A5047401370- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Cell Image Analysis Techniques
- Time Series Analysis and Forecasting
- Computer Science and Engineering
- Data Mining and Machine Learning Applications
- Explainable Artificial Intelligence (XAI)
- Image Processing Techniques and Applications
- Data Stream Mining Techniques
- Adversarial Robustness in Machine Learning
- Digital Imaging for Blood Diseases
- Video Surveillance and Tracking Methods
- Privacy-Preserving Technologies in Data
- Scientific Computing and Data Management
- Autonomous Vehicle Technology and Safety
- Network Security and Intrusion Detection
- Machine Learning and Data Classification
- Edcuational Technology Systems
- Cryptography and Data Security
- Food and Agricultural Sciences
- Stock Market Forecasting Methods
- Bayesian Modeling and Causal Inference
- Vehicle License Plate Recognition
- Mathematics, Computing, and Information Processing
- Data Quality and Management
German Research Centre for Artificial Intelligence
2017-2024
University of Kaiserslautern
2017-2022
Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
2021
Karakter
2020
University of North Sumatra
2020
University of Pembangunan Nasional Veteran Jawa Timur
2018
Traditional distance and density-based anomaly detection techniques are unable to detect periodic seasonality related point anomalies which occur commonly in streaming data, leaving a big gap time series the current era of IoT. To address this problem, we present novel deep learning-based approach (DeepAnT) for is equally applicable non-streaming cases. DeepAnT capable detecting wide range anomalies, i.e., contextual discords data. In contrast methods where learned, uses unlabeled data...
This paper presents a novel framework for the demystification of convolutional deep learning models time-series analysis. is step toward making informed/explainable decisions in domain time series, powered by learning. There have been numerous efforts to increase interpretability image-centric neural network models, where learned features are more intuitive visualize. Visualization series significantly challenging, as there no direct interpretation filters and inputs compared with imaging...
The need for robust unsupervised anomaly detection in streaming data is increasing rapidly the current era of smart devices, where enormous are gathered from numerous sensors. These sensors record internal state a machine, external environment, and interaction machines with other humans. It prime importance to leverage this information order minimize downtime machines, or even avoid completely by constant monitoring. Since each device generates different type data, it normally case that...
With the Internet of Things (IoT) devices becoming an integral part human life, need for robust anomaly detection in streaming data has also been elevated. Dozens distance-based, density-based, kernel-based, and cluster-based algorithms have proposed area detection. Recently, because robustness deep neural networks (DNN), different learning-based methods proposed. all these rapid developments, there exists a small number comparative studies methods. Even those studies, comparison is done...
The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, silent, recurrent acknowledged issue in this area is the lack consensus regarding its terminology. In particular, each new contribution seems to rely on own (and often intuitive) version terms like "explanation" "interpretation". Such disarray encumbers consolidation advances towards fulfillment scientific regulatory demands e.g., when comparing methods or establishing their compliance w.r.t....
Two-stage detectors are state-of-the-art in object detection as well pedestrian detection. However, the current two-stage inefficient they do bounding box regression multiple steps i.e. region proposal networks and heads. Also, anchor-based computationally expensive to train. We propose F2DNet, a novel architecture which eliminates redundancy of by replacing network with our focal head fast suppression head. benchmark F2DNet on top datasets, thoroughly compare it against existing conduct...
We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed first the different based image representations, i.e., color transform, connected component analysis, distance termed as Fi-Fo representation. representation is then fed for further refined representation-learning detecting evaluated on publicly available ICDAR-2017 Page Object Detection (POD) dataset its corrected...
With the evolution of deep learning in past decade, more biomedical related problems that seemed strenuous, are now feasible. The introduction U-net and Mask R-CNN architectures has paved a way for many object detection segmentation tasks numerous applications ranging from security to applications. In cell biology domain, light microscopy imaging provides cheap accessible source raw data study biological phenomena. By leveraging such techniques, human diseases can be easily diagnosed process...
The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models. However, in real life applications these models often encounter scenarios that are inadequately represented the data used training. There various reasons absence sufficient data, ranging from time cost constraints to ethical considerations. As a consequence, reliable usage models, especially safety-critical applications, still tremendous challenge....
This paper presents detailed anomaly detection evaluation on operational time-series data of Internet Things (IoT) based household devices in general and Heating, Ventilation Air Conditioning (HVAC) systems specific. Due to the number issues observed during widely used distance-based, statistical-based, cluster-based techniques, we also present a pattern-based approach for HVAC data. The usage IoT are enormously increasing will have major share near future. log these contains different...
With the advent of machine learning in applications critical infrastructure such as healthcare and energy, privacy is a growing concern minds stakeholders. It pivotal to ensure that neither model nor data can be used extract sensitive information by attackers against individuals or harm whole societies through exploitation infrastructure. The applicability these domains mostly limited due lack trust regarding transparency constraints. Various safety-critical use cases (mostly relying on...
Accurate cell segmentation in microscopic images is a useful tool to analyze individual behavior, which helps diagnose human diseases and development of new treatments. Cell cells image with many view allows quantification single cellular features, such as shape or movement patterns, providing rich insight into heterogeneity. Most the algorithms up till now focus on segmenting without classifying culture images. Discrimination among types can lead era high-throughput microscopy. Multiple...
Discrimination between cell types in the co-culture environment with multiple lines can assist examining interaction different populations. Identifying cultures addition to segmentation is essential for understanding cellular mechanisms associated disease states. In drug development, biologists are more interested models because they replicate tumor vivo better than monoculture models. Additionally, have a measurable effect on cancer response treatment. Co-culture critical designing maximum...
Traditional neural networks trained using point-based maximum likelihood estimation are deterministic models and have exhibited near-human performance in many image classification tasks. However, their insistence on representing network parameters with point-estimates renders them incapable of capturing all possible combinations the weights; consequently, resulting a biased predictor towards initialisation. Most importantly, these inherently unable to provide any uncertainty estimate for...
The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, silent, recurrent acknowledged issue in this area is the lack consensus regarding its terminology. In particular, each new contribution seems to rely on own (and often intuitive) version terms like "explanation" "interpretation". Such disarray encumbers consolidation advances towards fulfillment scientific regulatory demands e.g., when comparing methods or establishing their compliance with...
The need for a prospective student to know the interest of field study at college according his intelligence becomes one complex problems.The selection right makes students more enthusiastic attend and graduate on time.Therefore an intellectual test needs be tested with aim helping plan make decisions about choice within college.Through test, obtained level readiness choose by it has minimizes errors in majors.This aims build expert system application that provides recommendations results...
Penelitian ini berkaitan dengan proses klasifikasi Pneumonia Covid-19 (radang paru-paru atau pneumonia yang disebabkan oleh virus corona SARS-CoV-2) dari citra hasil foto rontgen / x-ray menggunakan pendekatan pembelajaran mesin. Klasifikasi dilakukan untuk menentukan apakah kondisi seseorang mengalami Covid-19, biasa, Normal Sehat. Untuk menghasilkan kinerja lebih baik, optimasi seringkali digunakan pada tahap pelatihan data. Banyak teknik melakukan tersebut, diantaranya adalah algoritma...
Abstrak. Segmentasi merupakan tahapan penting baik dalam pengolahan citra digital ataupun persiapan proses inti visi computer. awal yang diterapkan pada sebelum ke seperti pengenalan objek dan analisis objek. Dalam penelitian ini segmentasi menggunakan K-Means Clustering akan sebagai pemrosesan dari aplikasi jenis belimbing buah berdasarkan bentuk daun. Jenis digunakan adalah Bangkok Merah Filipin. Sebelum daun diambil (ekstraksi) ciri-ciri bentuk, warna, sebaginya, terlebih dahulu dilakukan...