Poly(isoindigo‐alt‐3,4‐difluorothiophene) (PIID2FT) analogues used as “polymer acceptors” in bulk‐heterojunction (BHJ) solar cells achieve >7 % efficiency when used in conjunction with the polymer ...donor PBFTAZ (model system; copolymer of benzo1,2‐b:4,5‐b′dithiophene and 5,6‐difluorobenzotriazole). Considering that most efficient polymer‐acceptor alternatives to fullerenes (e.g. PC61BM or its C71 derivative) are based on perylenediimide or naphthalenediimide motifs thus far, branched alkyl‐substituted PIID2FT polymers are particularly promising non‐fullerene candidates for “all‐polymer” BHJ solar cells.
Polymere als Sonnenanbeter: Analoga von Poly(isoindigo‐alt‐3,4‐difluorthiophen) (PIID2FT) bieten eine Alternative zu Fullerenen in ausschließlich aus Polymeren aufgebauten Bulk‐Heterokontakt(BHJ)‐Solarzellen. Die Verwendung von PIID2FT mit einem Polymerdonor mit großer Bandlücke ergibt Effizienzen von bis zu 7.3 % und für BHJ‐Solarzellen sehr gute Leerlaufspannungen von ca. 1.0 V.
The Human Health and Activity Laboratory (H2Al) is a new research facility at Luleå University of Technology implemented during 2018 as a smart home environment in an educational training apartment ...for nurses and therapists at the Luleå campus. This paper presents the design and implementation of the lab together with a discussion on potential impact. The aim is to identify and overcome economical, technical and social barriers to achieve an envisioned good and equal health and welfare within and from home environments. The lab is equipped with multiple sensor and actuator systems in the environment, worn by persons and based on digital information. The systems will allow for advanced capture, filtering, analysis and visualization of research data such as A/V, EEG, ECG, EMG, GSR, respiration and location while being able to detect falls, sleep apnea and other critical health and wellbeing issues. The resulting studies will be aimed towards supporting and equipping future home environments and care facilities, spanning from temporary care to primary care at hospitals, with technologies for activity and critical health and wellness issue detection. The work will be conducted at an International level and within a European context, based on a collaboration with other smart labs, such that experiments can be replicated at multiple sites. This paper presents some initial lessons learnt including design, setup and configuration for comparison of sensor placements and configurations as well as analytical methods.
Branched‐alkyl‐substituted poly(thieno3,4‐cpyrrole‐4,6‐dione‐alt‐3,4‐difluorothiophene) (PTPD2FT) can be used as a polymer acceptor in bulk heterojunction (BHJ) solar cells with a low‐band‐gap ...polymer donor (PCE10) commonly used with fullerenes. The “all‐polymer” BHJ devices made with PTPD2FT achieve efficiencies of up to 4.4 %. While, to date, most efficient polymer acceptors are based on perylenediimide or naphthalenediimide motifs, our study of PTPD2FT polymers shows that linear, all‐thiophene systems with adequately substituted main chains can also be conducive to efficient BHJ solar cells with polymer donors.
Polymere für mehr Leistung: Bulk‐ Heterokontakt(BHJ)‐Solarzellen mit verzweigt alkylsubstituiertem Poly(thieno3,4‐cpyrrol‐4,6‐dion‐alt‐3,4‐difluorthiophen) (PTPD2FT) als polymerer Akzeptor erzielen mit die höchsten Photospannungen (ca. 1.1 V) und Wirkungsgrade (bis 4.4 %), die bisher für BHJ‐Systeme beschrieben wurden. Als Donor fungiert ein Polymer mit schmaler Bandlücke, das normalerweise mit Fullerenakzeptoren eingesetzt wird. 2DT=2‐Decyltetradecyl, 2OD=2‐Octyldodecyl, 2HD=2‐Hexyldecyl.
DANTE is an application, which supports the annotation of ADLs captured using a pair of stereo cameras. DANTE is able to interpret the position and orientation of any object that is tagged with a ...special marker. Offline, users navigate frame-by-frame through captured scenes to annotate onset/completion of object interactions. The main utility is supporting the development of large annotated datasets, which is essential for the development and evaluation of context-aware models to interpret and monitor occupant behaviour within smart environments. DANTE only records scenes during which ‘tagged’ objects are interacted with therefore significantly reducing the amount of redundant footage recorded. The current study has extended the concepts of DANTE and has used it to support the annotation of additional sensor platforms. Results demonstrated both the capability of DANTE to support annotation of other platforms along with reducing the amount of time previously required to manually annotate such data by more than 45%.
In the development of SW applications, the workflow abstraction gives primary relevance to the way how some process can be accomplished through a sequence of connected steps. This largely conditions ...analysis, implementation architecture, and verification. In particular, testing activities are naturally oriented towards a data flow approach, which effectively exercises dependencies among steps. In several application scenarios, the workflow model cannot completely determine the sequencing of actions and it must rather leave space to variability. While easily encompassed both in the analysis and implementation stages, this comprises a major hurdle for the testing stage due to the explosion in the number of allowed execution orders and paths.
We address the problem reporting on the verification of the control software of a Computer Assisted Surgery system. In this case, the workflow abstraction captures the constraints of a medical protocol, and variability in the order of steps reflects dynamic adaptation of the course of actions to the specific characteristics of each patient. This largely increases the testing effort needed to accomplish the prescriptions of the IEC-62304 certification standard. To cope with the problem, we show how data flow analysis can be used to identify an appropriate set of constraints that can be exploited in the verification stage, so as to reduce the test suite while preserving coverage.
Comparing CNN and Human Crafted Features for Human Activity Recognition Cruciani, Federico; Vafeiadis, Anastasios; Nugent, Chris ...
2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI),
2019-Aug.
Conference Proceeding
Odprti dostop
Deep learning techniques such as Convolutional Neural Networks (CNNs) have shown good results in activity recognition. One of the advantages of using these methods resides in their ability to ...generate features automatically. This ability greatly simplifies the task of feature extraction that usually requires domain specific knowledge, especially when using big data where data driven approaches can lead to anti-patterns. Despite the advantage of this approach, very little work has been undertaken on analyzing the quality of extracted features, and more specifically on how model architecture and parameters affect the ability of those features to separate activity classes in the final feature space. This work focuses on identifying the optimal parameters for recognition of simple activities applying this approach on both signals from inertial and audio sensors. The paper provides the following contributions: (i) a comparison of automatically extracted CNN features with gold standard Human Crafted Features (HCF) is given, (ii) a comprehensive analysis on how architecture and model parameters affect separation of target classes in the feature space. Results are evaluated using publicly available datasets. In particular, we achieved a 93.38% F-Score on the UCI-HAR dataset, using 1D CNNs with 3 convolutional layers and 32 kernel size, and a 90.5% F-Score on the DCASE 2017 development dataset, simplified for three classes (indoor, outdoor and vehicle), using 2D CNNs with 2 convolutional layers and a 2x2 kernel size.
Nowadays, information and communication technologies (ICT) have become part of our everyday life, enhancing the quality of life and promoting new forms of social interaction. Despite the numerous ...benefits of ICT, older adults still present low rates of ICT adoption compared to other population segments. The lack of accessible User Interfaces has been identified as a major barrier. Traditional User Interfaces follow a design for all approach, typically ignoring the needs of older adults. Recent research in Human-Computer Interaction (HCI) proposes adaptive User Interfaces to suit the individual users abilities. Nevertheless, most of the existing approaches perform adaptation based on user profile groups and do not provide personalized adaptation in real-time. This paper introduces a conceptual framework for developing real-time adaptive User Interfaces. The system aims to target most common issues among older adults, {i.e.}cognitive decline and vision loss. The developed conceptual framework also presents novel strategic techniques to assess cognitive load and vision related issues in an unobtrusive manner for the user.
The use of smartphones for activity recognition is becoming common practice. Most approaches use a single pretrained classifier to recognize activities for all users. Research studies, however, have ...highlighted how a personalized trained classifier could provide better accuracy. Data labeling for ground truth generation, however, is a time-consuming process. The challenge is further exacerbated when opting for a personalized approach that requires user specific datasets to be labeled, making conventional supervised approaches unfeasible. In this work, we present early results on the investigation into a weakly supervised approach for online personalized activity recognition. This paper describes: (i) a heuristic to generate weak labels used for personalized training, (ii) a comparison of accuracy obtained using a weakly supervised classifier against a conventional ground truth trained classifier. Preliminary results show an overall accuracy of 87% of a fully supervised approach against a 74% with the proposed weakly supervised approach.