The global tech company Ericsson has been tracking the return rate of their products for over 30 years, using it as a key performance indicator (KPI). These KPIs play a critical role in making sound business decisions, identifying areas for improvement, and planning. To enhance the customer experience, the company highly values the ability to predict the number of returns in advance each month. However, predicting returns is a complex problem affected by multiple factors that determine when radios are returned. Analysts at the company have observed indications of a potential correlation between alarm data and the number of returns. This paper aims to address the need for better prediction models to improve return rate forecasting for radios, utilizing alarm data. The alarm data, which is stored in an internal database, includes logs of activated alarms at various sites, along with technical and logistical information about the products, as well as the historical records of returns. The problem is approached as a classification task, where radios are classified as either "return" or "no return" for a specific month, using the alarm dataset as input. However, due to the significantly smaller number of returned radios compared to the distributed ones, the dataset suffers from a heavy class imbalance. The imbalance class problem has garnered considerable attention in the field of machine learning in recent years, as traditional classification models struggle to identify patterns in the minority class of imbalanced datasets. Therefore, a specific method that addresses the imbalanced class problem was required to construct an effective prediction model for returns. Therefore, this paper has adopted a systematic approach inspired by similar problems. It applies the feature selection methods LASSO and Boruta, along with the resampling technique SMOTE, and evaluates various classifiers including the Support vector machine (SVM), Random Forest classifier (RFC), Decision tree (DT), and a Neural network (NN) with weights to identify the best-performing model. As accuracy is not suitable as an evaluation metric for imbalanced datasets, the AUC and AUPRC values were calculated for all models to assess the impact of feature selection, weights, resampling techniques, and the choice of classifier. The best model was determined to be the NN with weights, achieving a median AUC value of 0.93 and a median AUPRC value of 0.043. Likewise, both the LASSO+SVM+SMOTE and LASSO+RFC+SMOTE models demonstrated similar performance with median AUC values of 0.92 and 0.93, and median AUPRC values of 0.038 and 0.041, respectively. The baseline for the AUPRC value for this data set was 0.005. Furthermore, the results indicated that resampling techniques are necessary for successful classification of the minority class. Thorough pre-processing and a balanced split between the test and training sets are crucial before applying resampling, as this technique is sensitive to noisy data. While feature selection improved performance to some extent, it could also lead to unreadable results due to noise. The choice of classifier did not have an equal impact on model performance compared to the effects of resampling and feature selection.

<p dir="ltr">The emergence of time-dependent data provides researchers with unparalleled opportunities to investigate disaggregated levels of safety performance on roadway infrastructures. A disaggregated crash risk analysis uses both time-dependent data (e.g., hourly traffic, speed, weather conditions and signal controls) and fixed data (e.g., geometry) to estimate hourly crash probability. Despite abundant research on crash risk analysis, coordinated signalized intersections continue to require further investigation due to both the complexity of the safety problem and the relatively small number of past studies that investigated the risk factors of coordinated signalized intersections. This dissertation aimed to develop robust crash risk prediction models to better understand the risk factors of coordinated signalized intersections and to identify practical safety countermeasures. The crashes first were categorized into three types (same-direction, opposite-direction, and right-angle) within several crash-generating scenarios. The data needed were organized in hourly observations and included the following factors: road geometric features, traffic movement volumes, speeds, weather precipitation and temperature, and signal control settings. Assembling hourly observations for modeling crash risk was achieved by synchronizing and linking data sources organized at different time resolutions. Three different non-crash sampling strategies were applied to the following three statistical models (Conditional Logit, Firth Logit, and Mixed Logit) and two machine learning models (Random Forest and Penalized Support Vector Machine). Important risk factors, such as the presence of light rain, traffic volume, speed variability, and vehicle arrival pattern of downstream, were identified. The Firth Logit model was selected for implementation to signal coordination practice. This model turned out to be most robust based on its out-of-sample prediction performance and its inclusion of important risk factors. The implementation examples of the recommended crash risk model to building daily risk profiles and to estimating the safety benefits of improved coordination plans demonstrated the model’s practicality and usefulness in improving safety at coordinated signals by practicing engineers.</p>

Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A promising technique might be based on the classification of movements based on accelerometer signals by machine-learning algorithms, but the generalizability of classifiers trained on laboratory data to real-world datasets is a common issue. Here, three machine-learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were trained to detect fall events. We used a dataset containing intentional falls (SisFall) to train the classifier and validated the approach on a different dataset which included real-world accidental fall events of elderly people (FARSEEING). The results suggested that the linear SVM was the most suitable classifier in this cross-dataset validation approach and reliably distinguished a fall event from normal everyday activity at an accuracy of 93% and similarly high sensitivity and specificity. Thus, classifiers based on linear SVM might be useful for automatic fall detection in real-world applications.

This study investigates the performance of two keypoint detection algorithms, SIFTand LoFTR, for vehicle re-recognition on a 2+1 road in Täby, utilizing three differentmethods: proportion of matches, ”gates” based on the values of the features andSupport Vector Machines (SVM). Data was collected from four strategically placedcameras, with a subset of the data manually annotated and divided into training,validation, and testing sets to minimize overfitting and ensure generalization. TheF1-score was used as the primary metric to evaluate the performance of the variousmethods. Results indicate that LoFTR outperforms SIFT across all methods, with theSVM method demonstrating the best performance and adaptability. The findings havepractical implications in security, traffic management, and intelligent transportationsystems, and suggest directions for future research in real-time implementation andgeneralization across varied camera placements.

Near infrared spectroscopy (NIR) has become increasingly widespread throughout various fields as an alternative method for efficiently phenotyping crops and plants at rates unparalleled by conventional means. With growing reliability, the convergence of NIR spectroscopy and modern machine learning represent a promising methodology offering unprecedented access to rapid, high throughput phenotyping at negligible costs, representing prospects that excite agronomists and plant physiologists alike. However, as is true of all emergent methodologies, progressive refinement towards optimization exposes potential flaws and raises questions, one of which is the cornerstone of this study. Spectroscopic determination of plant functional traits utilizes plants' morphological and biochemical properties to make predictions, and has been validated at the community (inter-family) and individual crop (intraspecific) levels alike, yielding equally reliable predictions at both scales, yet what lies amid these poles on the spectrum of taxonomic scale remains unexplored territory. In this study, we replicated the protocol used in studies of the aforementioned taxonomic scale extremes and applied it to an intermediate scale. Interestingly, we found that predictive models built upon hyperspectral reflectance data collected across three genera of woody plants: Cornus, Rhododendron, and Salix, yielded inconsistent predictions of varying accuracy within and across taxa. Identifying the potential cause(s) underlying variability in predictive power at this intermediate taxonomic scale may reveal novel properties of the methodology, potentially permitting further optimization through careful consideration.

No description available.

No description available.

No description available.

Human Activity Recognition (HAR) is a widelyresearched field that has gained importance due to recentadvancements in sensor technology and machine learning. InHAR, sensors are used to identify the activity that a person is performing.In this project, the six everyday life activities walking,biking, sitting, standing, ascending stairs and descending stairsare classified using smartphone accelerometer and gyroscope datacollected by three subjects in their everyday life. To performthe classification, two different machine learning algorithms,Artificial Neural Network (ANN) and Support Vector Machine(SVM) are implemented and compared. Moreover, we comparethe accuracy of the two sensors, both individually and combined.Our results show that the accuracy is higher using only theaccelerometer data compared to using only the gyroscope data.For the accelerometer data, the accuracy is greater than 95%for both algorithms and only between 83-93% using gyroscopedata. Also, there is a small synergy effect when using both sensors,yielding higher accuracy than for any individual sensor data, andreaching 98.5% using ANN. Furthermore, for all sensor types, theANN outperforms the SVM algorithm, having a greater accuracyby more than 1.5-9 percentage points. / Aktivitetsigenkänning är ett noga studeratforskningsområde som växt i popularitet på senare tid på grundav nya framsteg inom sensorteknologi and maskininlärning. Inomaktivitetsigenkänning använder man sensorer för att identifieravilken aktivitet en person utför. I det här projektet undersökervi de sex olika vardagsmotionsaktiviteterna gå, cykla, sitta, stå och gå i trappor (up/ner) med hjälp av data från accelerometeroch gyroskop i en smartphone som samlats in av tre olikapersoner. Två olika maskininlärningsalgoritmer implementerasoch jämförs: Artificial Neural Network (ANN) och SupportVector Machine (SVM). Vidare jämför vi noggranheten förde två sensorna, både individuellt och gemensamt. Våra resultvisar att noggranheten är större när enbart accelerometerdatananvänds jämfört med att använda enbart gyroskopdatan. Föraccelerometerdatan erhålls en noggranhet större än 95 % förbåda algoritmerna medan den siffran bara är mellan 83-93 %för gyroskopdatan. Dessutom existerar det en synergieffekt vidanvändande av båda sensorerna, och noggranheten når då 98.5% vid användande av ANN. Vidare visar våra resultat att ANNhar en noggranhet som är 1.5-9 procentenheter bättre än SVMför alla sensorer. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

Nowadays, identification of fake data is an elaboratechallenge that calls for the use of machine learning techniques.This is due to the huge amount of data and its complexity makesthe differences indistinguishable even for the trained eye. In thisproject we use the MATLAB wlanTGnChannel System objectto simulate multipath fading channels that are comparable toreal impulse response measurements made by Ericsson AB of anindoor8×8MIMO (Multiple Input Multiple Output) system.We use an SVM classifier to compare the eigenvalues of theircorrelation covariance matrices, obtaining an accuracy of 84%.Comparing their power delay profiles (PDPs) happens to bea classification task of low complexity due to time resolutionlimitation in the real measurements. We suggest that the proposedMATLAB model strongly differs from the real data we have beenprovided with. / Nu för tiden så är identifiering av fejkad data en svår utmaning som ofta kräver maskininlärningstekniker. Detta beror på den stora mängden data och att komplexiteten i datat gör att skillnaderna kan vara svår att se även för ett tränat öga. I det här projektet använder vi oss av MATLABs systemobjekt wlanTGnChannel för att simulera flervägs fädningskanaler som kan jämföras med riktiga impulssvarsmätningar gjorda av Ericsson AB av ett innomhus 8 X 8 MIMO(Multiple Input Multiple Output) system. Vi använde en SVM (stödvektormaskins) klassificerare för att jämföra egenvärdena av deras korrelationskovariansmatriser, vilket erhåller en noggranhet på 84%. Att jämföra deras power delay profiles (PDP) råkar vara ett klassificeringsproblem av låg svårighetsgrad på grund av tidsupplösningsbegränsningar för de riktiga mätningarna. Vi vill påstå att den tilltänkta MATLAB- modellen aviker mycket från den givna datan. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm