<div> The Unmanned Aerial Vehicles (UAV) technology has evolved exponentially in recent years. Smaller and less expensive devices allow a world of new applications in different areas, but as this progress can be beneficial, the use of UAVs with malicious intentions also poses a threat. UAVs can carry weapons or explosives and access restricted zones passing undetected, representing a real threat for civilians and institutions. Acoustic detection in combination with machine learning models emerges as a viable solution since, despite its limitations related with environmental noise, it has provided promising results on classifying UAV sounds, it is adaptable to multiple environments, and especially, it can be a cost-effective solution, something much needed in the counter UAV market with high projections for the coming years. The problem addressed by this project is the need for a real-world adaptable solution which can show that an array of acoustic sensors can be implemented for the detection and localization of UAVs with minimal cost and competitive performance.<br><br></div><div> In this research, a low-cost acoustic detection system that can detect, in real time, about the presence and direction of arrival of a UAV approaching a target was engineered and validated. The model developed includes an array of acoustic sensors remotely connected to a central server, which uses the sound signals to estimate the direction of arrival of the UAV. This model works with a single microphone per node which calculates the position based on the acoustic intensity change produced by the UAV, reducing the implementation costs and being able to work asynchronously. The development of the project included collecting data from UAVs flying both indoors and outdoors, and a performance analysis under realistic conditions. <br><br></div><div> The results demonstrated that the solution provides real time UAV detection and localization information to protect a target from an attacking UAV, and that it can be applied in real world scenarios. </div><div><br></div>

The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. The models were compared and analyzed in regards to the univariate forecast accuracy on 20 randomly drawn time series from two different time frequencies from the M4 competition dataset. Forecasting was made dependent on one time lag (t-1) and forecasted three and six steps ahead respectively. The artificial neural network models outperformed the baseline Autoregressive model, showing notably lower mean average percentage error overall. The Multilayered perceptron models performed better than the Long short-term memory model overall, whereas the Long short-term memory model showed improvement on longer prediction time dimensions. As the training were done univariately  on a limited set of time steps, it is believed that the one layered-approach gave a good enough approximation on the data, whereas the added layer couldn’t fully utilize its strengths of processing power. Likewise, the Long short-term memory model couldn’t fully demonstrate the advantagements of recurrent learning. Using the same dataset, further studies could be made with another approach to data processing. Implementing an unsupervised approach of clustering the data before analysis, the same models could be tested with multivariate analysis on models trained on multiple time series simultaneously.

As the complexity of deep learning model increases, the transparency of the systems does the opposite. It may be hard to understand the predictions a deep learning model makes, but even harder to understand why these predictions are made. Using eXplainable AI (XAI), we can gain greater knowledge of how the model operates and how the input in which the model receives can change its predictions. In this thesis, we apply Integrated Gradients (IG), an XAI method primarily used on image data and on datasets containing tabular and time-series data. We also evaluate how the results of IG differ from various types of models and how the change of baseline can change the outcome. In these results, we observe that IG can be applied to both sequenced and nonsequenced data, with varying results. We can see that the gradient baseline does not affect the results of IG on models such as RNN, LSTM, and GRU, where the data contains time series, as much as it does for models like MLP with nonsequenced data. To confirm this, we also applied IG to SVM models, which gave the results that the choice of gradient baseline has a significant impact on the results of IG.

No description available.

Transportations role in society is increasingly important and today it has a prominent role in business, citizens lives as well as in the world economy. The increasing globalization and urbanization puts significant pressure on the existing transport system, with increasing demand for high-speed travel. However, this comes with implications on the environment, and the environmental concerns constitutes one of the biggest pressures in transport. And as the contemporary modes are bound by their technologies, enabling marginal rather than radical improvements, a possible window of opportunity for new radical technologies to enter the market can emerge. One new technology emerging within transportation today is called hyperloop, a technology that could prove to meet demand for faster, cheaper, safer and more environmentally efficient transportation. However, the technology is still in an early stage of development and hence surrounded by major uncertainties. Further, the nature of the technology necessitates overcoming several obstacles before it can reach commercial practice. And this together with a limited knowledge of the concept in Sweden makes it difficult to predict if hyperloop can become a viable transport alternative on the Swedish market. Which condensed lays the foundation to the purpose of this paper: "To give an overarching understanding of the Swedish transport market dynamics, together with a comprehensive evaluation of the hyperloop concept. And hence contribute to more inclusive knowledge and understanding of hyperloop’s viability in the Swedish context." Since the phenomenon has not been comprehensively studied previously, the elected research design is that of an exploratory case study, with an inductive, qualitative approach. To address the purpose, a literary review of the theoretical field was conducted. Looking in to previous research on disruptive innovation, diffusion of innovations, technical transitions, transformational pressure as well as window of opportunity. The empirical material gathered during the research process was derived from two main channels. Firstly, an extensive review of scientific articles about the hyperloop technology was conducted, providing insights on the technology and its surroundings. This was complemented by qualitative interviews to obtain material on the dynamics of the Swedish transport market as well as for understanding hyperloop in the Swedish context. The empirical study was further accompanied by a review of news articles and websites to map the most recent progress in the hyperloop development. By analyzing the empirical material through three frameworks; Characteristics of Diffusion, the Multi-Level Perspective (MLP) and Technology Readiness Level (TRL), interesting findings and conclusions were drawn. These together points towards that hyperloop, if the technology reaches its predicted performance, will have significant relative advantages and observable effects in the relation to the contemporary modes of transportation. Further, a noticeable window of opportunity, sprung from capacity shortages and pressure towards environmental sustainability, seems to exist on the Swedish market. A window which could be capitalized upon and justify hyperloop in the Swedish context. The current state of the technology does however come with implications as it so far is insufficient to decrease uncertainty amongst the potential adopters. Factors that likely will prolong the adoption of the technology in Sweden relates to the relative complexity of the system, its limited compatibility with existing practices and the low maturity of the technology. Hence, the hyperloop companies must prove the concept feasible and increase the maturity to gain sufficient acceptance and recognition. This paper contributes to the academic community by assessing the compatibility of hyperloop on the Swedish market, as well as if hyperloop could become a viable alternative transport solution in Sweden. It provides insight to specific perspectives of the Swedish market, its requirements and the demand for alternative transport solutions. Hence, this paper is considered to make both an analytical contribution in terms of evaluating the viability of disruptive technologies. And an empirical contribution by shedding light on new important insights for the potential diffusion of hyperloop. Insights that are significant for hyperloop actors as well as for dominant actors on the Swedish transport market. / Transporters roll i samhället blir allt viktigare och de har idag en framträdande roll inom näringsliv, medborgares liv samt världsekonomin. Den ökande globaliseringen och urbaniseringen sätter dock ett betydande tryck på det existerande transportsystemet, med ökande efterfrågan för höghastighetsalternativ. Detta medför implikationer för miljön, och oron kring transporters miljöpåverkan är ett av de största bekymren för transportsektorn. Eftersom de existerande transportalternativen är bundna av sin teknik, vilket begränsar dem till inkrementella snarare än radikala förbättringar, kan en möjlighet för nya transportsätt att komma in på marknaden öppna sig. En kommande ny teknik som utvecklas inom transport idag kallas hyperloop, en teknik som kan visa sig möta efterfrågan för snabbare, billigare, säkrare och mer miljösmarta transporter. Tekniken är dock i ett tidigt utvecklingsskede och är därav omgärdad av stora osäkerheter. Vidare kräver teknikens natur att flertalet hinder kommer att behöva överkommas innan tekniken kan nå kommersiellt bruk. Detta tillsammans med den begränsade kunskap som finns kring konceptet i Sverige gör det svårt att förutspå om hyperloop kan bli ett möjligt transportalternativ på den svenska marknaden. Kondenserat ligger detta till grund för syftet med den här uppsatsen: "Att ge en övergripande förståelse av dynamiken på den svenska transportmarknaden, tillsammans med en djupgående utvärdering av hyperloop konceptet. Och därav bidra till en mer inkluderande kunskap och förståelse kring hyperloops möjligheter i den svenska kontexten." Eftersom detta fenomen inte tidigare har studerats i större utsträckning valdes en forskningsdesign i form av en undersökande fallstudie med ett induktivt, kvalitativt tillvägagångssätt. För att adressera syftet gjordes en litterär översyn av det teoretiska fältet. Med inblickar i tidigare forskning kring disruptiv teknik, diffusion av innovation, tekniska övergångar, transformationstryck samt möjlighetsfönster. Det empiriska materialet till studien samlades in genom två kanaler i huvudsak. Först, genom en djupdykning i tidigare forskning och vetenskapliga artiklar relaterade till hyperlooptekniken, för att generera insikter kring tekniken och dess omgivning. Detta kompletteras med kvalitativa intervjuer för att erhålla material om dynamiken på den svenska transportmarknaden samt för att ge en förståelse av hyperloop i den svenska kontexten. Den empiriska studien kompletterades ytterligare med en översyn av nyhetsartiklar och webbplatser för att kartlägga de senaste framstegen i hyperlooputvecklingen. Genom att analysera det empiriska materialet med hjälp av tre ramverk; Egenskaper för Spridning av Innovation, Perspektiv i Multipla Nivåer (MLP) och Teknisk Mogenhetsnivå (TRL), kunde flertalet intressanta upptäckter och slutsatser dras. Vilka tillsammans pekar mot att hyperloop, om tekniken lyckas uppnå den predikterade prestandan, kommer att ha betydande relativa fördelar och synliga effekter i förhållande till dagens transportsätt. Vidare kan ett märkbart möjlighetsfönster, sprunget ur kapacitetsbrist och tryck mot miljömässig hållbarhet, identifieras på den svenska marknaden. Detta fönster skulle kunna kapitaliseras på och motivera hyperloop i den svenska kontexten. Teknologins nuvarande tillstånd har emellertid konsekvenser, eftersom den hittills inte är tillräcklig för att minska osäkerheten hos potentiella adopterare. Faktorer som sannolikt kommer att förlänga processen att adoptera tekniken i Sverige härstammar från systemets relativa komplexitet, dess begränsade kompatibilitet med befintliga metoder samt teknikens låga mogenhet. Därav är det essentiellt för hyperloopbolagen att bevisa konceptet möjligt och öka mogenheten för att få tillräcklig acceptans och erkännande. Detta arbete bidrar till det akademiska samhället genom att bedöma kompatibiliteten mellan hyperloop och den svenska marknaden, samt om hyperloop kan bli ett genomförbart transportalternativ i Sverige. Arbetet bidrar med insikter i specifika perspektiv på den svenska marknaden, dess krav samt efterfrågan för alternativa transportlösningar. Därav kan denna uppsats anses utgöra både ett analytiskt bidrag genom dess utvärdering av genomförbarheten av disruptiv teknik. Samt ett empiriskt bidrag genom att belysa viktiga insikter för den potentiella spridningen av hyperloop. Insikter som är viktiga för såväl hyperloopaktörer som de dominanta aktörerna på den svenska transportmarknaden.

In this dissertation, generalized additive neural networks (GANNs) and multilayer perceptrons (MLPs) are studied and compared as prediction techniques. MLPs are the most widely used type of artificial neural network (ANN), but are considered black boxes with regard to interpretability. There is currently no simple a priori method to determine the number of hidden neurons in each of the hidden layers of ANNs. Guidelines exist that are either heuristic or based on simulations that are derived from limited experiments. A modified version of the neural network construction with cross–validation samples (N2C2S) algorithm is therefore implemented and utilized to construct good MLP models. This algorithm enables the comparison with GANN models. GANNs are a relatively new type of ANN, based on the generalized additive model. The architecture of a GANN is less complex compared to MLPs and results can be interpreted with a graphical method, called the partial residual plot. A GANN consists of an input layer where each of the input nodes has its own MLP with one hidden layer. Originally, GANNs were constructed by interpreting partial residual plots. This method is time consuming and subjective, which may lead to the creation of suboptimal models. Consequently, an automated construction algorithm for GANNs was created and implemented in the SAS R statistical language. This system was called AutoGANN and is used to create good GANN models. A number of experiments are conducted on five publicly available data sets to gain insight into the similarities and differences between GANN and MLP models. The data sets include regression and classification tasks. In–sample model selection with the SBC model selection criterion and out–of–sample model selection with the average validation error as model selection criterion are performed. The models created are compared in terms of predictive accuracy, model complexity, comprehensibility, ease of construction and utility. The results show that the choice of model is highly dependent on the problem, as no single model always outperforms the other in terms of predictive accuracy. GANNs may be suggested for problems where interpretability of the results is important. The time taken to construct good MLP models by the modified N2C2S algorithm may be shorter than the time to build good GANN models by the automated construction algorithm / Thesis (M.Sc. (Computer Science))--North-West University, Potchefstroom Campus, 2011.

In this dissertation, generalized additive neural networks (GANNs) and multilayer perceptrons (MLPs) are studied and compared as prediction techniques. MLPs are the most widely used type of artificial neural network (ANN), but are considered black boxes with regard to interpretability. There is currently no simple a priori method to determine the number of hidden neurons in each of the hidden layers of ANNs. Guidelines exist that are either heuristic or based on simulations that are derived from limited experiments. A modified version of the neural network construction with cross–validation samples (N2C2S) algorithm is therefore implemented and utilized to construct good MLP models. This algorithm enables the comparison with GANN models. GANNs are a relatively new type of ANN, based on the generalized additive model. The architecture of a GANN is less complex compared to MLPs and results can be interpreted with a graphical method, called the partial residual plot. A GANN consists of an input layer where each of the input nodes has its own MLP with one hidden layer. Originally, GANNs were constructed by interpreting partial residual plots. This method is time consuming and subjective, which may lead to the creation of suboptimal models. Consequently, an automated construction algorithm for GANNs was created and implemented in the SAS R statistical language. This system was called AutoGANN and is used to create good GANN models. A number of experiments are conducted on five publicly available data sets to gain insight into the similarities and differences between GANN and MLP models. The data sets include regression and classification tasks. In–sample model selection with the SBC model selection criterion and out–of–sample model selection with the average validation error as model selection criterion are performed. The models created are compared in terms of predictive accuracy, model complexity, comprehensibility, ease of construction and utility. The results show that the choice of model is highly dependent on the problem, as no single model always outperforms the other in terms of predictive accuracy. GANNs may be suggested for problems where interpretability of the results is important. The time taken to construct good MLP models by the modified N2C2S algorithm may be shorter than the time to build good GANN models by the automated construction algorithm / Thesis (M.Sc. (Computer Science))--North-West University, Potchefstroom Campus, 2011.

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-17T14:06:04Z No. of bitstreams: 1 JOÃO VIVLIAN DE MORAES LIMA MARINUS - DISSERTAÇÃO PPGCC 2010..pdf: 2343869 bytes, checksum: 46e0a7984b1b956fbea2bfcba9e1f631 (MD5) / Made available in DSpace on 2018-08-17T14:06:04Z (GMT). No. of bitstreams: 1 JOÃO VIVLIAN DE MORAES LIMA MARINUS - DISSERTAÇÃO PPGCC 2010..pdf: 2343869 bytes, checksum: 46e0a7984b1b956fbea2bfcba9e1f631 (MD5) Previous issue date: 2010-11-29 / Nos últimos anos, várias pesquisas na área de processamento digital de voz estão sendo feitas, no sentido de criar técnicas que auxiliem o diagnóstico preciso por um especialista de patologias do trato vocal de maneira não invasiva, fazendo com que o paciente se sinta confortável na hora do exame. Este trabalho trata da investigação de técnicas para a classificação de vozes afetadas por patologias da laringe, em especial edema de Reinke, visando a construção de um sistema de apoio ao especialista. O sistema de auxílio ao diagnóstico de patologias da laringe, proposto nesta dissertação, é constituido de 3 etapas principais: pré-processamento do sinal de voz, extração de características e classificação. A etapa de pré-processamento consiste na aquisição do sinal de voz, na aplicação de um filtro de pré ênfase para a minimização dos efeitos da radiação dos lábios e da variação da área da glote, seguido da segmentação e janelamento do sinal. Também foi investigada a não utilização da pré-ênfase nessa etapa. Na fase de extração de características, são utilizados coeficientes obtidos a partir da análise por predição linear (coeficientes LPC), coeficientes cepstrais, coeficientes delta-cepstrais e um vetor de características combinando coeficientes LPC e coeficientes cepstrais. A etapa de classificação é dividida em duas partes: classificação entre voz normal e voz afetada por patologia, sem especificar qual patologia, e caso o sinal seja classificado como voz afetada por patologia, tem-se uma segunda parte, a qual é realizada a classificação entre voz afetada por edema de Reinke e voz afetada por outra patologia. Para as duas partes, foram testados 3 diferentes classificadores: Redes Neurais Multilayer Perceptron - MLP, Modelos de Misturas de Gaussianas e Quantização Vetorial. Para diferenciar entre voz normal e voz afetada por patologia, os melhores resultados foram obtidos utilizando Redes Neurais. Para diferenciar entre voz afetada por edema e voz afetada por outra patologia, os melhores resultados foram obtidos utilizando Quantização Vetorial. Em ambos os casos, os melhores resultados foram obtidos ao se utilizar coeficientes cepstrais e sem utilização da pré-ênfase. / In recent years, several studies in digital voice processing are being made in order to create techniques to support a noninvasive accurate diagnosis of vocal tract diseases by aspecialist, making the patient feel comfortable during examination. This work deals with the investigation of techniques for classification of voices affected by laryngeal pathologies, especially Reinke’s edema, aiming to build a support system to the specialist. The system for the diagnosis of laryngeal pathologies, proposed here, consists of three main steps: preprocessing the speech signal, feature extraction and classification. Preprocessing corresponds the acquisition of voice signal, the application of a pre-emphasis filter for minimizing the radiation effects from the lips and from variation in glottal area, and the signal segmentation and windowing. The non-use of pre-emphasis was also investigated at this point. In the feature extraction step, we use coefficients obtained from the linear prediction analysis (LPC coefficients), cepstral coefficients, delta-cepstral coefficients, and afeature vectorc ombining LPC and cepstral coefficients. The classification is divided into two parts: classification of normal voice versus voice affected by pathology, without specifying which pathology, and if the signal is classified as voice affected by pathology, second part happens, which is performed by the classification between voice affected by Reinke’s edema and voice affected by other pathology. For both parties, 3 different classifiers were tested: Neural Networks Multilayer Perceptron - MLP, Gaussian Mixture Models and Vector Quantization. To differentiate between normal voice and voice affected by pathology, the best results were obtained using Neural Networks. To differentiate between voice affected by edema and voice affected by pathology, the best results were obtained using vector quantization. In both cases, the best results were obtained when usingcepstral coefficients and withoutuse of pre-emphasis.

El desarrollo de modelos matemáticos predictivos de distinto tipos de fenómenos son aplicaciones fundamentales y útiles de las técnicas de Minería de Datos. Un buen modelo se convierte en una excelente herramienta científica que requiere de la existencia y disposición de grandes volúmenes de datos, además de habilidad y considerable tiempo aplicado del investigador para integrar los conocimientos más relevantes y característicos del fenómeno en estudio. En el caso concreto de ésta tesis, los modelos de predicción desarrollados se enfocaron en la predicción contaminantes ambientales como el valor medio de Partículas Finas (PM2.5) presentes en el aire respirable con un tiempo de anticipación de 8 horas y del Ozono Troposférico Máximo (O3) con 24 horas de anticipación. Se trabajó con un interesante conjunto de técnicas de predicción partiendo con herramientas de naturaleza paramétrica tan sencillas como Persistencia, Modelación Lineal Multivariante, así como la técnica semi-paramétrica: Regresión Ridge además de herramientas de naturaleza no paramétrica como Redes Neuronales Artificiales (ANN) como Perceptron Multicapa (MLP), Perceptrón Multi Capa Cuadrática (SMLP), Función de Base Radial (RBF) y Redes Elman, así como Máquinas de Vectores Soporte (SVM), siendo las técnicas no paramétricas las que generalizaron mejor los fenómenos modelizados. / Salazar Ruiz, E. (2008). Desarrollo de modelos predictivos de contaminantes ambientales [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/2504 / Palancia

The main goal of this project, running at Neurofy AB, was that developing an AI recognition algorithm also known as, gas sensing algorithm or simply recognition algorithm, based on Artificial Intelligence (AI) technology, which would have the ability to detect or predict diary cattle diseases using odor signal data gathered, measured and provided by Gas Sensor Array (GSA) also known as, Electronic Nose or simply E-nose developed by the company. Two major challenges in this project were to first overcome the noises and errors in the odor signal data, as the E-nose is supposed to be used in an environment with difference conditions than laboratory, for instance, in a bail (A stall for milking cows) with varying humidity and temperatures, and second to find a proper feature extraction method appropriate for GSA. Normalization and Principal component analysis (PCA) are two classic methods which not only intended for re-scaling and reducing of features in a data-set at pre-processing phase of developing of odor identification algorithm, but also it thought that these methods reduce the affect of noises in odor signal data. Applying classic approaches, like PCA, for feature extraction and dimesionality reduction gave rise to loss of valuable data which made it difficult for classification of odors. A new method was developed to handle noises in the odors signal data and also deal with dimentionality reduction without loosing of valuable data, instead of the PCA method in feature extraction stage. This method, which is consisting of signal segmentation and Autoencoder with encoder-decoder, made it possible to overcome the noise issues in data-sets and it also is more appropriate feature extraction method due to better prediction accuracy performed by the AI gas recognition algorithm in comparison to PCA. For evaluating of Autoencoder monitoring of its learning rate of was performed. For classification and predicting of odors, several classifier, among alias, Logistic Regression (LR), Support vector machine (SVM), Linear Discriminant Analysis (LDA), Random forest Classifier (RFC) and MultiLayer perceptron (MLP), was investigated. The best prediction was obtained by classifiers MLP . To validate the prediction, obtained by the new AI recognition algorithm, several validation methods like Cross validation, Accuracy score, balanced accuracy score , precision score, Recall score, and Learning Curve, were performed. This new AI recognition algorithm has the ability to diagnose 3 different diary cattle diseases with an accuracy of 96% despite lack of samples. / Syftet med detta projekt var att utveckla en igenkänning algoritm baserad på maskinintelligens (Artificiell intelligens (AI) ), även känd som gasavkänning algoritm eller igenkänningsalgoritm, baserad på artificiell intelligens (AI) teknologi såsom maskininlärning ach djupinlärning, som skulle kunna upptäcka eller diagnosera vissa mjölkkor sjukdomar med hjälp av luktsignaldata som samlats in, mätts och tillhandahållits av Gas Sensor Array (GSA), även känd som elektronisk näsa eller helt enkelt E-näsa, utvecklad av företaget Neorofy AB. Två stora utmaningar i detta projekt bearbetades. Första utmaning var att övervinna eller minska effekten av brus i signaler samt fel (error) i dess data då E-näsan är tänkt att användas i en miljö där till skillnad från laboratorium förekommer brus, till example i ett stall avsett för mjölkkor, i form av varierande fukthalt och temperatur. Andra utmaning var att hitta rätt dimensionalitetsreduktion som är anpassad till GSA. Normalisering och Principal component analysis (PCA) är två klassiska metoder som används till att både konvertera olika stora datavärden i datamängd (data-set) till samma skala och dimensionalitetsminskning av datamängd (data-set), under förbehandling process av utvecling av luktidentifieringsalgoritms. Dessa metoder används även för minskning eller eliminering av brus i luktsignaldata (odor signal data). Tillämpning av klassiska dimensionalitetsminskning algoritmer, såsom PCA, orsakade förlust av värdefulla informationer som var viktiga för kllasifisering. Den nya metoden som har utvecklats för hantering av brus i luktsignaldata samt dimensionalitetsminskning, utan att förlora värdefull data, är signalsegmentering och Autoencoder. Detta tillvägagångssätt har gjort det möjligt att övervinna brusproblemen i datamängder samt det visade sig att denna metod är lämpligare metod för dimensionalitetsminskning jämfört med PCA. För utvärdering of Autoencoder övervakning of inlärningshastighet av Autoencoder tillämpades. För klassificering, flera klassificerare, bland annat, LogisticRegression (LR), Support vector machine (SVM) , Linear Discriminant Analysis (LDA), Random forest Classifier (RFC) och MultiLayer perceptron (MLP) undersöktes. Bästa resultate erhölls av klassificeraren MLP. Flera valideringsmetoder såsom, Cross-validering, Precision score, balanced accuracy score samt inlärningskurva tillämpades. Denna nya AI gas igenkänningsalgoritm har förmågan att diagnosera tre olika mjölkkor sjukdomar med en noggrannhet på högre än 96%.