In this paper, we analyze the effectiveness of transfer learning on classifying electronic components. Transfer learning reuses pre-trained models to save time and resources in building a robust classifier rather than learning from scratch. Our work introduces a lightweight CNN, coined as VoltaVision, and compares its performance against more complex models. We test the hypothesis that transferring knowledge from a similar task to our target domain yields better results than stateof-the-art models trained on general datasets. Traditional transfer learning uses large pre-trained models on general classification tasks to cut down on the time required for training.

The immune response is a dynamic process by which the body determines whether an antigen is self or nonself. The state of this dynamic process is defined by the relative balance and population of inflammatory and regulatory actors which comprise this decision making process. The goal of immunotherapy as applied to, e.g. Rheumatoid Arthritis (RA), then, is to bias the immune state in favor of the regulatory actors - thereby shutting down autoimmune pathways in the response. While there are several known approaches to immunotherapy, the effectiveness of the therapy will depend on how this intervention alters the evolution of this state. Unfortunately, this process is determined not only by the dynamics of the process, but the state of the system at the time of intervention - a state which is difficult if not impossible to determine prior to application of the therapy. To identify such states we consider a mouse model of RA (Collagen-Induced Arthritis (CIA)) immunotherapy; collect high dimensional data on T cell markers and populations of mice after treatment with a recently developed immunotherapy for CIA; and use feature selection algorithms in order to select a lower dimensional subset of this data which can be used to predict both the full set of T cell markers and populations, along with the efficacy of immunotherapy treatment.

The heart is one of the most vital organs in the human body. It supplies blood and nutrients in other parts of the body. Therefore, maintaining a healthy heart is essential. As a heart disorder, arrhythmia is a condition in which the heart's pumping mechanism becomes aberrant. The Electrocardiogram is used to analyze the arrhythmia problem from the ECG signals because of its fewer difficulties and cheapness. The heart peaks shown in the ECG graph are used to detect heart diseases, and the R peak is used to analyze arrhythmia disease. Arrhythmia is grouped into two groups - Tachycardia and Bradycardia for detection. In this paper, we discussed many different techniques such as Deep CNNs, LSTM, SVM, NN classifier, Wavelet, TQWT, etc., that have been used for detecting arrhythmia using various datasets throughout the previous decade. This work shows the analysis of some arrhythmia classification on the ECG dataset. Here, Data preprocessing, feature extraction, classification processes were applied on most research work and achieved better performance for classifying ECG signals to detect arrhythmia. Automatic arrhythmia detection can help cardiologists make the right decisions immediately to save human life. In addition, this research presents various previous research limitations with some challenges in detecting arrhythmia that will help in future research.

It was not long before James and Skyler became close friends. The paternal-like connection between the two previous strangers surprised Acharya. James would often brag about Skyler in the mannerism of a proud father. Anchor was fond of James as well. She would run to him and leap in his arms while Data would bark frantically for her attention, hoping for those magic words: "Don't get me." After some coaxing, James agreed to fly with Skyler. Even with his limited flying time, James could tell Skyler was gifted. Moreover, Skyler enjoyed flying again since the death of his best friend. It was pouring all day on the North Shore as James and Acharya sat in James' office at the forest research center, watching the rain through the large window. The downpour was relaxing, and James loved the sound.

From the technology that helps self-driving cars recognize stop signs, to medical advancements that help produce COVID-19 vaccines, to studying the unconscious bias found in algorithms, the Luddy School of Informatics, Computing and Engineering is involved in all parts of AI development. As artificial intelligence continues to infiltrate everyday life, IU's researchers are focused on developing these technologies, while working to ensure their research is safe and ethical. The Luddy Center for Artificial Intelligence is set to open this month, providing researchers a place to focus on the intersection of robotics, complex networks, health and social media. Kay Connelly, Luddy School's associate dean of research, studies proactive health and AI technologies that can help the terminally ill and older people as they age, specifically wearable devices. She said proactive health is like "Fitbit before Fitbit."

We consider the problem of discrete distribution estimation under locally differential privacy. Distribution estimation is one of the most fundamental estimation problems, which is widely studied in both non-private and private settings. In the local model, private mechanisms with provably optimal sample complexity are known. However, they are optimal only in the worst-case sense; their sample complexity is proportional to the size of the entire universe, which could be huge in practice (e.g., all IP addresses). We show that as long as the target distribution is sparse or approximately sparse (e.g., highly skewed), the number of samples needed could be significantly reduced. The sample complexity of our new mechanism is characterized by the sparsity of the target distribution and only weakly depends on the size the universe. Our mechanism does privatization and dimensionality reduction simultaneously, and the sample complexity will only depend on the reduced dimensionality. The original distribution is then recovered using tools from compressive sensing. To complement our theoretical results, we conduct experimental studies, the results of which clearly demonstrate the advantages of our method and confirm our theoretical findings.

Luddy School of Informatics, Computing, and Engineering dean Raj Acharya poses for a headshot. Acharya will step down mid-March to participate in an artificial intelligence research initiative at IU. Courtesy of Indiana University Dean of the Luddy School of Informatics, Computing, and Engineering Raj Acharya will step down mid-March to participate in an artificial intelligence research initiative. Acharya said the school will hire an acting dean to replace him and then conduct a national search to find a permanent dean. Acharya launched the Department of Intelligent Systems Engineering in 2016 and has been dean since July 2016. He will now be associate vice president for research with the specific task of promoting artificial intelligence.

Epilepsy is the fourth most common neurological disorder, affecting about 1% of the population at all ages. As many as 60% of people with epilepsy experience focal seizures which originate in a certain brain area and are limited to part of one cerebral hemisphere. In focal epilepsy patients, a precise surgical removal of the seizure onset zone can lead to effective seizure control or even a seizure-free outcome. Thus, correct identification of the seizure onset zone is essential. For clinical evaluation purposes, electroencephalography (EEG) recordings are commonly used. However, their interpretation is usually done manually by physicians and is time-consuming and error-prone. In this work, we propose an automated epileptic signal classification method based on modern deep learning methods. In contrast to previous approaches, the network is trained directly on the EEG recordings, avoiding hand-crafted feature extraction and selection procedures. This exploits the ability of deep neural networks to detect and extract relevant features automatically, that may be too complex or subtle to be noticed by humans. The proposed network structure is based on a convolutional neural network with residual connections. We demonstrate that our network produces state-of-the-art performance on two benchmark data sets, a data set from Bonn University and the Bern-Barcelona data set. We conclude that modern deep learning approaches can reach state-of-the-art performance on epileptic EEG classification and automated seizure onset zone identification tasks when trained on raw EEG data. This suggests that such approaches have potential for improving clinical practice.

Despite recent blows to the footwear industry, there's ample reason to be hopeful with cutting-edge technology. "We're living in amazing times where new innovations coming out of research in these fields is capturing people's imaginations. And those innovations will be realities in the not-too-distant future," said Acharya. "Today, we're creating machine-learning algorithms to help retailers incorporate all these sources of data and solve new business challenges." He pointed to returns forecasting -- and how data science can help -- as one example.

Anurag Acharya's problem was that the Google search bar is very smart, but also kind of dumb. As a Googler working on search 13 years ago, Acharya wanted to make search results encompass scholarly journal articles. A laudable goal, because unlike the open web, most of the raw output of scientific research was invisible--hidden behind paywalls. People might not even know it existed. "I grew up in India, and most of the time you didn't even know if something existed. If you knew it existed, you could try to get it," Acharya says.