follow-up after adjusting for gender, sex, socioeconomic status, and baseline IGUESS score (ß = 0.206, P = 0.003). The indirect effect showed that attachment to fathers through self-esteem was a significant mediating effect (ß = 0.078, P = 0.045). Parental marital conflicts were associated with increases in IGD features in children through poor father-child attachment, and in turn, the lower levels of self-esteem in the children.ConclusionsParents, especially fathers, should make an effort to bond with their children to reduce the risk of their children’s developing the IGD features.

D2D-LSTM: LSTM-Based Path Prediction of Content Diffusion Tree in Device-to-Device Social Networks

With the proliferation of mobile device users, the Device-to-Device (D2D) communication has ascended to the spotlight in social network for users to share and exchange enormous data. Different from classic online social network (OSN) like Twitter and Facebook, each single data file to be shared in the D2D social network is often very large in data size, e.g., video, image or document. Sometimes, a small number of interesting data files may dominate the network traffic, and lead to heavy network congestion. To reduce the traffic congestion and design effective caching strategy, it is highly desirable to investigate how the data files are propagated in offline D2D social network and derive the diffusion model that fits to the new form of social network. However, existing works mainly concern about link prediction, which cannot predict the overall diffusion path when network topology is unknown. In this article, we propose D2D-LSTM based on Long Short-Term Memory (LSTM), which aims to predict complete content propagation paths in D2D social network. Taking the current user's time, geography and category preference into account, historical features of the previous path can be captured as well. It utilizes prototype users for prediction so as to achieve a better generalization ability. To the best of our knowledge, it is the first attempt to use real world large-scale dataset of mobile social network (MSN) to predict propagation path trees in a top-down order. Experimental results corroborate that the proposed algorithm can achieve superior prediction performance than state-of-the-art approaches. Furthermore, D2D-LSTM can achieve 95% average precision for terminal class and 17% accuracy for tree path hit.

Symmetric Metric Learning with Adaptive Margin for Recommendation

Metric learning based methods have attracted extensive interests in recommender systems. Current methods take the user-centric way in metric space to ensure the distance between user and negative item to be larger than that between the current user and positive item by a fixed margin. While they ignore the relations among positive item and negative item. As a result, these two items might be positioned closely, leading to incorrect results. Meanwhile, different users usually have different preferences, the fixed margin used in those methods can not be adaptive to various user biases, and thus decreases the performance as well. To address these two problems, a novel Symmetic Metric Learning with adaptive margin (SML) is proposed. In addition to the current user-centric metric, it symmetically introduces a positive item-centric metric which maintains closer distance from positive items to user, and push the negative items away from the positive items at the same time. Moreover, the dynamically adaptive margins are well trained to mitigate the impact of bias. Experimental results on three public recommendation datasets demonstrate that SML produces a competitive performance compared with several state-of-the-art methods.