Implementing machine learning: chances and challenges

2022 ◽  
Vol 70 (1) ◽  
pp. 90-101
Author(s):  
Michael Heizmann ◽  
Alexander Braun ◽  
Markus Glitzner ◽  
Matthias Günther ◽  
Günther Hasna ◽  
...  

Abstract Finding and implementing a suitable machine learning (ML) solution to a task at hand has several facets. The technical side of ML has widely been discussed in detail, see, e. g., (Heizmann, M., A. Braun, M. Hüttel, C. Klüver, E. Marquardt, M. Overdick and M. Ulrich. 2020. Artificial Intelligence with Neural Networks in Optical Measurement and Inspection Systems. at – Automatisierungstechnik 68(6): 477–487). This contribution focusses on the industrial implementation issues of ML projects, particularly for machine vision (MV) tasks. Especially in small and medium-sized enterprises (SMEs), resources cannot be activated at will in order to use a new technology like ML. We take this into account by, on the one hand, helping to realistically evaluate the opportunities and challenges involved in implementing ML projects for a given task. On the other hand, we consider not only technical aspects, but also organizational, social and customer-related ones. It is discussed which know-how a company itself has to bring into an ML project and which tasks can also be performed by service providers. Here, it becomes clear that ML techniques can be used at different levels of detail. The question of “make or buy” is therefore also an entrepreneurial one when introducing ML into one’s own products and processes, and must be answered with a view to one’s own possibilities and structures.

2004 ◽  
Vol 12 (1) ◽  
pp. 36-48
Author(s):  
Britt-Louise Gunnarsson

This article explores the complex relationship between enterprise and discourse from a sociolinguistic viewpoint. A model of communication is presented which depicts the multilayered framework of texts within organizations. With this model as a background, results from two studies on enterprise discourse are discussed. The first study analyzed communication within banks and structural engineering companies in Sweden, Germany and Great Britain. Interviews were held with staff at different levels, and written documents were analyzed. Though of course the discourse within the studied companies had much in common, differences were found as well, which can be explained by variation in sector, the organizational culture and the national culture. The second study focused on the multilingual production of texts in a Swedish based international company. An analysis of company brochures produced in different European branches showed considerable variation in relation to content, arguments and style. Though the headquarters steered the sales companies by means of a common text base, the various brochures also revealed differences that reflected ideas from the local level. Both studies thus show how the creation of uniqueness and attractiveness on the one hand takes place within the limits set by the sector concerned and on the other is determined by the relevant national culture(s). The company is part of a wider sectoral network that frequently has well-established discourse traditions. Moreover, a company also operates within a national culture, or several cultures, forcing it to adapt to national discourse patterns as well.


2012 ◽  
Vol 215-216 ◽  
pp. 368-371
Author(s):  
Wen Ya Li ◽  
Xue Qin Ren ◽  
Yan Sun

The new technology is based on the original four-color gill box, and adding the application of the controller. On the one hand, achieve the sliver color’s order can be matched at will, and every single sliver can be changed about the color and length, and the length of changeover portion can be designed easily, so that the final product color can be achieved in a color from deep to shallow gradients, and also can be two colors that is one of them becomes shallow gradually while another color deepened gradually; on the other hand, achieve the ratio of the colored sliver is adjustable without basal sliver feeding. In the other words, on the premise of output sliver thickness to maintain constant, the cross-section’s color of the sliver is ensured to be any independent color of the four feeding sliver colors, you can also have two or more color combinations. Using this new technology to produce the gradient product has been very popular in foreign countries, but is still rare in the domestic market. So this new technology will have positive effect on textile field, it can provide more new opportunities to the textile enterprises.


2020 ◽  
Vol 68 (6) ◽  
pp. 477-487
Author(s):  
Michael Heizmann ◽  
Alexander Braun ◽  
Markus Hüttel ◽  
Christina Klüver ◽  
Erik Marquardt ◽  
...  

AbstractOptical measuring and inspection systems play an important role in automation as they allow a comprehensive and non-contact quality assessment of products and processes. In this field, too, systems are increasingly being used that apply artificial intelligence and machine learning, mostly by means of artificial neural networks. Results achieved with this approach are often very promising and require less development effort. However, the supplementation and replacement of classical image processing methods by machine learning methods is not unproblematic, especially in applications with high safety or quality requirements, since the latter have characteristics that differ considerably from classical image processing methods. In this paper, essential aspects and trends of machine learning and artificial intelligence for the application in optical measurement and inspection systems are presented and discussed.


2017 ◽  
Vol 28 (1-2) ◽  
pp. 28-35 ◽  
Author(s):  
B. A. Baranovski

Nowadays, bioecological characteristics of species are the basis for flora and vegetation studying on the different levels. Bioecological characteristics of species is required in process of flora studying on the different levels such as biotopes or phytocenoses, floras of particular areas (floras of ecologically homogeneous habitats), and floras of certain territories. Ramensky scale is the one of first detailed ecological scales on plant species ordination in relation to various environmental factors; it developed in 1938 (Ramensky, 1971). A little later (1941), Pogrebnyak’s scale of forest stands was proposed. Ellenberg’s system developed in 1950 (Ellenberg, 1979) and Tsyganov’s system (Tsyganov, 1975) are best known as the systems of ecological scales on vascular plant species; these systems represent of habitat detection by ecotopic ecomorphs of plant species (phytoindication). Basically, the system proposed by Alexander Lyutsianovich Belgard was the one of first system of plant species that identiified ectomorphs in relation to environmental factors. As early as 1950, Belgard developed the tabulated system of ecomorphs using the Latin ecomorphs abbreviation; he also used the terminology proposed in the late 19th century by Dekandol (1956) and Warming (1903), as well as terminology of other authors. The article analyzes the features of Belgard’s system of ecomorphs on vascular plants. It has certain significance and advantages over other systems of ecomorphs. The use of abbreviated Latin names of ecomorphs in tabular form enables the use shortened form of ones. In the working scheme of Belgard’s system of ecomorphs relation of species to environmental factors are represented in the abbreviated Latin alphabetic version (Belgard, 1950). Combined into table, the ecomorphic analysis of plant species within association (ecological certification of species), biotope or area site (water area) gives an explicit pattern on ecological structure of flora within surveyed community, biotope or landscape, and on environmental conditions. Development and application by Belgrard the cenomorphs as «species’ adaptation to phytocenosis as a whole» were completely new in the development of systems of ecomorphs and, in this connection, different coenomorphs were distinguished. Like any concept, the system of ecomorphs by Belgard has the possibility and necessity to be developed and added. Long-time researches and analysis of literature sources allow to propose a new coenomorph in the context of Belgard’s system of ecomorphs development: silvomargoant (species of forest margin, from the Latin words margo – edge, boundary (Dvoretsky, 1976), margo – margin, ad margins silvarum – along the deciduous forest margins). As an example of ecomorphic characterization of species according to the system of ecomorphs by Belgard (when the abbreviated Latin ecomorph names are used in tabular form and the proposed cenomorph is used), it was given the part of the table on vascular plants ecomorphs in the National Nature Park «Orelsky» (Baranovsky et al). The Belgard’s system of ecomorphs is particularly convenient and can be successfully applied to data processing in the ecological analysis of the flora on wide areas with significant species richness, and the proposed ecomorph will be another necessary element in the Belgard’s system of ecomorphs. 


2011 ◽  
Vol 21 (3-4) ◽  
pp. 135-140 ◽  
Author(s):  
Toni A. Krol ◽  
Sebastian Westhäuser ◽  
M. F. Zäh ◽  
Johannes Schilp ◽  
G. Groth

2021 ◽  
Vol 37 (01) ◽  
pp. 045-052
Author(s):  
Mario Bazanelli Junqueira Ferraz ◽  
Guilherme Constante Preis Sella

AbstractNasal dorsal preservation surgery was described more than 100 years ago, but recently has gained prominence. Our objective is to show the surgical technique, the main indications and counterindications, and the complications. It is a technique that does not cause the detachment of the upper lateral cartilage (ULC) from the nasal septum, and has the main following sequence: preparation of the septum and its resection can be at different levels (high or low, i.e., SPAR [septum pyramidal adjustment and repositioning] A or B); preparation of the pyramid; transversal osteotomy; lateral osteotomy(s); and septopyramidal adjustment. The result is a nose with a lower radix than the original, a deprojection of the nasal dorsum tending to maintain its original shape; an increase in the interalar distance (IAD) and enlargement of the nasal middle ⅓; and loss of projection of the nasal tip and roundness of the nostrils. Thus, the ideal candidate is the one who benefits from such side effects, that is: tension nose, that is, high radix with projected dorsum, projected anterior nasal septal angle (ANSA), narrow middle ⅓, narrow IAD, thin nostrils and straight perpendicular plate of the ethmoid (PPE), and, depending on the characteristics, the deviated nose. The counterindications are low radix, irregularities in the nasal dorsum, ANSA lower than rhinion, and a wide middle ⅓. And the main stigmas are: a nose with a very low radix, middle ⅓ enlarged, residual hump, and saddling of the supratip area. Other issues of this technique are: the shape of the radix; the need or not to remove PPE; wide dorsum; irregular dorsum; ANSA lower than rhinion; weak cartilages; long nasal bone; deviated PPE; and obsessive patient. We conclude that this is a great technique for noses with characteristics suitable to it; care must be taken with the stigmas it can cause.


2020 ◽  
pp. 1-17
Author(s):  
Francisco Javier Balea-Fernandez ◽  
Beatriz Martinez-Vega ◽  
Samuel Ortega ◽  
Himar Fabelo ◽  
Raquel Leon ◽  
...  

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.


Author(s):  
Davorin Cimermančič ◽  
Janez Kušar ◽  
Tomaž Berlec

AbstractChanging a traditional company into a lean one is a very complex and time-consuming process that needs to be addressed in an appropriate way, otherwise the project of introduction of leanness into a company may fail on the one hand and even have a negative impact on business operations of the company on the other. When introducing a change, a step-by-step procedure leading to a progress may be of great help. The paper outlines a general procedure of leanness, an important part of which is a lean agent. A portfolio analysis is also used as a measure of leanness or as an indicator of the desired direction. The applied working methods were mainly active workshops and interviews with employees. The procedure has been tested on an example of a Slovene company; first, the existing situation is outlined, then the leanness steps taken according to the procedure and the final result after the first transition of the procedure.


2021 ◽  
Vol 22 (S3) ◽  
Author(s):  
Junyi Li ◽  
Huinian Li ◽  
Xiao Ye ◽  
Li Zhang ◽  
Qingzhe Xu ◽  
...  

Abstract Background The prediction of long non-coding RNA (lncRNA) has attracted great attention from researchers, as more and more evidence indicate that various complex human diseases are closely related to lncRNAs. In the era of bio-med big data, in addition to the prediction of lncRNAs by biological experimental methods, many computational methods based on machine learning have been proposed to make better use of the sequence resources of lncRNAs. Results We developed the lncRNA prediction method by integrating information-entropy-based features and machine learning algorithms. We calculate generalized topological entropy and generate 6 novel features for lncRNA sequences. By employing these 6 features and other features such as open reading frame, we apply supporting vector machine, XGBoost and random forest algorithms to distinguish human lncRNAs. We compare our method with the one which has more K-mer features and results show that our method has higher area under the curve up to 99.7905%. Conclusions We develop an accurate and efficient method which has novel information entropy features to analyze and classify lncRNAs. Our method is also extendable for research on the other functional elements in DNA sequences.


2020 ◽  
Vol 11 (1) ◽  
pp. 217-227 ◽  
Author(s):  
Roger Andre Søraa ◽  
Eduard Fosch-Villaronga

AbstractIn this article, we investigate the relation between gender and exoskeleton development through the lens of intersectionality theory. Exoskeleton users come in a wide variety of shapes, sizes, and genders. However, it is often the case that wearable robot engineers do not develop such devices primarily on the premise that the product should fit as many end users as possible. Instead, designers tend to use the one-size-fits-all approach – a design choice that seems legitimate from the return of an investment viewpoint but that may not do as much justice to end users. Intended users of exoskeletons have a series of user criteria, including height, weight, and health condition, in the case of rehabilitation. By having rigid inclusion criteria for whom the intended user of the technology can be, the exclusion criteria will grow in parallel. The implications and deep-rootedness of gender and diversity considerations in practices and structural systems have been largely disregarded. Mechanical and robot technology were historically seen as part of a distinct male sphere, and the criteria used today to develop new technology may reflect the biases that existed in another time that should no longer be valid. To make this technology available for all, we suggest some tools to designers and manufacturers to help them think beyond their target market and be more inclusive.


Sign in / Sign up

Export Citation Format

Share Document