Refine
Year of publication
- 2021 (63) (remove)
Document type
- Conference Proceeding (63) (remove)
Language
- English (63) (remove)
Has full text
- No (63)
Is part of the Bibliography
- Yes (63)
Keywords
- Machine learning (4)
- Bone screw (2)
- Manufacturing (2)
- Reference model (2)
- Smart screwdriver (2)
- Software engineering (2)
- SusAF (2)
- Sustainability (2)
- Torque limitation (2)
- 2D differential microcoils (1)
- 3D-Data (1)
- 5G (1)
- AI in manufacturing (1)
- Adversarial image (1)
- Appropriate resolution prototyping (1)
- Artificial intelligence (1)
- Artificial neural network (1)
- Autism spectrum disorder (ASD) (1)
- Blockchain (1)
- Body cameras (1)
- CNN generalisability (1)
- COVID-19 pandemic (1)
- Cancer (1)
- Cloud (1)
- Cloud-edge computing (1)
- Clustering (1)
- Concept drift detection (1)
- Context-aware systems (1)
- Convolutional neural network (1)
- Cost based metric (1)
- Cross company business model (1)
- Deep learning (1)
- Dementia (1)
- Digital human modeling (DHM) (1)
- Digitalization (1)
- Digizitation (1)
- Dimensional layout conception (1)
- Distributed DNN (1)
- Distributed data validation network (1)
- Domain expert interviews (1)
- Eddy-current transducers (1)
- Edge Computing (1)
- Edge cloud computing (1)
- Edge security (1)
- Electromagnetic simulation (1)
- Energy forecast (1)
- Entwicklungsprozess (1)
- Error prediction (1)
- Explainable ML (1)
- Extended reality (1)
- Facial emotion recognition (FER) (1)
- Factory operations commission (1)
- Feature extraction (FE) (1)
- Filter-based feature selection methods (1)
- Fuzzy logic (1)
- Grinding burn (1)
- Hearing impairment (1)
- Human-robot collaboration (1)
- Hybrid AI (1)
- Industry 4.0 (1)
- Insertion speed (1)
- Intra-abdominal pressure (1)
- IoT (1)
- Keynote (1)
- Laparoscopic images (1)
- Laparoscopy (1)
- Locality aware (1)
- Lung lesion (1)
- Lung mechanics (1)
- Micro non-destructive evaluation (1)
- Microwave imaging (1)
- Minimum viable product (1)
- Mobile-access edge computing (1)
- Mobility management (1)
- Natural language processing (1)
- Neural networks (1)
- Neuro-fuzzy (1)
- OR-layout (1)
- Occupational fields (1)
- Older workers (1)
- Operating room (OR) (1)
- Oulu-CASIA (1)
- Peer-reviewed conference (1)
- Poster (1)
- Product engineering (1)
- Production (1)
- Production data (1)
- Produktentwicklung (1)
- Reminisence therapy (1)
- Risk analysis (1)
- Robotics (1)
- Role understanding (1)
- SHAP values (1)
- Security (1)
- Semantic segmentation (1)
- Service design (1)
- Service innovation (1)
- Service prototyping (1)
- Service quality (1)
- Small data (1)
- Software development practitioners (1)
- Software product (1)
- Software sustainability (1)
- Subject orientation (1)
- Surgical actions (1)
- Surgical tool detection (1)
- Sustainability design (1)
- Sustainability effects (1)
- Task migration (1)
- Test rig (1)
- Usability Praktiker (1)
- User eXperience (1)
- User experience (1)
- User requirements engineering (1)
- Video-assisted thoracoscopic surgery (VATS) (1)
- Visual attention network (1)
- mHealth (1)
The Elephant in the Room - Educating Practitioners on Software Development for Sustainability
(2021)
Distributed machine learning algorithms that employ Deep Neural Networks (DNNs) are widely used in Industry 4.0 applications, such as smart manufacturing. The layers of a DNN can be mapped onto different nodes located in the cloud, edge and shop floor for preserving privacy. The quality of the data that is fed into and processed through the DNN is of utmost importance for critical tasks, such as inspection and quality control. Distributed Data Validation Networks (DDVNs) are used to validate the quality of the data. However, they are prone to single points of failure when an attack occurs. This paper proposes QUDOS, an approach that enhances the security of a distributed DNN that is supported by DDVNs using quorums. The proposed approach allows individual nodes that are corrupted due to an attack to be detected or excluded when the DNN produces an output. Metrics such as corruption factor and success probability of an attack are considered for evaluating the security aspects of DNNs. A simulation study demonstrates that if the number of corrupted nodes is less than a given threshold for decision-making in a quorum, the QUDOS approach always prevents attacks. Furthermore, the study shows that increasing the size of the quorum has a better impact on security than increasing the number of layers. One merit of QUDOS is that it enhances the security of DNNs without requiring any modifications to the algorithm and can therefore be applied to other classes of problems.
Training of neural networks requires often high computational power and large memory on Graphics Processing Unit (GPU) hardware. Many cloud providers such as Amazon, Azure, Google, Siemens, etc, provide such infrastructure. However, should one choose a cloud infrastructure or an on premise system for a neural network application, how can these systems be compared with one another? This paper investigates seven prominent Machine Learning benchmarks, which are MLPerf, DAWNBench, DeepBench, DLBS, TBD, AIBench, and ADABench. The recent popularity and widespread use of Deep Learning in various applications have created a need for benchmarking in this field. This paper shows that these application domains need slightly different resources and argue that there is no standard benchmark suite available that addresses these different application needs. We compare these benchmarks and summarize benchmarkrelated datasets, domains, and metrics. Finally, a concept of an ideal benchmark is sketched.
Potentials of Semantic Image Segmentation Using Visual Attention Networks for People with Dementia
(2021)
Due to the increasing number of dementia patients, it is time to include the care sector in digitization as well. Digital media, for example, can be used on tablets in memory care and have considerable potential for reminiscence therapy for people with dementia. The time consuming assembly of digital media content has to be automated for the caretakers.
This work analyzes the potentials of semantic image segmentation with Visual Attention Networks for reminiscence therapy sessions. These approaches enable the selection of digital images to satisfy the patients individual experience and biographically. A detailed comparison of various Visual Attention Networks evaluated by the BLEU score is shown. The most promising networks for semantic image segmentation are VGG16 and VGG19.
In edge/fog computing infrastructures, the resources and services are offloaded to the edge and computations are distributed among different nodes instead of transmitting them to a centralized entity. Distributed Hash Table (DHT) systems provide a solution to organizing and distributing the computations and storage without involving a trusted third party. However, the physical locations of nodes are not considered during the creation of the overlay which causes some efficiency issues. In this paper, Locality aware Distributed Addressing (LADA) model is proposed that can be adopted in distributed infrastructures to create an overlay that considers the physical locations of participating nodes. LADA aims to address the efficiency issues during the store and lookup processes in DHT overlay. Additionally, it addresses the privacy issue in similar proposals and removes any possible set of fixed entities. Our studies showed that the proposed model is efficient, robust and is able to protect the privacy of the locations of the participating nodes.
Plastic cocktails in rivers
(2021)
Correlation between intra-abdominal pressure and lung mechanics during laparoscopic gynecology
(2021)
The approach of using current transients to model the nucleation rate as reported in the seminal work of Scharifker and Mostany is limited to electrodeposition system without bath hydrodynamics (BHD). Therefore, in this work in situ electroanalytical approach is proposed to unveil the influence of BHD on the nucleation kinetics of electrochemically deposited Nickel-Cobalt alloy system (eNiCo). Using the Hydrodynamic linear sweep voltammetry (HLSV) technique, the limiting current density as a function of BHD is computed, wherein it increased (for eNiCo alloys) from 186 mA/cm² to 222.6 mA/cm² on increasing BHD from 0 to 42 cm/s, respectively. Consecutively, the diffusion layer thickness is found to decrease from 19 µm to ca. 15.8 µm on increasing BHD from 0 to 42 cm/s, respectively. Additionally, from Nyquist plots recorded using the Galvanostatic Electrochemical Impedance Spectroscopy (GEIS), the charge transfer coefficient (Rct), exchange current density (io) and double layer capacitance (Cdl) as a function of BHD is computed. It is found that Rct decreased and io, Cdl increased as function of BHD. Thereby, indicating the enhancement in the charge transfer on the cathode surface and reduction in the thickness of the diffusion layer. Hence, with the use of BHD, it is possible to control the growth kinetics, therefore enabling the deposition of tailor-made materials possessing specific required properties.
Microfabricated 2D inductive eddy-current transducers operating in a reflection differential transmitter-receiver mode are presented for the micro nondestructive detection of micro grinding burn. 2D spiral circular microcoils are employed as excitation coils, while an innovatively conceptualized “interconnected split-D” type differential microcoil is used as a sensing coil. Finite element modelling using COMSOL revealed the efficacy of proposed concept in non-destructive testing of small grinding burn having a width of 100 µm. The induced sensing coil voltage changed as a function of presence of grinding burn, with successful recording of the signal for the investigated lift-off range of 250 µm - 1000 µm for 100 kHz to 1 MHz driving frequencies of excitation coil. Experimental validation showed a 94% increase in the induced voltage of the sensing coil in presence of grinding burn on increasing the driving frequency of excitation coil from 100 kHz to 1 MHz. Thereby, revealing the superficial nature of the grinding burn defect, and showing the efficacy of the proposed concept for the non-destructive testing of grinding burn.
Investigations to improve the adhesion between the PECVD coated silicon carbide thin films and monocrystalline (110) silicon wafer substrate is reported. The surface treatment of silicon wafer is realized by roughening the wafer surface by wet etching in 1.8M potassium hydroxide solution at 50°C with ultrasonic agitation. The average surface roughness of the silicon wafer was increased from 2.9 nm for polished wafer to a range between 32 nm to 250 nm by wet etching for a duration of 10 minutes to 55 minutes, respectively. The adhesion between the PECVD coated silicon carbide thin films (ca. 300 nm thickness) and the silicon wafers with varying surface roughness was characterized by means of scanning scratch test. The critical load initially increased from 153 mN to 169 mN on increasing the average surface roughness from 2.9 nm to 33 nm, respectively. While with further increase in average surface roughness adversely in-fluenced the adhesion indicated by a gradual decrement in the critical load to 124 mN for the maximum investigated average surface roughness of 250 nm.
Mobility management is a key feature of mobile edge
computing. We present an edge cloud infrastructure testbed to
explore various mobility scenarios. The design objection of this testbed has been a flexible open platform based on commodity hardware that can easily be scaled with more edge devices and compute resources to perform various edge cloud experiments. As first experiments on our testbed, we have investigated the feasibility of task migration among edge devices caused by edge device overload and unpredictable user movements. We describe the migration process and present some measurements to demonstrate the feasibility.
In modern industrial production lines, the integration and interconnection of various different manufacturing components, like robots, laser cutting machines, milling machines, CNC-machines, etc. allows for a higher degree of autonomous production on the shop floor. Manufacturers of these increasingly complex machines are beginning to equip their business models with bidirectional data flows to other factories. This is creating a digital, cross-company shop floor infrastructure where the transfer of information is controlled by digital contracts. To establish a trusted ecosystem, the new technology "blockchain" and a variety of technology stacks must be combined while ensuring security. Such blockchain-based frameworks enable bidirectional trust across all contract partners. Essential data flows are defined by specific technical representation of contract agreements and executed through smart contracts.This work describes a platform for rapid cross-company business model instantiation based on blockchain for establishing trust between the enterprises. It focuses on selected security aspects of the deployment- and configuration processes applied by the industrial ecosystem. A threat analysis of the platform shows the critical security risks. Based on an industrial dynamic machine leasing use case, a risk assessment and security analysis of the key platform components is carried out.