004 Informatik
Refine
Document Type
- Conference proceeding (25)
- Journal article (9)
- Doctoral Thesis (1)
Is part of the Bibliography
- yes (35)
Institute
- Technik (35) (remove)
Publisher
Advancing mental health diagnostics: AI-based method for depression detection in patient interviews
(2023)
In this paper, we present a novel artificial intelligence (AI) application for depression detection, using advanced transformer networks to analyse clinical interviews. By incorporating simulated data to enhance traditional datasets, we overcome limitations in data protection and privacy, consequently improving the model’s performance. Our methodology employs BERT-based models, GPT-3.5, and ChatGPT-4, demonstrating state-of-the-art results in detecting depression from linguistic patterns and contextual information that significantly outperform previous approaches. Utilising the DAIC-WOZ and Extended-DAIC datasets, our study showcases the potential of the proposed application in revolutionising mental health care through early depression detection and intervention. Empirical results from various experiments highlight the efficacy of our approach and its suitability for real-world implementation. Furthermore, we acknowledge the ethical, legal, and social implications of AI in mental health diagnostics. Ultimately, our study underscores the transformative potential of AI in mental health diagnostics, paving the way for innovative solutions that can facilitate early intervention and improve patient outcomes.
With the rapid development of globalization, the demand for translation between different languages is also increasing. Although pre-training has achieved excellent results in neural machine translation, the existing neural machine translation has almost no high-quality suitable for specific fields. Alignment information, so this paper proposes a pre-training neural machine translation with alignment information via optimal transport. First, this paper narrows the representation gap between different languages by using OTAP to generate domain-specific data for information alignment, and learns richer semantic information. Secondly, this paper proposes a lightweight model DR-Reformer, which uses Reformer as the backbone network, adds Dropout layers and Reduction layers, reduces model parameters without losing accuracy, and improves computational efficiency. Experiments on the Chinese and English datasets of AI Challenger 2018 and WMT-17 show that the proposed algorithm has better performance than existing algorithms.
In clothing e-commerce, the challenge of optimally recommending clothing that suits a user’s unique characteristics remains a pressing issue. Many platforms simply recommend best-selling or popular clothing, without taking into account important attributes like user’s face color, pupil color, face shape, age, etc. To solve this problem, this paper proposes a personalized clothing recommendation algorithm that incorporates the established 4-Season Color System and user-specific biological characteristics. Firstly, the attributes and colors of clothing are classified by Fnet network, that can learn disjoint label combinations and mitigate the issue of excessive labels. Secondly, on the basis of the 4-Season Color System, the user’s face color model is trained by combined MobileNetV3_DTL, which ensures the model’s generalization and improves the training speed. Thirdly, user’s face shape and age are divided into different categories by an Inception network. Finally, according to the users’ face color, age, face shape and other information, personalized clothing is recommended in a coarse-to-fine manner. Experiments on five datasets demonstrate that the algorithm proposed in this paper achieves state-of-the-art results.
Most Question-answering (QA) systems rely on training data to reach their optimal performance. However, acquiring training data for supervised systems is both time-consuming and resource-intensive. To address this, in this paper, we propose TFCSG, an unsupervised similar question retrieval approach that leverages pre-trained language models and multi-task learning. Firstly, topic keywords in question sentences are extracted sequentially based on a latent topic-filtering algorithm to construct unsupervised training corpus data. Then, the multi-task learning method is used to build the question retrieval model. There are three tasks designed. The first is a short sentence contrastive learning task. The second is the question sentence and its corresponding topic sequence similarity judgment task. The third is using question sentences to generate their corresponding topic sequence task. The three tasks are used to train the language model in parallel. Finally, similar questions are obtained by calculating the cosine similarity between sentence vectors. The comparison experiment on public question datasets that TFCSG outperforms the comparative unsupervised baseline method. And there is no need for manual marking, which greatly saves human resources.
In this paper, it aims to model wind speed time series at multiple sites. The five-parameter Johnson distribution is deployed to relate the wind speed at each site to a Gaussian time series, and the resultant m-dimensional Gaussian stochastic vector process Z(t) is employed to model the temporal-spatial correlation of wind speeds at m different sites. In general, it is computationally tedious to obtain the autocorrelation functions (ACFs) and cross-correlation functions (CCFs) of Z(t), which are different to those of wind speed times series. In order to circumvent this correlation distortion problem, the rank ACF and rank CCF are introduced to characterize the temporal-spatial correlation of wind speeds, whereby the ACFs and CCFs of Z(t) can be analytically obtained. Then, Fourier transformation is implemented to establish the cross-spectral density matrix of Z(t), and an analytical approach is proposed to generate samples of wind speeds at m different sites. Finally, simulation experiments are performed to check the proposed methods, and the results verify that the five-parameter Johnson distribution can accurately match distribution functions of wind speeds, and the spectral representation method can well reproduce the temporal-spatial correlation of wind speeds.
In recent years, 3D facial reconstructions from single images have garnered significant interest. Most of the approaches are based on 3D Morphable Model (3DMM) fitting to reconstruct the 3D face shape. Concurrently, the adoption of Generative Adversarial Networks (GAN) has been gaining momentum to improve the texture of reconstructed faces. In this paper, we propose a fundamentally different approach to reconstructing the 3D head shape from a single image by harnessing the power of GAN. Our method predicts three maps of normal vectors of the head’s frontal, left, and right poses. We are thus presenting a model-free method that does not require any prior knowledge of the object’s geometry to be reconstructed.
The key advantage of our proposed approach is the substantial improvement in reconstruction quality compared to existing methods, particularly in the case of facial regions that are self-occluded in the input image. Our method is not limited to 3d face reconstruction. It is generic and applicable to multiple kinds of 3D objects. To illustrate the versatility of our method, we demonstrate its efficacy in reconstructing the entire human body.
By delivering a model-free method capable of generating high-quality 3D reconstructions, this paper not only advances the field of 3D facial reconstruction but also provides a foundation for future research and applications spanning multiple object types. The implications of this work have the potential to extend far beyond facial reconstruction, paving the way for innovative solutions and discoveries in various domains.
The aim of this work is the development of artificial intelligence (AI) application to support the recruiting process that elevates the domain of human resource management by advancing its capabilities and effectiveness. This affects recruiting processes and includes solutions for active sourcing, i.e. active recruitment, pre-sorting, evaluating structured video interviews and discovering internal training potential. This work highlights four novel approaches to ethical machine learning. The first is precise machine learning for ethically relevant properties in image recognition, which focuses on accurately detecting and analysing these properties. The second is the detection of bias in training data, allowing for the identification and removal of distortions that could skew results. The third is minimising bias, which involves actively working to reduce bias in machine learning models. Finally, an unsupervised architecture is introduced that can learn fair results even without ground truth data. Together, these approaches represent important steps forward in creating ethical and unbiased machine learning systems.
AI-based prediction and recommender systems are widely used in various industry sectors. However, general acceptance of AI-enabled systems is still widely uninvestigated. Therefore, firstly we conducted a survey with 559 respondents. Findings suggested that AI-enabled systems should be fair, transparent, consider personality traits and perform tasks efficiently. Secondly, we developed a system for the Facial Beauty Prediction (FBP) benchmark that automatically evaluates facial attractiveness. As our previous experiments have proven, these results are usually highly correlated with human ratings. Consequently they also reflect human bias in annotations. An upcoming challenge for scientists is to provide training data and AI algorithms that can withstand distorted information. In this work, we introduce AntiDiscriminationNet (ADN), a superior attractiveness prediction network. We propose a new method to generate an unbiased convolutional neural network (CNN) to improve the fairn ess of machine learning in facial dataset. To train unbiased networks we generate synthetic images and weight training data for anti-discrimination assessments towards different ethnicities. Additionally, we introduce an approach with entropy penalty terms to reduce the bias of our CNN. Our research provides insights in how to train and build fair machine learning models for facial image analysis by minimising implicit biases. Our AntiDiscriminationNet finally outperforms all competitors in the FBP benchmark by achieving a Pearson correlation coefficient of PCC = 0.9601.
Deep learning-based EEG detection of mental alertness states from drivers under ethical aspects
(2021)
One of the most critical factors for a successful road trip is a high degree of alertness while driving. Even a split second of inattention or sleepiness in a crucial moment, will make the difference between life and death. Several prestigious car manufacturers are currently pursuing the aim of automated drowsiness identification to resolve this problem. The path between neuro-scientific research in connection with artificial intelligence and the preservation of the dignity of human individual’s and its inviolability, is very narrow. The key contribution of this work is a system of data analysis for EEGs during a driving session, which draws on previous studies analyzing heart rate (ECG), brain waves (EEG), and eye function (EOG). The gathered data is hereby treated as sensitive as possible, taking ethical regulations into consideration. Obtaining evaluable signs of evolving exhaustion includes techniques that obtain sleeping stage frequencies, problematic are hereby the correlated interference’s in the signal. This research focuses on a processing chain for EEG band splitting that involves band-pass filtering, principal component analysis (PCA), independent component analysis (ICA) with automatic artefact severance, and fast fourier transformation (FFT). The classification is based on a step-by-step adaptive deep learning analysis that detects theta rhythms as a drowsiness predictor in the pre-processed data. It was possible to obtain an offline detection rate of 89% and an online detection rate of 73%. The method is linked to the simulated driving scenario for which it was developed. This leaves space for more optimization on laboratory methods and data collection during wakefulness-dependent operations.
Fault diagnosis of rolling bearings is an essential process for improving the reliability and safety of the rotating machinery. It is always a major challenge to ensure fault diag- nosis accuracy in particular under severe working conditions. In this article, a deep adversarial domain adaptation (DADA) model is proposed for rolling bearing fault diagnosis. This model con- structs an adversarial adaptation network to solve the commonly encountered problem in numerous real applications: the source domain and the target domain are inconsistent in their distribution. First, a deep stack autoencoder (DSAE) is combined with representative feature learning for dimensionality reduction, and such a combination provides an unsupervised learning method to effectively acquire fault features. Meanwhile, domain adaptation and recognition classification are implemented using a Softmax classifier to augment classification accuracy. Second, the effects of the number of hidden layers in the stack autoencoder network, the number of neurons in each hidden layer, and the hyperparameters of the proposed fault diagnosis algorithm are analyzed. Third, comprehensive analysis is performed on real data to vali- date the performance of the proposed method; the experimental results demonstrate that the new method outperforms the existing machine learning and deep learning methods, in terms of classification accuracy and generalization ability.
Facial beauty prediction (FBP) aims to develop a machine that automatically makes facial attractiveness assessment. In the past those results were highly correlated with human ratings, therefore also with their bias in annotating. As artificial intelligence can have racist and discriminatory tendencies, the cause of skews in the data must be identified. Development of training data and AI algorithms that are robust against biased information is a new challenge for scientists. As aesthetic judgement usually is biased, we want to take it one step further and propose an Unbiased Convolutional Neural Network for FBP. While it is possible to create network models that can rate attractiveness of faces on a high level, from an ethical point of view, it is equally important to make sure the model is unbiased. In this work, we introduce AestheticNet, a state-of-the-art attractiveness prediction network, which significantly outperforms competitors with a Pearson Correlation of 0.9601. Additionally, we propose a new approach for generating a bias-free CNN to improve fairness in machine learning.
”I have never seen one who loves virtue as much as he loves beauty,” Confucius once said. If beauty is more important as goodness, it becomes clear why people invest so much effort in their first impression. The aesthetic of faces has many aspects and there is a strong correlation to all characteristics of humans, like age and gender. Often, research on aesthetics by social and ethic scientists lacks sufficient labelled data and the support of machine vision tools. In this position paper we propose the Aesthetic-Faces dataset, containing training data which is labelled by Chinese and German annotators. As a combination of three image subsets, the AF-dataset consists of European, Asian and African people. The research communities in machine learning, aesthetics and social ethics can benefit from our dataset and our toolbox. The toolbox provides many functions for machine learning with state-of-the-art CNNs and an Extreme-Gradient-Boosting regressor, but also 3D Morphable Model technolo gies for face shape evaluation and we discuss how to train an aesthetic estimator considering culture and ethics.
We propose a method for recognizing dynamic gestures using a 3D sensor. New aspects of the developed system include problem-adapted data conversion and compression as well as automatic detection of different variants of the same gesture via clustering with a suitable metric inspired by Jaccard metric. The combination of Hidden Markov Models and clustering leads to robust detection of different executions based on a small set of training data. We achieved an increase of 5% recognition rate compared to regular Hidden Markov Models. The system has been used for human-machine interaction and might serve as an assistive system in physiotherapy and neurological or orthopedic diagnosis.
Investigation of tympanic membrane influences on middle-ear impedance measurements and simulations
(2020)
This study simulates acoustic impedance measurements in the human ear canal and investigates error influences due to improperly accounted evanescence in the probe’s near field, cross-section area changes, curvature of the ear canal, and pressure inhomogeneities across the tympanic membrane, which arise mainly at frequencies above 10 kHz. Evanescence results from strongly damped modes of higher order, which can only be found in the near field of the sound source and are excited due to sharp cross-sectional changes as they occur at the transition from the probe loudspeaker to the ear canal. This means that different impedances are measured depending on the probe design. The influence of evanescence cannot be eliminated completely from measurements, however, it can be reduced by a probe design with larger distance between speaker and microphone. A completely different approach to account for the influence of evanescence is to evaluate impedance measurements with the help of a finite element model, which takes the precise arrangement of microphone and speaker in the measurement into account. The latter is shown in this study exemplary on impedance measurements at a tube terminated with a steel plate. Furthermore, the influences of shape changes of the tympanic membrane and ear canal curvature on impedance are investigated.
This study describes a non-contact measuring and system identification procedure for evaluating inhomogeneous stiffness and damping characteristics of the annular ligament in the physiological amplitude and frequency range without the application of large static external forces that can cause unnatural displacements of the stapes. To verify the procedure, measurements were first conducted on a steel beam. Then, measurements on an individual human cadaveric temporal bone sample were performed. The estimated results support the inhomogeneous stiffness and damping distribution of the annular ligament and are in a good agreement with the multiphoton microscopy results which show that the posterior-inferior corner of the stapes footplate is the stiffest region of the annular ligament.
This study describes a non-contact measuring and parameter identification procedure designed to evaluate inhomogeneous stiffness and damping characteristics of the annular ligament in the physiological amplitude and frequency range without the application of large static external forces that can cause unnatural displacements of the stapes. To verify the procedure, measurements were first conducted on a steel beam. Then, measurements on an individual human cadaveric temporal bone sample were performed. The estimated results support the inhomogeneous stiffness and damping distribution of the annular ligament and are in a good agreement with the multiphoton microscopy results which show that the posterior-inferior corner of the stapes footplate is the stiffest region of the annular ligament. This method can potentially help to establish a correlation between stiffness and damping characteristics of the annular ligament and inertia properties of the stapes and, thus, help to reduce the number of independent parameters in the model-based hearing diagnosis.
Due to the large interindividual variances and the poor optical accessibility of the ear, the specificity of hearing diagnostics today is severely restricted to a certain clinical picture and quantitative assessment. Often only a yes or no decision is possible, which depends strongly on the subjective assessment of the ENT physician. A novel approach, in which objectively obtainable, non invasive audiometric measurements are evaluated using a numerical middle ear model, makes it possible to make the hidden middle ear properties visible and quantifiable. The central topic of this paper is a novel parameter identification algorithm that combines inverse fuzzy arithmetic with an artificial neural network in order to achieve a coherent diagnostic overall picture in the comparison of model and measurement. Its usage is shown at a pathological pattern called malleus fixation where the upper ligament of the malleus is pathologically stiffened.
A fully passive RFID temperature sensor SoC with an accuracy of ±0.4 ◦C (3σ) from 0 ◦C to 125 ◦C
(2019)
This paper presents a fully passive 13.56 -MHz RFID temperature sensor system-on-chip. Its power management unit operates over a large temperature range using a zero temperature coefficient bias source. On-chip temperature sensing is accomplished with low-voltage, low-power CMOS circuitry, and time-domain signal processing. Two readout commands have been defined to study supply noise sensitivity: 1) standard readout, where just a single set of data is transferred to the reader and 2) serial readout, where several sets of data are sent one after the other to the reader. With the standard readout command, the sensor suffers from interference from the RFID command packet and outputs interference as well, while the sensor outputs no interference with the serial readout command. Measurements show that sensor resolution with serial readout is improved by a factor of approximately 16 compared to standard readout. The chip was fabricated in a standard 0.35-μm CMOS technology and chip-on-board mounted to a tuned RFID transponder coil on an aluminum core FR4 PCB substrate. Real time wireless temperature sensing has been demonstrated with a commercial HF RFID reader. With a two-point calibration, the SoC achieves a 3σ sensing accuracy of ±0.4 ◦C from 0◦C to 125 ◦C.
The complexity of supply chains increases, especially due to the geographical spread of supplier and customer networks. In the connected and automated supply chains of the industry 4.0, even more nodes are incorporated in supply chains. This paper discusses the possible improvement of process quality in the industry 4.0 through the different blockchain and distributed ledger technologies. We derived hypotheses from a literature review and asked German blockchain experts from the industry to validate and discuss the hypotheses. We find that the different blockchain technologies and consensus algorithms have different strength with regard to quality improvement. One central finding is that IOTA, developed especially for the IoT and deemed the ’next evolutionary step’ is scalable and hence may increase the process efficiency, but at the same time is more vulnerable than other blockchain implementations, which again may reduce the overall process quality.
SLAM systems are mainly applied for robot navigation while research on feasibility for motion planning with SLAM for tasks like bin-picking, is scarce. Accurate 3D reconstruction of objects and environments is important for planning motion and computing optimal gripper pose to grasp objects. In this work, we propose the methods to analyze the accuracy of a 3D environment reconstructed using a LSD-SLAM system with a monocular camera mounted onto the gripper of a collaborative robot. We discuss and propose a solution to the pose space conversion problem. Finally, we present several criteria to analyze the 3D reconstruction accuracy. These could be used as guidelines to improve the accuracy of 3D reconstructions with monocular LSD-SLAM and other SLAM based solutions.