| 1. |
- Alsouda, Yasser, et al.
(författare)
-
IoT-based Urban Noise Identification Using Machine Learning : Performance of SVM, KNN, Bagging, and Random Forest
- 2019
-
Ingår i: Proceedings of the International Conference on Omni-Layer Intelligent Systems (COINS '19). - New York : ACM Publications. - 9781450366403 ; , s. 62-67
-
Konferensbidrag (refereegranskat)abstract
- Noise is any undesired environmental sound. A sound at the same dB level may be perceived as annoying noise or as pleasant music. Therefore, it is necessary to go beyond the state-of-the-art approaches that measure only the dB level and also identify the type of noise. In this paper, we present a machine learning based method for urban noise identification using an inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine, k-nearest neighbors, bootstrap aggregation, and random forest) for noise classification. We evaluate our approach experimentally with a data-set of about 3000 sound samples grouped in eight sound classes (such as car horn, jackhammer, or street music). We explore the parameter space of the four algorithms to estimate the optimal parameter values for classification of sound samples in the data-set under study. We achieve a noise classification accuracy in the range 88% - 94%.
|
|
| 2. |
- Augustsson, Katarina
(författare)
-
Dietary heterocyclic amines and human cancer risk
- 1998
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Heterocyclic amines formed in meat during cooking are multi-site animal carcinogens and form DNA adducts in human tissues, but their relevance to human carcinogenesis has yet to be determined. The aim of this thesis was to investigate, by epidemiological methods, whether heterocyclic amines are responsible for part of the diet-related cancer burden in humans. Frequently eaten fried meat dishes in an elderly population in Stockholm, Sweden, were identified, and we found meat to be eaten, on the average, 1.4 times per day, and frying to be the most popular cooking method. Altogether, 22 frequently consumed dishes were fried/baked in a standardized manner under controlled conditions at 150, 175, 200, and 225°C, and the content of heterocyclic amines, including IQ, MelQ, MelQx, DiMelQx, and PhlP, was determined. The formation of heterocyclic amines was found to be temperature-related and the highest amounts were detected in minute steak, pork filet, and bacon fried at 225°C. A method to assess the individual intake of heterocyclic amines in an epidemiological context was developed by linking values for heterocyclic amines obtained from chemical analyses to food consumption data collected by means of a semi-quantitative food frequency questionnaire comprising 188 food items. Variables used to assess the intake of heterocyclic amines were intake frequency, type of dish, cooking method, portion size, degree of surface browning of the meat, and intake of gravy. When the number or dishes in the food frequency module was reduced from 39 to 15 dishes, based on the most informative dishes according to the total intake or the between-person variance, only a limited amount of misclassification was introduced. The total daily intake of IQ, MelQ, MelQx, DiMelQx, and PhlP among controls ranged from zero to 1816 ng, with a median of 77 ng. Relative risks of cancer were estimated in a population-based case-control study in Stockholm, and information was retrieved from 553 controls, 352 cases of colon cancer, 249 rectal cancer cases, 273 bladder cancer cases, and 138 cases of kidney cancer. The study disentangles the effect of meat from the effect of heterocyclic amines, and we found that an intake of heterocyclic amines within the usual dietary range in the study base is unlikely to increase the incidence of cancer of the colon, rectum, bladder, or kidney. However, for intakes above 1900 ng/day, our data are consistent with the possibility of human carcinogenicity, but the precision is extremely low.
|
|
| 3. |
- Augustsson, Kristoffer, et al.
(författare)
-
Leveransledtidsreduktionens påverkan på räntabilitet
- 2017
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Det sägs ofta att ’tid är pengar’, men hur mycket är tid egentligen värt? I denna studie undersöktes leveransledtidens påverkan på tillverkande företags räntabilitet. Studie utgår från en konceptuell modell utvecklad av Wikner (2015), där strategiska ledtider definieras samt sätts i förbindelse med de tre absoluta mätetalen intäkt, kostnad och investering. I studien utvecklas en proposition som beskriver hur en leveransledtidsreduktion påverkar ett tillverkande företags räntabiliteten? Propositionen diskuteras sedan med respondenter från ett fallföretag innan den revideras. Den reviderade propositionen ligger sedermera till grund för beräkningen av leveransledtidsreduktionens påverkan på tillverkande företags räntabilitet. Studien resulterar i ett beslutsstöd som kvantitativt påvisar en leveransledtidsreduktions påverkan på tillverkande företags räntabilitet.
|
|
| 4. |
- Bos, Marlies
(författare)
-
Greenhouse gas emissions when freezing and thawing sewage sludge and compost
- 2013
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Freezing/thawing cycles can significantly increase greenhouse gas emissions due to physical and biological mechanisms. Therefore this research was done to see if this is also the case for compost and sewage sludge. The main focus was on nitrous oxide. The set-up of the experiments was based on the outcomes of several trial experiments. 4 substrates were tested: non-nitrified mesophilic sewage sludge, nitrified mesophilic sewage sludge, 2 weeks old compost and 1 month old compost. The two composts had a clear difference in ammonium content. The substrates were first frozen at a temperature of -27 °C, and then thawed at a temperature of 5 °C. Controls were kept at a temperature of 5 °C during the whole experiment. All substrates were tested in triplicates. Emissions of carbon dioxide, methane and nitrous oxide were measured. No clear effect of freezing/thawing was observed on the greenhouse gas emissions from non-nitrified sewage sludge. From the nitrified sewage sludge the emissions of both carbon dioxide and nitrous oxide increased during thawing. The cumulative emission of carbon dioxide was 17500 µg g-1 initial C from the frozen and thawed sewage sludge, and 11170 µg g-1 initial C from the controls. The cumulative emission of nitrous oxide in the sewage sludge that had been frozen and thawed was about 3500 µg g-1 initial N, for the controls this was 3000 µg g-1 initial N. Both the increase carbon dioxide and nitrous oxide emissions were probably due to increased substrate availability, caused by the die-off of micro-organisms during freezing. The nitrous oxide probably came from denitrification. In both of the composts no effect of the freezing and thawing was observed on the emissions of carbon dioxide and methane, but it had a clear effect on the emission of nitrous oxide: in the 1 month old compost a clear emission peak was observed during the first days of thawing. For the one month compost this was probably due to a physical mechanism of trapped nitrous oxide inside the compost which could escape during the thawing period. An unexpected result was the large difference between the two composts considering the amounts of nitrous oxide emissions, which were expected to be approximately the same due to equal nitrate amounts. However, the cumulative nitrous oxide emission from the frozen and thawed 2 weeks compost was 3,00 µg g-1 initial N at the end, while from the 1 month compost this was 1220 µg g-1 initial N. Since the ammonium in the 1 month compost had decreased with 32,5%, and only 17,5% for 2 weeks compost, the large amount of nitrous oxide probably came from the conversion of ammonium. However, it is still not clear whether this comes from nitrification of the ammonium, or from denitrification of the nitrate formed during the experiment. The conclusion was that freezing/thawing increases emissions of carbon dioxide and nitrous oxide from nitrified sewage sludge during thawing, and the emissions of nitrous oxide from compost during thawing. Recommendations for further research are to find out which processes, nitrification or denitrification, are responsible for the nitrous oxide production. Also research to compost with different nitrate amounts is recommended.
|
|
| 5. |
- Cabrall, Christopher D., et al.
(författare)
-
Validity and reliability of naturalistic driving scene categorization judgments from crowdsourcing
- 2016
-
Konferensbidrag (refereegranskat)abstract
- A common challenge with processing naturalistic driving data for many different possible driving research interests or applications is that humans may need to categorize great volumes of recorded visual information until automated algorithms might be trained to do so alone.This study, by means of the online platform CrowdFlower, investigated the potential of crowdsourcing to provide content identification categorizations of driving scene features (e.g., presence of another vehicle, straight road segments, etc.) at greater scale than a single person or a small team of researchers would be capable of. The validity and reliability of CrowdFlower results were examined, both with and without employing a set of randomly embedded controlled questions (Gold Test Questions) intermixed with experimental questions (Work Mode). In total, 200 workers from 46 countries participated in this study, and the collection of data lasted one and a half days.By employing Gold Test Questions, we found significantly more accurate and consistent responses from external workers at both a smaller and larger scale of video segment categorizations for the identification of common driving scene elements (e.g., position and behavior of other vehicles, road and signage characteristics, etc.). In terms of validity and at the small scale, an average accuracy of 91% on paired items was found with the controlled questions compared to 78% without. A difference in bias was found where without Gold Test Questions external workers returned more false positives than false negatives whereas the opposite was found true of the condition with Gold Test Questions. At the large scale (making use of the controlled questions), a random subset of categorizations returned similar levels of accuracy (95%) and a similar pattern of error bias. In terms of reliability and at the small scale, where segments were rated in triplicate redundancy, the percentage of unanimous agreement was found significantly higher when using controlled questions (90%) than without them (65%). Across the small scale of internally validated answers, more than two-thirds of any correct categorization were unanimously returned and 86% or more of any correct categorization was returned by a majority vote. Where it would be infeasible to validate every response for accuracy, similar voting reliability results were found to exist across the responses of the large scale.Overall results support compelling evidence for CrowdFlower as being able to yield valid and reliable crowdsourced categorizations of naturalistic driving scene contents in a short period of time and thus a potentially powerful and as-of-yet under-utilized resource in the toolbox of driving research and driving automation development.
|
|
| 6. |
|
|
| 7. |
-
Coordination, organizations, institutions, norms, and ethics for governance of multi-agent systems XIV : international workshop, COINE 2021, London, UK, May 3, 2021 : revised selected papers
- 2022
-
Samlingsverk (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- This book constitutes revised selected papers from the thoroughly refereed proceedings of the International Workshop on Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XIV, COINE 2021, held in London, UK, May 3, 2021.The 9 full papers included in this book were carefully reviewed and selected from 12 submissions. They were organized in topical sections as follows: Invited talk; conceptual frameworks architectures for collaboration and coordination; and modelling and understanding social behaviour using COINE technologies.
|
|
| 8. |
- Coorevits, Pascal, et al.
(författare)
-
Electronic health records : new opportunities for clinical research
- 2013
-
Ingår i: Journal of Internal Medicine. - : Wiley-Blackwell. - 0954-6820 .- 1365-2796. ; 274:6, s. 547-60
-
Tidskriftsartikel (refereegranskat)abstract
- Clinical research is on the threshold of a new era in which electronic health records (EHRs) are gaining an important novel supporting role. Whilst EHRs used for routine clinical care have some limitations at present, as discussed in this review, new improved systems and emerging research infrastructures are being developed to ensure that EHRs can be used for secondary purposes such as clinical research, including the design and execution of clinical trials for new medicines. EHR systems should be able to exchange information through the use of recently published international standards for their interoperability and clinically validated information structures (such as archetypes and international health terminologies), to ensure consistent and more complete recording and sharing of data for various patient groups. Such systems will counteract the obstacles of differing clinical languages and styles of documentation as well as the recognized incompleteness of routine records. Here, we discuss some of the legal and ethical concerns of clinical research data reuse and technical security measures that can enable such research while protecting privacy. In the emerging research landscape, cooperation infrastructures are being built where research projects can utilize the availability of patient data from federated EHR systems from many different sites, as well as in international multilingual settings. Amongst several initiatives described, the EHR4CR project offers a promising method for clinical research. One of the first achievements of this project was the development of a protocol feasibility prototype which is used for finding patients eligible for clinical trials from multiple sources.
|
|
| 9. |
- Ehteram, Mohammad, et al.
(författare)
-
Prediction of future groundwater levels under representative concentration pathway scenarios using an inclusive multiple model coupled with artificial neural networks
- 2022
-
Ingår i: Journal of Water and Climate. - : IWA Publishing. - 2040-2244 .- 2408-9354. ; 13:10, s. 3620-3643
-
Tidskriftsartikel (refereegranskat)abstract
- Groundwater (GW) plays a key role in water supply in basins. As global warming and climate change affect groundwater level (GWL), it is important to predict it for planning and managing water resources. This study investigates the GWL of the Yazd-Ardakan Plain basin in Iran for the base period of 1979-2005 and predicts for periods of 2020-2059 and 2060-2099. Lagged temperature and rainfall are used as inputs to hybrid and standalone artificial neural network (ANN) models. In this study, the rat swarm algorithm (RSA), particle swarm optimisation (PSO), salp swarm algorithm (SSA), and genetic algorithm (GA) are used to adjust ANN models. The outcomes of these models are then entered into an inclusive multiple model (IMM) as an ensemble model. In this study, the output of climate models is also inserted into the IMM model to improve the estimation accuracy of temperature, rainfall, and GWL. The monthly average temperature for the base period is 12.9 degrees C, while average temperatures for 2020-2059 under RCP 4.5 and RCP 8.5 scenarios are 14.5 and 15.1 degrees C, and for 2060-2099 they are 16.41 and 18.5 degrees C under the same scenarios, respectively. In future periods, rainfall is low in comparison with the base period. Lagged rainfall and temperature of the base period are inserted into ANN-RSA, ANN-SSA, ANN-PSO, ANN-GA, and ANN models to predict GWL for the base period. Outputs of IMM, ANN, and the five hybrid models (ANN-RSA, ANN-SSA, ANN-PSO, and ANN-GA) indicate that root mean square errors (RMSE) are 2.12, 3.2, 4.58, 6.12, 6.98, and 7.89 m, respectively, in the testing level. It is found that GWL depletion in 2020-2059 under RCP 4.5 and RCP 8.5 scenarios are 0.60-0.88 m and 0.80-1.16 m, and in 2060-2099 under the same scenarios they are 1.49-1.97 m and 1.75-1.98 m, respectively. The results highlight the need to prevent overexploitation of GW in the Ardakan-Yazd Plain to avoid water shortages in the future.
|
|
| 10. |
|
|
