Статті в журналах з теми "Local Interpretable Model-Agnostic Explanations (LIME)"

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically creates an explanation for a single prediction by any ML model by learning a simpler interpretable model (e.g., linear classifier) around the prediction through generating simulated data around the instance by random perturbation, and obtaining feature importance through applying some form of feature selection. While LIME and similar local algorithms have gained popularity due to their simplicity, the random perturbation methods result in shifts in data and instability in the generated explanations, where for the same prediction, different explanations can be generated. These are critical issues that can prevent deployment of LIME in sensitive domains. We propose a deterministic version of LIME. Instead of random perturbation, we utilize Agglomerative Hierarchical Clustering (AHC) to group the training data together and K-Nearest Neighbour (KNN) to select the relevant cluster of the new instance that is being explained. After finding the relevant cluster, a simple model (i.e., linear model or decision tree) is trained over the selected cluster to generate the explanations. Experimental results on six public (three binary and three multi-class) and six synthetic datasets show the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME), where we quantitatively determine the stability and faithfulness of DLIME compared to LIME.

In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.

Abstract In advancement of interpretable machine learning (IML), this research proposes local interpretable model-agnostic explanations (LIME) as a new visualization technique in a novel informative way to analyze the foreign direct investment (FDI) inflow. This article examines the determinants of FDI inflow through IML with a supervised learning method to analyze the foreign investment determinants in Hungary by using an open-source artificial intelligence H2O platform. This author used three ML algorithms—general linear model (GML), gradient boosting machine (GBM), and random forest (RF) classifier—to analyze the FDI inflow from 2001 to 2018. The result of this study shows that in all three classifiers GBM performs better to analyze FDI inflow determinants. The variable value of production in a region is the most influenced determinant to the inflow of FDI in Hungarian regions. Explanatory visualizations are presented from the analyzed dataset, which leads to their use in decision-making.

AbstractDeep neural networks are successfully used for object and face recognition in images and videos. In order to be able to apply such networks in practice, for example in hospitals as a pain recognition tool, the current procedures are only suitable to a limited extent. The advantage of deep neural methods is that they can learn complex non-linear relationships between raw data and target classes without limiting themselves to a set of hand-crafted features provided by humans. However, the disadvantage is that due to the complexity of these networks, it is not possible to interpret the knowledge that is stored inside the network. It is a black-box learning procedure. Explainable Artificial Intelligence (AI) approaches mitigate this problem by extracting explanations for decisions and representing them in a human-interpretable form. The aim of this paper is to investigate the explainable AI methods Layer-wise Relevance Propagation (LRP) and Local Interpretable Model-agnostic Explanations (LIME). These approaches are applied to explain how a deep neural network distinguishes facial expressions of pain from facial expressions of emotions such as happiness and disgust.

Sarcasm detection in dialogues has been gaining popularity among natural language processing (NLP) researchers with the increased use of conversational threads on social media. Capturing the knowledge of the domain of discourse, context propagation during the course of dialogue, and situational context and tone of the speaker are some important features to train the machine learning models for detecting sarcasm in real time. As situational comedies vibrantly represent human mannerism and behaviour in everyday real-life situations, this research demonstrates the use of an ensemble supervised learning algorithm to detect sarcasm in the benchmark dialogue dataset, MUStARD. The punch-line utterance and its associated context are taken as features to train the eXtreme Gradient Boosting (XGBoost) method. The primary goal is to predict sarcasm in each utterance of the speaker using the chronological nature of a scene. Further, it is vital to prevent model bias and help decision makers understand how to use the models in the right way. Therefore, as a twin goal of this research, we make the learning model used for conversational sarcasm detection interpretable. This is done using two post hoc interpretability approaches, Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP), to generate explanations for the output of a trained classifier. The classification results clearly depict the importance of capturing the intersentence context to detect sarcasm in conversational threads. The interpretability methods show the words (features) that influence the decision of the model the most and help the user understand how the model is making the decision for detecting sarcasm in dialogues.

Classification is needed in disaster investigation, traffic control, and land-use resource management. How to quickly and accurately classify such remote sensing imagery has become a popular research topic. However, the application of large, deep neural network models for the training of classifiers in the hope of obtaining good classification results is often very time-consuming. In this study, a new CNN (convolutional neutral networks) architecture, i.e., RSSCNet (remote sensing scene classification network), with high generalization capability was designed. Moreover, a two-stage cyclical learning rate policy and the no-freezing transfer learning method were developed to speed up model training and enhance accuracy. In addition, the manifold learning t-SNE (t-distributed stochastic neighbor embedding) algorithm was used to verify the effectiveness of the proposed model, and the LIME (local interpretable model, agnostic explanation) algorithm was applied to improve the results in cases where the model made wrong predictions. Comparing the results of three publicly available datasets in this study with those obtained in previous studies, the experimental results show that the model and method proposed in this paper can achieve better scene classification more quickly and more efficiently.

To address the current lack of dynamic susceptibility contrast magnetic resonance imaging (DSC–MRI)-based radiomics to predict isocitrate dehydrogenase (IDH) mutations in gliomas, we present a multicenter study that featured an independent exploratory set for radiomics model development and external validation using two independent cohorts. The maximum performance of the IDH mutation status prediction on the validation set had an accuracy of 0.544 (Cohen’s kappa: 0.145, F1-score: 0.415, area under the curve-AUC: 0.639, sensitivity: 0.733, specificity: 0.491), which significantly improved to an accuracy of 0.706 (Cohen’s kappa: 0.282, F1-score: 0.474, AUC: 0.667, sensitivity: 0.6, specificity: 0.736) when dynamic-based standardization of the images was performed prior to the radiomics. Model explainability using local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP) revealed potential intuitive correlations between the IDH–wildtype increased heterogeneity and the texture complexity. These results strengthened our hypothesis that DSC–MRI radiogenomics in gliomas hold the potential to provide increased predictive performance from models that generalize well and provide understandable patterns between IDH mutation status and the extracted features toward enabling the clinical translation of radiogenomics in neuro-oncology.

Metastatic cancers account for up to 90% of cancer-related deaths. The clear differentiation of metastatic cancers from primary cancers is crucial for cancer type identification and developing targeted treatment for each cancer type. DNA methylation patterns are suggested to be an intriguing target for cancer prediction and are also considered to be an important mediator for the transition to metastatic cancer. In the present study, we used 24 cancer types and 9303 methylome samples downloaded from publicly available data repositories, including The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO). We constructed machine learning classifiers to discriminate metastatic, primary, and non-cancerous methylome samples. We applied support vector machines (SVM), Naive Bayes (NB), extreme gradient boosting (XGBoost), and random forest (RF) machine learning models to classify the cancer types based on their tissue of origin. RF outperformed the other classifiers, with an average accuracy of 99%. Moreover, we applied local interpretable model-agnostic explanations (LIME) to explain important methylation biomarkers to classify cancer types.

AbstractResearch in social psychology has shown that people’s biased, subjective judgments about another’s personality based solely on their appearance are not predictive of their actual personality traits. But researchers and companies often utilize computer vision models to predict similarly subjective personality attributes such as “employability”. We seek to determine whether state-of-the-art, black box face processing technology can learn human-like appearance biases. With features extracted with FaceNet, a widely used face recognition framework, we train a transfer learning model on human subjects’ first impressions of personality traits in other faces as measured by social psychologists. We find that features extracted with FaceNet can be used to predict human appearance bias scores for deliberately manipulated faces but not for randomly generated faces scored by humans. Additionally, in contrast to work with human biases in social psychology, the model does not find a significant signal correlating politicians’ vote shares with perceived competence bias. With Local Interpretable Model-Agnostic Explanations (LIME), we provide several explanations for this discrepancy. Our results suggest that some signals of appearance bias documented in social psychology are not embedded by the machine learning techniques we investigate. We shed light on the ways in which appearance bias could be embedded in face processing technology and cast further doubt on the practice of predicting subjective traits based on appearances.

Predictive maintenance has become important for avoiding unplanned downtime of modern vehicles. With increasing functionality the exchanged data between Electronic Control Units (ECU) grows simultaneously rapidly. A large number of in-vehicle signals are provided for monitoring an aging process. Various components of a vehicle age due to their usage. This component aging is only visible in a certain number of in-vehicle signals. In this work, we present a signal selection method for in-vehicle signals in order to determine relevant signals to monitor and predict powertrain component aging of vehicles. Our application considers the aging of powertrain components with respect to clogging of structural components. We measure the component aging process in certain time intervals. Owing to this, unevenly spaced time series data is preprocessed to generate comparable in-vehicle data. First, we aggregate the data in certain intervals. Thus, the dynamic in-vehicle database is reduced which enables us to analyze the signals more efficiently. Secondly, we implement machine learning algorithms to generate a digital model of the measured aging process. With the help of Local Interpretable Model-Agnostic Explanations (LIME) the model gets interpretable. This allows us to extract the most relevant signals and to reduce the amount of processed data. Our results show that a certain number of in-vehicle signals are sufficient for predicting the aging process of the considered structural component. Consequently, our approach allows to reduce data transmission of in-vehicle signals with the goal of predictive maintenance.

Artificial Intelligence (AI) imaging diagnosis is developing, making enormous steps forward in medical fields. Regarding diabetic nephropathy (DN), medical doctors diagnose them with clinical course, clinical laboratory data and renal pathology, mainly evaluate with light microscopy images rather than immunofluorescent images because there are no characteristic findings in immunofluorescent images for DN diagnosis. Here, we examined the possibility of whether AI could diagnose DN from immunofluorescent images. We collected renal immunofluorescent images from 885 renal biopsy patients in our hospital, and we created a dataset that contains six types of immunofluorescent images of IgG, IgA, IgM, C3, C1q and Fibrinogen for each patient. Using the dataset, 39 programs worked without errors (Area under the curve (AUC): 0.93). Five programs diagnosed DN completely with immunofluorescent images (AUC: 1.00). By analyzing with Local interpretable model-agnostic explanations (Lime), the AI focused on the peripheral lesion of DN glomeruli. On the other hand, the nephrologist diagnostic ratio (AUC: 0.75833) was slightly inferior to AI diagnosis. These findings suggest that DN could be diagnosed only by immunofluorescent images by deep learning. AI could diagnose DN and identify classified unknown parts with the immunofluorescent images that nephrologists usually do not use for DN diagnosis.

Many machine learning models show black box characteristics and, therefore, a lack of transparency, interpretability, and trustworthiness. This strongly limits their practical application in clinical contexts. For overcoming these limitations, Explainable Artificial Intelligence (XAI) has shown promising results. The current study examined the influence of different input representations on a trained model’s accuracy, interpretability, as well as clinical relevancy using XAI methods. The gait of 27 healthy subjects and 20 subjects after total hip arthroplasty (THA) was recorded with an inertial measurement unit (IMU)-based system. Three different input representations were used for classification. Local Interpretable Model-Agnostic Explanations (LIME) was used for model interpretation. The best accuracy was achieved with automatically extracted features (mean accuracy Macc = 100%), followed by features based on simple descriptive statistics (Macc = 97.38%) and waveform data (Macc = 95.88%). Globally seen, sagittal movement of the hip, knee, and pelvis as well as transversal movement of the ankle were especially important for this specific classification task. The current work shows that the type of input representation crucially determines interpretability as well as clinical relevance. A combined approach using different forms of representations seems advantageous. The results might assist physicians and therapists finding and addressing individual pathologic gait patterns.

Background: The Soluble Epoxide Hydrolase (sEH) is a ubiquitously expressed enzyme in various tissues. The inhibition of the sEH has shown promising results to treat hypertension, alleviate pain and inflammation. Objective: In this study, the power of machine learning has been employed to develop a predictive QSAR model for a large set of sEH inhibitors. Methods: In this study, the random forest method was employed to make a valid model for the prediction of sEH inhibition. Besides, two new methods (Treeinterpreter python package and LIME, Local Interpretable Model-agnostic Explanations) have been exploited to explain and interpret the model. Results: The performance metrics of the model were as follows: R2=0.831, Q2=0.565, RMSE=0.552 and R2 pred=0.595. The model also demonstrated good predictability on the two extra external test sets at least in terms of ranking. The Spearman’s rank correlation coefficients for external test set 1 and 2 were 0.872 and 0.673, respectively. The external test set 2 was a diverse one compared to the training set. Therefore, the model could be used for virtual screening to enrich potential sEH inhibitors among a diverse compound library. Conclusion: As the model was solely developed based on a set of simple fragmental descriptors, the model was explained by two local interpretation algorithms, and this could guide medicinal chemists to design new sEH inhibitors. Moreover, the most important general descriptors (fragments) suggested by the model were consistent with the available crystallographic data. The model is available as an executable binary at http://www.pharm-sbg.com and https://github.com/shamsaraj.

The outbreak of COVID-19 has caused more than 200,000 deaths so far in the USA alone, which instigates the necessity of initial screening to control the spread of the onset of COVID-19. However, screening for the disease becomes laborious with the available testing kits as the number of patients increases rapidly. Therefore, to reduce the dependency on the limited test kits, many studies suggested a computed tomography (CT) scan or chest radiograph (X-ray) based screening system as an alternative approach. Thereby, to reinforce these approaches, models using both CT scan and chest X-ray images need to develop to conduct a large number of tests simultaneously to detect patients with COVID-19 symptoms. In this work, patients with COVID-19 symptoms have been detected using eight distinct deep learning techniques, which are VGG16, InceptionResNetV2, ResNet50, DenseNet201, VGG19, MobilenetV2, NasNetMobile, and ResNet15V2, using two datasets: one dataset includes 400 CT scan and another 400 chest X-ray images. Results show that NasNetMobile outperformed all other models by achieving an accuracy of 82.94% in CT scan and 93.94% in chest X-ray datasets. Besides, Local Interpretable Model-agnostic Explanations (LIME) is used. Results demonstrate that the proposed models can identify the infectious regions and top features; ultimately, it provides a potential opportunity to distinguish between COVID-19 patients with others.

The COVID-19 global pandemic caused by the widespread transmission of the novel coronavirus (SARS-CoV-2) has become one of modern history’s most challenging issues from a healthcare perspective. At its dawn, still without a vaccine, contagion containment strategies remained most effective in preventing the disease’s spread. Patient isolation has been primarily driven by the results of polymerase chain reaction (PCR) testing, but its initial reach was challenged by low availability and high cost, especially in developing countries. As a means of taking advantage of a preexisting infrastructure for respiratory disease diagnosis, researchers have proposed COVID-19 patient screening based on the results of Chest Computerized Tomography (CT) and Chest Radiographs (X-ray). When paired with artificial-intelligence- and deep-learning-based approaches for analysis, early studies have achieved a comparatively high accuracy in diagnosing the disease. Considering the opportunity to further explore these methods, we implement six different Deep Convolutional Neural Networks (Deep CNN) models—VGG16, MobileNetV2, InceptionResNetV2, ResNet50, ResNet101, and VGG19—and use a mixed dataset of CT and X-ray images to classify COVID-19 patients. Preliminary results showed that a modified MobileNetV2 model performs best with an accuracy of 95 ± 1.12% (AUC = 0.816). Notably, a high performance was also observed for the VGG16 model, outperforming several previously proposed models with an accuracy of 98.5 ± 1.19% on the X-ray dataset. Our findings are supported by recent works in the academic literature, which also uphold the higher performance of MobileNetV2 when X-ray, CT, and their mixed datasets are considered. Lastly, we further explain the process of feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which contributes to a better understanding of what features in CT/X-ray images characterize the onset of COVID-19.

Advances in the trusted autonomy of air-traffic management (ATM) systems are currently being pursued to cope with the predicted growth in air-traffic densities in all classes of airspace. Highly automated ATM systems relying on artificial intelligence (AI) algorithms for anomaly detection, pattern identification, accurate inference, and optimal conflict resolution are technically feasible and demonstrably able to take on a wide variety of tasks currently accomplished by humans. However, the opaqueness and inexplicability of most intelligent algorithms restrict the usability of such technology. Consequently, AI-based ATM decision-support systems (DSS) are foreseen to integrate eXplainable AI (XAI) in order to increase interpretability and transparency of the system reasoning and, consequently, build the human operators’ trust in these systems. This research presents a viable solution to implement XAI in ATM DSS, providing explanations that can be appraised and analysed by the human air-traffic control operator (ATCO). The maturity of XAI approaches and their application in ATM operational risk prediction is investigated in this paper, which can support both existing ATM advisory services in uncontrolled airspace (Classes E and F) and also drive the inflation of avoidance volumes in emerging performance-driven autonomy concepts. In particular, aviation occurrences and meteorological databases are exploited to train a machine learning (ML)-based risk-prediction tool capable of real-time situation analysis and operational risk monitoring. The proposed approach is based on the XGBoost library, which is a gradient-boost decision tree algorithm for which post-hoc explanations are produced by SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME). Results are presented and discussed, and considerations are made on the most promising strategies for evolving the human–machine interactions (HMI) to strengthen the mutual trust between ATCO and systems. The presented approach is not limited only to conventional applications but also suitable for UAS-traffic management (UTM) and other emerging applications.

Background Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients’ prognosis early and administer precise treatment are of great significance. Objective The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. Methods In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. Results Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. Conclusions The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.

Abstract Context Postoperative hypercortisolemia mandates further therapy in patients with Cushing’s disease (CD). Delayed remission (DR) is defined as not achieving postoperative immediate remission (IR), but having spontaneous remission during long-term follow-up. Objective We aimed to develop and validate machine learning (ML) models for predicting DR in non-IR patients with CD. Methods We enrolled 201 CD patients, and randomly divided them into training and test datasets. We then used the recursive feature elimination (RFE) algorithm to select features and applied 5 ML algorithms to construct DR prediction models. We used permutation importance and local interpretable model–agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. Results Eighty-eight (43.8%) of the 201 CD patients met the criteria for DR. Overall, patients who were younger, had a low body mass index, a Knosp grade of III–IV, and a tumor not found by pathological examination tended to achieve a lower rate of DR. After RFE feature selection, the Adaboost model, which comprised 18 features, had the greatest discriminatory ability, and its predictive ability was significantly better than using Knosp grading and postoperative immediate morning serum cortisol (PoC). The results obtained from permutation importance and LIME algorithms showed that preoperative 24-hour urine free cortisol, PoC, and age were the most important features, and showed the reliability and clinical practicability of the Adaboost model in DC prediction. Conclusions Machine learning–based models could serve as an effective noninvasive approach to predicting DR, and could aid in determining individual treatment and follow-up strategies for CD patients.

e16569 Background: In 2017, prostate cancer (PCa) was the second most common cancer in men after lung cancer. While there are different courses of action to treat the disease, its mortality in Peru is higher than 50%. Conventionally, PCa is diagnosed by evaluating tissue biopsies, and classified according to the Gleason grading system. Novel molecular classifications of PCa have been proposed for diagnostic and prognostic purposes. The main goal of this work is to implement a tool predicting the disease free time of patient according to the genomic expression and highlight the genes playing an influential role on the prediction. Methods: Modern techniques to classify data keep getting broader and more accurate, in particular with the introduction of Neural Networks(NN). We implement an Artificial Neural Network automatic genomic classification strategy based on a Local Interpretable Model-Agnostic Explanations (LIME) algorithm because it allows the network to choose the features of major discriminative significance. As a proof-of-concept, we selected a sub-set of 3530 genes related to recurrence from 499 PCa genomes to build the neural networks. Results: The resulting neural network, trained and tested on cancer cell 2010 database and validate on the MSKCC data the can predict the time of recurrence within a range of three months based on the genomic expression with an accuracy of 96,9% and a loss of less than 9%. Using the implemented LIME algorithm, our results indicate that this subset of genes is informative of recurrence and plays a substantial role in the prediction. Conclusions: Instead of using a classic fully connected layer, we implemented different types of Deep Learning networks where the final network provides the predicted survival rate or time to recurrence. This information will allow the doctors to propose the best course of treatment. Our method is able to generate an augmented score, enabling a more accurate evaluation of risk and personalized treatment strategy

An application of explainable artificial intelligence on medical data is presented. There is an increasing demand in machine learning literature for such explainable models in health-related applications. This work aims to generate explanations on how a Convolutional Neural Network (CNN) detects tumor tissue in patches extracted from histology whole slide images. This is achieved using the “locally-interpretable model-agnostic explanations” methodology. Two publicly-available convolutional neural networks trained on the Patch Camelyon Benchmark are analyzed. Three common segmentation algorithms are compared for superpixel generation, and a fourth simpler parameter-free segmentation algorithm is proposed. The main characteristics of the explanations are discussed, as well as the key patterns identified in true positive predictions. The results are compared to medical annotations and literature and suggest that the CNN predictions follow at least some aspects of human expert knowledge.

Short-term Photovoltaic (PV) Power Forecasting (STPF) is considered a topic of utmost importance in smart grids. The deployment of STPF techniques provides fast dispatching in the case of sudden variations due to stochastic weather conditions. This paper presents an efficient data-driven method based on enhanced Random Forest (RF) model. The proposed method employs an ensemble of attribute selection techniques to manage bias/variance optimization for STPF application and enhance the forecasting quality results. The overall architecture strategy gathers the relevant information to constitute a voted feature-weighting vector of weather inputs. The main emphasis in this paper is laid on the knowledge expertise obtained from weather measurements. The feature selection techniques are based on local Interpretable Model-Agnostic Explanations, Extreme Boosting Model, and Elastic Net. A comparative performance investigation using an actual database, collected from the weather sensors, demonstrates the superiority of the proposed technique versus several data-driven machine learning models when applied to a typical distributed PV system.

Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations of the classification decisions. Spinal posture data of healthy subjects and various pathologies (back pain, spinal fusion, osteoarthritis), as well as synthetic data, were used for modeling. A one-class support vector machine was used as a pathology-independent classifier. The outputs were transformed into a probability distribution according to Platt’s method. Interpretation was performed using the explainable artificial intelligence tool Local Interpretable Model-Agnostic Explanations. The results were compared with those obtained by commonly used binary classification approaches. The best classification results were obtained for subjects with a spinal fusion. Subjects with back pain were especially challenging to distinguish from the healthy reference group. The proposed method proved useful for the interpretation of the predictions. No clear inferiority of the proposed approach compared to commonly used binary classifiers was demonstrated. The application of dynamic spinal data seems important for future works. The proposed approach could be useful to provide an objective orientation and to individually adapt and monitor therapy measures pre- and post-operatively.

This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.

Abstract Background Machine learning (ML) can be an effective tool to extract information from attribute-rich molecular datasets for the generation of molecular diagnostic tests. However, the way in which the resulting scores or classifications are produced from the input data may not be transparent. Algorithmic explainability or interpretability has become a focus of ML research. Shapley values, first introduced in game theory, can provide explanations of the result generated from a specific set of input data by a complex ML algorithm. Methods For a multivariate molecular diagnostic test in clinical use (the VeriStrat® test), we calculate and discuss the interpretation of exact Shapley values. We also employ some standard approximation techniques for Shapley value computation (local interpretable model-agnostic explanation (LIME) and Shapley Additive Explanations (SHAP) based methods) and compare the results with exact Shapley values. Results Exact Shapley values calculated for data collected from a cohort of 256 patients showed that the relative importance of attributes for test classification varied by sample. While all eight features used in the VeriStrat® test contributed equally to classification for some samples, other samples showed more complex patterns of attribute importance for classification generation. Exact Shapley values and Shapley-based interaction metrics were able to provide interpretable classification explanations at the sample or patient level, while patient subgroups could be defined by comparing Shapley value profiles between patients. LIME and SHAP approximation approaches, even those seeking to include correlations between attributes, produced results that were quantitatively and, in some cases qualitatively, different from the exact Shapley values. Conclusions Shapley values can be used to determine the relative importance of input attributes to the result generated by a multivariate molecular diagnostic test for an individual sample or patient. Patient subgroups defined by Shapley value profiles may motivate translational research. However, correlations inherent in molecular data and the typically small ML training sets available for molecular diagnostic test development may cause some approximation methods to produce approximate Shapley values that differ both qualitatively and quantitatively from exact Shapley values. Hence, caution is advised when using approximate methods to evaluate Shapley explanations of the results of molecular diagnostic tests.

Objective: The number of patients requiring prolonged mechanical ventilation (PMV) is increasing worldwide, but the weaning outcome prediction model in these patients is still lacking. We hence aimed to develop an explainable machine learning (ML) model to predict successful weaning in patients requiring PMV using a real-world dataset.Methods: This retrospective study used the electronic medical records of patients admitted to a 12-bed respiratory care center in central Taiwan between 2013 and 2018. We used three ML models, namely, extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), to establish the prediction model. We further illustrated the feature importance categorized by clinical domains and provided visualized interpretation by using SHapley Additive exPlanations (SHAP) as well as local interpretable model-agnostic explanations (LIME).Results: The dataset contained data of 963 patients requiring PMV, and 56.0% (539/963) of them were successfully weaned from mechanical ventilation. The XGBoost model (area under the curve [AUC]: 0.908; 95% confidence interval [CI] 0.864–0.943) and RF model (AUC: 0.888; 95% CI 0.844–0.934) outperformed the LR model (AUC: 0.762; 95% CI 0.687–0.830) in predicting successful weaning in patients requiring PMV. To give the physician an intuitive understanding of the model, we stratified the feature importance by clinical domains. The cumulative feature importance in the ventilation domain, fluid domain, physiology domain, and laboratory data domain was 0.310, 0.201, 0.265, and 0.182, respectively. We further used the SHAP plot and partial dependence plot to illustrate associations between features and the weaning outcome at the feature level. Moreover, we used LIME plots to illustrate the prediction model at the individual level. Additionally, we addressed the weekly performance of the three ML models and found that the accuracy of XGBoost/RF was ~0.7 between weeks 4 and week 7 and slightly declined to 0.6 on weeks 8 and 9.Conclusion: We used an ML approach, mainly XGBoost, SHAP plot, and LIME plot to establish an explainable weaning prediction ML model in patients requiring PMV. We believe these approaches should largely mitigate the concern of the black-box issue of artificial intelligence, and future studies are warranted for the landing of the proposed model.

AbstractHealthcare using body sensor data has been getting huge research attentions by a wide range of researchers because of its good practical applications such as smart health care systems. For instance, smart wearable sensor-based behavior recognition system can observe elderly people in a smart eldercare environment to improve their lifestyle and can also help them by warning about forthcoming unprecedented events such as falls or other health risk, to prolong their independent life. Although there are many ways of using distinguished sensors to observe behavior of people, wearable sensors mostly provide reliable data in this regard to monitor the individual’s functionality and lifestyle. In this paper, we propose a body sensor-based activity modeling and recognition system using time-sequential information-based deep Neural Structured Learning (NSL), a promising deep learning algorithm. First, we obtain data from multiple wearable sensors while the subjects conduct several daily activities. Once the data is collected, the time-sequential information then go through some statistical feature processing. Furthermore, kernel-based discriminant analysis (KDA) is applied to see the better clustering of the features from different activity classes by minimizing inner-class scatterings while maximizing inter-class scatterings of the samples. The robust time-sequential features are then applied with Neural Structured Learning (NSL) based on Long Short-Term Memory (LSTM), for activity modeling. The proposed approach achieved around 99% recall rate on a public dataset. It is also compared to existing different conventional machine learning methods such as typical Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) where they yielded the maximum recall rate of 94%. Furthermore, a fast and efficient explainable Artificial Intelligence (XAI) algorithm, Local Interpretable Model-Agnostic Explanations (LIME) is used to explain and check the machine learning decisions. The robust activity recognition system can be adopted for understanding peoples' behavior in their daily life in different environments such as homes, clinics, and offices.

AbstractDepression is a common illness worldwide with potentially severe implications. Early identification of depressive symptoms is a crucial first step towards assessment, intervention, and relapse prevention. With an increase in data sets with relevance for depression, and the advancement of machine learning, there is a potential to develop intelligent systems to detect symptoms of depression in written material. This work proposes an efficient approach using Long Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) to identify texts describing self-perceived symptoms of depression. The approach is applied on a large dataset from a public online information channel for young people in Norway. The dataset consists of youth’s own text-based questions on this information channel. Features are then provided from a one-hot process on robust features extracted from the reflection of possible symptoms of depression pre-defined by medical and psychological experts. The features are better than conventional approaches, which are mostly based on the word frequencies (i.e., some topmost frequent words are chosen as features from the whole text dataset and applied to model the underlying events in any text message) rather than symptoms. Then, a deep learning approach is applied (i.e., RNN) to train the time-sequential features discriminating texts describing depression symptoms from posts with no such descriptions (non-depression posts). Finally, the trained RNN is used to automatically predict depression posts. The system is compared against conventional approaches where it achieved superior performance than others. The linear discriminant space clearly reveals the robustness of the features by generating better clustering than other traditional features. Besides, since the features are based on the possible symptoms of depression, the system may generate meaningful explanations of the decision from machine learning models using an explainable Artificial Intelligence (XAI) algorithm called Local Interpretable Model-Agnostic Explanations (LIME). The proposed depression symptom feature-based approach shows superior performance compared to the traditional general word frequency-based approaches where frequency of the features gets more importance than the specific symptoms of depression. Although the proposed approach is applied on a Norwegian dataset, a similar robust approach can be applied on other depression datasets developed in other languages with proper annotations and symptom-based feature extraction. Thus, the depression prediction approach can be adopted to contribute to develop better mental health care technologies such as intelligent chatbots.

Abstract Background Malaria is still a major global health burden, with more than 3.2 billion people in 91 countries remaining at risk of the disease. Accurately distinguishing malaria from other diseases, especially uncomplicated malaria (UM) from non-malarial infections (nMI), remains a challenge. Furthermore, the success of rapid diagnostic tests (RDTs) is threatened by Pfhrp2/3 deletions and decreased sensitivity at low parasitaemia. Analysis of haematological indices can be used to support the identification of possible malaria cases for further diagnosis, especially in travellers returning from endemic areas. As a new application for precision medicine, we aimed to evaluate machine learning (ML) approaches that can accurately classify nMI, UM, and severe malaria (SM) using haematological parameters. Methods We obtained haematological data from 2,207 participants collected in Ghana: nMI (n = 978), SM (n = 526), and UM (n = 703). Six different ML approaches were tested, to select the best approach. An artificial neural network (ANN) with three hidden layers was used for multi-classification of UM, SM, and uMI. Binary classifiers were developed to further identify the parameters that can distinguish UM or SM from nMI. Local interpretable model-agnostic explanations (LIME) were used to explain the binary classifiers. Results The multi-classification model had greater than 85% training and testing accuracy to distinguish clinical malaria from nMI. To distinguish UM from nMI, our approach identified platelet counts, red blood cell (RBC) counts, lymphocyte counts, and percentages as the top classifiers of UM with 0.801 test accuracy (AUC = 0.866 and F1 score = 0.747). To distinguish SM from nMI, the classifier had a test accuracy of 0.96 (AUC = 0.983 and F1 score = 0.944) with mean platelet volume and mean cell volume being the unique classifiers of SM. Random forest was used to confirm the classifications, and it showed that platelet and RBC counts were the major classifiers of UM, regardless of possible confounders such as patient age and sampling location. Conclusion The study provides proof of concept methods that classify UM and SM from nMI, showing that the ML approach is a feasible tool for clinical decision support. In the future, ML approaches could be incorporated into clinical decision-support algorithms for the diagnosis of acute febrile illness and monitoring response to acute SM treatment particularly in endemic settings.

Predicting brain age has become one of the most attractive challenges in computational neuroscience due to the role of the predicted age as an effective biomarker for different brain diseases and conditions. A great variety of machine learning (ML) approaches and deep learning (DL) techniques have been proposed to predict age from brain magnetic resonance imaging scans. If on one hand, DL models could improve performance and reduce model bias compared to other less complex ML methods, on the other hand, they are typically black boxes as do not provide an in-depth understanding of the underlying mechanisms. Explainable Artificial Intelligence (XAI) methods have been recently introduced to provide interpretable decisions of ML and DL algorithms both at local and global level. In this work, we present an explainable DL framework to predict the age of a healthy cohort of subjects from ABIDE I database by using the morphological features extracted from their MRI scans. We embed the two local XAI methods SHAP and LIME to explain the outcomes of the DL models, determine the contribution of each brain morphological descriptor to the final predicted age of each subject and investigate the reliability of the two methods. Our findings indicate that the SHAP method can provide more reliable explanations for the morphological aging mechanisms and be exploited to identify personalized age-related imaging biomarker.

AbstractExplainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer data from the UCI Archive and a recently collected running injury data. Our results show that the most important features differ depending on the technique. We argue that a combination of several explanation techniques could provide more reliable and trustworthy results. In particular, local explanations should be used in the most critical cases such as false negatives.

AbstractN4-acetylcytidine (ac4C) is a post-transcriptional modification in mRNA which plays a major role in the stability and regulation of mRNA translation. The working mechanism of ac4C modification in mRNA is still unclear and traditional laboratory experiments are time-consuming and expensive. Therefore, we propose an XG-ac4C machine learning model based on the eXtreme Gradient Boost classifier for the identification of ac4C sites. The XG-ac4C model uses a combination of electron-ion interaction pseudopotentials and electron-ion interaction pseudopotentials of trinucleotide of the nucleotides in ac4C sites. Moreover, Shapley additive explanations and local interpretable model-agnostic explanations are applied to understand the importance of features and their contribution to the final prediction outcome. The obtained results demonstrate that XG-ac4C outperforms existing state-of-the-art methods. In more detail, the proposed model improves the area under the precision-recall curve by 9.4% and 9.6% in cross-validation and independent tests, respectively. Finally, a user-friendly web server based on the proposed model for ac4C site identification is made freely available at http://nsclbio.jbnu.ac.kr/tools/xgac4c/.

Abstract Objectives Urine sample manipulation including substitution, dilution, and chemical adulteration is a continuing challenge for workplace drug testing, abstinence control, and doping control laboratories. The simultaneous detection of sample manipulation and prohibited drugs within one single analytical measurement would be highly advantageous. Machine learning algorithms are able to learn from existing datasets and predict outcomes of new data, which are unknown to the model. Methods Authentic human urine samples were treated with pyridinium chlorochromate, potassium nitrite, hydrogen peroxide, iodine, sodium hypochlorite, and water as control. In total, 702 samples, measured with liquid chromatography coupled to quadrupole time-of-flight mass spectrometry, were used. After retention time alignment within Progenesis QI, an artificial neural network was trained with 500 samples, each featuring 33,448 values. The feature importance was analyzed with the local interpretable model-agnostic explanations approach. Results Following 10-fold cross-validation, the mean sensitivity, specificity, positive predictive value, and negative predictive value was 88.9, 92.0, 91.9, and 89.2%, respectively. A diverse test set (n=202) containing treated and untreated urine samples could be correctly classified with an accuracy of 95.4%. In addition, 14 important features and four potential biomarkers were extracted. Conclusions With interpretable retention time aligned liquid chromatography high-resolution mass spectrometry data, a reliable machine learning model could be established that rapidly uncovers chemical urine manipulation. The incorporation of our model into routine clinical or forensic analysis allows simultaneous LC-MS analysis and sample integrity testing in one run, thus revolutionizing this field of drug testing.

She's the dollars, she's my protection; she's a promise, in the year of election. Sister, I can't let you go; I'm like a preacher, stealing hearts at a traveling show. For love or money, money, money... Desire -- U2, "Desire" (1988) For the love of money. In the worship of things. Desire has traditionally been employed by advertising as a means of selling product. Regardless of culture, more powerful than context, desire is invoked as one of capitalism's iron-clad codes of quality. The Uses of Desire in Advertising Specifically, two variants have been most common. That in which desire is: (1) stimulated or (2) sated by a product. Crucial to advertisers, in both cases the product is more powerful than the thing the audience finds most powerful: the physical surge, the emotional rush, the chemical compulsion we label "desire". In the case of the former, a typical approach has been to create an equation in which product intervenes in the relationship between man and woman (and it is always man and woman), stimulating the psycho-physiological desire of one for the other. A classic pre-post design. Absent the product, desire would not arise, ad text often alleges. This tack is well captured in this ad for a perfume. Implicit in this approach is the assumption that the ad reader will desire desire. If so, he or she -- equally desirous of this turn of events -- will insert him or herself into the scenario, engaging in a symbolic, if not actual purchase of the product1. As we saw above, desire is often depicted via substitute symbols -- flashing red neon, burning matches, flame-blowers, stifling heat and raging brush fires2. The product is then used to extinguish such signs -- metaphorically quenching desire. This is the satiation variant identified at the outset. Standardised Desire? This last is an Australian ad, but in a wide variety of contexts, the same formula of product/desire appears. A recent Malaysian ad, for instance, plays out like this: a motorbike roars up to a doorstep; its leather-clad rider dismounts. Removing the helmet we find beneath a ... beautiful long-haired woman. Cut to a medium shot of the front door opening. A similarly-clad male leans against the molding. Rugged, firm, slightly aloof. Cut to product name: Dashing for Men. Followed by a picture of the cologne. "The Dashing Sensation" is then posted -- ripe with the implication that the cologne has worked its magical, magnetic attraction uniting female and male. It should be pointed out that Malaysia is a market with a significant western presence. Its top advertising firms are American, British and Italian. Thus, if one were curious as to whether desire was inherently a "cultural universal" or rather due to accession (i.e. the movement of intellectual and corporate capital), Euro-American presence would certainly be a factor to consider 3. Innovating Desire Bringing us to Japan. Desire is also a major theme there, as well. However, there, Japanese firms dominate ad production. And, interestingly, though the above-mentioned formulations do appear, desire in Japan also has its own specialised discourse. Rather than a relationship between the consumable and the consumer's emotional/physical state, discourse about desire can transpire independent of the product. Desire is often simply about desire. This is in keeping with a trend (or, more formally, a stage) of development Japanese advertising has achieved -- what I call "product-least advertising"; a condition in which discourse is about many things other than consumption. One of these things being desire. In closing I will wonder what this might say about Japanese society. Japanese Approaches to Desire As noted above, it is not the case that messages of product-induced desire do not appear in Japan. They are certainly more pervasive than in their Islamic neighbor, Malaysia. And, like America, desire is treated in an array of ways. Object-Mediated Desire One approach, admittedly less conventional, posits the product as medium. Only through the product will desire be manifested. In this ad, though verbal substitutes are invoked -- "lust", "love", "lick", "pinch", bite", "touch" -- desire is the guiding force as the figures trapped inside the product's bar code move mechanically toward physical consummation. Of particular note is the product's multi-faceted relationship to desire: it subsumes desire, stimulates it, provides a forum and means for its expression, and is the device securing its culmination ... the ad text is ambiguous as to which is controlling. This is a definitive "postmodern ad", pregnant with shifting perspective, situational action, oppositional signs and interpretive possibilities. The kind of text so-called "cultural studies" intends by the term "polysemy" (the notion that multiple meanings are contained in any sign -- see Fiske). In the case of desire, postmodern ads tell us not that desire is multiple. Rather, it is a singular (i.e. universally experienced) condition which may be differentially manifested and variously interpretable vis-à-vis singular object/products. Object-Induced Desire For instance, in this ad, again for instant noodles, two salarymen contemplate the statement "this summer's new product is stimulating". Each conjures a different image of just what "stimulating" means. For the younger man, a veritable deluge of sexual adoration; for his elder, an assault by a gang of femmes toughs. And while the latter man's fantasy would not qualify as the conventional definition of "desire", the former would. Thus, despite its polysemic trappings, the ad varies little from the standard approach outlined at the outset (plates 1 and 2). It posits that the product possesses sufficient power to stimulate desire for its consumer in external, unrelated others. Object-Directed Desire One of sociology's earliest complaints about capitalism was its reduction of people to the status of things. Social relations became instrumental acts aimed at achieving rational ends; the personalities, thoughts and qualities of those human agents engaged in the exchange become secondary to the sought good. Advertising, according to early semiotic critiques (see for instance Williamson), has only intensified this predilection, though in a different way. Ads instrumentalise by creating equality between the product presented and the person doing the presenting. When the presenter and product are conflated -- as in the case where a major star clasps the product to her bosom and addresses the camera with: "it's my Nice Once" (the product name) -- the objectification of the human subject may be unavoidable. The material and corporeal meld. She cherishes the drink. If we desire her (her status, her style, her actual physical being) but are realistic (and thus willing to settle for a substitute) ... we can settle for the simulation (her drink). This kind of vicarious taking, this symbolic sharing is common in advertising. Played out over and over the audience quickly learns to draw an equal sign between the two depicted objects (product and star). Purchasing one enables us to realise our desire (however incompletely) for the other. Sometimes the product and person are separated, but in a way that the discourse is about longing. The product is consumed because the human can't be -- perhaps a less satisfactory substitute, but a replacement, nonetheless. Or, as in the ad below, the two might be interchangeable. Interior. Bright yellow room without any discernible features. No walls, windows or furniture. Tight shot of black fishnet stockings, barely covered by a yellow dress. The legs swivel in a chair, allowing a fleeting shot of the model's crotch. Cut to a darkened interior. The product sits next to a set of wrenches. Cut back to first interior. Medium tight of the model's bare shoulders. She spins in her chair. Cut to the mechanic working on the engine of a car. Female voiceover: "Hey! Work AGAIN? ... Let's play!" Cut to tight shot of her pursed lips. "Hey! ... let's go for a drive", accompanying consecutive shots of the mechanic wiping sweat from his brow and the vamp's derriere. Next, a sequence of fast, tight images: mechanic revving the engine, the model's face, then her upper body viewed through heavily-ventilated apparel. "Oh", she says, "cars are cuter, huh?" The mechanic pauses to consider. Walks over to the product, pops the top. "When it comes to that sort of man..." her VO says as he gulps the drink, "women are suckers". Tight on woman's face: "(he's a) rake", she pouts. To better appreciate this endemic correspondence between objectification and desire, consider this ad for a car named "Rosso" ("red" in Italian, "aka" in Japanese). The model, "Anna", is tinted head to toe in red (red, of course, being the universal signifier for passion and desire)4. She and/or the car rouse enough passion in a male by-stander to literally make his blood boil. This, in turn, produces steam which, in turn, sends air current of sufficient force to propel Anna's skirt skyward. This, in turn, converts the man's face into an embarrassed and/or impassioned red. "Rosso!" he gushes enthusiastically -- reference to car, his condition, Anna and, presumably, her panties5. Thus, the desire for things -- people included -- is by no means disappearing in Japanese advertising. The name of the game is still to sell that which has been produced. Although Japanese ads have moved toward a decentring of product -- an introduction of consumption-least discourse, with a concomitant increase in popular cultural and societal content -- the great majority still speak in the language of "here it is, buy it!" The prevailing tenor is still object-oriented. And the spill-over, as we just saw, is a tendency to depict humans and their interactions in objectified terms. A recent ad, for the discount store LLAOX, is rather stark in this regard. A young man displays photos of the many items (guitars, television, appliances) he found at LLAOX. In the final shot, of an attractive woman standing in front of the items, he proudly boasts: "I found her at LLAOX, too!" Subject-Oriented Desire Like ads in other countries, then, Japanese ads tend to place the object ahead of the subject. Desire for the person depicted in the ad is either ancillary to the desire expressed for the product, or else exists as a function of the subject's objectified status. However, an accreting number of Japanese ads have begun orienting desire toward one or both of the subjects in the ad, over or independent of the object for sale. A man and woman in their early thirties sit at a table sipping whiskey. The woman leans toward the man and in a perky voice utters: "Hey, let's turn in soon." The man protests, pointing to the drink: "we haven't finished this, yet." The woman tilts her head. She insists "let's head home." Then in a conspiratorial undertone "it's that day" and winks. The man's elbow falls off the tabletop. The woman blows him a kiss. Cut to a cat hiding beneath one of his paws in embarrassment. (Source: Nikka All Malt Whiskey -- Japan, 1993) Admittedly, not all ad discourse involves desire. But of late considerable ad space has been devoted to human relations and longing6. Consider this promo for a health drink. A man stands on his verandah in his t-shirt and pyjama bottoms. He looks groggy. Cut to a young woman watering her plants on the adjacent porch. "Hey!" she coos to her bushes, "are you lively?" She tends the pots along the centre divider. Is she addressing her foliage or the young man on the other side? He cranes his neck to steal a peek. She seems unaware. He lays his head on his forearms, admiring her. Cut to a shot of her regarding the product; drinking it; savouring the taste. The text reads: "With Lactia you will bloom beautifully." The woman enthuses audibly: "happiness!" Her voyeur, still in thrall, emits a sigh, suddenly straightens and declares aloud (in English): "Nice!" The previous two examples feature desire by adults. Considerable contemporary desire-centred discourse, however, focuses on teens. In these cases the product is sometimes introduced as a symbol for desire -- as in this case of a potato chip which snaps crisply each time a boy's romantic advance is repelled. A boy and girl walk along a boardwalk. The boy tentatively reaches for his partner's hand. Just then an approaching bicyclist toots his horn and cleaves a path between the two. A superimposed chip snaps. Next, seated on the shoreline, the boy reaches out again. Suddenly, a wind-blown ball rolls past, prompting his intended to abruptly vacate her position. He is left, literally clutching air. Another chip snaps again. The boy reaches out to touch the girl's handprint in the sand. He utters "I like you". The girl turns and asks "what did you say?" He impotently shrugs "nothing at all." Cut to a box of the chips. This youthful obsession with desire plays prominently in ads. First, because it fits well with the "mini-drama" format currently favoured in Japanese advertising. Second, because it is an effective technique for capturing viewer interest. The emotional tugs keep the audience attending to the ad beyond the first viewing. In the following ad, while desire for the product is the punch line, the entire ad is structured around unrequited desire. The confusion of the former for the latter not only redounds to product value, but predisposes the audience toward empathy and engagement. A teenage girl in her plaid uniform steers her bike into its berth outside school. Her voiceover identifies the bike name, shows how one touch locks the wheel in place and the seat in the vertical position. "Oh!" a quavering male voice utters off camera. "Can I ask name?" Japanese being a language that often operates without articles and pronouns, we aren't sure which name he means. Quick zoom in on the girl's expectant expression. "Eh?" she asks breathlessly. Her narration stops, her heart soars, glowing a vibrant red over her white sweater. "The bike's name", her interlocutor clarifies. All at once, the throbbing red heart is extinguished, fading to a black circular smudge. Her expectant smile dissolves into disappointment. Not all scenarios are downers, however. In the following case the product is a prop -- at best an accoutrement -- in the teenage game of expressing desire. A spry girl pours hot water into two cups. Off camera an older female voice asks whether she isn't supposed to be resting. "Don't worry about it", the girl replies. Cut to exterior shot. She's wearing a short coat, backing through the front door with the two cups in her hands. Cut to an angled reaction shot: a handsome boy leans across his bike, placing a letter in the post. He holds the letter up. "This", he says. Cut to the girl, now leaning against the entryway of the building, sipping her drink. Haltingly, in a breathy voice, she utters: "To... tomorrow... would have been... okay. But..." Japanese being the language of implication we read this as "it's fine the way it is working out." With the girl in the foreground, we see the boy leaning against the entryway on the opposite side contemplating his drink. Cut to a long angled shot from high above. The two teens sup in the cool evening air, alone, intimate, yet separated by the building's bright entrance. The narrator closes with a message about the nutritional value of the drink -- wholly unrelated to the unequivocal web of intimacy spun by these two youths. This ad offers us a perfect take on how desire is constructed and reproduced in contemporary ads in Japan. A perfect place for us to close. Evolving Desire? Desire is not new to advertising, but the form in which it is currently being expressed is. In Japan, at least, where commercials strive for polysemy in the volatile, evanescent and ultimately quixotic struggle for audience attention, communication is increasingly about things unrelated to the product. High on the list are affection, intimacy and sexuality -- aspects of human existence which bear considerable connection to desire. Reproduced in a variety of forms, played out in an array of contexts, by a variety of demographic "types", such commercial communications have the effect of centralising desire as a major theme in contemporary Japanese society7. The increase in so-called "secondary discourse"8 about human longing is palpable. But what to make of it? Clear explanations lie in "social evolution" -- factors such as: Japan's remarkable achievement of its postwar economic goals; its subsequent economic meltdown and accreting political malaise; the dramatic decline in corporate loyalty; disintegration of the family; increased urbanisation, atomisation and anomie; the stratification of generations and economic classes; increased materialism and attention to status; the concomitant loss of a personal raison d'être and collective moral beacon. In fact, all the reasons that Emile Durkheim diagnosed in fin de siècle France in inventing the discipline of sociology and Murakami Ryu has recently discerned a century later in fin de siècle Japan. Desire is a manifestation of social breakdown, as well as a plea for its resolution. As we enter a new century -- indeed a new millenium -- it is an empirical question worth monitoring whether the Japanese obsession with desire will continue to swell. Footnotes 1. Although the claims in this paper are qualitative, rather than quantitative, without question it is true that both men and women in Japanese television advertising are depicted as desiring. In this way, one could claim that desire exists independent of gender in ads. At the same time, it is almost certain that desire is often depicted as being manifested differentially by men and women. However, as one can infer from the data below, this is not always so (viz. "True Love"). Moreover, while women (or men) might more often fit one or another of the constructs below (i.e. object-mediated, object-induced, object-directed, subject-oriented) than their opposite number, cases can generally be found in which both (male and female) are depicted desiring in each of the stated relationships. 1. Thinking of this (fire-desire) symbol-set generally (and this ad specifically), one is reminded of the Springsteen lyric: At night I wake up with the sheets soaking wet and a freight train running through the middle of my head; Only you can cool my desire. I'm on fire. -- Bruce Springsteen: "I'm on Fire" (1984) Reminding one of the lyric by Shocking Blue from their decade-spanning Number 1 single (1970 by the Dutch band as well as the 1986 cover version by Bananarama): I'm your Venus, I'm your fire at your desire. If not the Earth, Wind and Fire phrasing from "That's the Way of the World" (1975): Hearts of fire, creates love desire... Of course, the fire/desire combo might also have become a universal association due to the easy opportunity (at least in English) to commit a rhyme (no matter how cloddish). 2. It has yet to be determined that desire is a cultural universal. However, the universal presence and relatively uniform logic of the "machinery of capitalism" (a major aspect of which is advertising) certainly serves as a powerful prod. That machinery overlaps culture and tends to act on it in relatively similar ways (one of which may just be the discourse about desire). This, of course, makes no claims about universal outcomes. I have addressed the interaction of capitalism and context and the themes of global/local, homogeneity/heterogeneity, universal/particular in a series of articles concerning information transfer, body, color, and advertising form in comparative context. Please see my home page for references to and greater detail on this work. 3. Regarding red as signifier, see Branston & Stafford (7). Also see my work on color universals ("The Color of Meaning") and culture-specific colour conventions ("The Color of Difference"). 4. Support for this interpretation can be found in other ads, as ideas and practices in Japanese advertising tend to travel in twos or threes. During this same period, Suzuki Move placed Leonardo DiCaprio behind the wheel. As he tooled around the city, his accelleration was such as to raise the skirts of two by-standers. DiCaprio promptly braked, placed the car in reverse, rolled astride the two women, and impishly pointing at each, identified the shade of underpants ("white and strawberry") they were sporting. 5. And let me reiterate: All such depictions are exclusively about sexual/emotional longing between men and women. 6. As I am mainly working with Japanese data in this article, I feel comfortable only seeking to draw conclusions about Japanese society. Certainly, one could fathom conducting the same sort of analysis and arriving at the same general conclusions about other postmodern, capitalist, commercial-centred, consumer-oriented societies. 7. The word is O'Barr's. It bears considerable similarity to Barthes's "second order signification". Plates 1 Caliente perfume (USA, 1994) 9 Georgia canned coffee (Japan, 1999) 2 Old Spice cologne (USA, 1994) 10 Rosso (Japan, 1998) 3 Coke (Australia, 1994) 11 LLAOX (Japan, 1999) 4 Dashing cologne (Malaysia, 1997) 12 Lactia (Japan, 1997) 5 Cup Noodles (Japan, 1998) 13 5/8 and 3/5 Chips (Japan, 1993) 6 Cup Noodles (Japan, 1998) 14 Gachyarinko (Japan, 1999) 7 Nescafe Excella (ice coffee; Japan, 1999) 15 Hotpo (health drink; Japan 1999) 8 Various ads References Barthes, Roland. Mythologies. Jonathan Cape, 1972 (1957). Branston, G., and R. Stafford. The Media Student's Book. London: Routledge, 1996. Fiske, John. Television Culture. London: Methuen, 1987. Holden, Todd. "The Color of Meaning: The Significance of Black and White in Television Commercials." Interdisciplinary Information Sciences 3.2 (1997): 125-146. ---. "The Color of Difference: Critiquing Cultural Convergence via Television Advertising" Interdisciplinary Information Sciences 5.1 (1999): 15-36. O'Barr. Culture and the Ad: Exploring Otherness in the World of Advertising. Boulder, Co.: Westview Press, 1994. Williamson, Judith. Decoding Advertisements: Ideology and Meaning in Advertising. London: Marion Boyers, 1979. Citation reference for this article MLA style: Todd Joseph Miles Holden. "The Evolution of Desire in Advertising: From Object-Obsession to Subject-Affection." M/C: A Journal of Media and Culture 2.5 (1999). [your date of access] <http://www.uq.edu.au/mc/9907/adverts.php>. Chicago style: Todd Joseph Miles Holden, "The Evolution of Desire in Advertising: From Object-Obsession to Subject-Affection," M/C: A Journal of Media and Culture 2, no. 5 (1999), <http://www.uq.edu.au/mc/9907/adverts.php> ([your date of access]). APA style: Todd Joseph Miles Holden. (1999) The evolution of desire in advertising: from object-obsession to subject-affection. M/C: A Journal of Media and Culture 2(5). <http://www.uq.edu.au/mc/9907/adverts.php> ([your date of access]).