Chatbots are interactive systems that communicate using natural language with human users, via a textual interface or voice activation. These tools are useful for many spheres of business such as Customer Service, Sales, Education and Learning, Health and Entertainment. Recently, chatbots have become popular, with significant growth in the software industry, especially text-based chatbots. This is encouraging developers to create their own tools, as well as attracting efforts from researchers into this area. Despite this highlight, technologies to guarantee the quality of chatbots and user satisfaction are not keeping up with the growing demand for these tools. Considering this, there is a need to propose technologies capable of supporting developers and development teams in the process of building and evaluating chatbots. Therefore, this research proposes to develop artifacts applicable to the design and evaluation process of chatbots, based on quality attributes identified in systematic literature reviews related to Usability and User Experience (UX), due to the importance and impact that these aspects have on user satisfaction and the perceived quality of the system. The first artifact is the U2Chatbot inspection checklist, developed to assist development teams in the process of identifying defects in text-based chatbots. The second artifact is a set of interface design patterns, DP-U2Chatbot, containing useful examples to support developers in the process of building chatbots. The technologies were subjected to the necessary evaluations. The results of the empirical study regarding the U2Chatbot inspection checklist indicated that participants considered the technology useful for discovering defects in chatbots, however, ease of use could be improved. The participants' experience discreetly influenced the effectiveness and efficiency of the technique, leading us to believe that professionals with a certain level of inspection experience can benefit more from the checklist. Regarding the evaluation of DP-U2Chatbot design patterns, the results generally indicated that the technology is easy to understand and useful in supporting the design of chatbots, helping to build better tools.

When teaching software testing, it is essential that the students have access to the practical application of the theoretical concepts regarding software testing techniques. Thus, it is important that support materials and real artifacts are available for the practical application of the testing approaches. Despite this importance, undergraduate students from computer science courses still face difficulties in the practical application of the contents covered in the classroom. In this work in progress, our goal is to support the learning process by offering artifacts that allows students to improve their practical skills in software testing. For this, an analysis of the set of test techniques taught in classes and required by the job market was carried out. We also performed an analysis of the features of the repositories that provide support artifacts for teaching these techniques. Considering that the identified repositories are not in Portuguese, we present a high-fidelity prototype of a new Brazilian repository, aggregating the identified artifacts and proposing new ones for supporting testing teaching.

Usability and User Experience are high-impact quality factors for the design of interactive systems, since they impact how we use them in daily life activities. Despite the importance of these quality attributes, several users report problems when interacting with information systems. Considering the need to meet different quality standards, software testing is an important area for identifying software defects. Despite the proposal of different approaches for A/B testing in the context of Usability and UX evaluation, there are still some improvement opportunities. For instance, after carrying out a literature review, we did not identify an A/B testing process that could be applied for identifying both usability and user experience problems. Furthermore, most of the A/B testing processes in the context of human computer interaction do not gather qualitative data, which makes it difficult to identify what to improve in the selected version of a software to meet the users’ needs. Considering the above, this paper proposes a new A/B testing process that allows the evaluation of both usability and user experience attributes. For each of the A/B testing processes found in our literature review, we gathered data on the categorization of the process, its activities, the roles within the process, and the artifacts that were employed during the planning, conducting and reporting of the test. We then organized our results creating a new process that would consider all relevant activities and artifacts from previous work.

Quality can be achieved in software development by identifying and fixing defects, improving the development process and including configuration management activities. However, for novice development teams, including the above activities may be difficult when developing large or complex information systems. Thus, to gain insight on how to improve software quality, novice software engineers may review reports from real software development projects and apply lessons learned. In this paper, we report how software engineering activities for quality assurance were adapted within three power company information system projects. We explain how activities regarding version tracking, software testing and user interface design were carried out by three novice software development teams within a software organization of about 40 collaborators. Our results indicate that version control can be costly at first, but is useful to assess the current state of the development of features. Furthermore, though low-cost evaluation and design approaches, the end product can meet users' needs and reduce rework when launching a version of an information system.

Chatbots are conversational interfaces that enable humanlike dialogue and can be designed in a textual chat format or a graphical interface with voice and embedding options. In the last year, there has been a significant growth in the emergence of chatbots in the market and this popularization has attracted the efforts of researchers to this area. Despite the existence of techniques to evaluate these tools, there is an urgent need to propose solutions that also support the chatbot design process. Currently, there is no knowledge of a specific list of requirements capable of supporting development teams in the process of designing these tools. In view of this, this directed study proposes a literature review aiming at deepening the knowledge about these tools and identifying important quality attributes in academic and industry sources. As a result, this directed study presents a list composed of 82 requirements related to Usefulness, Ease of Use and Presence to aid the design of these tools. These requirements presented in this study are useful to guide developers in the process of building quality chatbots, making this task less challenging and for researchers who aim to propose technologies that contribute to the development of better and better chatbots.

To mitigate financial loss and follow the recommended sanitary measures due to the COVID-19 pandemic, self-reading, a method in which a consumer reads and reports his own energy consumption, has been presented as an efficient alternative for power companies. In such context, this work presents a solution for self-reading via chatbot in chatting applications. This solution is under development as part of a research and development (R&D) project. It is integrated with a method based on image processing that automatically reads the energy consumption and recognizes the identification code of a meter for validation purposes. Furthermore, all processes utilize cognitive services from the IBM Watson platform to recognize intentions in the dialog with the consumers. The dataset used to validate the proposed method for self-reading contains examples of analogical and digital meters used by Equatorial Energy group. Preliminary results presented accuracies of 77.20% and 84.30%, respectively, for the recognition of complete reading sequences and identification codes in digital meters and accuracies of 89% and 95.20% in the context of analogical meters. Considering both meter types, the method obtains an accuracy per digit of 97%. The proposed method was also evaluated with UFPR-AMR public dataset and achieves a result comparable to the state of the art.

Melhorar o engajamento de discentes e facilitar o acesso à informação têm se tornado mais relevantes no contexto educacional. Em virtude do isolamento social gerado pela pandemia da COVID-19, recursos didáticos como podcasts e vídeos podem ser explorados para alcançar este objetivo. Com o intuito manter os discentes atualizados e engajados durante o ensino remoto, o grupo PETComp da Universidade Federal do Maranhão montou uma equipe para desenvolver um podcast sobre conteúdos relacionados à Tecnologia da Informação. Este artigo apresenta o processo de produção dos episódios do podcast. Após a preparação do material e lançamento do podcast em plataformas digitais, foi coletada a opinião dos discentes sobre o mesmo através de um questionário. Os resultados indicam que o podcast contribuiu para disponibilizar conteúdos construídos pelos discentes de forma descontraída, permitindo a atualização em temas relevantes e o engajamento dos ouvintes.

Na educação de surdos é importante a utilização de ferramentas e metodologias visuais no processo de ensino. Porém, quanto às tecnologias de informação e comunicação para apoio à tradução de sentenças para a Língua Brasileira de Sinais (LIBRAS), não há consenso sobre qual tecnologia utilizar. Este artigo apresenta uma análise das ferramentas existentes para este fim. Foi feito o levantamento e análise: (a) das funcionalidades dos aplicativos; (b) das avaliações dos usuários dos aplicativos estudados; e (c) de entrevistas com profissionais sobre suas experiências com o uso desses aplicativos no ambiente educacional. Como resultado, pode-se entender o potencial dessas ferramentas no processo de ensino a surdos e perceber qual ferramenta é a mais promissora.

As the number of mobile devices has increased, software development teams have focused on releasing mobile applications, allowing users to carry out transactions, access information and improve their lifestyle more efficiently. Nevertheless, even when providing useful means for carrying out daily tasks, users report dissatisfaction or frustration when using these applications. For energy companies, mobile applications that fail to provide both usefulness and ease of use may reduce their adoption and an increase in the company’s workload, as users will require company workers to solve problems they could solve on their own. In this paper, we report how we applied exploratory testing and ad-hoc usability inspection to identify improvement opportunities during the development of a mobile application that would allow users to measure their power consumption, supporting social distancing in the context of the COVID-19 pandemic. After identified a set of functional and usability problems, the development team redesigned the application, which was perceived as both useful and easy to use from the point of view of the managers that requested it. Also, we report lessons learned that are useful for practitioners willing to replicate this experience.

Self-reading is a process in which the consumer is responsible for measuring his own energy consumption, which can be done through digital platforms, such as websites or mobile applications. The Equatorial Energy group's electric utilities have been working on developing a chatbot application through which consumers can send an image of their energy meter to a server that runs a method based on image processing and deep learning for the automatic recognition of consumption reading. However, these methods in a solution available to the public should consider factors such as response time and accuracy, so that it presents a satisfactory response time when it needs to handle a large number of simultaneous requests. Therefore, this paper presents a comparative study between approaches developed for the automatic recognition of consumption readings in images of electric meters sent to the server. Response time performances are analyzed through stress tests that simulate the real application scenario. The mean average precision (mAP) and the accuracy metrics of the methods are also analyzed in order to evaluate the generalization of the used convolutional neural networks.

As uncommon as its incidence is, melanoma is considered to be one of the most aggressive and deadly skin cancers today. Risk factors for the development of the disease are related to exposure to ultraviolet rays and family history. Currently, the diagnosis is made through dermatoscopy, a noninvasive technique that aims to observe the structures of the skin. The diagnosis of melanoma is linked to the professional's experience in identifying the disease. With the advancement of computing, solutions based on deep learning were suggested to help diagnose the disease. This work has as main objective the adaptation of a capsule neural network for the task of detecting melanoma in medical images. The proposed architecture consists of the VGG16 neural network combined with a capsule neural network. The results obtained by the proposed model fed with the ISIC Archive database proved to be promising when compared to the literature, obtaining an accuracy of 92.6, sensitivity of 90.9 and specificity of 92.8.

As companhias do setor elétrico têm apresentado a autoleitura como uma alternativa eficiente para mitigar perdas financeiras e seguir as medidas sanitárias recomendadas em virtude da pandemia do Covid-19. Nesse contexto, este trabalho apresenta uma solução de chatbot para a autoleitura por meio de aplicativos de mensagens. O chatbot é integrado a um método que aplica processamento de imagem e inteligência computacional para a leitura automática do consumo de energia. Essa solução encontra-se em desenvolvimento no âmbito de um projeto de pesquisa e desenvolvimento (P&D). Preliminarmente, o método de reconhecimento das leituras apresenta acurácia de 89% e 77,2% para os medidores analógicos e digitais, respectivamente.

Brazilian Electricity Regulatory Agency (ANEEL) defines as non-technical losses the problems that happen during the energy consumption measurement process. A feasible alternative to reduce those losses is the energy consumption reading process performed by customers, called self-reading. This process might be executed across digital platforms such as mobile applications and the customers would register and send consumption information. In this context, the consumption reading using voice is a simple way for the public that has lower affinity for technology to perform self-reading. Therefore, this work proposes an end-to-end speech recognition method applied to the energy consumption measurement that uses a neural network architecture based on Recurrent Neural Network Transducer (RNN- T). The proposed method uses a modified architecture called Residual Recurrent Neural Network Transducer (RRNN-T) which contains a Residual Skip that make its behavior similar to a network shallower than RNN - T by skipping some layers in the training process. That strategy saves computational cost of the inference process and disk space. A spelled sequence of digits is the input of the proposed method that recognizes those digits and outputs the electrical energy consumption reading measured in kilowatts per hour. The dataset used in this work contains 111,224 samples of spelled sequences divided into 70% for training and 30% for test. The proposed method obtains 0.05 word error rate (WER) and inference time less than 3 seconds on mobile devices.

Alunos ingressantes em cursos de ensino superior sentem dificuldade em se adaptar à nova modalidade de ensino. Nesse contexto, o evento da Semana do Calouro é realizado pelos discentes do grupo PET de Ciência da Computação da Universidade Federal do Maranhão acompanhados por professores como uma atividade de integração aos novos discentes do curso de Ciência da Computação. Este artigo relata a experiência de aplicar diversas atividades com o intuito de esclarecer as dúvidas geradas pelo ingresso no novo ambiente, bem como aumentar a visibilidade dos contextos do curso. Ao término das atividades, o feedback dos discentes apontou para a utilidade das mesmas para conhecer as oportunidades dentro da universidade em termos de projetos, pesquisas e áreas de atuação, assim como soluções para problemas que surgiram durante sua execução.

Breast cancer is one of the leading causes of death by cancer among women. The high mortality rates and the occurrence of this cancer worldwide show the importance of the investigation and development of means for the detection and early diagnosis of this disease. Computer-Aided Detection and Diagnosis systems have been developed to improve diagnostic accuracy by radiologists. This work proposes a method for discriminating patterns of malignancy and benignity of masses in digitized mammography images through the analysis of local features. The method comparatively applies the Scale-Invariant Feature Transform (SIFT), Speed Up Robust Feature (SURF), Oriented Fast and Rotated BRIEF (ORB) and Local Binary Pattern (LBP) descriptors for local feature extraction. These features are represented by a Bag of Features (BoF) model, applied to provide new representations of the data and to reduce its dimensionality. Finally, the features are used as input for the Support Vector Machine (SVM), Adaptive Boosting (Adaboost) and Random Forests (RF) classifiers to differentiate malignant and benign masses. The method obtained significant results, reaching 100% sensitivity, 99.65% accuracy and 99.24% specificity for benign and malignant mass classification.

Breast cancer is a global health problem which mainly affects the female population. It is known that early detection increases the chances of effective treatment, improving the disease prognosis. It remains a challenge to detect the lesion with high detection rate and ensure, at the same time, low rates of false positives . Aiming this objective, this work proposes an efficient method for detection of mass regions on digitized mammograms though diversity analysis, geostatistical and concave geometry (Alpha Shapes). We evaluate the detection rate for each feature extraction using Support Vector Machine in MIAS and DDSM database, with 74 and 621 mammograms, respectively, all containing at least one mass region. The obtained results are promising, reaching 97.30% of detection rate and 0.89 false positive per image for MIAS database and also 91.63% of detection rate and 0.86 false positive per image for DDSM database. Specifically, in DDSM obtaining high detection rate and low rate of false positives when using concave geometry to extract features in a large database.

A methodology to texture analysis of masses in digitized mammography is proposed.Our methodology uses only the texture analysis for recognition.We provide the specialist bigger support to the diagnosis of breast cancer.We cooperate to a more precise diagnosis and support in the medical intervention. A World Health Organization (WHO) report estimates that in 2015, at least 561 thousand women will die of breast cancer. Although breast cancer is considered a disease of the developed world, nearly 50% of the cases and 58% of the deaths occur in the less developed countries. A mammogram is a way of discovering not just the palpable tumors that cause cancer but also other lesions that are not perceived during the physical examination performed by the expert physician or during self-exams; however, it is known that this exam is targeted for women after the age of 40 because age is one of the factors that can cause great variations in sensitivity during the exam. Besides the patient's age, the expert's experience and the quality of the images obtained during the exam are decisive factors in the detection of breast cancer. This work presents two novelties. The first is the use of Local Binary Patterns (LBPs) to generate a representation of a Region of Interest (ROI) image. Over this representation, we generate other representations using techniques such as image histograms, gray-level co-occurrence matrices (GLCMs) and gray-level run-length matrices (GLRLMs). These representations allow texture analysis through several perspectives. The second novelty uses these representations as input to the application of indexes adapted from ecology (Shannon, McIntosh, Simpson, Gleason and Menhinick) as texture descriptors. Based on this strategy, we analyze mammographic image textures to classify regions of these images as benign or malignant using a Support Vector Machine (SVM). The best result achieved was of 88.31% accuracy, 85% sensitivity, 91.89% specificity, a positive probability ratio of 10.48, a negative probability ratio of 0.16, and an area under the Receiver Operating Characteristic (ROC) curve of 0.88, obtained through the Shannon index. We believe that the proposed method, with some adaptations, may also be used for image texture analysis of several different lesions such as lung nodules, glaucoma and prostates. This belief is based on the achieved results and the method's simplicity.

INTRODUCTION: Breast cancer is the second most common type of cancer in the world, being more common among women and representing 22% of all new cancer cases every year. The sooner it is diagnosed, the better the chances of a successful treatment are. Mammography is one way to detect non-palpable tumors that cause breast cancer. However, it is known that the sensitivity of this exam can vary considerably due to factors such as the specialist's experience, the patient's age and the quality of the images obtained in the exam. The use of computational techniques involving artificial intelligence and image processing has contributed more and more to support the specialists in obtaining a more precise diagnosis. METHODS: This paper proposes a methodology that exclusively uses texture analysis to describe features of masses in digitized mammograms. To increase the efficiency of texture feature extraction, the diversity index's capability to detect patterns of species co-occurrence is used. For this purpose, the Gleason and Menhinick indexes are used. Finally, the extracted texture is classified using the Support Vector Machine, looking to differentiate the malignant masses from the benign. RESULTS: The best result was obtained using the Gleason index, with 86.66% accuracy, 90% sensitivity, 83.33% specificity and an area under the ROC Curve (Az) of 0.86. CONCLUSION: Both indexes showed statistically similar performance; however, the Gleason index was slightly superior.

Breast cancer is configured as a public health problem that affects mainly women population. One of the main ways of prevention is through screening mammography. The interpretation made by the physician is a repetitive task because of a low contrast image and the examination of several exams. So, computer systems have been proposed to aid detection step and helps physician, with the aim to increase sensitivity at the same time that reduces invasive procedures. Although these systems had improved the sensitivity of the original examination of mammography, they also generate a lot of false positives. This paper presents a methodology for reducing false positives by analyzing the diversity of approaches with improved spatial decomposition. After experiments the results reaches a high level of sensitivity at the same time promote a high rate of reduction of false positives. (C) 2013 Elsevier Ltd. All rights reserved.