Article
Computer Science, Information Systems
Manan Sharma, Shivam Tiwari, Gaurav Ruhela, Suchetana Chakraborty, Dip Sankar Banerjee
Summary: The study introduces a novel clustering technique for behavioral analysis, which efficiently uncovers hidden routines and captures patterns in ubiquitous data. Additionally, three different techniques are evaluated for comparative study, showing the high efficiency of the proposed method in handling high-dimensional data.
INTERNET OF THINGS
(2022)
Article
Computer Science, Theory & Methods
Mohanad Abukmeil, Stefano Ferrari, Angelo Genovese, Vincenzo Piuri, Fabio Scotti
Summary: In recent years, the rise of big data has made it more challenging to uncover hidden structures within messy and high-dimensional datasets. Exploratory data analysis and unsupervised generative learning models play a crucial role in discovering significant features and patterns in data. Researchers can leverage these methods for data exploration and learning representations through study and practice.
ACM COMPUTING SURVEYS
(2021)
Article
Automation & Control Systems
Zhiwei Xing, Meng Wen, Jigen Peng, Jinqian Feng
Summary: The paper introduces a novel discriminative semi-supervised NMF (DSSNMF) algorithm that effectively utilizes label information from a portion of the data, with empirical experiments demonstrating its effectiveness.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Lixin Yuan, Guoqiang Yang, Qian Xu, Tong Lu
Summary: In this paper, a novel supervised feature selection method called FSDOC is proposed for accurate data classification. FSDOC includes an optimization algorithm to capture directional outliers and two correcting algorithms to capture redundant features. The effectiveness of FSDOC is demonstrated through theoretical guarantees, analysis, and extensive experiments.
PATTERN RECOGNITION
(2022)
Article
Food Science & Technology
Paramasivam Suresh Kumar, Thayumanavan Shuprajhaa, Pushpavalli Subramaniyan, Arumugam Mohanasundaram, Karur Nallappagounder Shiva, Muthu Mayilvaganan, Uma Subbaraya
Summary: The color of banana skin significantly affects purchasing and consumption choices. This study identified multiple ripening stages for traditional banana varieties and revealed the complex relationship between skin color and texture attributes. The research also showed changes in sugar to acid ratio and glycemic index throughout the ripening process.
Article
Chemistry, Applied
Kathrin Vollmer, Michael Czerny, Ana Luciea Vaesquez-Caicedo, Salima Varona Iglesias, Jan Frank, Reinhold Carle, Christof Bjoern Steingass
Summary: The study found that PCT technology can avoid the off-flavors in pineapple juice, but repeated use of PCT treatment can result in increased loss of volatile compounds.
Article
Computer Science, Artificial Intelligence
Haifeng Zhao, Qi Li, Zheng Wang, Feiping Nie
Summary: The paper introduces a new unsupervised feature selection method that optimizes the model through adaptive graph learning strategy and uncorrelated constraint to enhance discriminability.
COGNITIVE COMPUTATION
(2022)
Review
Biochemistry & Molecular Biology
Maria Mgella Zinga, Ebtesam Abdel-Shafy, Tadele Melak, Alessia Vignoli, Silvano Piazza, Luiz Fernando Zerbini, Leonardo Tenori, Stefano Cacciatore
Summary: KODAMA is a valuable tool in metabolomics research for exploratory analysis of high-dimensional data, which requires tailored statistical analysis and dimensionality reduction. KODAMA excels at revealing local structures and detecting different relationships in experimental datasets, and can correlate extracted features with accompanying metadata.
FRONTIERS IN MOLECULAR BIOSCIENCES
(2023)
Article
Multidisciplinary Sciences
Michael Schaefer, Ulrike Faltings, Bjorn Glaser
Summary: DOES is a free dataset of European scrap classes, suitable for developing industrial applications or researching classification algorithms. The dataset includes images of scrap with varying degrees of corrosion attack and uses a technique to extract overlapping rectangles from raw images, enabling training of deep learning algorithms without any disadvantage.
Article
Computer Science, Artificial Intelligence
Song Tang, Yan Zou, Zihao Song, Jianzhi Lyu, Lijuan Chen, Mao Ye, Shouming Zhong, Jianwei Zhang
Summary: This study proposes a new source data-free unsupervised domain adaptation method, which addresses the limitations of existing methods in defining geometric structures and depicting semantic relationships by conducting semantic consistency learning on a manifold.
Article
Computer Science, Artificial Intelligence
Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng
Summary: Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain. This paper proposes a novel approach called SHOT, which learns the feature extraction module for the target domain by fitting the target data features to a frozen source classification module. It also introduces a labeling transfer strategy to improve the accuracy of predictions in the target domain.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geography, Physical
Matthew Stevenson, Christophe Mues, Cristian Bravo
Summary: LiDAR technology provides detailed three-dimensional elevation maps of urban and rural landscapes. This paper proposes a convenient task-agnostic tile elevation embedding method using unsupervised Deep Learning. The potential of the embeddings is tested by predicting deprivation indices, showing improved performance compared to using standard demographic features alone. The paper also demonstrates the coherent tile segments generated by the embedding pipeline using Deep Learning and K-means clustering.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Xinyue Wang, Liping Jing, Yilin Lyu, Mingzhe Guo, Tieyong Zeng
Summary: Imbalance classification is a challenging research topic in machine learning where discriminative features are difficult to acquire. This study introduces a Smooth Soft-Balance Discriminative Analysis method to preprocess underrepresented data and mine the structure of majority classes, achieving better classification performance compared to state-of-the-art methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Wenjing Jing, Linzhang Lu, Qilong Liu
Summary: A novel semi-supervised nonnegative Tucker decomposition method is proposed, which incorporates the graph construction of the data space and the available label information of the sample data to improve data representation performance.
APPLIED INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Allison Ferranti, Taylor Hayward
Summary: This study used solid-phase microextraction combined with two-dimensional gas chromatography and group-type quantification to investigate the volatile compounds associated with the flavor of avocados. The results showed that the abundance of flavor-related compound groups, such as terpenes and alcohols, decreased during avocado ripening, while the aldehyde group remained constant. This technique provides a better understanding of the volatile compounds associated with the flavor of avocados.
JOURNAL OF SEPARATION SCIENCE
(2022)
Article
Chemistry, Applied
Jaime Zacarias-Garcia, Peter E. Lux, Reinhold Carle, Ralf M. Schweiggert, Christof B. Steingass, Lorenzo Zacarias, Maria J. Rodrigo
Summary: This study identified the PYP/XES gene family in Citrus for the first time, showing their involvement in xanthophyll esterification in citrus fruit tissues and their influence on carotenoid accumulation and fruit pigmentation.
Article
Chemistry, Applied
Sevcan Ersan, Julia C. Berning, Patricia Esquivel, Victor M. Jimenez, Reinhold Carle, Bianca May, Ralf Schweiggert, Christof B. Steingass
JOURNAL OF FOOD COMPOSITION AND ANALYSIS
(2020)
Article
Food Science & Technology
Christof B. Steingass, Jennifer Dickreuter, Sabine Kuebler, Ralf M. Schweiggert, Reinhold Carle
Summary: Fresh-cut pineapple cubes obtained from sea-freighted and air-freighted pineapples showed significant differences in chemical composition and volatile compounds. Fully ripe AF fruit is more suitable for producing fresh-cut products, displaying higher concentrations of volatiles and lower microbial counts.
EUROPEAN FOOD RESEARCH AND TECHNOLOGY
(2021)
Correction
Food Science & Technology
Christof B. Steingass, Jennifer Dickreuter, Sabine Kuebler, Ralf M. Schweiggert, Reinhold Carle
Summary: A correction to this paper has been published.
EUROPEAN FOOD RESEARCH AND TECHNOLOGY
(2021)
Article
Chemistry, Applied
Kathrin Vollmer, Michael Czerny, Ana Luciea Vaesquez-Caicedo, Salima Varona Iglesias, Jan Frank, Reinhold Carle, Christof Bjoern Steingass
Summary: The study found that PCT technology can avoid the off-flavors in pineapple juice, but repeated use of PCT treatment can result in increased loss of volatile compounds.
Article
Biochemistry & Molecular Biology
Roland Schex, Veronika M. Lieb, Christian Schaefer, Ralf Schweiggert, Christof B. Steingass
Summary: By characterizing the pigment profiles of red- and yellow-fleshed arils of defined cultivars of Taxus baccata L. and Taxus x media Rehder, it was found that there are 43 carotenoids present, with exceptional retro-carotenoids dominating the profiles. The red arils are mainly comprised of rhodoxanthin, while the yellow arils contain eschscholtzxanthin and esters. Total carotenoid concentrations ranged from 17.00 to 58.78 μg/g fresh weight, with the highest concentrations of rhodoxanthin found in the red arils of Taxus x media Rehder. Overall, Taxus arils are a promising source of unique carotenoids, especially retro-carotenoids.
Article
Biochemical Research Methods
Roland Schex, Ralf Schweiggert, Christof B. Steingass
Summary: The mass spectrometry approach used in this study aimed at characterizing retro-carotenoids, which have unique structural features and colors, and are of interest to the food industry. APCI-QTOF-HRMS analysis enabled the detection and identification of retro-carotenoids in natural sources by analyzing their specific ion species and fragmentation patterns. The results showed that the polyene backbone of retro-carotenoids greatly influenced their mass fragmentation.
RAPID COMMUNICATIONS IN MASS SPECTROMETRY
(2022)
Article
Biochemistry & Molecular Biology
Annette Wagner, Stefan Dussling, Stefano Scansani, Peter Bach, Michael Ludwig, Christof B. Steingass, Frank Will, Ralf Schweiggert
Summary: This study investigated the juice production of red-fleshed 'Weirouge' apples using the innovative spiral filter press technology in an oxygen-reduced atmosphere. The results showed that the spiral filter pressed juices had a more brilliant red color and significantly higher amounts of oxidation-sensitive constituents compared to juices produced with conventional systems. The differences in color and phenolic compounds between the juices produced with different pressing systems were maintained during storage, suggesting that the spiral filter press is a promising technology for the production of juices with better color and retention of oxidation-sensitive constituents.
Article
Food Science & Technology
Annette Wagner, Stefan Dussling, Alexander Nowak, Lisa Zimmermann, Peter Bach, Michael Ludwig, Keshav Kumar, Frank Will, Ralf Schweiggert, Christof B. Steingass
Summary: Blackcurrant juices were produced using different pressing systems, including an oxygen-excluding spiral filter press and conventional pressing systems. The study found that the total and individual anthocyanin contents were not significantly different between the two pressing methods. Storage temperature had a strong impact on anthocyanin levels, while the pressing system did not. In a model solution, factors such as sugar content, ascorbic acid content, and pH value had a significant influence on anthocyanin levels during heat treatment.
EUROPEAN FOOD RESEARCH AND TECHNOLOGY
(2023)
Article
Chemistry, Applied
Jorge Warner, Tobias Pohnl, Christof B. Steingass, Diego Bogarin, Reinhold Carle, Victor M. Jimenez
Summary: The alcohol-insoluble residue in different species of Vanilla plants was fractionated into various soluble pectins, hemicellulose, and lignocellulose. The differences in the composition of these fractions distinguished V. dressleri and V. planifolia from the other species. These findings have implications for cell wall digestion and protoplast culture in the Orchidaceae family.
CARBOHYDRATE POLYMER TECHNOLOGIES AND APPLICATIONS
(2023)
Article
Food Science & Technology
Annette Wagner, Jan Irmler, Jelena Nagypal, Peter Bach, Michael Ludwig, Frank Will, Ralf Schweiggert, Christof Bjoern Steingass
Summary: This study evaluated the volatiles, sensory profiles, consumer acceptance, and preference of juices from red-fleshed 'Weirouge' apples produced in 2019 and 2020 using three different dejuicing systems. The results showed differences in the volatiles profiles and sensory characteristics of the juices processed with an innovative spiral filter press compared to conventional systems. Consumer preference analysis indicated a clear preference for the juices obtained from the decanter system.
EUROPEAN FOOD RESEARCH AND TECHNOLOGY
(2023)
Article
Plant Sciences
Aysun Ozturk, Christof B. Steingass, Ralf Schweiggert, Reinhold Carle, Oktay Yemis, Sevcan Ersan
Summary: Phenolic compounds from two black chokeberry cultivars grown in Turkey were analyzed using HPLC-DAD-ESI-MSn. The study found that a three-step extraction with methanol/formic acid yielded complete extraction of anthocyanins, hydroxycinnamic acids, and flavonol glycosides from the berries in just 60 seconds. The analysis identified several cyanidin glycosides, hydroxycinnamic acids, and quercetin mono-and di-glycosides in both cultivars. The research also developed a rapid UHPLC-DAD method for high throughput screening of chokeberry phenolics, offering faster compound separation and lower solvent consumption compared to HPLC.
JOURNAL OF APPLIED BOTANY AND FOOD QUALITY
(2023)
Review
Food Science & Technology
Patricia Esquivel, Jessie Usaga, Ralf Schweiggert, Christof B. Steingass, Victor M. Jimenez
Summary: This review compiles the current state of knowledge on the effects of thermal and nonthermal processing and fermentation on selected compounds in potentially health-promoting tropical fruit juices. It discusses the functional properties of pineapple, pitaya, guava, and papaya fruits and the impact of processing techniques on the retention of their functional constituents.
ACS FOOD SCIENCE & TECHNOLOGY
(2022)
Article
Food Science & Technology
Patricia Esquivel, Maria Vinas, Christof B. Steingass, Maike Gruschwitz, Eric Guevara, Reinhold Carle, Ralf M. Schweiggert, Victor M. Jimenez
FRONTIERS IN SUSTAINABLE FOOD SYSTEMS
(2020)
Article
Agriculture, Multidisciplinary
Christof B. Steingass, Kathrin Vollmer, Ehab M. R. Metwali, Naif M. S. Kadasa, Omar A. Almaghrabi, Ralf Schweiggert, Reinhold Carle
INTERNATIONAL JOURNAL OF AGRICULTURE AND BIOLOGY
(2020)
