In the field of telecommunications and cloud communications, accurately and in real-time detecting whether a human or an answering machine has answered an outbound call is of paramount importance. This problem is of particular significance during campaigns as it enhances service quality, efficiency and cost reduction through precise caller identification. Despite the significance of the field, it remains inadequately explored in the existing literature. This paper presents an innovative approach to answering machine detection that leverages transfer learning through the YAMNet model for feature extraction. The YAMNet architecture facilitates the training of a recurrent-based classifier, enabling real-time processing of audio streams, as opposed to fixed-length recordings. The results demonstrate an accuracy of over 96% on the test set. Furthermore, we conduct an in-depth analysis of misclassified samples and reveal that an accuracy exceeding 98% can be achieved with the integration of a silence detection algorithm, such as the one provided by FFmpeg.

Many deep-learning computer vision systems analyse objects not previously observed by the system. However, such tasks can be simplified if the objects are marked beforehand. A straightforward method for marking is printing 2D symbols and attaching them to the objects. Selecting these symbols can affect the performance of the CV system, as similar symbols may require extended training time and a larger training dataset. It is possible to find good symbols differentiated by the given neural network easily. Still, there were no efforts to generalise such findings in the literature, and it is not known if the symbols optimal for one network would work just as well in the other. We explored how transferable symbol selection is between the networks. To this end, 30 sets of randomly selected and augmented symbols were classified by-five neural networks. Each network was given the same training dataset and the same training time. Results were ranked and compared, which allowed the identification of networks which performed similarly so that the symbol selection could be generalised between them.

Audio fingerprinting techniques have seen great advances in recent years, enabling accurate and fast audio retrieval even in conditions when the queried audio sample has been highly deteriorated or recorded in noisy conditions. Expectedly, most of the existing work is centered around music, with popular music identification services such as Apple’s Shazam or Google’s Now Playing designed for individual audio recognition on mobile devices. However, the spectral content of speech differs from that of music, necessitating modifications to current audio fingerprinting approaches. This paper offers fresh insights into adapting existing techniques to address the specialized challenge of speech retrieval in telecommunications and cloud communications platforms. The focus is on achieving rapid and accurate audio retrieval in batch processing instead of facilitating single requests, typically on a centralized server. Moreover, the paper demonstrates how this approach can be utilized to support audio clustering based on speech transcripts without undergoing actual speech-to-text conversion. This optimization enables significantly faster processing without the need for GPU computing, a requirement for real-time operation that is typically associated with state-of-the-art speech-to-text tools.

Deep learning techniques in computer vision (CV) tasks such as object detection, classification, and tracking can be facilitated using predefined markers on those objects. Selecting markers is an objective that can potentially affect the performance of the algorithms used for tracking as the algorithm might swap similar markers more frequently and, therefore, require more training data and training time. Still, the issue of marker selection has not been explored in the literature and seems to be glossed over throughout the process of designing CV solutions. This research considered the effects of symbol selection for 2D-printed markers on the neural network’s performance. The study assessed over 250 ALT code symbols readily available on most consumer PCs and provided a go-to selection for effectively tracking n-objects. To this end, a neural network was trained to classify all the symbols and their augmentations, after which the confusion matrix was analysed to extract the symbols that the network distinguished the most. The results showed that selecting symbols in this way performed better than the random selection and the selection of common symbols. Furthermore, the methodology presented in this paper can easily be applied to a different set of symbols and different neural network architectures.

Artificial Intelligence (AI) is one of the most promising technologies of the 21. century, with an already noticeable impact on society and the economy. With this work, we provide a short overview of global trends, applications in industry and selected use-cases from our international experience and work in industry and academia. The goal is to present global and regional positive practices and provide an informed opinion on the realistic goals and opportunities for positioning B&H on the global AI scene.

The vehicle routing problem is one of the most complex problems in the field of combinatorial optimization. Creating optimal routes leads to timely delivery of orders to end customers, which increases the efficiency of the company and enables maximum earnings. The problem of vehicle routing with a series of real-world constraints is called the rich vehicle routing problem (RVRP). The paper presents an approach to solving RVRP, where the asymmetric routing problem with a heterogeneous vehicle fleet, time windows, customer-vehicle constraints and a number of others is observed. The approach solves the problem in two phases, by dividing customers into clusters using a discrete metaheuristic Bat algorithm, and by solving the routing problem for each obtained cluster. The proposed approach has been tested for 26 days of delivery from large warehouses in Bosnia and Herzegovina. Significant savings were achieved compared to previously implemented approaches. All created routes were feasible. The approach automatically creates routes, and gives results in a shorter time than previously used approaches. Time does not increase significantly with the increase in the number of customers, which is a great advantage of the proposed approach.

By successfully solving the problem of forecasting, the processes in the work of various companies are optimized and savings are achieved. In this process, the analysis of time series data is of particular importance. Since the creation of Facebook’s Prophet, and Amazon’s DeepAR+ and CNN-QR forecasting models, algorithms have attracted a great deal of attention. The paper presents the application and comparison of the above algorithms for sales forecasting in distribution companies. A detailed comparison of the performance of algorithms over real data with different lengths of sales history was made. The results show that Prophet gives better results for items with a longer history and frequent sales, while Amazon’s algorithms show superiority for items without a long history and items that are rarely sold.

Many public figures, companies and associations are planning events in different cities and at the same time have active profiles on social media. The planning process requires processing a large amount of data and different parameters when choosing the best event venue. Social media captures a large number of fan actions per day. This paper describes the process of selecting the most appropriate cities to organize events, aided by data collected from social media. The problem is defined as a combinatorial optimization problem. A modified metaheuristic Bat algorithm was proposed, implemented, and described in detail to solve the problem. Although the original Bat algorithm is designed to solve continuous optimization problems, the implemented bat algorithm is adapted to solve the defined problem. The algorithm is compared to the exhaustive search method for smaller instances, and to the greedy and genetic algorithm for larger instances. The algorithm was tested on benchmark data on cities in 20 European countries, as well as on real data collected from pages on the social network Facebook. Bat algorithm has shown superior results compared to other techniques, both in time and in the quality of the solutions generated.

Distribution companies often store goods in large warehouses. Orders are collected and prepared for transport. Large-scale warehouses are often divided into sectors. Each worker collects a part of the order from the assigned sector. In that case, workers often pick small orders and the process is not optimal. Therefore, order batching is done, where one worker collects multiple orders at a time. In this paper, an innovative concept of orders batching in a warehouse with a 48-hour delivery based on a metaheuristic approach is described. The algorithm divides each order by sectors. An analysis of each part of the order is done and the possibility of batching based on the order content is checked. The order batching is based on the discrete Bat algorithm. The transport scheme and the order of loading goods into the truck are observed. In the order picking process, a number of standard constraints such as weight and item priorities are considered. The concept has been implemented and tested for 50 days of warehouse operation in one of the largest warehouses in Bosnia and Herzegovina. The algorithm is compared with the earlier approach of collecting orders in the warehouse, and significant progress has been observed in the number of kilometers traveled on a daily basis.

—The problem of transport optimization is of great importance for the successful operation of distribution companies. To successfully find routes, it is necessary to provide accurate input data on orders, customer location, vehicle fleet, depots, and delivery restrictions. Most of the input data can be provided through the order creation process or the use of various online services. One of the most important inputs is an estimate of the unloading time of the goods for each customer. The number of customers that the vehicle serves during the day directly depends on the time of unloading. This estimate depends on the number of items, weight and volume of orders, but also on the specifics of customers, such as the proximity of parking or crowds at the unloading location. Customers repeat over time, and unloading time can be calculated from GPS data history. The paper describes the innovative application of machine learning techniques and delivery history obtained through a GPS vehicle tracking system for a more accurate estimate of unloading time. The application of techniques gave quality results and significantly improved the accuracy of unloading time data by 83.27% compared to previously used methods. The proposed method has been implemented for some of the largest distribution companies in Bosnia and Herzegovina.

ABSTRACT Transportation management, as a part of the supply chain management, is a complex process that consists of planning and delivering goods to customers. The paper presents a complete multi-phase intelligent and adaptive transportation management system, which includes data collection, parameter tuning, and the heuristic algorithm based on the Tabu search for vehicle routing. The paper describes the procedure for collecting Global Positioning System (GPS) data and analyzing the compliance with the proposed routes based on the data collected. The described routing algorithm is powerful and supports many real-world limitations. An algorithm for the anomaly detection in the GPS data is presented as well as the usage of collected GPS data to improve the future results of the algorithm. The concept was implemented and tested on real data in some of the largest distribution companies in Bosnia and Herzegovina. The proposed approach resulted with more than satisfactory results in real-world application.

In all information systems it is very important to operate with correct information. Incorrect information can lead to many problems that can cause direct financial and reputation loss of the company. Data used by the system can be gathered by sensors, scripts or by hand. In all those cases, mistakes are possible. It is important to detect mistakes on time and stop them from propagating further into the system. In this paper, a novel multi-step anomaly detection algorithm based on the greatest common divisor and median value is described. The algorithm for anomaly detection in historical sales data is used as a part of the smart warehouse management system which is implemented in some of the largest distribution companies in Bosnia and Herzegovina. The algorithm showed significant results in anomaly detection on company orders and improved a number of processes in the operation of the smart warehouse management system. The algorithm described can also be used in other areas where the transaction data is collected, such as sales and banking,